A computer-implemented method for homogenizing datasets that have different ontologies to optimize performance of machine learning models that use the datasets includes mapping concepts between the different ontologies of the datasets based on ontology matching. The concepts are scored based on a relation between the concepts to identify certain ones of the concepts that are more important to improving the performance of the machine learning models. The different ontologies are merged based on the scoring to generate a merged ontology that includes the identified concepts. The datasets are transformed into a homogenized dataset according to the merged ontology. A machine learning model is generated based on the homogenized dataset. The method has applications including, but not limited to, use cases in computational biology, medical AI and healthcare, cyberthreat security, public safety and smart cities for optimizing machine learning processes or supporting decision making.
A computer-implemented method for enabling a base station (BS) to provide configuration commands wirelessly to a reconfigurable intelligence surface (RIS) includes establishing a new codebook for each configuration from a previous set of configurations. The method further includes generating an RIS control message based on embedding amplitude-modulated (AM) signals into Orthogonal Frequency-Division Multiplexing (OFDM) signals using the new codebook and providing the RIS control message to the RIS to control the RIS. The method can be used to optimize and/or allow enhanced decision making for controlling the RIS using the BS. For instance, the method can synchronize its radio scheduler decisions and the optimization of the RIS configuration seamlessly and/or disguise RIS control messages into New Radio OFDM symbols. In some embodiments, machine learning (ML) and/or artificial intelligence (AI) techniques (e.g., a neural network (NN)) can be used.
H04B 7/04 - Diversity systemsMulti-antenna systems, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
H04B 7/0456 - Selection of precoding matrices or codebooks, e.g. using matrices for antenna weighting
H04L 5/00 - Arrangements affording multiple use of the transmission path
A computer-implemented method for multimodal fact-checking includes receiving, from an agent system, new textual data indicating a textual claim. The method further includes segmenting the evidences that are in the different modalities and/or the different data formats into trackable multi-modal unit-based pairs and transforming image-based multi-modal evidences that are in the image data formats into the non-image formats. The method also includes inputting the textual claim, the trackable multi-modal unit-based pairs, and output from a generative artificial intelligence (AI) model into a multimodal explanation generator to generate final multimodal explanation information. The method has applications including, but not limited to, use cases in machine learning and medicine / healthcare, e.g., generating final multimodal explanation information indicating the veracity of whether a patient has a medical condition and a subset of evidences that support the veracity of whether the patient has the medical condition, which can help optimize decision making.
Various examples of the present disclosure relate to an artificial intelligence-based method, system, and computer program for combining multiple diagnoses and their explanations to aid in the decision-making process of healthcare professionals, such as doctors. For example, a computer-implemented method for machine learning-based evaluation of isolated health evaluations of a patient comprises obtaining (120) a plurality of sets of isolated health evaluations of the patient, with each set comprising information on an isolated outcome and a textual explanation of the isolated outcome, with the respective isolated outcome being based on the isolated health evaluation of the patient, inputting (130) at least the information on the isolated outcome of the plurality of sets of isolated evaluations into a first machine learning model, with the first machine learning model being trained to output (132) a predicted overall diagnosis based on the isolated outcomes, inputting (150) the predicted overall diagnosis and at least the textual explanation of the isolated outcome of the plurality of sets of isolated evaluations into a second machine learning model, with the second machine learning model being trained to output (155) a textual explanation of the predicted overall diagnosis based on the predicted overall diagnosis and the textual explanation of the isolated outcomes, and providing (170) the predicted overall diagnosis and the textual explanation of the predicted overall diagnosis.
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
Various examples of the present disclosure relate to methods for generating and using digital flow charts from manuals and/or guidelines, in order to guide a user through one or more digital flow charts to support a decision-making process of the user, e.g., a healthcare-related decision-making process of a doctor, or a decision-making process of a repair technician attempting to repair a device. The present disclosure leverages artificial intelligence, and in particular a (large) language model, to generate digital flow charts from manuals and/or guidelines, which are then used, in an interactive process, to support the decision-making process of the user e.g. in medical diagnostics/applications and in healthcare.
G16H 10/20 - ICT specially adapted for the handling or processing of patient-related medical or healthcare data for electronic clinical trials or questionnaires
G16H 50/20 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
G16H 50/70 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
G16H 70/20 - ICT specially adapted for the handling or processing of medical references relating to practices or guidelines
6.
UNIFORM ANALYSIS OF MULTILINGUAL RECORDS VIA KNOWLEDGE GRAPH TRANSLATION AND TRANSFER LEARNING
A computer-implemented method includes receiving input text documents in a majority language and training a plurality of models using the input text documents. Training the plurality of models using the input text documents includes conjunctively training a text to knowledge graph model in the majority language and a text to knowledge graph model in the minority language and conjunctively training a text translation model and a knowledge graph translation model, wherein one or more weights from the text to text translation model is shared with the knowledge graph translation model. The method has applications including, but not limited to, use cases in machine learning and medicine / healthcare, e.g., performing uniform analysis of multilingual records of a patient via knowledge graph translation and transfer learning, and improving text to knowledge graph extraction and knowledge graph translation for medical records in multiple languages, which can help optimize decision making.
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
7.
SELF-CORRECTING PROTOTYPE-BASED LEARNING FRAMEWORK FOR DEBIASING TRAINING DATA
A prototype-based model with one prototype per class is analyzed based on a comparison between a class-wise quality metric and a threshold for each prototype per class pair. A new prototype is added for each class in response to the class-wise quality metric for a respective prototype per class pair being below the threshold. The prototype-based model is retrained using the new prototype. A number of training samples closest to each prototype per class pair of the retrained prototype-based model is counted based on a distance measure. Sample weights for the training samples closest to each prototype per class pair is computed based on the number. A target model is trained using the computed sample weights. The method has applications including, but not limited to, use cases in computational biology, medical AI and healthcare, and cyber threat security for optimizing machine learning processes or supporting decision making.
A method of inductive graph machine learning uses information recorded or collected from an established network including a plurality of entities with relationships existing between the plurality of entities to generate a graph representation of the established network. The plurality of entities form nodes and the relationships existing between the plurality of entities form edges of the graph representation. A new entity is mapped to a latent space. An extended network is created by connecting the new entity to one or more of the plurality of entities of the established network according to their distance in the latent space. The extended network and a graph machine learning (ML) predictor is optimized and used to make predictions about the new entity.
G16H 50/30 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indicesICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for individual health risk assessment
9.
MACHINE LEARNING SYSTEMS AND METHODS FOR CLASSIFYING OR PREDICTING A PHENOTYPE BASED ON MICROBIOME DATA
The present disclosure relates to a machine learning system comprising an encoder configured to receive patient microbiome data, and associated patient bias data as input. The encoder comprises one or more processing layers, and one or more conditional normalization layers connected to the one or more processing layers, and is configured to encode the patient microbiome data, conditioned by the associated patient bias data as a latent representation in a suitable (e.g., stochastic) embedding space. The machine learning system also comprises a decoder configured to receive the encoded latent representation as input and is configured to predict or classify a phenotype of the patient based on the patient microbiome data. Related optimized training methods and optimized medical diagnosis or optimized treatment recommendation systems in healthcare are also disclosed.
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
G06N 3/084 - Backpropagation, e.g. using gradient descent
10.
MACHINE LEARNING APPROACH TO PREDICT VIRUS OR CANCER MUTATIONS FOR VACCINE PRODUCTION OR DRUG DESIGN
A computer-implemented, machine learning method for predicting a top-k most likely mutated molecular sequences includes encoding a molecular sequence at a first time into a first vector in a latent space. A second vector is generated, by a time-varying mutation models, in the latent space using as input the first vector. The second vector indicates a time-varying influence of the molecular sequence on a mutated version of the molecular sequence at a subsequent time. The second vector is decoded to generate a prediction of the top-k most likely mutated molecular sequences for the molecular sequence at the subsequent time. The method has applications including, but not limited to, use cases in computational biology and medical AI and healthcare for optimizing vaccine design or supporting decision making in diagnosis and treatment of patients.
The present disclosure relates to a stable classification by components (SCBC) data processing architecture, configured to classify input data into one or more classes, comprising: a component detection module configured to compare the input data to a set of detection components, representing data patterns relevant for the classification, and determine a detection probability for each detection component based on the comparison. The SCBC data processing architecture further comprises a probabilistic reasoning module configured to compute one or more class prediction probabilities for the one or more classes based on the determined detection probabilities, a set of class-specific prior probabilities for the determined detection probabilities, and a set of class-specific reasoning probabilities for the determined detection probabilities. Application scenarios include medical and pharmaceutical applications, as well as healthcare in general such as interpretable and secure diagnosis and treatment recommendation systems. Related SCBC data processing system, methods and computer programs are also disclosed, as well as corresponding model training methods and systems.
A computer-implemented machine learning method for modelling multi-scale interactions includes determining a geometric vectorization based on a mapping of input data associated with a multi-scale system. Using a neural network and the mapped input data, one or more predicted vectors of the multi-scale system are generated. The neural network includes pooling and unpooling mechanisms that conserve equivariance to geometric primitives of the geometric vectorization by using a multi-blade projection that defines pooling or clustering of the pooling and unpooling mechanisms. The one or more predicted vectors are mapped to the multi-scale interactions of the multi-scale system. The method has applications including, but not limited to, use cases in computational biology, medical AI and healthcare, and orbiting body management for optimizing machine learning processes or supporting decision making.
G16C 10/00 - Computational theoretical chemistry, i.e. ICT specially adapted for theoretical aspects of quantum chemistry, molecular mechanics, molecular dynamics or the like
G16C 20/30 - Prediction of properties of chemical compounds, compositions or mixtures
A method performed by an access network controller is provided. The method includes providing, to a distributed unit (DU) of an access network, at least one scheduling policy for scheduling transmission of at least one transport block (TB) by a user equipment (UE). The at least one scheduling policy is based on statistical information about a respective waiting time, associated with each queue of a plurality of queues, each queue of the plurality of queues being associated with a respective logical processing unit (LPU) representing a hardware accelerator (HA) for processing TBs.
A computer-implemented method for developing a differential privacy model is provided. The method includes collecting a private and personal dataset comprising private and/or personal data and training the differential privacy model via backpropagation to optimize an expected accuracy of an adversarial loss and a privacy loss. The differential privacy model is associated with a continuous normalizing flow. The method further includes outputting the trained differential privacy model. The trained differential privacy model is configured to generate new synthetic datasets that are used to train one or more downstream tasks. The method has applications including, but not limited to, use cases in medicine / healthcare such as Electronic Health Record (EHR) generation, single and bulk cell sequencing data generation, and pre-training large multimodal language models (LLMs) associated with clinical data, and can further for example, be used to optimize machine learning tasks or to support decision making.
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
15.
METHODS, SYSTEM AND COMPUTER PROGRAMS FOR TRIGGERING AN EVENT AND FOR TRAINING AT LEAST ONE MACHINE LEARNING MODEL
Various examples relate to computer-implemented methods, systems, and computer programs for triggering an event and for training at least one machine learning model. The proposed methods, systems and computer programs provide an artificial intelligence-based approach for helping decision-making in various fields, such as healthcare fields, which may be used to help healthcare professionals in diagnosing or treating a disease or condition, or by crime specialists to solve a crime case. A computer-implemented method for triggering an event, the method comprising inputting (130) a representation of a first sequence of knowledge graphs representing a plurality of stages of a case, such as a crime case or medical case, and a representation of a second sequence of actions having been performed in the plurality of stages of the case into at least one machine learning model, wherein the at least one machine learning model is trained to output a predicted next action to perform and a corresponding predicted next stage of the case in response to the representations of the first sequence and the second sequence being input into the machine learning model, and triggering (140) an event based on at least one of the predicted next action to perform and the predicted next stage of the case, wherein the event being triggered comprises at least one of processing, using an algorithm or machine learning model, sensor data, such as camera sensor data, being related to the predicted action, and controlling a device or system, such as a controllable sensor device, medical device, autonomous vehicle, traffic control system or wearable device, based on the predicted action.
The present invention relates to a method, system and computer program for training a machine-learning model for prediction of one or more molecular properties of a molecule, and a method, system and computer program for applying such a machine-learning model. The present invention optimizes molecular simulation. It can be used in a variety of applications including, but not limited to, several anticipated use cases in drug development, material synthesis, and in healthcare. The computer-implemented method for training the machine-learning model comprises obtaining (110) an initial training sample for training the machine-learning model, the initial training sample representing a first molecule and comprising atomic coordinate information, chemical element information, and information on one or more molecular properties of the first molecule, generating (120) spatially perturbed atomic coordinate information for a spatially perturbed variation of the first molecule, deterministically (140, 145) calculating or estimating at least one molecular property of the spatially perturbed variation of the first molecule based on the initial training sample and based on a spatial deviation between the atomic coordinate information of the first molecule and the spatially perturbed atomic coordinate information, calculating (160) a first partial loss function between the information on the one or more molecular properties of the first molecule included in the initial training sample and predicted information on the one or more molecular properties of the first molecule predicted by the machine-learning model, calculating (170) a second partial loss function between the deterministically calculated or estimated at least one molecular property of the spatially perturbed variation of the first molecule and a corresponding prediction of the at least one molecular property predicted by the machine-learning model, and adjusting (190) the machine-learning model based on a result of the first and second partial loss function.
A computer-implemented method for predicting links in a temporal knowledge graph (TKG) includes determining one or more anchor nodes and computing, from each node to each anchor node of the TKG for each time-step, relational and temporal paths, and temporal and spatial distances. An embedding is determined for each node to a closest anchor node at each time-step using a vocabulary encoder that combines information received from separate encoders configured to encode the paths and distances. The embedding includes a type of relation. Scores are predicted for each embedding at a future time-step using a scoring function. Link prediction is performed to predict how interaction of the nodes change at the future time-step based on the scores. The present disclosure has applications including, but not limited to, use cases in computational biology, medical AI and healthcare, and cyber threat security for optimizing machine learning processes or supporting decision making.
A method of self-configuration of a reconfigurable intelligent surface (RIS) for optimizing a gain of a reflected beam between a base station (BS) and a User Equipment (UE) includes acquiring, using power sensing capabilities of the RIS, a power profile through sequential activation of probing beams. An angular position of the BS and the UE is obtained by identifying power profile peaks in the acquired power profile. An optimal RIS configuration is computed locally according to the obtained angular position of the BS and U. The RIS is self-configured by setting the computed optimal RIS configuration.
H04W 24/02 - Arrangements for optimising operational condition
H04B 7/04 - Diversity systemsMulti-antenna systems, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
H04B 7/06 - Diversity systemsMulti-antenna systems, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station
19.
METHOD AND SYSTEM FOR INTELLIGENT DATA COLLECTION AND MANAGEMENT FOR OPEN RAN INTELLIGENT CONTROLLERS
A method of operating an open radio access network (O-RAN) is provided. The O-RAN includes a Non-Real-Time RAN Intelligent Controller (Non-RT RIC) and a Near-Real-Time RAN Intelligent Controller (Near-RT RIC). An interface provided between the Non-RT RIC and the Near-RT RIC is used to send analytical data from the Near-RT RIC to the Non-RT RIC.
A computer-implemented method for predicting gene expression perturbations includes generating a knowledge graph (KG) from domain knowledge, where the KG describes relations including associations, similarities and/or interactions between a plurality of entities, the plurality of entities including at least a number of genes and perturbation agents. A machine-learning (ML) model is trained to predict perturbed gene expression from pre-perturbed gene expression data and learned embeddings of the plurality of entities of the KG. Gene expression data obtained from a subject-derived gene sample is provided and the trained ML model is used to predict a response of the gene sample in terms of gene expression changes effected by applying one or more perturbation agents to the gene sample.
G16B 25/10 - Gene or protein expression profilingExpression-ratio estimation or normalisation
G16B 5/00 - ICT specially adapted for modelling or simulations in systems biology, e.g. gene-regulatory networks, protein interaction networks or metabolic networks
An iterative artificial-intelligence (AI)-based prediction method includes receiving a dataset of knowledge, and processing the dataset of knowledge to produce one or more predictions, one or more explanations corresponding to the one or more predictions, and one or more output options. An output option of the one or more output options is presented to a user, the output option including a prediction and an explanation of the prediction. A reply is received including a feedback score regarding a degree of positive sentiment or negative sentiment from the user. Processing is performed, by using the feedback score, to determine a new or revised output option for presentation to the user. The method has applications including, but not limited to, use cases in computational biology and medical AI and healthcare for drug development, public safety and predictive maintenance, for optimizing outputs or supporting decision.
An iterative artificial-intelligence (AI)-based prediction method includes receiving a dataset of knowledge, and processing the dataset of knowledge to produce one or more predictions, one or more explanations, and one or more output options. Using an AI algorithm, one of the output options is selected and is presented to a user, the selected output option including a prediction and an explanation of the prediction. A reply including feedback information is received from the user. Using the feedback information from the user, at least one of the dataset of knowledge, the AI algorithm, an inference module, an explanation module, or an output module is/are updated. The method has applications including, but not limited to, use cases in computational biology and medical AI and healthcare for drug development, public safety and predictive maintenance, for optimizing outputs or supporting decision.
A computer-implemented method for providing for artificial intelligence (AI) framework identical pseudo random number generation includes storing a generator state as a static object within a compiled library having a plurality of layers, or in a runtime library associated with the compiled library, the generator state corresponding to a random state associated with a pseudo random number generation algorithm. Random number generations are scheduled using in each case the generator state, wherein the generator state is forwarded by an amount of random numbers drawn from previous layers of the compiled library executed prior to a current layer. The method has applications including, but not limited to, use cases in machine learning, computational biology, medical AI and healthcare, chemistry, physics, electrical or mechanical engineering.
Aspects of the disclosure relate to methods, computing devices and computer programs for training a graph neural network (GNN), as well as methods for node, edge or graph classification using a GNN. According to aspects of the present disclosure, a depth of a GNN may be adapted during training by adjusting the number of message passing layers, to ensure that an optimized number of layers is used which is large enough to grasp long-term dependencies, but is not too large, such that oversmoothing can be avoided. Aspects of the present disclosure can be used in a variety of applications including, but not limited to, several use cases in drug development, material informatics, and medical/healthcare.
A computer-implemented method for providing event-specific intervention recommendations includes acquiring at least two data streams of a patient by using one or more sensors. At least one entity-feature-graph is generated based on the acquired at least two data streams of the patient. At least one intervention is selected based on the generated entity-feature-graph, a trained graph classification model, and an information related to the patient. An information of the selected intervention is output to a user. The method has applications including, but not limited to, use cases in medical/healthcare for optimizing machine learning and supporting decision making.
A computer-implemented method for providing event-specific intervention recommendations includes acquiring at least two data streams of a patient by using one or more sensors, wherein at least one the data streams includes images. At least one entity-feature-graph is generated based on the acquired at least two data streams of the patient. At least one intervention is selected based on the generated entity-feature-graph and a trained graph classification model. An information of the selected intervention is output to a user. The method has applications including, but not limited to, use cases in medical/healthcare for optimizing machine learning and supporting decision making.
A computer-implemented method for providing event-specific intervention recommendations includes acquiring at least two data streams of a patient by using one or more sensors. A location of an event is determined based on the acquired at least two data streams of the patient. At least one entity-feature-graph is generated based on the acquired at least two data streams of the patient. At least one intervention is selected based on the generated entity-feature-graph, a trained graph classification model, and an information related to the determined location of the event. An information of the selected intervention is output to a user. The method has applications including, but not limited to, use cases in medical/healthcare for optimizing machine learning and supporting decision making.
A computer-implemented machine learning method for using a predicted property of an atomic system to train a graph machine learning model includes obtaining a candidates pool comprising a plurality of candidates and using an uncertainty-driven active learning (UDAL) to obtain a candidate specific machine learning interatomic potential (MLIP) model for a first batch of candidates. The method further includes incorporating the MLIP model into a self-tuning Hamiltonian Monte Carlo (HMC) simulator to generate an HMC output indicating the predicted property. The method also includes training the graph machine learning model based on a dataset comprising the HMC output. The method has applications including, but not limited to, use cases in medicine / healthcare, e.g., for drug design or treatment, and discovery of new materials, to optimize predictions or support decision making.
G16C 20/30 - Prediction of properties of chemical compounds, compositions or mixtures
G16C 10/00 - Computational theoretical chemistry, i.e. ICT specially adapted for theoretical aspects of quantum chemistry, molecular mechanics, molecular dynamics or the like
G16C 20/70 - Machine learning, data mining or chemometrics
G16B 15/30 - Drug targeting using structural dataDocking or binding prediction
29.
METHOD, APPARATUS AND COMPUTER SYSTEM FOR PATIENT-PHYSICIAN MATCHING
Some aspects of the present disclosure relate to a computer-implemented method for optimizing patient-physician matching, comprising obtaining (110), for a plurality of physicians, a representation of the respective physician, wherein the representation of a physician comprises a plurality of sub-representations representing a category of properties of the respective physician, obtaining (120), for one or more patients, a representation of the respective patient, the representation of a patient comprising information on one or more symptoms of the patient, determining (140), using an ensemble of machine learning models, matching scores representing matches between the plurality of physicians and the one or more patients, wherein the ensemble of machine learning models comprises separate sub-models for different categories of properties of the respective physicians, and wherein the ensemble of machine learning models takes the representations of the physicians and the representations of the one or more patients as input, and providing (190), based on the matching scores, information on one or more recommended matches between the plurality of physicians and the one or more patients. The present invention can be used in a variety of applications including, but not limited to, several anticipated use cases in decision making, medical diagnostics/applications and in healthcare.
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
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
30.
LIFESTYLE RECOMMENDATION SYSTEM FOR CHRONIC DISEASE MITIGATION
A computer-implemented, machine learning method for generating explainable lifestyle recommendations for mitigation of a medical condition of a patient includes extracting structured information from unstructured static data. Real-time data is transformed into a homogeneous representation. A portion of data is selected based on a pre-defined time interval or frequency. A patient graph is constructed using the structured information, the homogenous representation, and the portion of data. Whether there is a current risk is determined based on analyzing the real-time data. Whether there is a potential risk is determined based on the patient graph and a classification method. Recommendation candidates are generated based on features of other patients meeting a similarity condition with the patient using the patient graph and a hierarchy search. The method has applications including, but not limited to, use cases in medical AI / healthcare, for example to optimize predictions or treatments, or to support decision-making.
G16H 20/30 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
G16H 50/70 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
G16H 20/60 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to nutrition control, e.g. diets
G16H 20/70 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mental therapies, e.g. psychological therapy or autogenous training
G16H 50/30 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indicesICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for individual health risk assessment
31.
MULTI-MODAL REASONING SEGMENTATION TO ENHANCE LANGUAGE MODELS FOR HEALTHCARE REASONING ANALYSIS
A computer-implemented method for improving language models includes tokenization processing to concatenate an obtained image and texts with designated tags. An image encoder is trained to encode image information of the image. A two token representation is generated by a multi-modal generative agent using the encoded image information and the obtained texts. A text encoder and the image encoder are trained to encode the obtained image and texts. A text decoder and an image decoder are combined for the multi-modal reasoning segmentation by training the text decoder and the image decoder to generate a segmented image and segmented textual information using the two token representation in combination with an output of the text encoder and an output of the image encoder. The method has applications including, but not limited to, use cases in medical Al / healthcare, for example, for optimizing medical diagnosis or treatment or supporting decision making.
A computer-implemented method for remotely attesting program executions includes obtaining, by a verifier computing entity, a program associated with an original program, for example a shadow program. The method further includes obtaining, by the verifier computing entity, collected information associated with control-flow operations executed by an instrumented program, wherein the instrumented program is a variation of the original program. The verifier computing entity executes the program associated with the original program based on the collected information, and checks an output of the program associated with the original program.
A reflective device includes a control element and a reflective surface. The reflective surface includes a plurality of reflective elements, where each reflective element of the plurality of reflective elements has an antenna element and a phase shifter and is under control of the control element so as to reflect a radio-frequency (RF) signal incident on the reflective surface with an adjustable phase shift. An operating frequency of the reflective surface is configurable by at least a subset of the plurality of reflective elements being divided into a number of sub-elements that are individually switched via the control element from an activated state, in which a respective sub-element contributes to the reflection of the incident RF signal, to a deactivated state, in which the respective sub-element does not contribute to the reflection of the incident RF signal, and vice-versa.
H04B 7/04 - Diversity systemsMulti-antenna systems, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
A computer-implemented method for efficiently selecting features in a distributed system comprising a plurality of remote data sources and a computing system includes initializing a feature importance model and a feature redundancy model. The method further includes selecting a feature that maximizes an output from the feature importance model, accessing feature data associated with the feature and stored in one of the remote data sources, updating parameters of the feature importance model based on determining a true feature importance associated with the selected feature, and selecting one or more further features based on the feature importance model and the feature redundancy model. The method has applications including, but not limited to, use cases in medicine / healthcare, smart buildings and cities, energy distribution and management, public safety and predictive maintenance, for example, to optimize machine learning tasks or to support decision making.
A machine-learning method generates sparse explanations of feature selection from high¬ dimensional data. A training phase includes: encoding training data into latent space to generate first training embeddings, which are decoded to generate first reconstructed training data; computing sparsified feature selections of the first reconstructed training data; calculating reconstruction losses; calculating negative partial likelihood losses; encoding the sparsified feature selections of the first reconstructed training data into the latent space to generate second training embeddings; calculating negative double-pass partial likelihood losses based on the second training embeddings; and updating an embedding machine learning model used for the encoding and decoding based on the reconstruction losses, negative partial likelihood losses and negative double-pass partial likelihood losses. The method has applications including, but not limited to, use cases in medicine / healthcare, treatment, diagnosis or biomedical events, to optimize predictions or support decision making.
A computer-implemented method for providing prototype-based embedded clusters includes receiving training data associated with a plurality of individuals and embedding the training data using an encoder / decoder architecture to generate an embedding output associated with the encoder / decoder architecture. The method further includes determining a clustering partial likelihood based on inter-cluster discordance associated with the embedding output from embedding the training data using the encoder / decoder architecture, and generating prototypes indicating predicted hazards for the plurality of individuals based on the clustering partial likelihood. The method has applications including, but not limited to, use cases in medicine / healthcare, predictive maintenance, and/or smart cities / buildings, for example, to optimize machine learning tasks or to support decision making.
G16H 50/20 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
37.
EXPLAINING BLACK BOX NLP MODELS VIA ENSURING INTERMEDIATE HUMAN-UNDERSTANDABLE REPRESENTATIONS WITH PROTOTYPE-BASED LEARNING
A computer-implemented, machine learning method for providing human-understandable intermediate representations using prototype-based learning includes receiving textual input and generating a rationale using the textual input, where the rationale includes an explanation for the textual input. A closest prototype is identified based on the rationale and a defined distance measure. A classification label and a set of rationales for the closest prototype is provided to a user. The method has applications including, but not limited to, use cases in medicine / healthcare (e.g., for disease classification), resource allocation and data security, data integrity, crime investigation, for example, to optimize predictions or support decision-making.
A computer-implemented, machine learning method for guided programming of autonomous agents using a meta agent includes generating a first task that includes a start tag, script agents involved in the first task, and a timer associated with the first task or the script agents. A prompt is generated for each script agent of the script agents associated with the first task that includes the timer, wherein each script agent is configured to generate a script that corresponds to the prompt and includes an end tag for executing a second task associated with the prompt. An action is determined based on the script agents returning a response to the prompt or upon expiration of the timer. The method has applications including, but not limited to, use cases in medical Al / healthcare, cybersecurity, city planning, safer cities, industry 4.0 and material acquisition for optimization of actions or to support decision-making.
G05B 19/418 - Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
39.
METHOD AND APARATUS FOR DETECTION AND PREVENTION OF ANOMALOUS ACTIVITIES IN NEW CONTEXTS
The present disclosure relates to artificial intelligence systems employing machine learning that allow to predict anomalous activities and / events and to identify, optimize and decide on suitable counter measures. An aspect relates to a computer- implemented method for predicting behavior and/or relations of objects in a target region that are associated with anomalous types of behavior and / or relations, the method comprising, obtaining a plurality of data sets characterizing behavior and/or relations of the objects in the target region for a plurality of time intervals, generating, based on the obtained plurality of data sets, a first graph and, optionally, a second graph for the plurality of objects in the target region, wherein the first graph characterizes behavior and/or relations of the objects in the target region that are not associated with anomalous types of behavior and / or relations, and wherein the optional second graph characterizes behavior and/or relations of the objects in the target region that are associated with anomalous types of behavior and / or relations and predicting, using a trained neural network model, and based on the generated first graph and the optional second graph the behavior and/or relations of the objects in the target region that are associated with anomalous types of behavior and / or relations. Further aspects relate to associated methods for preventing occurrences of such anomalous types of behavior and / or relations as well as to corresponding apparatuses and computer programs. Possible applications include, crime prevention, disaster mitigation, health care interventions and industrial equipment maintenance.
In an embodiment, the present invention provides a computer-implemented, machine learning method for guided programming of autonomous agents. A large language model (LLM) prompt is intercepted between an LLM autonomous agent and an LLM. A guiding prompt is selected from a plurality of guiding prompts to inject into the LLM prompt based on a context of the LLM prompt. A modified LLM prompt that includes the selected guiding prompt is sent to the LLM. The modified LLM prompt and answer generated by the LLM is forwarded to the LLM autonomous agent. The method has applications including, but not limited to, use cases in medicine / healthcare, Cyber Threat Intelligence and performance portability of computer code, to optimize processes or predictions or to support decision making.
The present disclosure relates to artificial intelligence systems and methods for detecting, predicting and preventing outbreaks of rare pathogens. Applications for the present disclosure include, but are not limited to, use cases in the medical sector and in healthcare as well as for decision making in such sectors. More specifically, the present disclosure relates to machine learning technologies that allow to predict infection probabilities of rare pathogens within a population of persons in a medical context. Counter measures can be identified, optimized, and executed to improve patient safety, trigger infection control, and manage medical resources. One aspect relates to a computer-implemented method comprising: obtaining time and location resolved information characterizing movement and interaction of the plurality of persons in the environment of connected locations during a first time period, obtaining one or more test results confirming infection of one or more persons with the first pathogen within the first time period, obtaining a machine learning model trained for estimating the infection probabilities based on the time and location resolved information, and the one or more test results, and estimating the infection probabilities for the first pathogen and the plurality of persons based on inputting the obtained time and location resolved information, and the obtained test results into the trained machine learning model.
G16H 50/80 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for detecting, monitoring or modelling epidemics or pandemics, e.g. flu
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
G06N 3/084 - Backpropagation, e.g. using gradient descent
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
42.
AI-POWERED SYSTEM FOR PERSONALIZED HEALTH MANAGEMENT AND PREVENTION
Aspects of the present invention relate to a computer-implemented method for generating a causal inference model, CIM, for assisting treatment of and optimal decision making for a medical condition. The CIM comprises: (i) an input layer configured to receive an input data set characterizing patient behavior within a time interval associated with the medical condition, and a presence of a therapeutic treatment within the time interval, (ii) one or more processing layers connected to the input layer, and (iii) an output layer connected to the one or more processing layers, and configured to output an output data structure comprising a patient-specific prediction of a likelihood of a presence of a symptom of the medical condition within a future time interval, information of patient behavior correlated or causally associated with the predicted likelihood, and a recommendation for an interventive treatment for the medical condition in the future time interval. The method comprises obtaining a plurality of labeled input data sets characterizing patient behavior, and presence of a therapeutic treatment for a plurality of patients and a plurality of time intervals, wherein each labeled input data set comprises a label characterizing a presence of the symptom of the medical condition for a respective patient within a respective time interval; and generating the CIM for treatment of the symptom of the medical condition by training the CIM based on the obtained plurality of labeled input data sets. The method may also comprise machine learning (e.g. a large language model), configured for generating part of the labeled input data set. The present disclosure can be used in a variety of applications including, but not limited to, several anticipated use cases in medical device development, in medical diagnostics/applications and in healthcare.
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
A passive self-announcing reconfigurable intelligent surface (RIS). The passive self-announcing RIS includes reconfigurable elements configured for controllable reflections, and self-conjugating elements disposed together with the reconfigurable elements on a single passive reflective surface. The present invention can be used in a variety of applications including, but not limited to, RIS presence detection, RIS communication systems, and RIS signal propagation.
H04B 7/04 - Diversity systemsMulti-antenna systems, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
H04B 7/06 - Diversity systemsMulti-antenna systems, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station
In an embodiment, the present invention provides a computer-implemented, machine learning method for active mining for rare diseases. A patient disease profile is generated based on received input. Data of the patient disease profile is transformed into a representation in a feature space for comparison to representations of diseases in the feature space. One or more candidate diseases are identified based on distances in the feature space between the representation of the data and the representations of the diseases. One or more discriminative disease features are determined for one or more candidate diseases. An interview question is generated based on the one or more discriminative disease features. The method has applications including, but not limited to, use cases in medical Al / healthcare for optimization of predictions or to support decision-making.
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
45.
METHOD AND SYSTEM FOR DECONVOLUTION OF BULK RNA-SEQUENCING DATA
A method for deconvolution of bulk RNA sequencing data is provided. Input comprising single-cell RNA sequencing (RNA-seq) data is obtained, and diverse datasets are generated based on a principle of same generating mixture probability such that each of the diverse datasets has a same cell type mixture proportion. The generated diverse datasets are used as input datasets for training a prediction model using machine learning, including creating a causal prediction model in which virtual samples are generated from the generated diverse datasets, and performing contrastive learning on the causal prediction model, wherein a contrastive loss is used for the learning of invariant features with respect to a measurement mechanism by which the RNA-seq datasets have been generated. The trained prediction model is used to predict the mixture of cell type quantities in the bulk RNA sequencing data. It can also contribute to predictive optimization regarding patient-specific risks.
A reflective device includes a control element, and a reflective surface with a plurality of reflective elements. Each reflective element of the plurality of reflective elements includes an antenna element and a phase shifting arrangement and is under control of the control element so as to reflect a radio-frequency (RF) signal incident on the reflective surface with an adjustable phase shift. The plurality of reflective elements are connected to the control element via a cell selection bus system that interconnects the plurality of reflective elements.
H04B 7/04 - Diversity systemsMulti-antenna systems, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
47.
ARTIFICIAL INTELLIGENCE METHOD FOR MATERIAL PROPERTY OPTIMIZATION AND NEW MATERIAL GENERATION
A computer-implemented, machine learning method for material property optimization. A dataset for a material is obtained that includes a molecule shape description, a molecular weight, and a target material property for the material. The material is encoded to a computing format including a three dimensional (3D) graph representation of a main molecule for the material, a 3D graph representation of a side chain, the molecular weight, and a degree of substitution of the side chain. The 3D graph representations are encoded by a neural network that includes one or more graph attention layers each into a latent representation usable for the material property optimization. The method has applications including, but not limited to, use cases in medicine / healthcare (e.g., for AI assisted drug design), molecular or material design and development, and chemical engineering.
G16C 60/00 - Computational materials science, i.e. ICT specially adapted for investigating the physical or chemical properties of materials or phenomena associated with their design, synthesis, processing, characterisation or utilisation
G16C 20/30 - Prediction of properties of chemical compounds, compositions or mixtures
G16C 20/70 - Machine learning, data mining or chemometrics
48.
SECURE SETUP FOR DISTRIBUTED MONOTONIC COUNTER SERVICES
The present invention provides a computer-implemented method for providing a service to a trusted execution environment (TEE). A data item is written by a process running in the TEE to a pre-defined cache location. The data item is monitored to determine whether it is evicted from the pre-defined cache location. A setup procedure is accepted as complete based on the data item not being evicted from the pre-defined cache location. The present invention can be used in a variety of applications including, but not limited to, several anticipated use cases in cloud services, machine learning, and medical/healthcare. This invention can also provide lower access times if optimized for performance.
G06F 21/78 - Protecting specific internal or peripheral components, in which the protection of a component leads to protection of the entire computer to assure secure storage of data
ENSEMBLE-FREE, UNCERTAINTY-DRIVEN ACTIVE LEARNING FOR GENERATING CONCISE YET COMPREHENSIVE DATA SETS FOR TRAINING MACHINE LEARNED INTERATOMIC POTENTIALS
A computer-implemented, machine learning method for training interatomic potentials of an atomic system includes performing uncertainty-driven active learning. The uncertainty-driven active learning includes running an atomistic simulation using ensemble-free uncertainties to generate unlabeled atomic data. The ensemble-free uncertainties are derived from gradient features and used to terminate the atomistic simulation and bias the atomistic simulation toward unexplored regions of a configurational and/or chemical space of the atomic system. The uncertainty-driven active learning further includes performing active learning to select one or more atomic configurations from the unlabeled atomic data using a trajectory of the atomistic simulation and to train a machine learning model for the interatomic potentials using the one or more atomic configurations. The method can be used in a variety of applications including, but not limited to, several anticipated use cases in medical diagnostics/applications and in healthcare for example, to optimize predictions or support decision-making.
G16C 10/00 - Computational theoretical chemistry, i.e. ICT specially adapted for theoretical aspects of quantum chemistry, molecular mechanics, molecular dynamics or the like
50.
RECONFIGURABLE INTELLIGENT SURFACE, RIS, WITH SENSING CAPABILITIES AND METHOD FOR OPERATING THE SAME
A reflective device includes a control element and an array of reflective elements. Each reflective element of the array of reflective elements has an antenna element and a phase shifter and is under control of the control element so as to reflect a radio-frequency (RF) signal incident on the each reflective element with an adjustable phase shift, where different phase shifts are realized by the phase shifter channeling the RF signal into a specific one of a number of different delay lines. Each of the different delay lines includes an extension unit configured to extract a portion of a power of the RF signal channeled into the respective specific one delay line by the phase shifter and to measure or estimate the voltage, the current and/or the power of the extracted portion of the RF signal.
H04B 7/04 - Diversity systemsMulti-antenna systems, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
H04B 7/06 - Diversity systemsMulti-antenna systems, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station
A computer-implemented, machine learning method for preprocessing code for performance portability includes extracting performance critical code segments from an application and obtaining input data. Ground truth data is generated based on the input data and the application. Original code of the application is transpiled using a large language model (LLM) into a tensor computation language (TCL) candidate. Correctness of an implementation of the TCL candidate is verified using the ground truth data. The method has applications including, but not limited to, use cases in medicine/healthcare, and other artificial intelligence applications for preprocessing and optimizing code for performance portability.
A method for selecting an amino acid sequence for inclusion in a neoantigen vaccine from a set of candidate neoantigen amino acid sequences is provided. A plurality of cancer cells are simulated based on a set of input data related to a patient by predicting a cell surface presentation of each cancer cell. For each candidate neoantigen amino acid sequence, a likelihood is predicted of each candidate neoantigen amino acid sequence eliciting an immune response to the plurality of cancer cells based on the predicted cell surface presentation of each cancer cell. One or more amino acid sequences is selected for inclusion in the neoantigen vaccine that maximizes a likelihood of the neoantigen vaccine eliciting an immune response to the plurality of cancer cells based on the predicted likelihood of each candidate neoantigen amino acid sequence eliciting an immune response to the plurality of cancer cells.
A computer-implemented, machine learning method for determining optimized patient symptom-mitigation predictions includes receiving, from a user, profile information and user symptoms. The profile information and the user symptoms are matched to one of a plurality of profile clusters that are within one or more symptom-mitigation clusters created using textual data, the profile clusters being grouped within the one or more symptom-mitigation clusters based on profile information of authors of the textual data. A symptom-mitigation strategy is predicted based on the matching profile cluster. The method has applications including, but not limited to, use cases in medical AI / healthcare for optimization of predictions or to support decision-making.
G16H 50/20 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
G16H 50/70 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
G16H 50/80 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for detecting, monitoring or modelling epidemics or pandemics, e.g. flu
G16H 70/20 - ICT specially adapted for the handling or processing of medical references relating to practices or guidelines
G16H 70/40 - ICT specially adapted for the handling or processing of medical references relating to drugs, e.g. their side effects or intended usage
G16H 70/60 - ICT specially adapted for the handling or processing of medical references relating to pathologies
G16H 10/20 - ICT specially adapted for the handling or processing of patient-related medical or healthcare data for electronic clinical trials or questionnaires
G16H 10/60 - ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
G16H 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 15/00 - ICT specially adapted for medical reports, e.g. generation or transmission thereof
54.
CENTRALIZED ACCELERATION ABSTRACTION LAYER FOR RAN VIRTUALIZATION
A method of coordinating allocation of radio processing operations associated with multiple vRAN nodes to shared computing resources is provided. The method includes receiving, by a centralized Acceleration Abstraction Layer (AAL) broker implemented on top of a shared accelerating computing infrastructure, an operation request from a virtual operation associated with a vRAN node, the operation request specifying an operation to be accelerated. The AAL broker selects, using a predefined or configurable scheduling policy, a physical hardware accelerator for accelerated execution of the operation. The AAL broker forwards the operation request to a processing queue of the selected hardware accelerator.
A computer-implemented, machine learning method for cross-cohort predictions from medical data. Patients of one or more source cohorts are mapped to a feature space of a target cohort based on constraints. Patient distributions of the one or more source cohorts and the target cohort are learned. The patient distributions of the one or more source cohorts are corrected for the target cohort. The method has applications including, but not limited to medical AI, drug development, medical diagnostics/applications and in healthcare, for example, to optimize predictions or support decision making.
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
56.
METHOD TO GENERATE SAFE NATURAL LANGUAGE MEDICAL REPORTS FOR DISEASE CLASSIFICATION
The present invention provides a computer-implemented, machine learning method for generating safe text. A first portion of a trainable prompt is generated using negative influential features and positive influential features of a predicted condition. A second portion of the trainable prompt is trained to steer a pre-trained large language model (PLLM) to generate the safe text using at least the first portion of the trainable prompt. The method has applications including, but not limited to, use cases in medicine (e.g., digital medicine, personalized healthcare, AI-assisted drug or vaccine development, diagnosis or treatment, disease prediction, etc.), and cyber security.
A computer-implemented, machine learning method for spatiotemporal transfer learning. Sectors of an area are aggregated using preprocessed data from one or more data sources. The sectors are clustered based on different representations obtained for each context feature associated with each of the sectors. One or more context features that have a higher impact on a target feature to be predicted than other context features are identified from a plurality of context features and aggregated to obtain a representation of the area. Using the representation of the area, a particular sector within each of the clustered sectors is selected based on similarity to a respective centroid of the cluster to generate a set of particular sectors. A model associated with a source sector of the set of particular sectors is trained. The method has applications including, but not limited to smart cities, public safety and energy optimization.
A computer-implemented method mitigates side channel attacks in cache memory. The method includes: loading data into a cache line of the cache memory, which includes marking the data as sensitive in metadata of the cache line based on the data being tagged as sensitive; tracking interactions with the data; and determining whether the interactions with the data are not normal based on a preset criteria and the tracked interactions with the data.
G06F 21/55 - Detecting local intrusion or implementing counter-measures
G06F 21/54 - Monitoring users, programs or devices to maintain the integrity of platforms, e.g. of processors, firmware or operating systems during program execution, e.g. stack integrity, buffer overflow or preventing unwanted data erasure by adding security routines or objects to programs
59.
SIMULATED WHOLE EXOME SEQUENCING AND RNA SEQUENCING DATA FOR TUMOR CLONALITY
A computer-implemented, machine learning method for generating clone-specific tumor data includes obtaining a phased transcriptome file, a phased transcript file, and a clonal structure that represents a tumor clonal structure and comprises one or more nodes. For each node of the clonal structure: input mutational pools are determined for mutating the phase transcriptome file and the phased transcript file; DNA sequence reads are sampled from the phased transcript file and the sampled sequence DNA reads are mutated; RNA sequence reads are sampled from the phased transcriptome file and the sampled RNA sequence reads are mutated; a mutated genome is generated using the mutated DNA sequence reads; and a mutated transcriptome is generated using the mutated RNA sequence reads. The method has applications including, but not limited to, use cases in medical AI / healthcare for optimization of predictions or to support decision-making.
G16B 20/00 - ICT specially adapted for functional genomics or proteomics, e.g. genotype-phenotype associations
C12Q 1/6886 - Nucleic acid products used in the analysis of nucleic acids, e.g. primers or probes for diseases caused by alterations of genetic material for cancer
G16B 20/20 - Allele or variant detection, e.g. single nucleotide polymorphism [SNP] detection
G16B 30/00 - ICT specially adapted for sequence analysis involving nucleotides or amino acids
A method of providing radio context map information to a Multi-Access Edge Computing (MEC) application that is deployed at a MEC host and manages a 5G or Beyond 5G (B5G)-enabled network device is provided. The method includes registering and running a Radio Context Map Service (RCMS), on an MEC platform of the MEC host. The RCMS subscribes to location and radio information from existing MEC services of the MEC platform. The RCMS creates and updates a radio context map by processing location and radio information received from the subscribed MEC services and by combining the received location and radio information with additional application related context information provided through the MEC application or any other MEC application deployed at the MEC host. The RCMS provides the radio context map to the MEC application.
H04W 4/029 - Location-based management or tracking services
H04L 67/12 - Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
H04L 67/567 - Integrating service provisioning from a plurality of service providers
61.
DYNAMIC EMBEDDING-BASED MACHINE LEARNING TRAINING MECHANISM FOR EFFICIENT AND AGILE INTEGRATION OF NEW INFORMATION
A computer-implemented, machine learning method for a dynamic embedding-based machine learning training mechanism includes training, using an initial optimizer, an embedding-based neural network model based on a dataset to generate an initial computational graph having trainable variables. Based on receiving a new dataset: a new computational graph is generated, instantiated with new embedding dimensions migrated from the initial computational graph; a new optimizer is generated based on a weight matrix that fits to the trainable variables of the new computational graph; and weights of the trainable variables from the initial optimizer are migrated to the new optimizer. The embedding-based neural network model is trained with the new dataset by updating embeddings and learning new embeddings of the new dataset. The present invention can be used in a variety of applications including, but not limited to, several anticipated use cases in drug development, public safety, and medical/healthcare.
A computer-implemented method for artificial intelligence (AI) based risk/value assessment of a geographic area includes performing feature engineering to contextually enrich collected data. Three datasets are generated from the contextually enriched data, where a first dataset is generated by combining positive samples of the contextually enriched collected data with hard negative samples of the contextually enriched data, a second dataset is generated by combining the positive samples with soft negative samples of the contextually enriched data, and a third dataset is generated by combining the positive samples, hard negative samples, and soft negative samples. A machine learning model is trained to generate three different types of predictions for the risk/value assessment of the geographic area based on the three generated datasets.
A computer-implemented, artificial intelligence (Al) method for integrating fact-checked synthetic datasets with existing data to support Al-based decision making includes generating synthetic data using an automated few-shot prompting mechanism with a generative Al model. The automated few-shot prompting mechanism comprises: feeding the model with a data schema of an existing database containing the existing data, feeding the model with a query language description with an instruction to generate a query for a missing feature from a database containing ground truth information, executing the generated query to obtain the ground truth information for training the model, and prompting the trained model to generate the synthetic data. The generated synthetic data is integrated with the existing data. The present invention can be used in a variety of applications including, but not limited to, several anticipated use cases in public safety, crime investigation and disaster risk management and medical/healthcare.
A computer-implemented, machine learning method for incorporating a new entity in a knowledge graph for optimizing or improving a target property includes detecting counterfactual causes in a causality graph that are to be modified to achieve the target property. The causality graph is connected to the knowledge graph by links representing semantic relations. The new entity is generated in the knowledge graph by embedding the new entity in a latent space of the knowledge graph relative to existing entities. A change of causes in the causality graph resulting from generating the new entity in the knowledge graph is simulated. The method can be applied, for example, to use cases in medical/healthcare, smart cities or smart agriculture, for example, to support decision making using Artificial Intelligence (AI).
A computer-implemented method for training a machine learning—artificial intelligence model for multiple prediction tasks includes inputting data for tasks and additional data sources through a common trainable task representation function to obtain a data representation for each. Each resulting data representation is input through two individual trainable linear functions to obtain a corresponding prediction and adversarial prediction. A prediction error for the tasks, an adversarial error across edges of a graph, an auxiliary error for the additional data sources, and a graph error are determined. Parameters of the common trainable task representation function and the trainable linear functions are trained based on a comparison against a weighted sum of the errors. The present invention can be used in a variety of applications including, but not limited to, several anticipated use cases in drug development, material synthesis, and medical/healthcare.
A computer-implemented machine-learning method characterizes a tumor micro environment. The method includes: using a trained natural language processing machine learning model (NLP-model), extracting facts from biomedical text indicating relationship information between cell types and found gene names; using a reference database having gene names and aliases, grouping the extracted facts according to associated genes to generate extracted and grouped information; and generating a matrix from the extracted and grouped information with a first axis representing cell types and second axis representing genes. Each value of the matrix is calculated based on an importance of an associated gene taken and an associated weight. The associated weight is based associated publication meta information and/or an associated detection method's robustness and reliability. The method has applications including, but not limited to, use cases in drug development, medical artificial intelligence (AI)/healthcare for optimization of predictions or to support decision making.
G16B 5/00 - ICT specially adapted for modelling or simulations in systems biology, e.g. gene-regulatory networks, protein interaction networks or metabolic networks
G16B 25/10 - Gene or protein expression profilingExpression-ratio estimation or normalisation
G16H 50/50 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
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
The present disclosure relates to methods for determining a UE location within a cellular radio network. The UE (110) is associated with a base station, BS (112), of the network and the network includes at least one reconfigurable intelligent surface, RIS (114), wherein the RIS (114) has a RIS configuration set to serve the UE (110), the RIS configuration including a BS component and a UE component. In an embodiment, the method comprises obtaining, by a location estimation module (120) a current RIS configuration of the RIS (114); determining, by the location estimation module (120) the UE component of the current RIS configuration by using position information about the position of the BS (112) to compute and remove the BS component from the RIS configuration; and using, by the location estimation module (120) the UE component of the RIS configuration to infer an estimation of the location of the UE (110).
G01S 5/02 - Position-fixing by co-ordinating two or more direction or position-line determinationsPosition-fixing by co-ordinating two or more distance determinations using radio waves
H01Q 15/00 - Devices for reflection, refraction, diffraction or polarisation of waves radiated from an antenna, e.g. quasi-optical devices
A computer-implemented method for performing at least one computational operation on an encrypted input by at least one processor of a server in a client-server setting, where parameters of the computational operation are private to the server and the input is private to the client is provided. The method includes receiving, by the server, a ciphertext c of a leveled homomorphic encryption (LHE) scheme as encrypted input. Randomness is homomorphically added by the server to the ciphertext c and the resulting ciphertext b is transmitted to the client. The server receives a refreshed ciphertext b′ obtained by the client in a ciphertext refresh procedure including decrypting and re-encrypting the ciphertext b. The server homomorphically removes the previously added randomness from the received refreshed ciphertext b′ to obtain a refreshed ciphertext c′. The server performs the at least one computational operation on the refreshed ciphertext c′.
H04L 9/00 - Arrangements for secret or secure communicationsNetwork security protocols
H04L 9/06 - Arrangements for secret or secure communicationsNetwork security protocols the encryption apparatus using shift registers or memories for blockwise coding, e.g. D.E.S. systems
69.
SYSTEM AND METHOD FOR INDUCTIVE LEARNING ON GRAPHS WITH KNOWLEDGE FROM LANGUAGE MODELS
A computer-implemented method for inductive learning on graphs is provided. The graph includes a plurality of entities, where relationships exist between the plurality of entities, and where the plurality of entities and relationships have a name string. The method comprises creating for each entity of the plurality of entities of the graph a related text corpus, based on a respective name string of each entity. A pretrained language model is used to compute, from the related text corpus of each entity, a respective contextual entity embedding for each entity of the graph. A graph-based machine-learning (ML) model is trained, for each entity of the graph, the computed entity embeddings. These steps are repeated for unseen entities and the trained ML model is used to perform inductive predictions for the unseen entities.
A computer-implemented machine learning (ML) method is provided. The method includes computing a labeling matrix by applying a set of labeling functions (LFs) to data points of an unlabeled dataset. A projected labels matrix is generated by computing, based on the labeling matrix, LFs labels projections to undefined labels. An uncertainty of a respective label of the each labeled data point is estimated for each labeled data point based on an output of the LFs and the LFs labels projections. Data points are selected depending on the uncertainty estimated for the respective label of the each data point, and a labeling request for the selected data points is submitted to an oracle and updating the labeling matrix according to responses of the oracle.
A method for optimizing control flow in compiled computation graphs includes defining an intermediate representation (IR) of a computation graph, the computation graph IR including a main computation graph having at least one control flow primitive layer node pointing to one or more control flow sub-graph nodes. Fusable layer nodes of the main computation graph are identified and removed from the main computation graph, and the removed fusable layer nodes are duplicated into each of the one or more control flow sub-graph nodes. The method can be applied to machine learning frameworks, for example, for scientific computations such as in medical AI.
A computer-implemented method for accelerating the simulation of a molecular system is provided. The method includes learning a first set of parameters by executing a Hamiltonian Monte Carlo method on the molecular system based on a set of initial conditions. A simulation of the molecular system is executed based on the first set of parameters. Thermodynamics expectation values of the molecular system are predicted based on the executed simulation. The predicted thermodynamics expectation values are provided for a downstream machine learning task. The method has applications including, but not limited to, medical AI, drug development, medical diagnostics/applications, healthcare, material design catalyst design and high performance computing.
G16C 10/00 - Computational theoretical chemistry, i.e. ICT specially adapted for theoretical aspects of quantum chemistry, molecular mechanics, molecular dynamics or the like
73.
METHOD AND SYSTEM FOR TEMPORAL KNOWLEDGE GRAPH FORECASTING BASED ON PATTERN RECOGNITION
A predictive policing system includes a database of crime related scenarios in a number of past timesteps represented as temporal knowledge graphs (TKGs). Crime prediction devices generate relationship vectors that describe relations for each node of the TKGs for each available timestep. A dataset is created including vector sequences sets for each node of the TKGs, which are used as sequential inputs for training a pattern model to predict future relations for each node of the TKGs. A forecasting model is trained to predict nodes of the TKGs associated with each of the predicted future relations. Predicted future TKGs are assembled describing a crime scenario in an area of interest per future time steps of interest. A forecasting-based action recommendation system computes actions to steer the predicted scenario towards a desired scenario. Monitoring and/or surveillance devices deployed in the area of interest are adapted based on the computed actions.
The present application discloses a reflective device comprising an array of reflective elements (14) under control of a control element (20). Each reflective element (14) includes an antenna element (16) configured to receive a radio- frequency, RF, signal incident on the reflective element (14). Further, each reflective element (14) is configured to be operable in a functional operating state, in which an RF signal received by the antenna element (16) of the reflective element (14) is, at least partly, provided to be retransmitted by the antenna element (16) of the reflective element (14), and in a diagnostic operating state, in which an RF signal received by the antenna element (16) of the reflective element (14) is, at least partly, provided as an RF signal usable for analysis purposes. Furthermore, the present application discloses a method for operating such reflective device.
H01Q 3/26 - Arrangements for changing or varying the orientation or the shape of the directional pattern of the waves radiated from an antenna or antenna system varying the relative phase or relative amplitude of energisation between two or more active radiating elementsArrangements for changing or varying the orientation or the shape of the directional pattern of the waves radiated from an antenna or antenna system varying the distribution of energy across a radiating aperture
H04B 7/04 - Diversity systemsMulti-antenna systems, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
A computer-implemented method operates a large language model (LLM) in a secure and privacy preserving manner. The method includes: identifying an entity in a query, the query being configured to be processed by the LLM; generating a modified query by substituting the identified entity with a semantically similar entity; and submitting the modified query to the LLM. The present invention can be used in a variety of applications including, but not limited to, several anticipated use cases in customer service, cybersecurity, finance, and medical and healthcare.
An allocation system includes a memory storing instructions, and a processor. The processor is configured to access the memory and execute the instructions to: obtain data that includes profiles of doctors and clinical initial information of a patient that arrives at a hospital; preprocess the obtained data, wherein preprocessing includes a text preprocessing pipeline and word embedding; allocate a doctor to the patient that arrives at the hospital by using a neural network, wherein the neural network is machine-learned by using graph data of clinical narratives composed by doctors about patients, historical profiles of the patients and the profiles of doctors; and output information indicating the allocated doctor.
A method for training a machine-learning model for use in a Radio Access Network (RAN) controller of a wireless communication network comprises providing, by the RAN controller, a request for training a machine-learning model to a brokering entity. The method comprises triggering, by the brokering entity, an assignment of computational resources of a shared hardware accelerator device being separate from the RAN controller for a training application to be used for training the machine-learning model. The method comprises training, by the training application and using the assigned computational resources, the machine-learning model. The method comprises providing the trained machine-learning model to the RAN controller.
A computer-implemented method for extracting and mapping structured information to a data model includes obtaining text data from one or more unstructured data sources. Rephrased text data is determined using a Large Language Model (LLM), a preprocessing prompt, and the text data. Extracted data is determined using the LLM, an extraction prompt, the data model, and the rephrased text data. The extracted data is mapped to the data model. The method can be applied, for example, to medical use cases or cyberthreat detection, among others, to improve the data models and support decision making.
The present invention relates to a coronavirus vaccine composition, comprising one or more epitopes suitable for stimulating a broad adaptive immune response across a plurality of human leukocyte antigen (HLA) populations, for either MHC Class I and/or MHC Class II immunogenicity. The selection of such epitopes is made possible by the generation of predictive data by an artificial intelligence (AI)-driven platform, through the analysis of large scale epitope mapping of the SARS-CoV-2 proteome and epitope scoring based upon predicted immunogenicity, followed by robust statistical analysis and Monte Carlo-based simulation. The vaccine compositions of the present invention are suitable for use in the therapeutic or prophylactic treatment of SARS-CoV-2 infections. The invention also describes methods for using said compositions.
A method for secure aggregation, by a server, of client-provided inputs includes receiving, from each of a plurality of clients, a respective client input, for which a commitment is published. The commitments were computed using randomness and are aggregated by at least two super-clients and a sum of the aggregated commitments is published by each super-client. A sum of the received client inputs is published such that validity of the sum is checkable, by the clients, by comparing the sum of the received client inputs to a verification algorithm result that uses a sum of additive shares computed by the clients using the randomness, and by verifying that the published sum of the aggregated commitments is the same for each super-client. The method can be applied to use cases, for example, in digital medicine using medical data or smartcity applications to support decision-making.
H04L 9/00 - Arrangements for secret or secure communicationsNetwork security protocols
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
A computer-implemented method for generation of a machine learning model using weak supervision includes generating a labeling matrix of labeling function outputs by applying labeling functions to data features, and preassembling the labeling function outputs together with the data features for each data point to generate a training dataset. The machine learning model is trained using the training dataset. The invention can be applied to a number of use cases including, but not limited to use cases in digital medicine and automated or personalized healthcare, AI-assisted drug development (AIDD) or vaccine development, material or composition development, smart factories, smart industry, smart districts, market segmentation, recommender systems, predictive maintenance and energy control.
A COMPUTER-IMPLEMENTED METHOD AND SYSTEM FOR OPERATING AT LEAST ONE APPLICATION IN A TRUSTED COMPUTING ENABLED PLATFORM AND A CORRESPONDING APPLICATION
For providing an efficient operation of at least one application by simple means a computer-implemented method for operating at least one application in a trusted computing enabled platform is provided, wherein the platform comprises a trusted environment and an un-trusted environment, wherein the at least one application comprises multiple micro-services, and wherein at least one of the multiple micro- services is designed as a flexible micro-service, which can be deployed either in the trusted environment or in the un-trusted environment, comprising the steps: deciding on a deployment of the flexible micro-service in the trusted environment or in the un-trusted environment depending on at least one parameter of a requested security level of the at least one application and/or of a requested performance level of the at least one application and/or of a present or available platform characteristic or feature; and deploying the flexible micro-service in the trusted environment or in the un-trusted environment according to a result of the deciding step. Further, a corresponding system and a corresponding application are provided.
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
83.
CONSTRUCTION OF NEAREST NEIGHBOR STRUCTURES FOR GRAPH MACHINE LEARNING TECHNOLOGIES
A method for construction of nearest neighbor structures includes determining a set of cross-class neighborhood similarities based on a set of distributions of data obtained by applying a model to data present in a dataset. The method selects a first cross-class neighborhood similarity from the set of cross-class neighborhood similarities based on one or more inter-class cross-class neighborhood similarities and one or more intra-class cross-class neighborhood similarities, and builds a nearest neighbor graph based on the first cross-class neighborhood similarity. The present invention can be used in a variety of applications including, but not limited to, several anticipated use cases in drug development, material synthesis, and medical/healthcare.
G16H 50/20 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
G16H 20/10 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
84.
MITIGATION OF THE NOISY NEIGHBOR PROBLEM IN VRAN DEPLOYMENTS
A computer-implemented method configures virtual base stations in a network having an edge server and a platform server. The edge server and the platform server host the virtual base stations. Each respective virtual base station of the virtual base stations has a respective central unit and a respective distributed unit. The method includes: for each of the virtual base stations, jointly determining a respective distributed unit computing configuration and functional split and a respective central unit placement configuration to minimize a noisy neighbor problem based on a set of metrics collected from the virtual base stations.
The present invention relates to a computer-implemented method for execution of a cryptographic sortition among a group of parties (210, 220). According to an embodiment of the invention, the method comprises committing, by a first party (210) of the group, to a set of n party-specific secret keys k1, . . . , kn for a block cipher E; obtaining, by the first party (210) and at least a second party (220) of the group, a common input x and an index r; encrypting, by the first party (210), the input x with the r-th key kr of the committed keys k1, . . . , kn, thereby generating an output y1 of the block-cipher E, and publishing the output y1 together with the key kr used for encryption; and encrypting, by the second party (220), the common input x with the key kr published by the first party (210), thereby generating an output y1′ of the block-cipher E, and comparing the generated output y1′ with the output y1 published by the first party (210).
A computer-implemented method for predicting pathogen evolution includes computing a mutation trajectory of an input sample of a pathogen to be simulated by iteratively determining an update to a vector of changes based on a gradient that is computed with respect to the input sample using a loss associated with a prediction output of a trained differentiable surrogate model. Then, the method includes reconstructing changes to the input sample based on the iterative updates to obtain a predicted pathway of the pathogen evolution. The present invention can be used in a variety of applications including, but not limited to, several anticipated use cases in medical diagnostics/applications and in healthcare.
G16H 50/80 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for detecting, monitoring or modelling epidemics or pandemics, e.g. flu
G16B 10/00 - ICT specially adapted for evolutionary bioinformatics, e.g. phylogenetic tree construction or analysis
G16B 20/40 - Population geneticsLinkage disequilibrium
A computer-implemented method for generating task-relevant knowledge graphs from natural language text data includes performing triple distillation to generate a first distilled knowledge graph (KG) based on a first set of raw text and a first set of extractions. Performing triple distillation includes iteratively performing the following steps until a stop criteria is satisfied: mask the first set of raw text according to the first set of extractions to generate masked text, score the masked text to generate masked-text scores; score the first set of raw text to generate raw-text scores, compute importance scores for the first set of extractions based on the raw-text scores and the masked-text scores, select a subset of the first set of extractions, and based on determining that the stop criteria is satisfied, outputting the first set of extractions as the set of extractions for the first distilled KG. The present invention can be used in a variety of applications including, but not limited to, several anticipated use cases in drug development, material synthesis, inventory of items, detection of suspects from textual messages, and medical/healthcare.
A computer-implemented method for using a federated learning scheme within an Open Radio Access Network, O-RAN, is provided. The method comprising the following steps: providing an O-RAN; deploying a federated learning manager, FLM, in an O-RAN Non-Real-Time RAN Intelligent Controller, Non-RT RIC; coordinating by the FLM an involvement of the Non-RT RIC and an O-RAN Near-Real-Time RAN Intelligent Controller, Near-RT RIC, in at least one federated learning scheme; and executing the at least one federated learning scheme. Further, a corresponding system is provided.
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
89.
METHOD FOR OPERATING A VIRTUALIZED RADIO ACCESS NETWORK, VRAN, AND CONTROL SYSTEM IN A VRAN
The disclosure relates to a method of operating a virtualized radio access network, vRAN, wherein a radio cell (302) of the vRAN comprises one or multiple virtualized base stations, vBSs (304), serving a number of users (314) located within the coverage area of the radio cell (302), and at least one reconfigurable intelligent surface, RIS (316), and wherein the vBSs (304) include radio units, RUs (306), and distributed units, DUs (308), wherein each RU (306) is associated with at least on DU (308) and wherein the DUs (308) are deployed in an edge computing device (310) sharing the device's (310) available computing resources (311). According to embodiments, the method comprises using a controlling device (410) to determine configuration parameters of the at least one RIS (316) in terms of gain and/or phase of the reflective elements (317) of the RIS (316) that minimize the computing overhead of the DUs (308) deployed in the edge computing device (310).
H04W 24/02 - Arrangements for optimising operational condition
H04B 7/04 - Diversity systemsMulti-antenna systems, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
A method of operating a virtualized radio access point (vRAP) is provided. Transport blocks (TBs) are encoded/decoded by using iterative codes that exchange extrinsic information in each iteration. The exchanged extrinsic information is exploited to infer information about decodability of the data of the TBs.
H03M 13/00 - Coding, decoding or code conversion, for error detection or error correctionCoding theory basic assumptionsCoding boundsError probability evaluation methodsChannel modelsSimulation or testing of codes
H03M 13/11 - Error detection or forward error correction by redundancy in data representation, i.e. code words containing more digits than the source words using block codes, i.e. a predetermined number of check bits joined to a predetermined number of information bits using multiple parity bits
H03M 13/29 - Coding, decoding or code conversion, for error detection or error correctionCoding theory basic assumptionsCoding boundsError probability evaluation methodsChannel modelsSimulation or testing of codes combining two or more codes or code structures, e.g. product codes, generalised product codes, concatenated codes, inner and outer codes
H03M 13/35 - Unequal or adaptive error protection, e.g. by providing a different level of protection according to significance of source information or by adapting the coding according to the change of transmission channel characteristics
91.
GRAPH-BASED MULTIVARIATE TIME-SERIES FORECASTING FOR MULTI-SEASONALITY WITH META-LEARNING
A method for graph-based multivariate time-series forecasting with meta-learning that forecasts time-series with different properties includes meta-learning to select one or more forecasting models to use for one or more individual time-series based on a graph structure associated with the one or more individual time-series. The method further includes training a graph-neural network to determine node embeddings that act as exogenous variables for the one or more selected forecasting models.
A method for optimizing knowledge graph embeddings includes receiving textual data from an agent and generating a semantically clear knowledge graph based on resolving ambiguities within triples associated with the textual data. A prediction output is generated based on determining semantic-aware knowledge graph embeddings from the semantically clear knowledge graph. The prediction output is provided to the agent.
The invention provides a reflective device (10) as well as a method of operating a reflective device (10) comprising an array of reflective elements (14), each reflective element (14) being under control of a control element (28). According to an embodiment, the method comprises dividing, for each of the reflective elements (14), an incident RF signal into at least a first portion and at least a second portion; providing the first portion of the RF signal as reflection signal of the respective reflective element (14); and selectively setting either a first operational state, in which the second portion of the RF signal is provided as probing signal for performing an analysis of the incident RF signal, or a second operational state, in which the second portion of the RF signal is fed into an energy harvester (42) configured to collect the RF-energy of the RF signal.
H04B 7/04 - Diversity systemsMulti-antenna systems, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
94.
AUTOMATED DATA SHARING AND ANALYTICS USING A PRIVACY-PRESERVING DATA SPACE PLATFORM
A computer-implemented method for performing automated sharing of data and analytics across a data space platform includes receiving a request for a data analytics service from a first data stakeholder and providing an initial analysis to the first data stakeholder based on determining a portion of semantic data of the data space platform that is accessible to the first data stakeholder. The initial analysis is updated based on comparing the portion of semantic data with another portion of semantic data of the data space platform that is accessible to a second data stakeholder. The updated analysis is provided to the first data stakeholder. The method can be applied to machine learning and regression problems (continuous values) including, but not limited to, providing improvements to various technical fields such as medical diagnosis and treatment, operation system design and optimization, material design and optimization, telecommunication network design and optimization.
A computer-implemented method for combining different logical data models in a knowledge graph database and using the knowledge graph database for a machine learning prediction task includes building the knowledge graph database comprising sub-graphs each describing a different dimension of data. Node embeddings are learned for each of the different dimensions to obtain an artificial intelligence (AI) model comprising layers, wherein each layer is responsible for one of the different dimensions. One or more potential worlds or states represented by the sub-graphs are computed by performing link and/or node prediction in the knowledge graph database using the AI model.
A method for generating attention based video description using eye-tracking includes obtaining, using an eye-tracker device, raw gaze data associated with a user watching at least a portion of video data comprising a plurality of frames. The method further includes identifying attention objects and extracting one or more frames from the plurality of frames. The method also includes generating one or more individual textual reports for each of the identified attention objects based on the one or more extracted frames and outputting the one or more second individual textual reports that describe the video data in context of each of the identified attention objects. In some embodiments, the one or more individual textual reports are generated based on optimizing generated descriptions for the one or more individual textual reports by utilizing a name entity recognition model and a deep learning-based image semantic segmentation model.
A computer-implemented method anonymously verifies credentials while performing a membership test in a privacy-preserving manner. The method includes: executing a first committed-input-and-key-shares distributed oblivious pseudorandom function (DOPRF) protocol to obtain a set of first pseudorandom function (PRF) results, each result corresponding to one of a plurality of elements in a checklist held by a list holder; executing a second committed-input-and-key-shares DOPRF protocol to obtain a second PRF result corresponding to an identity of a prover; and determining whether one of the elements in the checklist corresponds to the identity of the prover based upon the set of first PRF results and the second PRF result.
H04L 9/32 - Arrangements for secret or secure communicationsNetwork security protocols including means for verifying the identity or authority of a user of the system
A method for ontology matching between a source and a target filters out non-matching pairs of the source and the target, to generate a dataset of possible matches. In a first loop, based on prediction results and uncertainty from a set of labeling functions of a labeling function (LF) committee, a data point is selected from the dataset and an annotation label is obtained for the data point. Additionally, labeling functions of the LF committee are selected and weighted based on prediction results against the dataset provided with annotation labels, and a weight of each of the selected LFs is adjusted to produce the prediction results and uncertainty of yet unlabeled data points of the dataset based on the data points of the dataset having already annotated a label. A second learning loop is executed that creates tuned labeling functions and augments the LF committee with the tuned labeling functions.
A computer-implemented method for generating and/or adjusting a heuristic function for a machine learning prediction. A machine learning prediction task including a target entity and attribute is received. Semantic relations are explored to generate relevant entities and attributes related to the target entity and attribute. The heuristic function is generated and/or adjusted based on the relevant entities and attributes.
A computer-implemented method of generating a spatially-aware, multi-modal knowledge graph for a machine learning task includes generating or receiving a static knowledge graph using static data, and generating or receiving a dynamic knowledge graph using dynamic data. The dynamic knowledge graph includes an event layer and at least one of an object layer and/or a user layer. The static and dynamic knowledge graphs are data structures stored in computer memory. The static knowledge graph and the dynamic knowledge graph are fused to generate the spatially-aware, multi-modal knowledge graph by encoding one or more nodes of the event layer as geospatial coordinates.
patents
