Methods and systems for question answering include generating (212) a tile from an image and encoding (214) the tile to generate an embedding vector. A set of neighbor objects is generated (302) based on an object of interest from a query. A first similarity is determined (306) between the object of interest and the embedding vector of the tile. Second similarities are determined (308) between the neighbor objects and the embedding vector of the tile. It is determined (316) that the tile is relevant responsive to the first similarity being greater than the second similarities. The query is answered (230) using the tile.
G06F 16/56 - Information retrievalDatabase structures thereforFile system structures therefor of still image data having vectorial format
G06F 16/583 - Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
G06F 16/532 - Query formulation, e.g. graphical querying
G06V 10/46 - Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]Salient regional features
G06V 10/74 - Image or video pattern matchingProximity measures in feature spaces
Systems and methods for natural disaster damage analysis. Aerial images are converted (710) into a set of property images. The property images are then clustered (720) using vector embedding. Clustering the property images includes classifying the property images into separate categories, determining a symmetric similarity between the property images in each category, and clustering the property images based on the similarity. A first artificial intelligence agent extracts (730) damage information from a set of representative members of the clustered property images, where the damage information includes damage level information and damage reasoning information. The damage information is then stored (740) in a datastore with at least two databases, where at least one of the databases stores damage reasoning information and at least one other one of the databases stores damage level information.
G06Q 10/06 - Resources, workflows, human or project managementEnterprise or organisation planningEnterprise or organisation modelling
G06Q 10/04 - Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
G06V 10/762 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
G06V 20/40 - ScenesScene-specific elements in video content
G06V 10/46 - Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]Salient regional features
Systems and methods for adaptive transformer aided-semantic communication with multi-resolution encoding. The systems and methods include encoding (1002) patches of an image by flattening the patches to one-dimensional (1D) vectors to form encoded patches and determining an attention score of each of the patches using a vision transformer (ViT) and determining (1004) a semantic relevance of each of the patches to a user query using the respective attention score. The systems and methods further include adaptively transmitting (1010) the encoded patches with different resolutions based upon an amount of the semantic relevance.
Systems and methods for optimizing spatio-temporal reasoning in artificial intelligence models. Pseudo labels for instruction-following data for fine-tuning tasks can be generated (510) based on a four-dimensional reconstruction of dynamic videos. A visual-language machine learning model (VLM) can be fine-tuned (520) with the fine-tuning tasks that increases spatio-temporal reasoning of the VLM. The spatio-temporal reasoning of the VLM can be optimized (530) based on a prediction generated by the VLM in natural language for ensuring increased accuracy of the VLM while preventing biased verification.
B60W 40/02 - Estimation or calculation of driving parameters for road vehicle drive control systems not related to the control of a particular sub-unit related to ambient conditions
5.
OPTIMIZING ARTIFICIAL INTELLIGENCE MODEL UNDERSTANDING OF COMPLEX TRAFFIC INTERACTIONS
Systems and methods for optimizing artificial intelligence model understanding of complex traffic interactions. Agents can be identified (510) from input videos based on agent heuristics. Interaction behaviors between the agents can be determined (520) based on interaction heuristics. An integrated dataset can be autonomously generated (530) based on the agents and the interaction behaviors that enhances performance of an artificial intelligence (AI) model to adapt to various scene attributes. Semantic understanding of the AI model can be optimized (540) based on the generated dataset by updating hidden states of the AI model through training.
Systems and methods for language-conditioned trajectory diffusion for understanding complex traffic scenes. Complex multi-modality scene context information that includes map information and agent information for agents in input videos can be captured with a language-conditioned trajectory diffusion simulation (LDTS) model. Spatiotemporal scene information can be extracted based on semantic information from text instructions with the LDTS model. The map information, agent information, and semantic information can be fused using a cross-attention fusion module of the LDTS model into text-conditioned encodings. Language-conditioned trajectories can be generated based on the text-conditioned encodings with the LDTS for performing downstream tasks.
Systems and methods for self-supervised feature disentanglement for calibration-free multi-camera multi-object tracking. View-specific features and viewagnostic features of a tracked entity can be identified (510) from different camera views by encoding masked detection features of the tracked entity. The masked detection features can be reconstructed (520) into single-view feature representations from the view-specific features. Cross-view feature representations can be generated (530) from the view-agnostic features that capture shared characteristics from the different camera views. The single-view feature representations and the cross-view feature representations can be combined (540) into multi-entity multi-camera tracks that capture the characteristics of the tracked entity from the different camera views for downstream tasks.
Systems and methods for optimizing visual reasoning task workflow. The systems and methods include generating (400) an initial workflow trajectory to train a model to perform a task, the initial workflow trajectory being formed from environmental information, a prompt, and visual information and storing (404) sub-workflows that form the initial workflow trajectory, the sub-workflows including actions that are performed by Application Programming Interfaces (APIs). The systems and methods further include refining (408) the initial workflow trajectory to form an augmented workflow by iteratively optimizing the sub-workflows of the initial workflow trajectory, the iteratively optimizing includes comparing the environmental information of the augmented workflow with the environmental information from the initial workflow trajectory and selecting a sub-workflow that better meets a predetermined criteria to perform the task and training (420) the model to perform the task with the augmented workflow.
Methods and systems for training a model include generating (204) a relightable neural radiance field (NeRF) reconstruction of an input video of a driving scene. A virtual object is inserted (206) into the driving scene using the NeRF reconstruction to create a simulated scene. Scene intrinsics are optimized (208) within the simulated scene. An autonomous driving model is trained (209) using the simulated scene.
G06N 3/006 - Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
Systems and methods for identifying an issue in an input image displayed on a user interface, the issue being a visual depiction of an aspect of the input image that training data used for training a model does not have sufficient training on, having sufficient training includes the model reaching a performance threshold in response to testing the model on the issue and generating a natural language description of the issue. The systems and methods further include generating a set of simulated images from the natural language description that reflect one or more variations of the issue, selecting one or more training images to provide selected one or more training images from the set of simulated images, the selected one or more training images increasing the one or more variations of the issue in the training data, and training the model using the selected one or more training images.
G06V 20/56 - Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
G06V 10/80 - Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
B60W 60/00 - Drive control systems specially adapted for autonomous road vehicles
B60W 40/02 - Estimation or calculation of driving parameters for road vehicle drive control systems not related to the control of a particular sub-unit related to ambient conditions
11.
MULTI-SENSOR APPROACH FOR FIBER-BASED MANHOLE / HANDHOLE LOCALIZATION AND CONDITION MONITORING
An integrated Distributed Fiber Optic Sensing (DFOS) system and method that combines Distributed Acoustic Sensing (DAS) and Distributed Temperature Sensing (DTS) that provides enhanced manhole/handhole (MH/HH) localization, condition diagnostics, and anomaly detection. The system and method leverages the capabilities of both sensing methods: DAS utilizes ambient noise and machine learning (ML) for acoustic signature identification, while DTS utilizes day/night temperature variations. This combined approach significantly improves MH localization accuracy from an initial value of standalone systems by cross-referencing DAS and DTS data.
G01D 5/353 - Mechanical means for transferring the output of a sensing memberMeans for converting the output of a sensing member to another variable where the form or nature of the sensing member does not constrain the means for convertingTransducers not specially adapted for a specific variable using optical means, i.e. using infrared, visible or ultraviolet light with attenuation or whole or partial obturation of beams of light the beams of light being detected by photocells influencing the transmission properties of an optical fibre
G01H 9/00 - Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves by using radiation-sensitive means, e.g. optical means
G01K 11/324 - Measuring temperature based on physical or chemical changes not covered by group , , , or using changes in transmittance, scattering or luminescence in optical fibres using Raman scattering
A differential algorithm and method for calibrating a physical digital model, or digital twin, of an optical line system (OLS) is provided. The OLS comprises a multi-span optical link with a plurality of Erbium-Doped Fiber Amplifiers (EDFAs), each having integrated total power monitors, and optical fiber spans. The method utilizes a minimal, pre-defined set of measurements organized into at least a first dataset and a second dataset. The calibration process segments the problem by using the first dataset to extract total fiber attenuation profiles. The second dataset is used in a deterministic, feature-extraction process that iteratively analyzes the EDFAs from the last stage to the first stage. This analysis involves computing numerical derivatives of measured signal and noise power profiles with respect to target EDFA control parameters.
H04B 10/25 - Arrangements specific to fibre transmission
H04B 10/079 - Arrangements for monitoring or testing transmission systemsArrangements for fault measurement of transmission systems using an in-service signal using measurements of the data signal
H04B 17/11 - MonitoringTesting of transmitters for calibration
H04B 17/21 - MonitoringTesting of receivers for calibrationMonitoringTesting of receivers for correcting measurements
13.
MULTI-EVENT DISTRIBUTED FORWARDING SENSING WITH DUAL-SENSOR ADAPTIVE BEAMFORMING
A distributed forwarding sensing system and method for multi-event localization and high-fidelity acoustic waveform reconstruction in which the method includes modeling a bi-directional distributed forwarding sensing scheme as an equivalent dual-element sensor array (SA2), where an event location (z) along a fiber is mapped to a direction-of-arrival (DOA) angle (α). Signals from first and second receivers are transformed into the time-frequency domain. Generalized Cross-Correlation with Phase Transform (GCCPHAT) is used to accurately localize multiple simultaneous events by estimating a time shift (Δτ). An adaptive beamforming technique, such as a Generalized Sidelobe Canceller (GSC), is then steered toward the desired event location to enhance the acoustic signal and mitigate noise and interference from other locations along the fiber, resulting in a high-fidelity reconstructed acoustic waveform suitable for machine learning classification.
G01D 5/353 - Mechanical means for transferring the output of a sensing memberMeans for converting the output of a sensing member to another variable where the form or nature of the sensing member does not constrain the means for convertingTransducers not specially adapted for a specific variable using optical means, i.e. using infrared, visible or ultraviolet light with attenuation or whole or partial obturation of beams of light the beams of light being detected by photocells influencing the transmission properties of an optical fibre
G01H 9/00 - Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves by using radiation-sensitive means, e.g. optical means
14.
POWER-AWARE DFOS DEPLOYMENT A HYBRID HEURISTIC AND INTEGER LINEAR PROGRAMMING STRATEGY
A novel, two-stage Distributed Fiber Optic Sensor (DFOS) placement strategy and method that ensures resilient monitoring of critical infrastructure during electrical power supply failures. This strategy and method combines a heuristic algorithm, PURE (Power Source-aware Route Exploration), with Integer Linear Programming (ILP) optimization. The PURE algorithm explores potential DFOS routes while explicitly considering the dependency of DFOS devices on the electrical power distribution network, ensuring routes electrically powered by the same electrical power feeder are disjoint. Subsequently, the ILP selects the optimal set of DFOS placements to minimize the total number of deployed sensors while meeting critical infrastructure monitoring requirements, such as redundant monitoring for high-importance links. The method enhances the observability of critical links, achieving 100% monitoring coverage for important links during simulated power outages affecting an electric feeder.
G01D 5/353 - Mechanical means for transferring the output of a sensing memberMeans for converting the output of a sensing member to another variable where the form or nature of the sensing member does not constrain the means for convertingTransducers not specially adapted for a specific variable using optical means, i.e. using infrared, visible or ultraviolet light with attenuation or whole or partial obturation of beams of light the beams of light being detected by photocells influencing the transmission properties of an optical fibre
G01H 9/00 - Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves by using radiation-sensitive means, e.g. optical means
15.
DYNAMIC MIXED ROUTING IN LLMS FOR MEDICAL DECISION MAKING
Methods and systems include embedding an input query, including contextual information. Performance and cost of executing the input query are predicted on each of a set of language models. The prediction is performed using a multi-armed bandit approach with each of the language models being represented by a respective arm. The input query is executed on a selected model that has a best balance of performance and cost.
G16H 50/70 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
G16H 10/20 - ICT specially adapted for the handling or processing of patient-related medical or healthcare data for electronic clinical trials or questionnaires
G16H 10/60 - ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
G16H 40/00 - ICT specially adapted for the management or administration of healthcare resources or facilitiesICT specially adapted for the management or operation of medical equipment or devices
Methods and systems for video processing include performing analyses on an input video from a vehicle to generate respective outputs. The outputs are combined into a structured hierarchical format that divides outputs into framelevel and video-level information. The outputs in the structured hierarchical format are processed using a large language model (LLM) to determine a driving action. The driving action is performed in the vehicle.
G06V 20/56 - Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
G06V 20/40 - ScenesScene-specific elements in video content
G06V 20/70 - Labelling scene content, e.g. deriving syntactic or semantic representations
B60W 40/02 - Estimation or calculation of driving parameters for road vehicle drive control systems not related to the control of a particular sub-unit related to ambient conditions
17.
VISUAL LANGUAGE MODEL INSTRUCTION TUNING FOR ENHANCED SPATIAL REASONING
Systems and methods for generating training data. More specifically, extracting bounding boxes and quaternion data of objects in selected image frames, the quaternion data representing a spatial orientation of the objects (702), determining coordinates of the bounding boxes and the quaternion data for the objects in the selected image frames (710), and evaluating kinematic quantities of the objects with monotonic timestamps of the selected image frames, the evaluation including scaling the objects using depth data from three dimensional (3D) imaging (712). The systems and methods further include correlating the kinemssatic quantities to natural language text (716), forming instruction-following training data for spatial reasoning based on the correlated kinematic quantities and natural language text, the spatial reasoning including performing tasks that include spatio-temporal dynamics (720), training a visual language model with the instruction-following training data (722), and predicting the kinematic quantities of environmental objects in live video feeds from an autonomous vehicle (726).
Systems and methods for multi-modality anomaly detection using artificial intelligence models such as fused models. Metric data and log data obtained from a monitored entity can be encoded (510) into metric representations and log representations by utilizing transformer encoders of a cross-joint variational autoencoder (CJVAE). The metric representations and the log representations can be fused (520) into a joint context representation by utilizing a fusion transformer encoder of the CJVAE. The joint context representation can be decoded (530) by utilizing transformer decoders of the CJVAE to reconstruct the metric representations and the log representations. An anomaly for the monitored entity can be detected (540) by aggregating detection results from the CJVAE based on the metric representations and the log representations, a metric-specific detection result from a metric detector, and a log-specific detection result from a log detector to resolve determined issues of the monitored entity caused by the anomaly.
Methods and systems for code generation include generating (302) code for tree root nodes responsive to a query that specifies a task. The tree root nodes are expanded (306) into trees based on foresting tree search using scattering to select varied directional prompts and sharing direction information between the trees. Generated code is output (316) corresponding to a node from the trees that satisfies a test case.
G16H 50/70 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
G16H 50/20 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
G16H 20/00 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
G16H 40/00 - ICT specially adapted for the management or administration of healthcare resources or facilitiesICT specially adapted for the management or operation of medical equipment or devices
Methods and systems include fine-tuning (200) a small language model (SLM) to determine a first probability distribution. Text is generated (210) with a large language model (LLM), including modifying a second probability distribution of the LLM using the first probability distribution so that the text is human-like. A detector is trained (220), using the text, to determine whether input text is generated by a human or by a language model.
G16H 50/20 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
21.
EVALUATING FAITHFULNESS OF EXPLAINABLE AI FOR MEDICAL DECISION MAKING
Methods and systems include fine-tuning (302) a classifier while masking part of a training dataset to cause a distribution of the classifier to match a distribution of an explainer model. A performance of the explainer model is determined (310) using the fine-tuned classifier to ensure that the explainer has an above-threshold fidelity. A downstream task is performed (320) using the classifier and the explainer model.
G16H 50/20 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
22.
EXPLAINABLE MULTI-MODAL TIME-SERIES PREDICTION FOR MEDICAL DECISION MAKING
Methods and systems include inferring (304) a first prediction and an explanation based on a time series input and a text input using a multi-modal prototype-based encoder. A second prediction is inferred (306) based on the text input and the explanation using a large language model. The first prediction and the second prediction are fused (308) to generate a fused prediction. A reflection is generated (309) based on the fused prediction, the second prediction, and the text input. The text input is refined (309) based on the reflection.
G16H 50/20 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
Systems and methods for property guided molecular optimization using artificial intelligence diffusion models. An equivariant continuous denoising diffusion implicit model autoencoder framework (DDIM-AE) can be trained (510) on a conformational dataset to predict raw data from data corrupted by a time-dependent noise to obtain a trained DDIM-AE that ensures controlled generation of threedimensional (3D) molecules. Linear optimization of semantic embeddings of 3D molecules can be performed (520) with a linear classifier to achieve a target property value from desired properties and obtain an optimized embedding. An optimized 3D molecule that includes molecular conformation with the desired properties while preserving interactions with biochemical molecules can be generated (530) from the optimized embedding with the trained DDIM-AE.
G16H 50/20 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
G16B 15/00 - ICT specially adapted for analysing two-dimensional or three-dimensional molecular structures, e.g. structural or functional relations or structure alignment
24.
SAMPLED LANGUAGE MODELS FOR MEDICAL DECISION MAKING
Methods and systems include searching (402) for prompt tokens in a document corpus, starting from a random point in the document corpus. A next token is added (404) to an updated prompt from the document corpus after the prompt tokens have been located. The searching and adding are iteratively repeated (402, 404) using the updated prompt until an end condition is reached. An action is performed (406) responsive to the updated prompt.
G06F 40/284 - Lexical analysis, e.g. tokenisation or collocates
G16H 50/20 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
25.
CROSS-DOMAIN MULTI-MODAL TIME SERIES ANNOTATION FOR MEDICAL DECISION MAKING
Methods and systems include generating (420) general annotations for input time series data based on annotations from one or more source domains. Domain-specific annotations are generated (430) for the input time series based on annotations from a target domain and based on the general annotations. An action is performed (440) responsive to the domain-specific annotations and the general annotations.
G16H 50/20 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
G16H 10/60 - ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
G06N 3/049 - Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
Methods and systems include estimating (212) situational weights for an agent based on a distance measure for steps taken by the agent. The situational weights are combined (216) with uncertainties from the agent for the steps to determine a total uncertainty for an action indicated by the agent. The action indicated by the agent is performed (206) responsive to the total uncertainty.
G16H 50/20 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
Methods and systems include fine-tuning (204) a surrogate model, using example images generated by a target model, to match a distribution of the target model. A new image is masked (206) to generate a masked image. A recovered image is generated (208) that fills in a masked region of the masked image using the surrogate model. The recovered image is compared (210) to the new image to determine that the new image was generated by the target model. An action is performed (306) responsive to the determination that the new image was generated by the target model.
G16H 50/20 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
28.
DIAGRAM ANALYSIS USING VISUAL LANGAUGE MODELS FOR MEDICAL DECISION MAKING
Methods and systems for image analysis include initializing (212) a set of initial regions that segment an input image. The initial regions are split (214) into split regions. The split regions are merged (216) into combined regions. Image analysis is performed (220) on the combined regions using a visual language model, responsive to a query. An action is performed (230) responsive to the image analysis in a downstream task.
G16H 50/20 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
G16H 30/20 - ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
G16H 30/40 - ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
G16H 10/20 - ICT specially adapted for the handling or processing of patient-related medical or healthcare data for electronic clinical trials or questionnaires
G16H 10/60 - ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
Systems and methods for visual retrieval augmented generation for artificial intelligence models such as multimodal large language models. Associations between image and description pairs can be identified (420) from an awareness dataset by finetuning a multi-modal large language model (MLLM) with the awareness dataset based on randomly chosen images added to each example from a relevant dataset. Visual distractions for image processing with the MLLM can be minimized (430) by finetuning the MLLM with a focus dataset based on randomly chosen images added to each example from the relevant dataset. Visual hallucinations from the MLLM can be mitigated (440) by finetuning the MLLM with a learning dataset based on related images having corresponding texts added to each example from the relevant dataset to utilize extracted information from associations between provided text from multiple images and a learning dataset.
Systems and methods for subgroup discovery for survival analysis. A survival analysis model can be fitted (510) to neighborhoods of points from a dataset to obtain a fitted model. The neighborhoods of points can be filtered (520) into a core group based on an expected prediction entropy metric. An undesirable event probability for the core group can be evaluated (530) based on a conditional rank distribution of the core group to obtain rejected points. An axis-aligned hyperrectangle can be generated (540) from an average of features in the core group to obtain a discovered subgroup, the axis-aligned hyperrectangle limited by the rejected points. An undesirable event for monitored entities predicted by a machine learning model that utilizes the discovered subgroup can be mitigated (550).
Methods and systems include comparing a description of an issue to documents to generate similarity scores for the documents. A set of most-relevant documents are selected from the documents based on the similarity scores. A large language model (LLM) is prompted to generate a solution to the issue. A corrective action is performed based on the solution to correct the issue.
G16H 50/20 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
G16H 50/70 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
G16H 10/60 - ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
G16H 50/30 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indicesICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for individual health risk assessment
Methods and systems include generating (412) a first question relating to supporting an input claim. A search is performed (414) based on the first question to identify evidence relating to the input claim. An answer to the first question is generated (416) based on the evidence. Additional questions are iteratively generated (412), with searches being performed (414)based on the additional questions, and with answers to the additional questions being generated (416) until a predetermined stop condition is reached. The input claim is classified (420) by predicting a label based on evidence identified by the searches.
G16H 50/20 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
G16H 10/60 - ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
ϕϕϕ-OTDR by transmitting a plurality of phase reference channels alongside the frequency-division multiplexed (FDM) channels. Compared with prior art in, more than one reference channel is used to achieve faster phase synchronization at the cost of higher bandwidth and system complexity.
G01M 11/00 - Testing of optical apparatusTesting structures by optical methods not otherwise provided for
G01D 5/353 - Mechanical means for transferring the output of a sensing memberMeans for converting the output of a sensing member to another variable where the form or nature of the sensing member does not constrain the means for convertingTransducers not specially adapted for a specific variable using optical means, i.e. using infrared, visible or ultraviolet light with attenuation or whole or partial obturation of beams of light the beams of light being detected by photocells influencing the transmission properties of an optical fibre
34.
ELASTIC FIBER OPTIC, TIME-OF-FLIGHT SENSOR FOR LONG DISTANCE LANDSLIDE MONITORING WITH SUB-MM PRECISION
Disclosed are systems and methods that employ elastic fiber optic, time-of-flight sensors for long distance landslide monitoring with sub-mm precision. The time-of-flight (ToF) sensor is integrated in conjunction with a single-photon avalanche diode (SPAD). By coupling both the emission source and the detector with a stretchable optical fiber, our inventive systems and methods continuously monitor the length of the stretchable optical fiber by measuring a traveling time of an optical pulse traversing the stretchable optical fiber. A significant, detectable change in the length of the stretchable optical fiber – indicative of ground movement or deformation, triggers an alarm, providing an early warning for potential landslides. As such, systems and methods according to aspects of the present disclosure provide a reliable, sensitive, precise, cost-effective, real-time solution for landslide detection and monitoring – a problem that has plagued the art.
G01B 11/16 - Measuring arrangements characterised by the use of optical techniques for measuring the deformation in a solid, e.g. optical strain gauge
G01D 5/353 - Mechanical means for transferring the output of a sensing memberMeans for converting the output of a sensing member to another variable where the form or nature of the sensing member does not constrain the means for convertingTransducers not specially adapted for a specific variable using optical means, i.e. using infrared, visible or ultraviolet light with attenuation or whole or partial obturation of beams of light the beams of light being detected by photocells influencing the transmission properties of an optical fibre
G01L 1/24 - Measuring force or stress, in general by measuring variations of optical properties of material when it is stressed, e.g. by photoelastic stress analysis
G08B 21/10 - Alarms for ensuring the safety of persons responsive to calamitous events, e.g. tornados or earthquakes
35.
T-CELL RECEPTOR COMPLEX OPTIMIZATION WITH REINFORCEMENT LEARNING
Systems and methods for particularly t-cell receptor complex optimization with reinforcement learning. Classifiers using variational information bottleneck with attention of experts (AVIB classifiers) can be fine-tuned (110) for different representations of desired t-cell receptor (TCR) sequences for a patient. Proximal policy optimization (PPO) models can be trained (120) with reinforcement learning using the AVIB classifiers as reward functions to achieve higher affinity in generating interaction sequences for the desired TCR sequences through automated decision making. The interaction sequences can be clustered (130) based on k-mer profiles to select the interaction sequences having highest binding scores in each cluster as final sequences. A biological functional potency of the final sequences can be validated (140).
G16B 40/00 - ICT specially adapted for biostatisticsICT specially adapted for bioinformatics-related machine learning or data mining, e.g. knowledge discovery or pattern finding
G16B 30/00 - ICT specially adapted for sequence analysis involving nucleotides or amino acids
G16B 20/20 - Allele or variant detection, e.g. single nucleotide polymorphism [SNP] detection
G16B 50/00 - ICT programming tools or database systems specially adapted for bioinformatics
C12Q 1/6883 - Nucleic acid products used in the analysis of nucleic acids, e.g. primers or probes for diseases caused by alterations of genetic material
36.
OPTIMIZING LARGE LANGUAGE MODELS WITH META LEARNING AND CHAIN OF THOUGHT
Systems and methods for optimizing large language models with meta learning and chain of thought. A large language model (LLM) can be fine-tuned (110) by generating optimized prompts based on an associated score of a generated output relative to a target output of a LLM-based optimizer using tuples of questions and the prompts generated from a dataset. Core features from the dataset that obtained top-ranked associated scores for the optimized prompts can be learned (120) by utilizing chain of thought mechanism with the LLM-based optimizer. A meta prompt from the core features can be generated (130) with the LLM-based optimizer to perform downstream tasks with the LLM.
G16H 50/20 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
37.
EFFICIENT PROCESSING RESOURCE USAGE IN LONG RANGE, MULTI-BAND BACKSCATTERING FIBER SENSING
Disclosed are distributed fiber optic sensing (DFOS) systems and methods that more efficiently employ processing resources which in turn provide one or more of reduced chip costs, reduced processing power necessary, and more supported bands by employing more frequency bands for DFOS sensor fiber locations farther away from an interrogator, and fewer frequency bands for DFOS sensor fiber locations nearer to the interrogator such that a more balanced performance is realized for locations along the length of the DFOS sensor fiber as compared with contemporary systems and methods.
G01D 5/353 - Mechanical means for transferring the output of a sensing memberMeans for converting the output of a sensing member to another variable where the form or nature of the sensing member does not constrain the means for convertingTransducers not specially adapted for a specific variable using optical means, i.e. using infrared, visible or ultraviolet light with attenuation or whole or partial obturation of beams of light the beams of light being detected by photocells influencing the transmission properties of an optical fibre
G01H 9/00 - Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves by using radiation-sensitive means, e.g. optical means
38.
GUIDING MULTIPLE MODELS WITH A LARGE LANGUAGE MODEL
Systems and methods for guiding multiple models with a large language model. An instruction code can be generated (110) for a very large language model (VLLM) to generate a general guidance to guide AI models that answer reasoning questions for query documents. The instruction code can be updated (120) with domain-specific information from reference materials to generate, with the VLLM, a reasoned answer for reasoning questions about the query documents generated based on the general guidance. The reasoned answers can be processed (130) into the general guidance with the VLLM. The reasoning question iteratively applied to the query documents can be answered (140) using the general guidance with the AI models to perform downstream tasks.
Methods and systems for image segmentation include initializing (204) a student model and a teacher model using a labeled dataset. An initial mask is generated (206) for an unlabeled image using the teacher model. The initial mask is refined (208) to generate a refined mask using a pretrained foundation model. The student model is tuned (210) using the unlabeled image and the refined mask as a pseudo-ground–truth label. The teacher model is updated (212) using the tuned student model.
Methods for a DFOS/DAS system that uses a Rayleigh backscattering optical signal, employs a transmitter/interrogator that generates optical signals with multiple frequencies and directs the generated optical signals into a optical fiber sensor, receives, by a receiver, backscattered signals, processes each frequency received and combines and interleaves frequency bands for improved signal-to-noise and a faster sampling rate. The receiver uses a correlation method for polarization and band combining/interleaving, that rotates the polarization and band diversities into a direction of one with highest averaged power, by aligning a same location along the length of the optical fiber sensor from different bands to a same clock cycle, apply correlation methods to the band diversities, to rotate the same location from the different bands to the same direction, and combines sub-bands allocated for SNR improvement, and delays resulting bands and interleaves them.
G01D 5/353 - Mechanical means for transferring the output of a sensing memberMeans for converting the output of a sensing member to another variable where the form or nature of the sensing member does not constrain the means for convertingTransducers not specially adapted for a specific variable using optical means, i.e. using infrared, visible or ultraviolet light with attenuation or whole or partial obturation of beams of light the beams of light being detected by photocells influencing the transmission properties of an optical fibre
G01H 9/00 - Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves by using radiation-sensitive means, e.g. optical means
41.
AUTOMATED FORM FILLING WITH RETRIEVAL AUGMENTED GENERATION FOR MEDICAL DECISION MAKING
Methods and systems for filling data include extracting text (102) from a structured document and document instructions to identify a field within the structured document. Text is extracted (102) from a contextual document to identify information relating to the field. Information is selected (118) from the contextual document based on a comparison between the extracted text from the contextual document and the extracted text from the structured document and document instructions. The field within the structured document is filled (210) using the selected information to create a filled document.
G06V 30/413 - Classification of content, e.g. text, photographs or tables
G16H 10/60 - ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
G16H 50/00 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
Methods and systems for patient stratification include learning (404) interdependent biomarkers as integrated time-series machine learning models. A disease stage is identified (424) for a patient based on collected biomarker data. A treatment for the patient is performed (430) based on the identified disease stage and a predicted future response of the patient.
G16H 50/20 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
G16H 20/00 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
G16H 50/70 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
G16H 10/60 - ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
G16B 20/00 - ICT specially adapted for functional genomics or proteomics, e.g. genotype-phenotype associations
Systems and methods for generating a three-dimensional (3D) scene include generating (1402) a depth video based on a text description input, a high-definition (HD) map input, and an ego trajectory input wherein geometry consistency guidance is applied to enforce geometry consistency in the depth video. A color video is generated (1405) based on the text description input, the HD map input, the ego trajectory input, and the depth video wherein geometry consistency guidance is applied to enforce geometry consistency in the color video; and generating (1408) a 3D scene based on the depth video, the color video, and the ego trajectory input.
G06T 7/90 - Determination of colour characteristics
G09B 9/042 - Simulators for teaching or training purposes for teaching control of vehicles or other craft for teaching control of land vehicles providing simulation in a real vehicle
44.
3D DRIVING SCENE GENERATION WITH OUTPAINTING AND INTERPOLATION
Systems and methods for generating a simulated scene include generating (1502), by a first diffusion network, a first key frame based on a text description input and a high definition (HD) map input. The first key frame is warped (1504) to a second viewpoint. a second key frame is generated (1506), by a second diffusion network, based on the text description input, the HD map input, and the warped first key frame. A middle frame is generated (1508), by a third diffusion network, between the first key frame and the second key frame based on the text description input, the HD map input, and projections from the first key frame and the second key frame.
G09B 9/042 - Simulators for teaching or training purposes for teaching control of vehicles or other craft for teaching control of land vehicles providing simulation in a real vehicle
45.
LLM SKILL LEARNING FOR MEDICAL DECISION MAKING THROUGH SELF-PLAY
Methods and systems for medical decision making include selecting (120) a strategy from a strategy library, expressed in natural language, and selecting (130) an improvement from an improvement library, expressed in natural language. The strategy is combined (140 with the improvement using a large language model (LLM) to generate an improved strategy. The improved strategy is evaluated (310) to generate feedback. The strategy library and the improvement library are updated (312) based on the feedback. An action is performed (314) based on the improved strategy.
G16H 50/20 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
G16H 50/70 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
G16H 20/00 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
Disclosed are systems and methods that employ distributed fiber optic sensing (DFOS) / distributed temperature sensing (DTS) to measure/monitor soil moisture and seepage at sub-meter spatial resolution over a large geographic area. In sharp contrast to the prior art which generally employed many, point soil moisture sensors, systems and methods according to aspects of the present disclosure employ DTS with an fiber optic sensor that advantageously senses soil temperature at sub-meter spatial resolution continuously. From these continuous, wide areas, high resolution DTS measurements, soil moisture and seepage determinations of soil in which the fiber optic sensor contacts are made.
G01K 11/32 - Measuring temperature based on physical or chemical changes not covered by group , , , or using changes in transmittance, scattering or luminescence in optical fibres
Systems and methods for generating 3D scenes include a masked red, green, blue, depth (RGBD) input, which is separated (1602) into a masked RGB input and a masked depth input. The masked depth input is compressed (1604). The masked RGB input is compressed (1606). A high definition (HD) map control signal is generated (1608) for a depth stream, and an HD map control signal is generated (1610) for an RGB stream. A depth output is generated (1616) based on inputs from the depth stream, the HD map control signal for the depth stream, text encoder, and random sampled noise. An RGB output is generated (1618) based on inputs from the RGB stream, the HD map control signal for an RGB stream, text encoder, and random sampled noise to train a dual stream diffusion network.
G09B 9/042 - Simulators for teaching or training purposes for teaching control of vehicles or other craft for teaching control of land vehicles providing simulation in a real vehicle
48.
LLMS FOR TIME SERIES PREDICTION IN MEDICAL DECISION MAKING
Methods and systems for time series analysis include generating (322) a text summary of a time series using a first large language model (LLM) agent. A prompt is generated (324) using a multi-modal encoder with the time series and the text summary as inputs. An event prediction is generated (326) using a second LLM agentwith the text summary and the prompt as inputs. An action is performed (330) responsive to the event prediction.
G16H 50/20 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
G16H 10/60 - ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
G16H 50/70 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
G16H 20/00 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
Systems and methods for view-conditioned diffusion for real-world vehicle gaussian splatting. A single perspective image can be transformed (110) using image transformation techniques to generate a training dataset that addresses a domain gap between synthetic data and real-world data in a traffic scene. A pre-trained diffusion model can be finetuned (120) with the training dataset to obtain a fine-tuned diffusion model. Perspective-aware images having different perspective views of an entity from the single perspective image can be generated (130) using the fine-tuned diffusion model. A large generative model (LGM) can be trained (140) using the perspective-aware images to generate a gaussian splatting model for the entity. View-conditioned simulations from the single perspective image can be generated (150) by using the gaussian splatting model for downstream tasks.
G06T 19/00 - Manipulating 3D models or images for computer graphics
G06T 5/20 - Image enhancement or restoration using local operators
B60W 40/02 - Estimation or calculation of driving parameters for road vehicle drive control systems not related to the control of a particular sub-unit related to ambient conditions
50.
LLM TIME SERIES ANALYSIS FOR MEDICAL DECISION MAKING
Methods and systems for time series analysis include encoding (224) input time series data using a pre-trained encoder. The encoded time series is mapped (114) to a format suitable for a large language model (LLM) using an alignment model. The mapped, encoded time series is analyzed (226) using the LLM to generate a text output. An action is performed (230) responsive to the text output.
G16H 50/20 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
51.
MULTI-CAMERA VIDEO ANALYSIS USING LARGE LANGUAGE MODELS
Systems and methods for multi-camera video analysis using large language models. Non-overlapping frames can be identified (110) from multiple video feeds from a base camera and secondary cameras. Similar information from the multiple video feeds can be filtered (115) to remove redundancies from the non-overlapping frames from the non-overlapping frames and obtain filtered frames. Textual data that describes semantic information of entities can be extracted (120) from the filtered frames using a vision-language model (VLM). Undetected objects can be identified (130) from the filtered frames by analyzing the textual data and the entities within different perspectives of the filtered frames. Combined textual captions that combines the textual data and descriptions of the undetected objects into embedded vectors can be generated (140) for the multiple video feeds. Corrective action can be performed (150) for a monitored entity based on the combined textual captions from the embedded vectors.
Disclosed are integrated DFOS / DAS systems, methods, and structures that advantageously detecting fuse cutoff blowing events using existing telecom cables. Our systems, methods, and structures employ an exciter to broadcast acoustic signal tracks and evaluated on wooden utility poles within a real-scale testbed, simulating fuse cutoff blowing events in the power grid. A Distributed Acoustic Sensing (DAS) system connected to an optical fiber sensor cable collects a 2D waterfall matrix. A frequency learning model is subsequently used to identify these acoustic events based on the results of frequency analysis.
G01H 9/00 - Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves by using radiation-sensitive means, e.g. optical means
G01D 5/353 - Mechanical means for transferring the output of a sensing memberMeans for converting the output of a sensing member to another variable where the form or nature of the sensing member does not constrain the means for convertingTransducers not specially adapted for a specific variable using optical means, i.e. using infrared, visible or ultraviolet light with attenuation or whole or partial obturation of beams of light the beams of light being detected by photocells influencing the transmission properties of an optical fibre
Systems and methods for t-cell receptor complex optimization using quantum variational autoencoders. Mixed-state t-cell receptor (TCR) embeddings and mixedstate major histocompatibility complex peptide (pMHC) embeddings can be generated (110) by embedding input TCR sequences and input pMHC sequences, respectively, using a quantum variational autoencoder (QVAE). A combinatorial optimization of the mixed-state TCR embeddings while fixing the mixed-state pMHC embeddings can be performed (120) using a machine learning-based predictor. TCR sequences from the mixed-state TCR embeddings and the mixed-state pMHC embeddings, after the combinatorial optimization, can be decoded (130) using the QVAE to generate an optimized TCR sequence. The optimized TCR sequence can be synthesized (140) as a synthetic compound for downstream tasks.
G16H 20/17 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients delivered via infusion or injection
54.
INCIDENT DIAGNOSIS WITH RETRIEVAL AUGMENTED LLM FOR MEDICAL DECISION MAKING
Methods and systems for anomaly analysis include generating (502) an incident timeline graph for an anomaly, based on a graph of relationships sensors and temporal information relating to anomalous sensor readings. Documents are retrieved (504) relating to the anomaly using a signature based on the incident timeline graph. A prompt is generated (506) using an anomaly description based on the incident timeline graph and examples taken from the retrieved documents. A report is generated (508) describing the incident using with the prompt as an input to a large language model. An action is performed (510) responsive to the anomaly based on information in the report.
G16H 50/20 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
G16H 40/67 - ICT specially adapted for the management or administration of healthcare resources or facilitiesICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for remote operation
G16H 15/00 - ICT specially adapted for medical reports, e.g. generation or transmission thereof
G16H 70/00 - ICT specially adapted for the handling or processing of medical references
Systems and methods for optimizing latency and coverage in ultra-wideband devices. Connections can be established (110) between beacons through signal transmissions. Positions of the beacons at a discovered area can be refined (120) within a topology having support beacons that fill gaps of coverage between the beacons based on synchronized signal handshakes. Latency and coverage of the beacons can be optimized (130) by prioritizing beacons within the topology based on proximity and signal strength.
H04W 4/80 - Services using short range communication, e.g. near-field communication [NFC], radio-frequency identification [RFID] or low energy communication
H04W 4/02 - Services making use of location information
H04W 4/38 - Services specially adapted for particular environments, situations or purposes for collecting sensor information
Methods and systems for tailored treatment include embedding (102) a T-cell receptor (TCR) sequence and embedding (104) an epitope sequence. The embedded TCR sequence and the embedded epitope sequence are processed with a discriminator (106) to generate a multi-class label. The multi-class label is classified (108) to generate a binary binding prediction. A treatment is generated (330) based on the binary binding prediction.
G16H 20/00 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
Systems and methods for sensor-agnostic indoor localization. The localization including locating (804) a target object in an indoor space by employing sensors of different modalities, converting (810) data from the sensors of different modalities into a single modality by employing a sensor-agnostic modality converter, and determining (812) from the data in the single modality a range of the target object from a fixed point to locate a position of the target object within the indoor space.
G01C 21/20 - Instruments for performing navigational calculations
G01C 5/06 - Measuring heightMeasuring distances transverse to line of sightLevelling between separated pointsSurveyors' levels by using barometric means
G01S 5/02 - Position-fixing by co-ordinating two or more direction or position-line determinationsPosition-fixing by co-ordinating two or more distance determinations using radio waves
Methods and systems for query processing include updating (304) a knowledge graph based on information extracted from a streaming information input. One or more queries relating to the streaming information input are processed (306) based on the knowledge graph. An action is performed (308) responsive to the one-or-more queries.
Disclosed are integrated DFOS / DAS systems, methods, and structures that advantageously enhances rainfall sensing by employing a Deep Phase-Magnitude Network (DFMN), dividing raw DFOS sensing data into phase and magnitude components, and performing targeted feature learning on each component independently. The disclosed systems, methods, and structures employ a Phase Frequency learnable filter (PFLF) for phase component filtering and utilize standard convolution layers on the magnitude component, advantageously leveraging inherent physical properties of optical fiber sensing. Finally, a phase-magnitude channel is formulated in a parallel network and subsequently fuses the features for a comprehensive analysis. Experimental results on collected fiber sensing data show that our systems and method according to aspects of the present disclosure perform favorably as compared with alternative, state-of-the-art approaches
G01H 9/00 - Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves by using radiation-sensitive means, e.g. optical means
G01D 5/353 - Mechanical means for transferring the output of a sensing memberMeans for converting the output of a sensing member to another variable where the form or nature of the sensing member does not constrain the means for convertingTransducers not specially adapted for a specific variable using optical means, i.e. using infrared, visible or ultraviolet light with attenuation or whole or partial obturation of beams of light the beams of light being detected by photocells influencing the transmission properties of an optical fibre
The present disclosure relates to medical and health decision making and, more particularly, to treatment based on tumor clonality estimates. Methods and systems include analyzing (230) genotypes of a tumor to identify clonality sub-types present in the tumor, using a machine learning model that is trained to learn a multilevel evolutionary process or genetic algorithm, by using a recursive Wasserstein objective to output the clonal sub-types, an ancestral structure, and a fitness model. A treatment is generated (240), tailored to the tumor using the clonal sub-types, and subclonal properties predicted by the model, such as subclone fitness.
G16H 20/00 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
G16B 20/00 - ICT specially adapted for functional genomics or proteomics, e.g. genotype-phenotype associations
G16H 15/00 - ICT specially adapted for medical reports, e.g. generation or transmission thereof
G16H 50/20 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
Disclosed are integrated DFOS / DAS systems, methods, and structures that employ a large-scale pretrained recognition model we refer to as an "acoustic-language model", which is pretrained with natural-language supervision ("contrastive language-audio pretraining". The acoustic-language model comprises two primary components: an acoustic encoder and a text encoder. These encoders are pretrained using a cross-modal approach on a vast dataset of acoustic features (such as images created from log Mel spectrograms) and their corresponding textual captions. When acoustic features and/or languages are input into their respective encoders within the model, they generate corresponding embedding vectors. Both embedding vectors are then linked in a joint multimodal space using linear projections. The acoustic classification tasks using this model are executed by assessing the similarity between the acoustic and language embedding vectors, essentially evaluating the maximum similarity between the acoustic features and the events described in a specific language.
Methods and systems for three-dimensional (3D) molecule generation include training (300) an autoencoder machine learning model that disentangles structural context of a molecule from properties of the molecule, using a loss function that further enforces equivariance of a coordinate representation and invariance of data likelihood. A 3D molecule is generated (320) using the trained autoencoder machine learning model.
G06N 3/042 - Knowledge-based neural networksLogical representations of neural networks
G16H 20/10 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
A method and device may convert (102) a motion dataset for use in a physics engine, wherein the physics engine includes a physics simulator and inverse dynamics network. The method and device may downsample (104) the motion dataset to obtain keyframes for motion generation and form a downsampled motion dataset. The method and device may execute a deep generative model (106) based on the downsampled motion dataset to generate a first generated motion. The method and device may execute the physics engine (110) by feeding keyframes into the physics simulator and the inverse dynamics network to generate a second generated motion. The method and device may combine (112) the first generated motion and the second generated motion to form a combined generated motion, by executing the physics engine with the first generated motion. The method and device may generate (114) a simulated motion video from the combined generated motion.
G06N 3/008 - Artificial life, i.e. computing arrangements simulating life based on physical entities controlled by simulated intelligence so as to replicate intelligent life forms, e.g. based on robots replicating pets or humans in their appearance or behaviour
Methods and systems for peptide binding prediction include predicting (202) a three-dimensional (3D) structure of a peptide and a major histocompatibility (MHC) complex to generate a graph. The 3D structure is refined (204) by pruning edges of the graph having a distance between the peptide and the MHC complex that is below a threshold value. Models for MHC-I and MHC-II binding prediction are trained (206), including Bayesian reweighting of data for the MHC-II binding prediction, using the pruned graph.
G16B 45/00 - ICT specially adapted for bioinformatics-related data visualisation, e.g. displaying of maps or networks
G16B 15/00 - ICT specially adapted for analysing two-dimensional or three-dimensional molecular structures, e.g. structural or functional relations or structure alignment
G06N 3/042 - Knowledge-based neural networksLogical representations of neural networks
Methods and systems for fairness-aware domain generalization include identifying 302 a sensitive attribute, first features related to the sensitive attribute, and second features irrelevant to the sensitive attribute. Domain-specific information for the first features and the second feature features is decoupled 304. A classifier is trained 306 with the first features and the second features to ensure cross-domain accuracy while maintaining fairness on the sensitive attribute.
G16H 50/20 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
66.
DOMAIN ADAPTATION OF ARTIFICIAL INTELLIGENCE MODELS BASED ON MULTI-SOURCE TIME-SERIES DATA
Systems and methods for domain adaptation of artificial intelligence (AI) models based on multi-source time-series data. Meta-data information from tuples of time-series data and corresponding labels for the time-series data can be learned (110) based on a fidelity loss with a prompt-based deep learning model (POND) using determined soft prompts. Mutual information from the meta-data information can be minimized (120) by minimizing a discrimination loss of domain-specific information from the meta-data information. A common prompt can be learned (130) with a learning objective that combines a training loss, the fidelity loss and the discrimination loss. AI models can be adapted (140) to perform downstream tasks for different domains by utilizing the common prompt for the AI models.
G06N 3/049 - Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
G06N 3/063 - Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using electronic means
G16H 50/20 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
67.
DOMAIN-ORIENTED LLM COMPRESSION FOR MEDICAL DECISION MAKING
Methods and systems for model compression include determining (202) importance values for respective parameters in a pre-trained model corresponding to general knowledge of the pre-trained model. Loss values are determined (204) for removal of the parameters based on the importance values and a regularization term corresponding to domain-specific knowledge. Parameters are pruned (208) from the pre-trained model based on the loss values to create a pruned model.
G06N 3/082 - Learning methods modifying the architecture, e.g. adding, deleting or silencing nodes or connections
G16H 50/20 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
Methods and systems for image segmentation include generating (104) features at multiple scales from an input image using a backbone model. The features are encoded (106) using a transformer encoder that creates a per-pixel embedding map from a high-resolution scale of the multiple scales using deformable attention layers that operate on progressively higher-resolution scales of the multiple scales. The features are decoded (108) using a transformer decoder to generate a segmentation mask.
G06T 3/4053 - Scaling of whole images or parts thereof, e.g. expanding or contracting based on super-resolution, i.e. the output image resolution being higher than the sensor resolution
Systems and methods include predicting (502) a first action step and a last action step based on an initial visual observation and a goal visual state and retrieving (504) multiple procedural plans from a procedural knowledge graph (PKG), trained using a set of training instructional videos, which start with the first action step and end with the last action step. A procedure plan is generated (506) using the retrieved multiple procedural plans. An instructional video is generated (514) based on the procedure plan.
Systems and methods for optimizing edge-assisted augmented reality (AR) devices. To optimize the AR devices, frame capture timings of AR devices can be profiled (110) that capture relationships between the AR devices. Requests from the AR devices can be analyzed (120) to determine accuracy of the frame capture timings of the AR devices based on a service level objective (SLO) metric. A frame timing plan that minimizes overall timing changes of the AR devices can be determined (130) by adapting the accuracy of the frame capture timings to optimal adjustments generated based on a change in device metrics for requests below an accuracy threshold. Current frame capture timings of cameras of the AR devices can be adjusted (140) based on the frame timing plan by generating a response pocket for the AR devices.
Systems and methods receive an annotated driving dataset including images capturing (1002) driving scenes and annotations including bounding boxes locating objects in the images. An image-caption dataset is obtained (1004) including images from common scenes and captions describing the images. A specialized dataset is accessed (1006) and includes data of specific rare or unseen categories. Problem-specific knowledge generates (1008) a list of rare or unseen categories. Dataset tuning (1010) is performed by applying vision language model (VLM) sub-categorization, cut and paste, image generation, or caption filtering to the annotated driving dataset, the image-caption dataset, and the specialized dataset based on the problem-specific knowledge. A dataset is combined (1012) and includes outputs from the dataset tuning and the annotated driving dataset. A machine learning model is trained (1014) using the combined dataset.
G06V 20/58 - Recognition of moving objects or obstacles, e.g. vehicles or pedestriansRecognition of traffic objects, e.g. traffic signs, traffic lights or roads
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
G06V 20/52 - Surveillance or monitoring of activities, e.g. for recognising suspicious objects
72.
ADVERSARIAL IMITATION LEARNING ENGINE FOR KPI OPTIMIZATION
Systems and methods for optimizing key performance indicators (KPIs) using adversarial imitation deep learning include processing (602) sensor data received from sensors to remove (604) irrelevant data based on correlation to a final KPI and generating (606), using a policy generator network with a transformer-based architecture, an optimal sequence of actions based on the processed sensor data. A discriminator network is employed (610) to differentiate between the generated action sequences and real-world high performance sequences employing. Final KPI results are estimated (612) based on the generated action sequences using a performance prediction network. The generated action sequences are applied (626) to the process to optimize the KPI in real-time.
G06Q 10/06 - Resources, workflows, human or project managementEnterprise or organisation planningEnterprise or organisation modelling
G06Q 10/04 - Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
G16H 10/60 - ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
G16H 50/50 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
Methods and systems include training (202) a model for rendering a three-dimensional volume using a loss function that includes a depth loss term and a distribution loss term that regularize an output of the model to produce realistic scenarios. A simulated scenario is generated (204) based on an original scenario, with the simulated scenario including a different position and pose relative to the original scenario in a three-dimensional (3D) scene that is generated by the model from the original scenario. A self-driving model is trained (206) for an autonomous vehicle using the simulated scenario.
B60W 60/00 - Drive control systems specially adapted for autonomous road vehicles
B60W 40/02 - Estimation or calculation of driving parameters for road vehicle drive control systems not related to the control of a particular sub-unit related to ambient conditions
G06N 3/008 - Artificial life, i.e. computing arrangements simulating life based on physical entities controlled by simulated intelligence so as to replicate intelligent life forms, e.g. based on robots replicating pets or humans in their appearance or behaviour
B60W 50/00 - Details of control systems for road vehicle drive control not related to the control of a particular sub-unit
Methods and systems for action detection include encoding (214) a text feature of an input textual description of an action using a visual language model (VLM). A video feature of an input video is encoded (212) using the VLM. The action in the video is recognized (224), based on the text feature and the video feature, to localize the action within the video. A person performing the action is located (222) within the video using the VLM.
G06V 40/20 - Movements or behaviour, e.g. gesture recognition
G06V 10/77 - Processing image or video features in feature spacesArrangements for image or video recognition or understanding using pattern recognition or machine learning using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]Blind source separation
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
Integrated DFOS systems and methods for 3D gunshot, localization, and tracking utilizing Artificial Intelligence enhanced (AI-enhanced) systems and methods for infrastructure security including electrical substations. Our systems and methods provide a comprehensive solution for substation security enhancement, integrating 3D gunshot localization, real-time tracking, and AI-driven analysis. Utilizing Distributed Acoustic Sensing (DAS) technology, our systems and methods precisely detect and triangulate the origin of gunshots in three-dimensional space. The trajectory of a bullet is determined, providing insights into the direction and potential target within the substation. AI algorithms discern between various acoustic events and provide identification of genuine threats. Upon detecting a potential gunshot, our system automatically correlates related acoustic events, such as the noise of a nearby vehicle, offering context and aiding in threat assessment. Our AI-enhanced system evaluates acoustic signals to determine real-time equipment damage resulting from gunshots, ensuring immediate remedial actions and anticipate potential future incidents.
Systems and methods for gradient-to-parameter ratio guided feature alignment for model adaptation. To adapt an artificial intelligence (AI) model to different domains, activation statistics for the AI model can be computed (110) from collected domain data. Weights of the AI model can be adjusted (120) based on the activation statistics of the training gradients. The AI model can be fine-tuned (130) by focusing adaptation intensity to layers with attention mechanism by using a ratio of gradient norm over parameter norm to obtain a fine-tuned AI model. The fine-tuned AI model can be employed to perform (140) downstream tasks such as cell segmentation from medical images.
G06N 3/084 - Backpropagation, e.g. using gradient descent
G06V 20/69 - Microscopic objects, e.g. biological cells or cellular parts
G16H 50/20 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
G16H 30/40 - ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
77.
ADVERSARIAL IMITATION LEARNING ENGINE FOR ACTION RISK ESTIMATION BASED ON SENSOR DATA
Systems and methods are provided for classifying components include monitoring (602) sensors to collect sensor data related to a state of a plurality of components; processing (606), by a computing system, the sensor data to generate an action sequence using a transformer-based policy network for each of the components. A risk score is generated (1204) for the action sequence using a Generative Adversarial Network (GAN), wherein the GAN includes a generator for generating action sequences and a discriminator to distinguish low-risk action sequences in accordance with a threshold. The low-risk action sequences are associated (1206) with components in the plurality of components based on the risk score. A status of the low-risk action sequences is communicated (1222) to the components.
Systems and methods for cable inspection using optical fiber sensing includes a hardware processor and a memory storing a computer program which, when executed by the hardware processor, causes the hardware processor to collect data (502) from a fiber optic cable and analyze (504) the data with a distributed fiber optic sensing (DFOS) system. Losses and anomalies and their locations are identified (506) in the cable. An alert is generated (514) based on the losses and anomalies.
G01D 5/353 - Mechanical means for transferring the output of a sensing memberMeans for converting the output of a sensing member to another variable where the form or nature of the sensing member does not constrain the means for convertingTransducers not specially adapted for a specific variable using optical means, i.e. using infrared, visible or ultraviolet light with attenuation or whole or partial obturation of beams of light the beams of light being detected by photocells influencing the transmission properties of an optical fibre
G01H 9/00 - Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves by using radiation-sensitive means, e.g. optical means
G01M 11/00 - Testing of optical apparatusTesting structures by optical methods not otherwise provided for
A computer-implemented method for synthesizing an image includes extracting (502) agent neural radiance fields (NeRFs) from driving video logs and storing (508) agent NeRFs in a database. For a driving video log to be edited, a scene NeRF and agent NeRFs are extracted (510) from the driving video log to be edited. One or more agent NeRFs are selected (512) from the database to insert into or replace existing agents in a traffic scene of the driving video log based on photorealism criteria. The traffic scene is edited (518) by inserting a selected agent NeRF into the traffic scene, replacing existing agents in the traffic scene with the selected agent NeRF, or removing one or more existing agents from the traffic scene. An image of the edited traffic scene is synthesized (522) by composing edited agent NeRFs with the scene NeRF and performing volume rendering.
Disclosed are systems and methods directed to a frequency analysis approach to transformer status monitoring using distributed fiber optic sensing to monitor a phase delay of a 120 Hz vibrational signal and determining an angular difference between a designated point and a reference point. Operationally, systems and methods according to aspects of the present disclosure identify phase delay patterns of a single transformer from its vibrational humming and combined vibrational signals of multiple transformers.
G01H 9/00 - Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves by using radiation-sensitive means, e.g. optical means
G01D 5/353 - Mechanical means for transferring the output of a sensing memberMeans for converting the output of a sensing member to another variable where the form or nature of the sensing member does not constrain the means for convertingTransducers not specially adapted for a specific variable using optical means, i.e. using infrared, visible or ultraviolet light with attenuation or whole or partial obturation of beams of light the beams of light being detected by photocells influencing the transmission properties of an optical fibre
H01F 27/40 - Structural association with built-in electric component, e.g. fuse
81.
LOCALIZATION-AWARE CONFIDENCE CALIBRATION FOR MEDICAL DECISION MAKING
Methods and systems for model calibration include training (210) an object detection model to generate confidence scores using calibration that is based on confidence, correlation, and matching, with accuracy of a location of bounding boxes being used with accuracy of object labels to keep the confidence scores close to an actual probability of correctness. Object detection is performed (230) on an image using the object detection model to generate a bounding box around an object, a label for the object, and a confidence score. An action is performed (240) responsive to the object and the confidence score.
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
G06V 10/764 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
G16H 50/20 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
G16H 30/40 - ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
82.
SELF-IMPROVING MODELS FOR AGENTIC VISUAL PROGRAM SYNTHESIS
Systems and methods for a self-improving model for agentic visual program synthesis. An agent can be continuously trained (140) using an optimal training tuple to perform (150) a corrective action to a monitored entity which in turn generates new input data for the training. To train the agent, an input question can be decomposed (110) into vision model tasks to generate task outputs. The task outputs can be corrected (120) based on feedback to obtain corrected task outputs. The optimal training tuple can be generated (130) by comparing an optimal tuple threshold with a similarity score of the input image, the input question, and the corrected task outputs.
Systems and methods for a self-improving data engine for autonomous vehicles is presented. To train the self-improving data engine for autonomous vehicles (SIDE), multi-modality dense captioning (MMDC) models can detect (110) unrecognized classes from diversified descriptions for input images. A vision-language-model (VLM) can generate (120) textual features from the diversified descriptions and image features from corresponding images to the diversified descriptions. Curated features, including curated textual features and curated image features, can be obtained (130) by comparing similarity scores between the textual features and top-ranked image features based on their likelihood scores. Annotations, including bounding boxes and labels, can be generated (140) for the curated features by comparing the similarity scores of labels generated by a zero-shot classifier and the curated textual features. The SIDE can be trained (150) using the curated features, annotations, and feedback.
G06V 20/56 - Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
G06V 10/74 - Image or video pattern matchingProximity measures in feature spaces
G06V 10/764 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
Methods and systems include determining (314) actions for agents in a driving scenario using a diffusion model, based on individual controllable behavior patterns for the agents. A state of the driving scenario is updated (316) based on the determined actions for the plurality of agents. The determination of actions and the update of the state are repeated (310) in a closed-loop fashion to generate simulated trajectories for the plurality of agents. A planner model is trained (318) to select actions for an operating agent based on the simulated trajectories.
G06N 3/008 - Artificial life, i.e. computing arrangements simulating life based on physical entities controlled by simulated intelligence so as to replicate intelligent life forms, e.g. based on robots replicating pets or humans in their appearance or behaviour
B60W 60/00 - Drive control systems specially adapted for autonomous road vehicles
85.
OPTISENSEGPT: CONTEXT-AWARE ANOMALY DETECTION WITH NATURAL LANGUAGE ALERTS AND ACTIONABLE RECOMMENDATIONS FOR DISTRIBUTED FIBER OPTIC SENSING APPLICATIONS
Disclosed are integrated systems and methods providing intelligent anomaly detection for DFOS systems and applications, the systems and methods utilizing a natural language processing model, such as ChatGPT, to generate real-time alerts with actionable recommendations and potential consequences based on detected anomalies. Our innovative solution – OptiSenseGPT – solves problems left uncured by traditional methods by delivering easily understandable alerts in natural language, enabling timely response by relevant personnel. Our integrated OptiSenseGPT systems and methods disclosed provide context-aware recommendations and consequences, enhancing decisionmaking and improving overall performance and safety of a monitored infrastructure or environment. Our OptiSenseGPT systems and methods advantageously provide integration of natural language processing; context-aware recommendations; presentation of potential consequences; adaptability and customization; and seamless integration.
Disclosed are integrated systems and methods employing distributed fiber optic sensing (DFOS) systems and methods to locate buried and/or aerial cables, as well as loop-back aerial cable sections and slack fiber lengths, in real-time. In sharp contrast to the prior art, systems and methods according to aspects of the present disclosure provide the location of cables without necessitating the opening of manholes/hand holes or pull cables to the round – thereby making the overall process faster, more cost-effective and more accurate and precise. Our inventive systems and methods provide a reliable and accurate alternative to current methods utilizing optical time domain reflectometry (OTDR), which requires known and accessible locations and may be ineffective for legacy fibers. By implementing systems and methods according to the present disclosure, service providers, carriers, and owners can efficiently maintain optical fiber networks and ensure reliable services for users
G01H 9/00 - Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves by using radiation-sensitive means, e.g. optical means
G01D 5/353 - Mechanical means for transferring the output of a sensing memberMeans for converting the output of a sensing member to another variable where the form or nature of the sensing member does not constrain the means for convertingTransducers not specially adapted for a specific variable using optical means, i.e. using infrared, visible or ultraviolet light with attenuation or whole or partial obturation of beams of light the beams of light being detected by photocells influencing the transmission properties of an optical fibre
G01S 19/01 - Satellite radio beacon positioning systems transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
87.
INTEGRATED DISTRIBUTED FIBER OPTIC SENSING SYSTEM FOR ENHANCED OFFSHORE WIND TURBINE MONITORING USING PHYSICS-INFORMED MACHINE LEARNING ALGORITHMS
Disclosed is an integrated DFOS system and method for enhanced offshore wind turbine monitoring using physics-informed machine learning algorithms that advantageously utilizes existing optical fiber communication cables; distributed fiber optic sensing (DFOS); Physics-informed machine learning algorithms; monitoring of critical underwater components; integrated data processing(DPU); and comprehensive monitoring.
G01N 21/95 - Investigating the presence of flaws, defects or contamination characterised by the material or shape of the object to be examined
G01N 21/88 - Investigating the presence of flaws, defects or contamination
G01H 9/00 - Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves by using radiation-sensitive means, e.g. optical means
G01K 11/32 - Measuring temperature based on physical or chemical changes not covered by group , , , or using changes in transmittance, scattering or luminescence in optical fibres
Systems and methods for leveraging semantic information for a multi-domain visual agent. Semantic information can be leveraged to obtain a multi-domain visual agent. To train the multi-domain visual agent, questions can be sampled (110) from question templates for domain-specific label spaces to obtain a unified label space. The domain-specific labels from the domain-specific label spaces can be mapped (120) into natural language descriptions (NLD) to obtain mapped NLD. The mapped NLD can be generated (130) into prompts by combining the questions sampled from the unified label space and the annotations. The semantic information can be learned (140) by iteratively generating outputs from tokens extracted from the prompts using a large-language model (LLM). The multi-domain visual agent (MDVA) can be trained (150) using the semantic information.
Methods and systems for operating a vehicle include prompting (915) a large language model LLM to generate parameters for a rule-based planner based on historical data for vehicles in a road scene. A trajectory is generated (916) using the parameters. A driving action is performed (920) to implement the trajectory.
Disclosed are integrated systems and operating methods that provide an integrated security system for substation monitoring and detection that effectively combines the strengths of distributed acoustic sensing, drones, and security cameras for comprehensive protection. The integrated system comprises a DAS system configured to monitor vibrations and acoustic signals along the length of fiber optic cables, one or more drones equipped with advanced sensors for aerial surveillance, and a plurality of security cameras installed throughout the substation to capture real-time video feeds and provide visual confirmation of activities. A central control system integrates and analyzes data from the DAS system, drones, and security cameras, and utilizes a novel, advanced algorithm, named Substation Security Analytics (SSA), specifically designed for the unique challenges associated with substation security monitoring and detection.
G08B 13/186 - Actuation by interference with heat, light, or radiation of shorter wavelengthActuation by intruding sources of heat, light, or radiation of shorter wavelength using active radiation detection systems by interruption of a radiation beam or barrier using light guides, e.g. optical fibres
G08B 13/196 - Actuation by interference with heat, light, or radiation of shorter wavelengthActuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
G08B 13/16 - Actuation by interference with mechanical vibrations in air or other fluid
B64C 39/02 - Aircraft not otherwise provided for characterised by special use
G01H 9/00 - Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves by using radiation-sensitive means, e.g. optical means
B64U 101/31 - UAVs specially adapted for particular uses or applications for imaging, photography or videography for surveillance
91.
RESOURCE ALLOCATION FOR POWER, COMMUNICATION, AND TRANSPORTATION INFRASTRUCTURE USING DISTRIBUTED FIBER OPTIC SENSING
Disclosed are integrated systems and methods that utilize a network of DFOS sensors installed on power lines, communication networks, and transportation systems, which continuously monitor infrastructures and provide real-time data. This data is collected, processed, and analyzed, and used to identify any affected areas of infrastructure and assess severity of any damage. Prioritization and resource allocation is performed and uses this analysis to prioritize restoration efforts and allocate resources such as repair crews, equipment, and materials to areas with a highest priority.
G06Q 50/50 - Business processes related to the communications industry
G06Q 50/40 - Business processes related to the transportation industry
H04L 67/12 - Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
G01D 5/353 - Mechanical means for transferring the output of a sensing memberMeans for converting the output of a sensing member to another variable where the form or nature of the sensing member does not constrain the means for convertingTransducers not specially adapted for a specific variable using optical means, i.e. using infrared, visible or ultraviolet light with attenuation or whole or partial obturation of beams of light the beams of light being detected by photocells influencing the transmission properties of an optical fibre
G06N 3/088 - Non-supervised learning, e.g. competitive learning
92.
DEEP LEARNING AND LANGUAGE MODEL ENHANCED SYSTEM FOR WIND TURBINE MONITORING USING DISTRIBUTED FIBER OPTIC SENSING (DL-LM-DFOS)
Disclosed is a deep learning and language model enhanced system and method for wind turbine monitoring using distributed fiber optic sensing (DL-LM-DFOS) which combines advantages of distributed fiber optic sensing with the power of deep learning and large language models. Our system and method automatically learns and extracts useful features from raw sensor data, detects complex patterns indicating potential issues, and incorporates and learns from a wide range of data, including textual data such as maintenance logs, operational notes, or alarm messages. As a result, our inventive system and method provide comprehensive, efficient, and predictive monitoring of wind turbines.
G06N 3/0442 - Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
Disclosed are displacement sensors constructed from optical fibers having a long elongation with low-cost ToF sensors that advantageously do not suffer the infirmities of the art. The ToF sensor and the optical fiber ends that launch and receive light are packaged such that no ambient light affects measurements, and the structure is protected from contamination which eliminates optical degradation. With multi-point measurement capabilities and the low-cost features of ToF sensors, many displacement sensors can be arranged in a mesh to map out displacements over a large area and over all directions for civil and/or geotechnical structures. Wireless or other communications mechanisms may be employed in conjunction with our novel sensors to send real time measurement data to a central office for real time monitoring and analysis.
G01B 11/16 - Measuring arrangements characterised by the use of optical techniques for measuring the deformation in a solid, e.g. optical strain gauge
G01B 11/02 - Measuring arrangements characterised by the use of optical techniques for measuring length, width, or thickness
G01D 5/353 - Mechanical means for transferring the output of a sensing memberMeans for converting the output of a sensing member to another variable where the form or nature of the sensing member does not constrain the means for convertingTransducers not specially adapted for a specific variable using optical means, i.e. using infrared, visible or ultraviolet light with attenuation or whole or partial obturation of beams of light the beams of light being detected by photocells influencing the transmission properties of an optical fibre
G01S 7/481 - Constructional features, e.g. arrangements of optical elements
G01S 17/10 - Systems determining position data of a target for measuring distance only using transmission of interrupted, pulse-modulated waves
94.
SEQUENTIAL EVENT MODELING FOR RISK FACTOR PREDICTION
Systems and methods for creating a model include converting (302) historical data into categorical time series data; de-noising (302) the categorical time series data by organizing events into transition sets and removing noisy transitions sets according to a coefficient of variation. A relationship graph is generated (306) that determines relationships between pairs of nodes, where the nodes relate to respective data sources and where the relationships indicate a degree of correlation between nodes based on the de-noised categorical time-series data, using a Hawkes process that determines a likelihood of a category transition based on historical events. An anomaly threshold is determined (308) based on anomaly scores for a validation dataset using the relationship graph, wherein a likelihood output of the Hawkes process that exceeds the anomaly threshold indicates an anomaly.
Disclosed are systems, methods, and structures that provide more accurate temperature measurements and/or derived measurements using distributed fiber optic sensing (DFOS) systems and methods. DFOS systems and methods according to aspects of the present disclosure employ distributed fiber optic sensing that determines real-time temperature changes and vehicle trajectories from two-dimensional (2D) DFOS data with very few labeled data. The 2D data is first divided into multiple grids and then pre-processed with image distortion methods to enrich diversity of temperature change patterns. The transformed grids are used to pre-train a masked autoencoder, which advantageously does not require labels. The encoder of the autoencoder learns intrinsic features of temperature and traffic patterns, which are later connected to an estimation network to solve downstream tasks trained on a small set of labeled data.
G01K 11/32 - Measuring temperature based on physical or chemical changes not covered by group , , , or using changes in transmittance, scattering or luminescence in optical fibres
G01D 5/353 - Mechanical means for transferring the output of a sensing memberMeans for converting the output of a sensing member to another variable where the form or nature of the sensing member does not constrain the means for convertingTransducers not specially adapted for a specific variable using optical means, i.e. using infrared, visible or ultraviolet light with attenuation or whole or partial obturation of beams of light the beams of light being detected by photocells influencing the transmission properties of an optical fibre
96.
SEQUENTIAL EVENT MODELING FROM MULTIVARIATE CATEGORICAL SENSOR DATA
Systems and methods include converting (300) historical data into categorical time series data and de-noising (302) the categorical time series data by removing noisy transitions sets according to a coefficient of variation. A likelihood of a category transition is determined (304) based on historical events using a Hawkes process to generate a relationship graph. Relationships between pairs of nodes are determined (306) using the relationship graph, where the relationships indicate a degree of correlation between the nodes based on de-noised categorical time-series data. An anomaly threshold is determined (308) based on anomaly scores for a validation dataset using the relationship graph, wherein a likelihood output of the Hawkes process that exceeds the anomaly threshold indicates an anomaly.
Explore aNd Pick"Explore aNd Pick"(mEnP) procedure, which helps network carriers deploy new types of DFOS sensors (e.g., each DFOS sensor is associated with multiple sensing fiber routes/channels) to cover/sense entire network infrastructures with a minimum number of DFOS sensors while advantageously providing network carriers 1) locations where to deploy DFOS sensors and, (2) how to establish sensing fiber routes/channels from the deployed sensors. Our inventive procedure includes two sub-procedures. The first sub-procedure adopts a modified route exploration method to obtain a set S that contains all the possible sensor placements and the corresponding sensing fiber routes/channels at each node in the given network infrastructure. A second sub-procedure applies a modified greedy set cover method to find the minimum subset from S that can cover all the network links in the given network infrastructure.
G01D 5/353 - Mechanical means for transferring the output of a sensing memberMeans for converting the output of a sensing member to another variable where the form or nature of the sensing member does not constrain the means for convertingTransducers not specially adapted for a specific variable using optical means, i.e. using infrared, visible or ultraviolet light with attenuation or whole or partial obturation of beams of light the beams of light being detected by photocells influencing the transmission properties of an optical fibre
G01H 9/00 - Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves by using radiation-sensitive means, e.g. optical means
98.
TRAINING A TIME-SERIES-LANGUAGE MODEL ADAPTED FOR DOMAIN-SPECIFIC TASKS
Systems and methods for training a time-series-language (TSLa) model adapted for domain-specific tasks. An encoder-decoder neural network can be trained (110) to tokenize time-series data to obtain a discrete-to-language embedding space. The TSLa model can learn (120) a linear mapping function by concatenating token embeddings from the discrete-to-language embedding space with positional encoding to obtain mixed-modality token sequences. Token augmentation can transform (130) the tokens from the mixed-modality token sequences with to obtain augmented tokens. The augmented tokens can train (140) the TSLa model using a computed token likelihood to predict next tokens for the mixed-modality token sequences to obtain a trained TSLa model. A domain-specific dataset can fine-tune (150) the trained TSLa model to adapt the trained TSLa model to perform a domain-specific task.
Methods and systems for generating text include sampling (302) a plurality of sentences generated by a language model in response to a query. A sentence is selected (304) from the plurality of sentences using a score that is based on token consistency between the plurality of sentences.
G16H 50/20 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
G16H 20/00 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
Systems and methods include generating (302) a detection output for an image over multiple iterations by applying a dropout randomly to a different convolutional layer of a learning model for each iteration. The detection outputs are clustered (304), on labels, for each iteration. A total surface area for the clusters is computed (306) over the iteration. A confidence is computed (308) for the image using the total surface area for the clusters as an uncertainty score. A system is disabled (310) if the confidence is below a threshold.
G06N 3/088 - Non-supervised learning, e.g. competitive learning
G06N 3/10 - Interfaces, programming languages or software development kits, e.g. for simulating neural networks
G06V 10/44 - Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersectionsConnectivity analysis, e.g. of connected components
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
G06V 10/98 - Detection or correction of errors, e.g. by rescanning the pattern or by human interventionEvaluation of the quality of the acquired patterns
patents
