Systems and methods for multi-agent causal discovery. In an embodiment, the system and method may include generating an initial causal graph, prompting a first AI agent to generate contextual data using metadata from the initial causal graph, prompting a second AI agent to generate causal constraints using the initial causal graph and the generated contextual data, wherein the second AI agent includes a prompt builder, and generating a refined causal graph using the generated causal constraints.
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 based on a four-dimensional reconstruction of dynamic videos. A visual-language machine learning model (VLM) can be fine-tuned with the fine-tuning tasks that increases spatio-temporal reasoning of the VLM. The spatio-temporal reasoning of the VLM can be optimized based on a prediction generated by the VLM in natural language for ensuring increased accuracy of the VLM while preventing biased verification.
G06V 10/778 - Active pattern-learning, e.g. online learning of image or video features
B60W 30/09 - Taking automatic action to avoid collision, e.g. braking and steering
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 for question answering include generating a tile from an image and encoding the tile to generate an embedding vector. A set of neighbor objects is generated based on an object of interest from a query. A first similarity is determined between the object of interest and the embedding vector of the tile. Second similarities are determined between the neighbor objects and the embedding vector of the tile. It is determined that the tile is relevant responsive to the first similarity being greater than the second similarities. The query is answered using the tile.
Systems and methods for natural disaster damage analysis. Aerial images are converted into a set of property images. The property images are then clustered 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 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 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.
Systems and methods for optimizing spatio-temporal reasoning in artificial intelligence models. Fine-tuning tasks including instruction-following data using coordinates can be generated from LiDAR annotations in real world dynamic videos. A visual-language machine learning model (VLM) can be fine-tuned with the fine-tuning tasks that increases spatio-temporal reasoning of the VLM. Biased verification can be prevented by verifying the spatio-temporal reasoning of the VLM based on a prediction generated by the VLM in natural language for ensuring increased accuracy of the VLM.
Systems and methods for self-supervised feature disentanglement for calibration-free multi-camera multi-object tracking. View-specific features and view-agnostic features of a tracked entity can be identified from different camera views by encoding masked detection features of the tracked entity. The masked detection features can be reconstructed into single-view feature representations from the view-specific features. Cross-view feature representations can be generated 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 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 artificial intelligence model understanding of complex traffic interactions. Identifying agents can be identified from input videos based on agent heuristics. Interaction behaviors between the agents can be determined based on interaction heuristics. An integrated dataset can be autonomously generated 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 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.
G06V 10/62 - Extraction of image or video features relating to a temporal dimension, e.g. time-based feature extractionPattern tracking
G06V 10/80 - Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
G06V 20/40 - ScenesScene-specific elements in video content
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
9.
ADAPTIVE WORKFLOW AUGMENTATION FOR IMPROVED TOOL AWARENESS IN AGENTIC TRAINING
Systems and methods for optimizing visual reasoning task workflow. The systems and methods include generating 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 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 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 the model to perform the task with the augmented workflow.
Methods and systems for training a model include generating a relightable neural radiance field (NeRF) reconstruction of an input video of a driving scene. A virtual object is inserted into the driving scene using the NeRF reconstruction to create a simulated scene. Scene intrinsics are optimized within the simulated scene. An autonomous driving model is trained using the simulated scene.
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.
Methods and systems for model calibration include training 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 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 responsive to the object and the confidence score.
G06V 10/774 - Generating sets of training patternsBootstrap methods, e.g. bagging or boosting
G06V 10/25 - Determination of region of interest [ROI] or a volume of interest [VOI]
G06V 10/764 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
G06V 20/70 - Labelling scene content, e.g. deriving syntactic or semantic representations
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
13.
Optical Line System Physical Digital Model Calibration Using a Differential Algorithm
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.
H04J 14/02 - Wavelength-division multiplex systems
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
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.
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
G06F 1/30 - Means for acting in the event of power-supply failure or interruption, e.g. power-supply fluctuations
15.
DiffOptics: A conditional diffusion model for optics sensing data imputation
A generative Artificial Intelligence (AI) framework is presented based on a conditional diffusion model for distributed acoustic sensing (DAS) data imputation. The proposed model, named “DiffOptics,” is capable of generating high-quality fiber sensing data by learning the distribution of existing acoustic sensing data and conditioning on an adjacent acoustic sensing signal. DiffOptics is designed to address two critical challenges in abnormal acoustic event detection: (1) DAS data imputation to enhance spatial resolution for more accurate event analysis and reduced data storage, and (2) the generation of synthetic DAS data to improve the performance of machine learning models for recognizing hazardous events. The model is evaluated in a real-scale testbed utilizing telecom fiber cables on utility poles to generate high-quality data of various acoustic events
G01H 9/00 - Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves by using radiation-sensitive means, e.g. optical means
G10L 25/30 - Speech or voice analysis techniques not restricted to a single one of groups characterised by the analysis technique using neural networks
16.
Memory-Augmented Fiber Sensing Recognition and Adaptation based on Disaggregated Computing with Double Privacy Protection
A system and method for Distributed Fiber Optic Sensing (DFOS) recognition and adaptation, which utilizes a memory-augmented neural network (MANN) and a disaggregated computing infrastructure (DCI) to achieve double privacy protection. The system separates the feature extraction encoder on a client-side machine from an external memory bank and similarity-based classification module on a server-side machine. In operation, the client computes an embedding from raw sensing data and transmits only the embedding vector to the server. The server performs classification and, during model fine-tuning, calculates and returns a gradient vector with respect to the embedding. This architecture ensures proprietary training data on the server is never exposed, while client raw sensing data remains private. The system supports continuous model adaptation and robust class-incremental learning.
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 (GCC-PHAT) 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.
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 3/00 - Thermometers giving results other than momentary value of temperature
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
G01K 15/00 - Testing or calibrating of thermometers
19.
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, determining coordinates of the bounding boxes and the quaternion data for the objects in the selected image frames, 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. The systems and methods further include correlating the kinematic quantities to natural language text, form 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, training a visual language model with the instruction-following training data, and predicting the kinematic quantities of environmental objects in live video feeds from an autonomous vehicle.
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
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 frame-level 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 20/58 - Recognition of moving objects or obstacles, e.g. vehicles or pedestriansRecognition of traffic objects, e.g. traffic signs, traffic lights or roads
G05D 1/243 - Means capturing signals occurring naturally from the environment, e.g. ambient optical, acoustic, gravitational or magnetic signals
G06V 20/40 - ScenesScene-specific elements in video content
Systems and methods for detecting artificial intelligence (AI) generated computer code. Lines of code can be masked from a candidate code to obtain perturbed codes. Missing code can be generated from the perturbed codes by employing an AI code generator model to obtain machine-filled codes. Probabilities of the candidate code probability and the machine-filled codes as AI-generated can be predicted by employing a surrogate model. The candidate code can be distinguished as AI-generated by comparing the probabilities against a detection threshold to obtain detection results.
G06F 21/57 - Certifying or maintaining trusted computer platforms, e.g. secure boots or power-downs, version controls, system software checks, secure updates or assessing vulnerabilities
Systems and methods are provided for optimizing video compression for remote vehicle control, including capturing, capturing video and sensor data from a vehicle using a plurality of sensors and high-resolution cameras, analyzing the captured video to identify critical regions within frames of the video using an attention-based module. Current network bandwidth is assessed and future bandwidth availability is predicted. Video compression parameters are predicted based on an analysis of the video and an assessment of the current network bandwidth using a control network, and the video is compressed based on the predicted parameters with an adaptive video compression module. The compressed video and sensor data is transmitted to a remote-control center, and received video and sensor data is decoded at the remote-control center. The vehicle is autonomously or remotely controlled from the remote-control center based on the decoded video and sensor data.
Systems and methods are provided for optimizing video compression for remote vehicle control, including capturing, capturing video and sensor data from a vehicle using a plurality of sensors and high-resolution cameras, analyzing the captured video to identify critical regions within frames of the video using an attention-based module. Current network bandwidth is assessed and future bandwidth availability is predicted. Video compression parameters are predicted based on an analysis of the video and an assessment of the current network bandwidth using a control network, and the video is compressed based on the predicted parameters with an adaptive video compression module. The compressed video and sensor data is transmitted to a remote-control center, and received video and sensor data is decoded at the remote-control center. The vehicle is autonomously or remotely controlled from the remote-control center based on the decoded video and sensor data.
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 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 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 40/20 - 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 management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
25.
Analytics-Aware Video Compression for Decision Making in Teleoperated Vehicle Control
Systems and methods are provided for optimizing video compression for remote vehicle control, including capturing, capturing video and sensor data from a vehicle using a plurality of sensors and high-resolution cameras, analyzing the captured video to identify critical regions within frames of the video using an attention-based module. Current network bandwidth is assessed and future bandwidth availability is predicted. Video compression parameters are predicted based on an analysis of the video and an assessment of the current network bandwidth using a control network, and the video is compressed based on the predicted parameters with an adaptive video compression module. The compressed video and sensor data is transmitted to a remote-control center, and received video and sensor data is decoded at the remote-control center. The vehicle is autonomously or remotely controlled from the remote-control center based on the decoded video and sensor data.
Systems and methods are provided for optimizing video compression for remote vehicle control, including capturing, capturing video and sensor data from a vehicle using a plurality of sensors and high-resolution cameras, analyzing the captured video to identify critical regions within frames of the video using an attention-based module. Current network bandwidth is assessed and future bandwidth availability is predicted. Video compression parameters are predicted based on an analysis of the video and an assessment of the current network bandwidth using a control network, and the video is compressed based on the predicted parameters with an adaptive video compression module. The compressed video and sensor data is transmitted to a remote-control center, and received video and sensor data is decoded at the remote-control center. The vehicle is autonomously or remotely controlled from the remote-control center based on the decoded video and sensor data.
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 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 into a joint context representation by utilizing a fusion transformer encoder of the CJVAE. The joint context representation can be decoded 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 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.
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
Systems and methods for detecting artificial intelligence (AI) generated computer code. Lines of code can be masked from a candidate code to obtain perturbed codes. Missing code can be generated from the perturbed codes by employing an AI code generator model to obtain machine-filled codes. Probabilities of the candidate code probability and the machine-filled codes as AI-generated can be predicted by employing a surrogate model. The candidate code can be distinguished as AI-generated by comparing the probabilities against a detection threshold to obtain detection results.
G06F 21/57 - Certifying or maintaining trusted computer platforms, e.g. secure boots or power-downs, version controls, system software checks, secure updates or assessing vulnerabilities
Systems and methods for detecting artificial intelligence (AI) generated computer code. Lines of code can be masked from a candidate code to obtain perturbed codes. Missing code can be generated from the perturbed codes by employing an AI code generator model to obtain machine-filled codes. Probabilities of the candidate code probability and the machine-filled codes as AI-generated can be predicted by employing a surrogate model. The candidate code can be distinguished as AI-generated by comparing the probabilities against a detection threshold to obtain detection results.
G06F 21/57 - Certifying or maintaining trusted computer platforms, e.g. secure boots or power-downs, version controls, system software checks, secure updates or assessing vulnerabilities
Methods and systems for code generation include generating code for tree root nodes responsive to a query that specifies a task. The tree root nodes are expanded 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 corresponding to a node from the trees that satisfies a test case.
G06F 11/3604 - Analysis of software for verifying properties of programs
G06F 8/35 - Creation or generation of source code model driven
G16H 40/63 - 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 local operation
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
31.
EVALUATING FAITHFULNESS OF EXPLAINABLE AI FOR MEDICAL DECISION MAKING
Methods and systems include fine-tuning 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 using the fine-tuned classifier to ensure that the explainer has an above-threshold fidelity. A downstream task is performed 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
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
32.
UNDETECTABLE TEXT GENERATION TO ASSIST IN MEDICAL DECISION MAKING
Methods and systems include fine-tuning a small language model (SLM) to determine a first probability distribution. Text is generated 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, 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
33.
ANALOG DUAL-COMB SENSING WITH CONTINUOUS-WAVE LOCAL OSCILLATION
Disclosed are schemes for analog dual-comb sensing with a continuous-wave local oscillator that provides analog dual-comb sensing and overcome limitations of the prior art, analog DCS schemes. Operationally, one optical frequency comb (OFC) is intensity modulated by an analog RF comb generator (such as SRD, NLTL, etc.) while the other OFC is phase-modulated by another analog RF comb generator having a slightly different frequency spacing. The intensity-modulated OFC, (in narrow-pulse shape) is used as the “probe” to measure a medium under test, while the phase-modulated OFC (in continuous waves) is used as a “local oscillator” and beat with the “probe” comb and amplify the output. In the detection stage, our schemes take the advantage of polarization diversity coherent detection, eliminating fading that infirmed previous schemes due to the polarization drift and phase noises.
Disclosed are systems, and methods providing optical network anomaly detection and localization based on forward transmission sensing and route optimization and network-wide global planning of sensing routes. Multiple sensing routes are selected to cover the entire network and each link in the network is guaranteed to contain a different combination of sensing routes. These routes are then monitored concurrently and analyzed centrally. When an anomalous event occurs at a specific link, receivers in the corresponding routes will detect optical characteristic changes. Since the sensing route combination is unique for each link, a global analysis of the optical characteristic change will indicate the exact link that causes the event.
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
Systems and methods for evaluating multimodal retrieval augmented generation (RAG) performance. The systems and methods include generating an internal response from a user input and a RAG database and generating a relevancy score for quantifying a relevance of the internal response to information retrieved from the RAG database based on the user input and a correctness score quantifying accuracy of the internal response to the information retrieved from the RAG database. The systems and methods further include generating a combined score from the relevancy score and correctness score and selectively performing a task based on the relevancy score, the correctness score, or the combined score.
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 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 three-dimensional (3D) molecules. Linear optimization of semantic embeddings of 3D molecules can be performed 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 from the optimized embedding with the trained DDIM-AE.
G06F 30/27 - Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
37.
SAMPLED LANGUAGE MODELS FOR MEDICAL DECISION MAKING
Methods and systems include searching for prompt tokens in a document corpus, starting from a random point in the document corpus. A next token is added to an updated prompt from the document corpus after the prompt tokens have been located. The searching and adding are iteratively repeated using the updated prompt until an end condition is reached. An action is performed responsive to the updated prompt.
G06F 40/284 - Lexical analysis, e.g. tokenisation or collocates
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 50/20 - 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
38.
Multi-span OSNR and GSNR Prediction Using Cascaded Learning
Disclosed is a method of cascaded learning applied to GSNR prediction using component optical amplifier, fiber, and transceiver models. The component models are measured and trained separately, before the devices are deployed into the field. Specifically, amplifier and transceiver model are trained based on measurement data, and fiber nonlinearity model are trained based on the synthesis data generated by a Gaussian Noise (GN) model. The optical link model contains all three component models and connects them as the physical order in the optical link. A small number of end-to-end measurements are used to train the optical link model to reduce the accumulated loss and adapt the model to the physical multi-span link.
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
39.
DISTRIBUTED CODE GENERATION FOR VISION APPLICATIONS
Systems and methods for generating and executing distributed code. The systems and methods include receiving serial code generated by a large language model (LLM) for vision applications and analyzing the serial code with a trained model to identify code dependencies and detect independent application programming interface (API) calls. The systems and methods further include transforming the serial code by incorporating program semantics that enable concurrent execution of the independent API calls and generating distributed code configured for execution on a container orchestration platform cluster, wherein the distributed code includes service calls that can be understood and executed by a runtime system.
A technique for dual-comb high-resolution distributed sensing that employs a “gating” feature to the probe comb in the time-domain. Operationally, probe comb signals are gated as blocks and sent into a optical fiber with adjusted time intervals. In a signal processing stage, the block signals are merged as a complete analysis window such that every spatial resolution can be reconstructed. By sliding the window, the entire optical fiber can advantageously be monitored. Our technique advantageously breaks a sensing distance bottleneck found in conventional, dual-comb distributed fiber sensing, thereby providing high-spatial resolution sensing over a long distance.
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
41.
CROSS-DOMAIN MULTI-MODAL TIME SERIES ANNOTATION FOR MEDICAL DECISION MAKING
Methods and systems include generating general annotations for input time series data based on annotations from one or more source domains. Domain-specific annotations are generated for the input time series based on annotations from a target domain and based on the general annotations. An action is performed 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
42.
Power-Aware DFOS Placement Strategy for Resilient Infrastructure Monitoring
Disclosed is a distributed acoustic sensing (DAS) placement method that explicitly accounts for power supply limitations. By strategically positioning DAS devices within a network in a manner that optimizes power availability and minimizes risk of monitoring blind spots during power outages, our method enhances overall resilience of a DAS monitoring system. Our method combines a heuristic algorithm, PURE (Power Source-aware Route Exploration), with Integer Linear Programming (ILP) optimization. The PURE algorithm explores all possible fiber routes that satisfy both fiber-side constraints-such as linear, non-branching routes within the operational range and power-side constraints, ensuring that DFOS devices are powered independently. The ILP then selects the optimal set of DFOS units to minimize the total number of sensors while meeting monitoring requirements. Our method ensures continuous monitoring even under adverse conditions and reduces costs associated with DAS deployment by eliminating a need for extensive new infrastructure or redundant systems.
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
43.
RECOVERY-BASED BLACK BOX DETECTION OF AI-GENERATED CONTENT FOR MEDICAL DECISION MAKING
Methods and systems include fine-tuning a surrogate model, using example images generated by a target model, to match a distribution of the target model. A new image is masked to generate a masked image. A recovered image is generated that fills in a masked region of the masked image using the surrogate model. The recovered image is compared to the new image to determine that the new image was generated by the target model. An action is performed 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
44.
SITUATIONAL AWARENESS UNCERTAINTY PROPAGATION FOR MEDICAL DECISION MAKING
Methods and systems include estimating situational weights for an agent based on a distance measure for steps taken by the agent. The situational weights are combined 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 responsive to the total uncertainty.
G06N 7/01 - Probabilistic graphical models, e.g. probabilistic networks
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
45.
DIAGRAM ANALYSIS USING VISUAL LANGAUGE MODELS FOR MEDICAL DECISION MAKING
Methods and systems for image analysis include initializing a set of initial regions that segment an input image. The initial regions are split into split regions. The split regions are merged into combined regions. Image analysis is performed on the combined regions using a visual language model, responsive to a query. An action is performed responsive to the image analysis in a downstream task.
G06V 10/26 - Segmentation of patterns in the image fieldCutting or merging of image elements to establish the pattern region, e.g. clustering-based techniquesDetection of occlusion
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 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
G06V 20/62 - Text, e.g. of license plates, overlay texts or captions on TV images
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
46.
DISTRIBUTED CODE GENERATION AND EXECUTION FOR REAL TIME MARINE APPLICATIONS
Systems and methods for executing code. The systems and methods include generating code by querying a model wherein one portion of the code is conditioned on an output on a second portion of the code, analyzing functions in the code with a second model to evaluate opportunities to implement tasks on devices, marking the code to designate portions of the code that can be performed on the devices, and assigning portions of the code to the devices based on capabilities of the devices. The systems and methods further include distributing the portions of the code to the devices, wherein the conditional portion of the code is distributed onto a first device and the second portion is distributed onto an edge device, executing the code across the devices, and transmitting data collected by the edge device to the first device upon meeting the condition in the code.
Two-stage domain-specific signal generation schemes using a text-conditional a generative audio model. The first stage includes an Event-classification simulator with language-audio models (e.g., CLAP models), which advantageously prevents the text-conditional generative model from generating incorrect data. The second stage incorporates a Domain shifter, which performs impulse-response convolution and background noise in addition to synthesized data, emulating unique sensing signals fiber optic sensing deployments, such as those from DAS. Advantageously, our inventive schemes can generate various synthesized data belonging to unique domains and store them as a special dataset. In terms of physical effort, our techniques only need record one impulse response and one background noise, significantly reducing data collection burden and costs typically associated with fine-tuning models. Of further advantage, our inventive schemes can be applied to other unique audio devices (e.g., laser microphones) or unique environments (e.g., underwater).
G10L 13/08 - Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
G10L 13/04 - Details of speech synthesis systems, e.g. synthesiser structure or memory management
G10L 25/60 - Speech or voice analysis techniques not restricted to a single one of groups specially adapted for particular use for comparison or discrimination for measuring the quality of voice signals
48.
Successive Interference Cancellation for Forward Phase Sensor using DAS
Disclosed is a WDM network in which both DAS and forward phase sensing systems are deployed at add/drop nodes of fiber links. Whereas DAS systems can monitor immediate fiber spans connected to the add-drop nodes, forward phase sensors will monitor an entire link between the nodes. With DAS providing precise locations of vibration sources at the immediate fiber spans, we utilize that information and successively subtract these vibration signals (by applying proper time delay according to their location) from the forward phase signal monitoring of the entire link. The resulting signal after successive interference cancellation (SIC) only contains phase information at intermediate fiber spans, effectively isolating those signal sources from the those retrieved by DAS.
H04J 14/02 - Wavelength-division multiplex systems
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
H04B 10/073 - Arrangements for monitoring or testing transmission systemsArrangements for fault measurement of transmission systems using an out-of-service signal
H04B 10/25 - Arrangements specific to fibre transmission
49.
GUIDING PRIVATE ARTIFICIAL INTELLIGENCE MODELS WITH PUBLIC SOLUTIONS
Systems and methods for guiding private artificial intelligence models with public solutions. A very large language model (VLLM) can be iteratively queried with an instruction code including public entities with associated public documents to generate public solutions. Rationale features can be extracted from the public solutions with the VLLM. The instruction code can be updated by combining an input query about public entities, the public solutions with the rationale features, text from reference chunks, and an input query about a single private entity, following a pre-determined template, to yield a private instruction code about a single private entity. The private instruction code can be answered with private large language models (PLLM) to obtain private answers for performing downstream tasks.
Distributed fiber optic sensing (DFOS)/distributed acoustic sensing (DAS) that illustrate inventive techniques—applicable to all embedded systems—that deliver high-bandwidth traffic from a DFOS system to a cloud or other processing resources in real-time, employ firmware that operates at a register-transfer level and writes data repeatedly into the embedded host memory directly—without software intervention after initial configuration. This technique advantageously enables the use of the relatively large host memory to compensate for any software jitter. Preferably configured, the firmware employs only a small buffer to compensate for a transaction and host-memory arbitration latency. A second dedicated thread sends out data from the user space buffer to a cloud, or a connected server. Remote procedures that are executed on a remote system (a computer, network of computers, or cloud), receive data transmitted from the embedded system, and perform further processing as necessary.
G06F 13/28 - Handling requests for interconnection or transfer for access to input/output bus using burst mode transfer, e.g. direct memory access, cycle steal
G01H 9/00 - Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves by using radiation-sensitive means, e.g. optical means
G06F 13/16 - Handling requests for interconnection or transfer for access to memory bus
Systems and methods for subgroup discovery for survival analysis. A survival analysis model can be fitted to neighborhoods of points from a dataset to obtain a fitted model. The neighborhoods of points can be filtered into a core group based on an expected prediction entropy metric. An undesirable event probability for the core group can be evaluated based on a conditional rank distribution of the core group to obtain rejected points. An axis-aligned hyperrectangle can be generated 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.
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 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 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 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.
Methods and systems include generating a first question relating to supporting an input claim. A search is performed based on the first question to identify evidence relating to the input claim. An answer to the first question is generated based on the evidence. Additional questions are iteratively generated, with searches being performed based on the additional questions, and with answers to the additional questions being generated until a predetermined stop condition is reached. The input claim is classified by predicting a label based on evidence identified by the searches.
G06F 40/40 - Processing or translation of natural language
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 70/20 - ICT specially adapted for the handling or processing of medical references relating to practices or guidelines
Systems and methods for generating and executing distributed code. The systems and methods include analyzing code dependencies in a serial code with a trained model to evaluate opportunities to implement tasks in parallel and marking the serial code with indicators to designate portions of the serial code that can be performed on a plurality of computing devices. The methods and systems further include distributing the portions of the serial code to the plurality of computing devices and executing the serial code in parallel across the plurality of computing devices using an execution engine to coordinate execution across the computing devices.
Methods and systems for context reduction include identifying a context document relating to a query. A number of sentences of the context document to preserve is determined. The sentences of the context document are ranked according to respective similarities between the sentences and the query. A reduced context is generated that preserves the determined number of highest ranked sentences of the context document and eliminates other sentences from the context document. The query is executed with a language model, including the reduced context in a prompt, to generate a response.
Disclosed are techniques that provide efficient routing strategies for AllReduce transfers, which are the the dominant traffic in machine learning-centric datacenters, resulting in faster parameter synchronization in distributed machine learning and improving the average training time by over 9%. As compared with the prior art, our efficient route of AllReduce traffic advantageously maximizes bandwidth allocation while minimizing bandwidth tax, accelerates training speed of distributed machine learning models or large language models in optical circuit switching-based clouds, and more efficiently provisions indirect optical paths, by leveraging the unused ports or bandwidth resources from GPU servers that run single or standalone computing jobs.
H04B 10/80 - Optical aspects relating to the use of optical transmission for specific applications, not provided for in groups , e.g. optical power feeding or optical transmission through water
57.
RAG-ENHANCED PROBLEM SOLVING FOR MEDICAL DECISION MAKING
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
G06F 18/22 - Matching criteria, e.g. proximity measures
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
58.
Cross-Correlation-Based Manhole Localization Using Ambient Traffic and Fiber Sensing
Systems and methods for manhole localization along deployed fiber optic cables that employs cross-correlation methodologies and ambient road traffic operating proximate to the manholes including fiber optic telecommunications cables to detect the manhole locations using distributed fiber optic sensing (DFOS). Advantageously the manhole locations are determined without employing labor intensive field surveys.
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
59.
REINFORCED CAUSAL STRUCTURE LEARNING FOR ONLINE ROOT CAUSE ANALYSIS
Systems and methods for root cause analysis (RCA) including embedding new batch data and a previous hidden state to form state-specific embedded data, forming a state-specific attributed graph with the state-specific embedded data and a directed acyclic graph (DAG) from a previous batch and decoding the DAG to learn a state-specific policy. The systems and method further include sampling an action from the state-specific policy to form a state-specific DAG and combining the state-specific DAG with an action from a state-invariant action to form a complete DAG. Some embodiments of the present invention further include evaluating the complete DAG to identify irregularities in Key Performance Indicators (KPIs) and responding, using RCA response techniques to irregularities in KPIs.
H04L 41/0631 - Management of faults, events, alarms or notifications using root cause analysisManagement of faults, events, alarms or notifications using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis
H04L 41/16 - Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using machine learning or artificial intelligence
60.
T-Cell Receptor Repertoire Selection Prediction with Physical Model Augmented Pseudo-Labeling for Personalized Medicine Decision Making
Systems and methods for predicting T-Cell receptor (TCR)-peptide interaction, including training a deep learning model for the prediction of TCR-peptide interaction by determining a multiple sequence alignment (MSA) for TCR-peptide pair sequences from a dataset of TCR-peptide pair sequences using a sequence analyzer, building TCR structures and peptide structures using the MSA and corresponding structures from a Protein Data Bank (PDB) using a MODELLER, and generating an extended TCR-peptide training dataset based on docking energy scores determined by docking peptides to TCRs using physical modeling based on the TCR structures and peptide structures built using the MODELLER. TCR-peptide pairs are classified and labeled as positive or negative pairs using pseudo-labels based on the docking energy scores, and the deep learning model is iteratively retrained based on the extended TCR-peptide training dataset and the pseudo-labels until convergence.
G16B 15/00 - ICT specially adapted for analysing two-dimensional or three-dimensional molecular structures, e.g. structural or functional relations or structure alignment
Systems and methods for predicting T-Cell receptor (TCR)-peptide interaction, including training a deep learning model for the prediction of TCR-peptide interaction by determining a multiple sequence alignment (MSA) for TCR-peptide pair sequences from a dataset of TCR-peptide pair sequences using a sequence analyzer, building TCR structures and peptide structures using the MSA and corresponding structures from a Protein Data Bank (PDB) using a MODELLER, and generating an extended TCR-peptide training dataset based on docking energy scores determined by docking peptides to TCRs using physical modeling based on the TCR structures and peptide structures built using the MODELLER. TCR-peptide pairs are classified and labeled as positive or negative pairs using pseudo-labels based on the docking energy scores, and the deep learning model is iteratively retrained based on the extended TCR-peptide training dataset and the pseudo-labels until convergence.
G16B 15/00 - ICT specially adapted for analysing two-dimensional or three-dimensional molecular structures, e.g. structural or functional relations or structure alignment
Disclosed are techniques for time-interleaved phase-OTDR (ϕ-OTDR) with nested phase references that advantageously enables faster synchronization times. Our inventive techniques employ nested phase references which enables faster phase synchronization in time-interleaved ϕ-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.
H04B 10/071 - Arrangements for monitoring or testing transmission systemsArrangements for fault measurement of transmission systems using a reflected signal, e.g. using optical time domain reflectometers [OTDR]
Disclosed is a parameter server orchestration architecture and procedure for accelerating the training of large language models that advantageously improves inter-machine network traffic thereby accelerating the training speed of LLMs. Our inventive procedure advantageously (i) minimizes the amount of inter-machine network traffic thereby accelerating the training speed of LLMs from a global perspective; (ii) optimizes the topology design for a given LLM training job so that less inter-machine traffic is produced; (iii) optimizes the number of workers used and their placement for a given LLM training job; (iv) optimizes number of parameter servers employed and their placement for a given LLM training job; (v) optimizes the workload distribution between different parameter servers such that inter-machine network traffic is reduced; and (vi) efficiently allocates network bandwidth and routing paths for inter-machine network traffic.
Disclosed are integrated DFOS systems and methods that advantageously integrates fiber sensing technology with advanced grid analysis to enhance the resilience of electrical distribution systems by providing accurate and efficient risk assessments. Utilizing real-time observations from Distributed Fiber Optic Sensing (DFOS), it accurately evaluates risks associated with probable events and calculates the risk of line failures. The method develops a modified risk-aware system that incorporates minimized system loss, voltage violations, power flow violations, the number of switching operations, and radiality constraints. By integrating DFOS data with existing grid data, the method enables rapid system adaptation and localized fault detection, advancing the state of the art in grid resilience and reliability.
H02J 13/00 - Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the networkCircuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
H02J 3/00 - Circuit arrangements for ac mains or ac distribution networks
65.
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 for different representations of desired t-cell receptor (TCR) sequences for a patient. Proximal policy optimization (PPO) models can be trained 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 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.
Disclosed are systems and methods for distributed fiber optic sensing (DFOS)/distributed acoustic sensing (DAS) that circumvent traditional data path(s) from an analog-to-digital converter (ADC) to a central processor (CPU). In sharp contrast to the prior art, systems and methods according to aspects of the present disclosure employ a direct peripheral component interconnect express (PCIe) connection to graphics processing unit (GPU) random access memory (RAM). This inventive architecture eliminates any need for data to pass through the CPU, thereby facilitating data acquisition streaming and enabling real-time processing of significantly larger data sets than is possible with contemporary DFOS systems.
A distributed fiber optic sensing (DFOS)/distributed acoustic sensing (DAS) system and method employing a fiber optic sensor cable that collects vibrational data of individual utility poles suspending the fiber optic sensor cable and stores the vibrational data in a central office (CO). Machine learning (ML) models are developed, trained, and utilized to analyze vibrational features of the utility poles and determine their integrity. Additionally, DFOS/DAS systems and methods according to the present disclosure determine the location(s) of fiber coils that exist along a length of a fiber optic sensor cable.
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
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
69.
ADAPTION OF AGENTIC MODELS TO PRODUCTION ENVIRONMENT
Systems and methods for adapting an agentic artificial intelligence (AI) model is provided. The systems and methods include extracting embeddings of a user input and determining an execution time and input domain according to the embeddings of the user input. The systems and methods further include developing an inference plan according to the execution time and input domain, and selecting modules that satisfy the inference plan considering output accuracy and execution time to satisfy an execution time accuracy tradeoff.
Systems and methods for action detection are provided. The systems and methods include generating action prediction labels and bounding boxes for objects detected in video frames and comparing the action prediction labels and the bounding boxes with corresponding ground labels, determining a classification loss and a localization loss, and determining a reversibility action loss by comparing the action prediction labels with known actions indices and logical constraints and a speed action loss by comparing the action prediction labels with known actions indices and logical constraints. The systems and methods further include combining the classification loss, localization loss, reversibility action loss, and speed action loss to evaluate a total loss and selecting the action prediction with a lowest total loss as an action assertion and performing reactionary actions in a connected device in response to the action assertion.
G06V 20/40 - ScenesScene-specific elements in video content
G06V 10/25 - Determination of region of interest [ROI] or a volume of interest [VOI]
G06V 10/764 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
Systems and methods for action detection are provided. The systems and methods include extracting an object from a video frame and forming an embedding to provide an extracted object, labeling an action using natural language text, evaluating an attention between the extracted object and the action, matching the extracted object and the action with a minimum object-interaction loss, and tracking the extracted object through a set of continuous video frames.
A wireless acoustic sensor network with a compressed acoustic-language model/acoustic recognition model which is pretrained with a language model contrastive language-audio pretraining which involves two main components: an acoustic encoder and a text encoder which are trained on a large dataset of acoustic features and their textual captions. Inputting acoustic features or language generates embedding vectors. These vectors are linked in a joint latent space. Acoustic classification tasks involve assessing similarity between these embedding vectors. Users interact with the model using language input for classification. The architecture of this model permits the segregation of the pre-trained framework into distinct acoustic and text encoders, enabling their deployment across various devices, for instance, positioning the acoustic encoder on edge nodes and the text encoder on a central node.
G10L 19/00 - Speech or audio signal analysis-synthesis techniques for redundancy reduction, e.g. in vocodersCoding or decoding of speech or audio signals, using source filter models or psychoacoustic analysis
73.
REAL-TIME ESTIMATION OF ICE THICKNESS ON FIBER OPTIC CABLES USING HYBRID SIGNAL PROCESSIN DISTRIBUTED ACOUSTIC SENSING DATA
Disclosed are systems and methods that employ distributed fiber optic sensing (DFOS)/distributed acoustic sensing (DAS) to monitor and provide real-time estimation of ice thickness on fiber optic communications facilities, and which integrate DSA data with a hybrid processing technique that combines frequency domain decomposition (FDD) and stochastic subspace identification (SSI). Aspects of our innovative systems and methods include: i) Hybrid Signal Processing Techniques; ii) Real-time, Continuous Ice Monitoring; iii) Enhanced Noise Robustness and Non-linear Dynamics Handling; and iv) Adaptability and Scalability.
Systems and methods for handling missing data with multi-domain graph-guided networks. Graph structures can be learned with masked dimension extension based on incomplete input data obtained from monitored entities to generate inferred graphs. Time and frequency domain forecasts generated based on the inferred graphs with a variable-wise mixture mechanism can be combined to generate combined forecasts. The combined forecasts can be aligned to time and frequency domains to obtain final forecasts that capture domain-invariant similarities between variables. A corrective action generated with multi-domain graph-guided networks for the monitored entities based on the final forecasts can be performed.
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.
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
76.
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 for a very large language model (VLLM) to generate a general guidance to guide Al models that answer reasoning questions for query documents. The instruction code can be updated 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 into the general guidance with the VLLM. The reasoning question iteratively applied to the query documents can be answered using the general guidance with the Al models to perform downstream tasks.
Methods and systems for patient stratification include learning interdependent biomarkers as integrated time-series machine learning models. A disease stage is identified for a patient based on collected biomarker data. A treatment for the patient is performed 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
78.
SEMI-SUPERVISED IMAGE SEGMENTATION FOR MEDICAL DECISION MAKING
Methods and systems for image segmentation include initializing a student model and a teacher model using a labeled dataset. An initial mask is generated for an unlabeled image using the teacher model. The initial mask is refined to generate a refined mask using a pretrained foundation model. The student model is tuned using the unlabeled image and the refined mask as a pseudo-ground truth label. The teacher model is updated using the tuned student 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
79.
AUTOMATED FORM FILLING WITH RETRIEVAL AUGMENTED GENERATION FOR MEDICAL DECISION MAKING
Methods and systems for filling data include extracting text from a structured document and document instructions to identify a field within the structured document. Text is extracted from a contextual document to identify information relating to the field. Information is selected 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 using the selected information to create a filled document.
G06F 40/117 - TaggingMarking up Designating a blockSetting of attributes
G06V 10/75 - Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video featuresCoarse-fine approaches, e.g. multi-scale approachesImage or video pattern matchingProximity measures in feature spaces using context analysisSelection of dictionaries
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
G06V 30/412 - Layout analysis of documents structured with printed lines or input boxes, e.g. business forms 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
80.
3D DRIVING SCENE GENERATION WITH OUTPAINTING AND INTERPOLATION
Systems and methods for generating a simulated scene include generating, 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 to a second viewpoint. a second key frame is generated, 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, 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.
Systems and methods for detecting Large Language Model (LLM) generated text are provided. The systems and methods include sampling a text passage to generate alternative samples conditioned on the text passage based on a next token prediction in a surrogate LLM model and scoring a likelihood that the test passage sample is generated by an LLM model. The scoring includes a conditional probability which quantifies a distribution gap of a log of logits from the surrogate LLM model. The systems and methods further include comparing the scored text passage with a sample text generated in the surrogate LLM model trained to imitate a target LLM model. The comparison includes transforming the scores into a scaled representation and normalizing the scores.
Systems and methods for online multi-modality root cause analysis. A root cause of a detected system fault can be identified based on a fused causal graph that represents the relationship of the factors and correlation of multi-modality data by, determining long-term temporal dependencies and causal relation from system entities and key performance indicators (KPI) of a cloud computing system using dilated convolutional neural networks, analyzing a correlation of factors from multi-modality data to assess contributions of the factors to causing a detected system fault, and learning a relationship of the factors and correlation of multi-modality data with contrastive representation learning. System maintenance that corrects the detected system fault caused by the root cause can be performed autonomously.
Methods and systems for classification include performing multi-label classification on an input using a trained model to generate classification outputs corresponding to respective labels. The classification outputs are fused to generate a joint opinion. It is determined that the input is out of distribution as compared to a training dataset of the trained model based on a joint belief of the joint opinion. An action is performed responsive to the determination that the input is out of distribution.
A large language model (LLM) powered voice-to-data documentation system and operating method for field inspection and infrastructure assessment which converts spoken language into precise, structured digital data in real-time and overcomes limitations of manual notetaking and data transcription by providing real-time, accurate interpretation of technical terminology and context, significantly reducing human error and enhancing data integrity. Our system and method provide immediate decision-making and problem-solving, markedly improving the speed and efficiency of infrastructure maintenance and compliance processes and may be portable, thereby permitting their use in challenging field environments, enabling inspectors to focus on critical assessment tasks without the distraction of cumbersome documentation procedures.
Methods and systems for time series analysis include generating a text summary of a time series using a first large language model (LLM) agent. A prompt is generated using a multi-modal encoder with the time series and the text summary as inputs. An event prediction is generated using a second LLM agent with the text summary and the prompt as inputs. An action is performed 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
86.
METHOD FOR LARGE-AREA SOIL MONITORING BY DISTRIBUTED TEMPERATURE SENSING
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.
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.
Disclosed are systems and methods that analyze DFOS sensing data from different optical fibers located within the same cable, and discern how many of the different optical fibers are routed in different directions, their distances, or the circuits through which they pass. When combined with cable survey techniques, our systems and methods according to aspects of the present disclosure rapidly identify optical fiber cable diversity. Our inventive systems and methods according to aspects of the present disclosure employ a route condition matched engine and interactive feedback between field technicians and DFOS systems. These aspects are coupled with interactive-AI-based algorithms to solve what we have called, a cable diversity puzzle quickly, with minimum field efforts.
Systems and methods for generating a three-dimensional (3D) scene include generating 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 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 a 3D scene based on the depth video, the color video, and the ego trajectory input.
Systems and methods for generating 3D scenes include a masked red, green, blue, depth (RGBD) input, which is separated into a masked RGB input and a masked depth input. The masked depth input is compressed. The masked RGB input is compressed. A high definition (HD) map control signal is generated for a depth stream, and an HD map control signal is generated for an RGB stream. A depth output is generated 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 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.
Systems and methods for generating categorical data for missing values in anomaly detection systems. In an embodiment, irregular time-series data can be aligned into regular time-series data by utilizing a generated timestamp sequence to obtain aligned time-series data. Missing values from the aligned time-series data can be filled with generated categorical time-series data. Anomaly detection can be performed for the cyber-physical system to obtain system anomalies. A corrective action can be performed to resolve issues with the cyber-physical system caused by the system anomalies.
Methods and systems for image analysis include processing an input image with a convolutional model that generates classification maps and a segmentation map. Pixels are identified in the classification maps that correspond to intensity peaks to detect objects. Object boundaries are generated in the segmentation map around the pixels to segment objects. Objects are classified using the object boundaries and the pixels to associate regions of the input image with respective classes. An action is performed responsive to the objects.
G06V 20/69 - Microscopic objects, e.g. biological cells or cellular parts
G06V 10/26 - Segmentation of patterns in the image fieldCutting or merging of image elements to establish the pattern region, e.g. clustering-based techniquesDetection of occlusion
G06V 10/764 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
93.
POWER GRID INTELLIGENCE: AI PLATFORM FOR INFRASTRUCTURE INSPECTION AND LOCALIZATION
Disclosed is an artificial intelligence-based platform for infrastructure inspection, localization and maintenance of power grid structures that advantageously allows electrical utility service providers to evaluate the condition of distribution grid components at scale before failures. Our inventive systems, and methods of the platform employ a vehicle-mounted, camera-based inspection system that passively collects maintenance-related data during routine operation. A vehicle mounted computing platform—coupled with multiple sensors including stereo cameras, inertial measurement unit, and global positioning system—are combined with AI powered software that provides multiple monitoring applications including utility pole detection, pole GPS location, situational awareness/object recognition of any pole-mounted instruments, and anomaly detection resulting from weather-related or other events.
Systems and methods for view-conditioned diffusion for real-world vehicle gaussian splatting. A single perspective image can be transformed 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 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 using the fine-tuned diffusion model. A large generative model (LGM) can be trained 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 by using the gaussian splatting model for downstream tasks.
Methods and systems for time series analysis include encoding input time series data using a pre-trained encoder. The encoded time series is mapped to a format suitable for a large language model (LLM) using an alignment model. The mapped, encoded time series is analyzed using the LLM to generate a text output. An action is performed responsive to the text output.
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 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 50/20 - 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
96.
CABLE LAYOUT DETECTION FOR SUBSEA CABLES BY DISTRIBUTED ACOUSTIC SENSING FOR OFFSHORE WIND FARMS
Disclosed are systems and methods employing distributed fiber optic sensing (DFOS)/distributed acoustic sensing (DAS) in conjunction with mathematical algorithms, and an optional camera to determine layout of subsea cables. The subsea cables are pressure wave detectors of the DAS system and employ mathematical algorithms which map detected pressure waves to sea waves to determine subsea cable layout. When a subsea cable is installed below the seabed, pressure changes due to the waves on the sea surface are still detected. When DAS data is integrated with an optional camera visual input namely: a relative subsea cable layout may be determined by assuming a uniform planar sea wave propagating through the sea; an absolute cable layout may be determined by considering actual sea wave shape detected by the camera; and wave shapes may be determined based on a known subsea cable layout.
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
97.
MONITORING SYSTEM OF OFFSHORE WINDFARM POWER CABLE USING FIBER-OPTIC DISTRIBUTED ACOUSTIC SENSING
Disclosed are systems and methods employing distributed fiber optic sensing (DFOS)/distributed acoustic sensing (DAS) that continuously monitor the buried/exposed status of undersea power cables for offshore wind farms. Our DAS systems and methods continuously monitor dynamic conditions characterizing undersea power cables and advantageously detect dynamic strain of an optical fiber that may be part of a composite cable with the power cable. By measuring and monitoring these dynamic conditions, a change in status from buried to exposed is determined and service personnel deployed before damage occurs to the power cable.
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
G01H 9/00 - Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves by using radiation-sensitive means, e.g. optical means
98.
HYBRID PHYSICS-INFORMED MACHINE LEARNING SYSTEM FOR PREDICTIVE MAINTENANCE AND THERMAL MANAGEMENT OF SUBMARINE CABLES
Disclosed are DFOS/DTS systems, methods, and structures that employ physics-informed machine learning, Finite Element Analysis (FEA) in combination with DFOS/DTS to enhance the detection, prediction, and management of thermal anomalies in submarine cables. Our integrated approach advantageously leverages FEA to simulate accurate temperature distributions within the cable, identifies potential hot spots, and validates these with real-time DTS data. By integrating advanced machine learning algorithms, our systems and methods continuously learn from both simulated and real-world data, predicting potential failure points and suggesting preemptive maintenance actions. A hybrid model, combining data-driven and physics-based approaches, incorporates uncertainty quantification methods, providing confidence intervals for predictions. Our systems and methods enhance the reliability, efficiency, and lifespan of submarine cables, by providing anomaly detection and predictive maintenance indications for the submarine cables.
G06F 30/23 - Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
G06F 30/18 - Network design, e.g. design based on topological or interconnect aspects of utility systems, piping, heating ventilation air conditioning [HVAC] or cabling
G06F 119/08 - Thermal analysis or thermal optimisation
99.
EXPLANATION-ASSISTED DATA AUGMENTATION FOR GRAPH NEURAL NETWORK TRAINING
Systems and methods for explanation-assisted data augmentation for training graph neural networks. The GNN can be trained using a training dataset to generate explainer subgraphs of labeled graphs. The explainer subgraphs can be transformed into perturbed subgraphs by utilizing explanation assisted empirical risk minimization (EA-ERM) learned by the GNN to generate an augmented training dataset. The GNN can be further trained with the augmented training dataset and the training dataset to perform downstream tasks using input data with corresponding labels.
B60W 60/00 - Drive control systems specially adapted for autonomous road vehicles
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
100.
LLM SKILL LEARNING FOR MEDICAL DECISION MAKING THROUGH SELF-PLAY
Methods and systems for medical decision making include selecting a strategy from a strategy library, expressed in natural language, and selecting an improvement from an improvement library, expressed in natural language. The strategy is combined with the improvement using a large language model (LLM) to generate an improved strategy. The improved strategy is evaluated to generate feedback. The strategy library and the improvement library are updated based on the feedback. An action is performed 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
patents
