1069 results about "Artificial neuronal network" patented technology

Aspects of this disclosure relate to digital compensators, such as digital predistortion systems. Digital predistortion systems disclosed herein use a neural Volterra approach. Such digital predistortion systems can include a feature processing path comprising a feature artificial neural network, an envelope processing path, multipliers configured to multiply respective output signals of the feature processing path and the envelope processing path, and a combiner configured to generate a combined output signal based on at least output signals of the multipliers. The combined output signal is a digitally predistorted version of an input signal.

An inspection method for a lithium secondary battery can improve the reliability, accuracy, and reproducibility of inspection results by advancing a learning of an artificial neural network according to one or more divided regions of one or more surfaces of the lithium secondary battery and one or more types of defects occurring in each region.

The invention provides a reservoir pressure salinity scheduling method based on a physical information neural network (PINN). The reservoir pressure salinity scheduling method comprises the following steps: Step 1, salinity prediction based on a physical information neural network (PINN) model; the method comprises the following steps: in a PINN model framework, embedding a physical law of salinity conservation into a multi-layer perceptron (MLP) artificial neural network for training so as to carry out salinity prediction; step 2, establishing an estuary water-salt model based on a three-dimensional ocean numerical FVCOM model; step 3, carrying out upstream reservoir salty water pressing and light water supplementing emergency scheduling based on salinity forecast; comprising the following steps: Step3.1, establishing a multi-objective function; and Step3.2, solving a scheduling model. According to the method, the salinity momentum conservation constraint can be considered, the salinity prediction accuracy under the influence of different upstream flows and downstream tidal ranges can be improved, and the emergency scheduling of the reservoir for the salt tide invasion of the estuary drinking water source can be carried out in combination with the scheduling model, so that the water supply safety is ensured.

The invention discloses a manufacturing defect-oriented multi-scale composite material mechanical property prediction method, and belongs to the technical field of composite material mechanical property analysis. The method comprises the following steps: based on a multi-scale representative volume element (RVE) theory, respectively constructing parameterized models containing pores and fiber dislocations in a microscopic scale and a mesoscale; the equivalent elastic parameters under each scale are calculated through a finite element numerical homogenization technology, and an agent model is constructed in combination with an artificial neural network, so that the calculation cost is remarkably reduced, and the high-efficiency cross-scale prediction of the rigidity and strength performance of the composite material is realized. The method overcomes the defect of defect modeling of a traditional model, has high precision and high efficiency, and is suitable for performance evaluation and optimization design of composite material structures in the fields of aerospace, rail transit and the like.

Methods, systems, and devices for wireless communications are described. A user equipment (UE) may receive a control signal configuring a low-density pattern for channel state information (CSI) reference signal (RS) reception for a set of multiple antenna ports. The low-density pattern may indicate a subset of the set of multiple antenna ports for the CSI-RS reception via one or more resource blocks (RBs). The UE may receive a set of multiple CSI-RSs that is based on the low-density pattern. In some cases, the UE, or some other training device, may train an artificial neural network to process the CSI-RSs according to the low-density pattern. The artificial neural network may be an example of a generalized neural network or a neural network specific to one or more low-density patterns. The UE may transmit a CSI report based on processing the CSI-RSs according to the low-density pattern.

A stacked processor-plus-memory device includes a processing die with an array of processing elements of an artificial neural network. Each processing element multiplies a first operand—e.g. a weight—by a second operand to produce a partial result to a subsequent processing element. To prepare for these computations, a sequencer loads the weights into the processing elements as a sequence of operands that step through the processing elements, each operand stored in the corresponding processing element. The operands can be sequenced directly from memory to the processing elements or can be stored first in cache. The processing elements include streaming logic that disregards interruptions in the stream of operands.

Robot calibration is crucial in multi-robot cooperative systems where the inaccuracy of robots can add up and cause large errors in the final trajectory of handled parts or process tools. In this work, a two-step calibration approach is proposed based on artificial neural networks (ANNs) and definition of compensated pose for a master-slave cooperative robot system. Measuring the pose of master and slave robots at different locations in their shared workspace is required to create pairs of joint angles and output pose errors as training data. The generated data is used to train two ANN models for compensating the master-slave relative error and the master robot errors. The master-slave relative error is corrected by introducing a compensated pose for the slave robot with respect to the master robot. A neural network is then trained to predict the error parameters of the compensated pose for the joint angles of both robots as the input. The master robot is then corrected individually using another ANN model to address the absolute accuracy of the cooperative system.Measurements and simulations have been performed on a dual-robot cooperative system before and after geometric calibration. The process of cross validation is carried out to find the best network architecture for the optimal performance in correcting the robots'errors. It has been shown that even after pre-existing model-based calibration of each robot, both the absolute accuracy of the master robot and the relative tracking accuracy can be further improved by the proposed implementation of ANN calibration.

Systems, methods and apparatus of vehicle control. For example, a vehicle includes: a multi-master serial bus (e.g., a controller area network (CAN) bus); electronic control units connected to the bus and configured to communicate with each other through the bus; a transceiver connected to the bus and configured to monitor communication traffic on the bus to generate inputs; and an artificial neural network configured to generate, based on the inputs, a classification of anomaly for the communication traffic on the bus. The vehicle is configured to apply a security measure in response to the classification of anomaly for the communication traffic on the bus.

Aspects of this disclosure relate to digital compensators, such as digital predistortion systems. Digital predistortion systems disclosed herein use a neural Volterra approach. Such digital predistortion systems can include a first processing path, an envelope processing path comprising an envelope artificial neural network, multipliers configured to multiply respective output signals of the first processing path and the envelope processing path, and a combiner configured to generate a combined output signal based on at least output signals of the multipliers. The combined output signal is a digitally predistorted version of the input signal.

There is described a computer-implemented method to monitor operational performance of a system based on sensor data associated with the operation of the system. Received sensor data is processed to provide a plurality of input signals for an Artificial Neural Network, ANN. This processing involves transforming the sensor data into a plurality of components that are characteristic of the operation of the system and normalised with respect to activity values within the ANN, each component having a corresponding component value, and for each component, determining a difference value between the normalised component value and a respective feedback value from the ANN and generating an input signal representative of the difference value. By monitoring activity associated with the ANN, anomalous activity indicative of a departure from normal operation of the system is detected.

The invention discloses an aluminum-based material rolling process optimization method based on a response surface method and machine learning, which comprises the following steps: collecting related data of an aluminum-based material rolling process, and establishing a rolling process database; determining key rolling process parameters influencing the performance of the aluminum-based material based on the database; a mathematical model used for describing the key rolling process parameters and the relation between the interaction of the key rolling process parameters and the aluminum-based material performance indexes is established, and prediction results of the aluminum-based material performance indexes under different key rolling process parameter combinations are calculated according to the mathematical model. Aluminum-based materials with performance indexes meeting preset requirements and key rolling process parameter combinations corresponding to the aluminum-based materials are predicted to serve as a preliminary optimization result data set; and constructing a back propagation artificial neural network model optimized by a genetic algorithm to predict aluminum-based material performance indexes corresponding to different key rolling process parameter combinations, and screening out an optimal key rolling process parameter combination and an aluminum-based material performance index corresponding to the optimal key rolling process parameter combination from the aluminum-based material performance indexes. According to the method, the quality of the aluminum-based material is remarkably improved through the proposed collaborative optimization strategy.

The invention discloses a rapid progression type nasopharyngeal carcinoma risk prediction method based on an artificial neural network, and relates to the field of medical informatics crossing. The invention provides a rapid progressive nasopharyngeal carcinoma risk prediction method based on an artificial neural network, and aims to solve the problem that a rapid progressive nasopharyngeal carcinoma patient is difficult to recognize in time by depending on TNM staging and experience judgment in the prior art. According to the method, historical case data collection, missing value filling and standardization preprocessing, core feature determination through feature screening, class imbalance correction, feature coding and feature matrix construction are sequentially carried out, an artificial neural network model is trained and optimized under a cross validation framework, and performance and threshold values are determined on a validation set. During clinical application, patient features are input, and the model outputs a rapid progress risk probability and a risk level. Compared with a conventional staging or linear model, the method can improve the prediction accuracy, and achieves the early recognition and individualized treatment of a high-risk patient.

There is provided a volume preserving trainable artificial neural network and a system and a method for building a volume preserving trainable artificial neural network. In an aspect, an artificial neural network including: an input layer to receive input data; one or more sequentially connected hidden layers, the first hidden layer connected to the input layer, to perform operations on the input data, each hidden layer including: one or more volume-preserving rotation sublayers; one or more volume-preserving permutation sublayers; one or more volume-preserving diagonal sublayers; and an activation sublayer; and a downsizing output layer connected to the activation sublayer of the last hidden layer. In some cases, the activation sublayer includes a grouped activation function acting on a grouping of input variables to the activation sublayer.

Bird's eye view (BEV) semantic mapping systems and methods are provided. A method includes receiving an image captured by a monocular camera having a first point of view (POV) of an environment including a plurality of features. The method further includes processing, by an artificial neural network (ANN), the captured image to generate a semantic map for the captured image, the semantic map associated with a second POV different from the first POV. The features exhibit a uniform scale in the semantic map. Additional methods and associated systems are also provided.

Koopman operator theory is a widely used method to analyze, control, and predict the behavior of the states of a non-linear dynamical system using measurement functions in Hilbert space. Real time approximation of the Koopman operator is crucial in order to adapt and understand behavior of underlying non-linear dynamical system. Traditional approaches leverage matrix-based methods or artificial neural networks to approximate Koopman operator. However, such methods necessitate significant power and computational resources, therefore may not be suitable for applications that require real-time on-board processing. The problems of the conventional approaches are resolved based on a recent development of brain inspired spiking neural networks and neuromorphic computing platforms, as these offer extremely low-energy computation and real-time responses. Embodiments of the present disclosure provide implementation of a Spiking Neural Network (SNN) based architecture that efficiently approximate Koopman operator with minimal length of data and demonstrates significant computational savings.

The invention relates to an automatic depression risk assessment method based on a natural language processing technology. The method comprises the following steps: performing selective conversation content interviews with a subject by using a voice conversation function of artificial intelligence; dialogue recording and text data between the patient and artificial intelligence are obtained; performing automatic transcription and speaker separation on the original speech transcription text data, and constructing a structured question and answer dialogue sequence; generating a structured question prompt related to the depressive symptom by using a large language model, and splicing the structured question prompt with the original dialogue content; designing an artificial neural network pre-training language model coding word vector, fusing position coding, a self-attention mechanism, a problem-guided attention mechanism and a bidirectional long short-term memory network, and extracting deep semantic features related to depression risks; finally, continuous depression risk scores are output, correlation verification is carried out on the continuous depression risk scores and standard PHQ-8 scores, and the accuracy, robustness and interpretability of depression risk assessment are effectively improved.

A system for real-time generation of therapeutic plans based on predictive analytics of patient profile data including a processor of a therapeutic plan server (TPS) node configured to host a machine learning (ML) module and connected to at least one patient-entity node over a network and a memory on which are stored machine-readable instructions that when executed by the processor, cause the processor to: receive the patient profile data including patient nutrients intake data and medications intake data from the at least one patient-entity node; parse the patient profile data to derive a plurality of key classifying features; query a local database to retrieve local historical patients-related data based on the plurality of key classifying features; generate at least one classifier feature vector based on the plurality of key classifying features and the local historical patients-related data; provide the at least one feature vector to the ML module coupled to an Artificial Neural Network (ANN); receive a plurality of nutrients-medications correlation parameters from a therapeutic plan predictive model generated by the ML module using outputs of the ANN based on the at least one feature vector; and generate a therapeutic plan for the at least one patient-entity node based on the nutrients-medications correlation parameters.

An air data indicating and calibrating arrangement and method for a vertical take-off and landing aircraft, in particular a helicopter, for providing information on an air speed of the vertical take-off and landing aircraft and for providing information on an altitude of the vertical take-off and landing aircraft are described. The vertical take-off and landing aircraft includes a pitot tube device for determining a stagnation air pressure at a position of the pitot tube device and a static port device for determining a static air pressure at a position of the static port device. The air data indicating arrangement includes an air speed and altitude determination module to determine in real-time the air speed and the altitude of the vertical take-off and landing aircraft from flight data by using a regressor obtained by training an artificial neural network with training data.

The present application relates to the technical field of sewage treatment, and particularly relates to a sewage treatment intelligent aeration control method based on a weighted fusion model. Inflow water quality monitoring data set, process water quality monitoring data set, effluent water quality monitoring data set, aeration quantity monitoring data set and equipment working condition monitoring data set are acquired. The inflow water quality monitoring data set, the process water quality monitoring data set, the effluent water quality monitoring data set and the aeration quantity monitoring data set are fused into a water quality aeration fusion data set, and the equipment working condition monitoring data set and the aeration quantity monitoring data set are fused into a working condition aeration fusion data set. The water quality aeration fusion data set is input into a deep artificial neural network sub-model with adjustable parameters, and the working condition aeration fusion data set is input into a long short-term memory neural network sub-model with adjustable parameters. The results of the two models are fused into a long short-term memory neural network fusion model with adjustable parameters, and are fused according to the weight coefficients after percentage error normalization.

A receiver of an optical communication system includes an organic photoelectric conversion device configured to convert optical signals received from a transmitter into an electrical signal; and a demodulator configured to input the electrical signal to a trained artificial neural network and demodulate the electrical signal based on an output of the trained artificial neural network.

The disclosed exemplary embodiments include computer-implemented systems, apparatuses, and processes that perform homomorphic computations on encrypted third-party data within a distributed computing environment. For example, an apparatus receives a homomorphic public key and encrypted transaction data characterizing an exchange of data from a computing system, and encrypts modelling data associated with a first predictive model, such as a machine learning model or an artificial neural network model, using the homomorphic public key. The apparatus may perform homomorphic computations that apply the first predictive model to the encrypted transaction data in accordance with the encrypted first modelling data, and transmit an encrypted first output of the homomorphic computations to the computing system, which may decrypt the encrypted first output using a homomorphic private key and generate decrypted output data indicative of a predicted likelihood that the data exchange represents fraudulent activity.

An apparatus is provided that includes a memory array including non-volatile memory cells configured to store weights of an artificial neural network, a bit line coupled to a plurality of the non-volatile memory cells, and an interface circuit coupled to the bit line, the interface circuit configured to amplify an output impedance of the memory array.

A processor-implemented method includes constructing a non-contiguous attention mask corresponding to selected key-value (KV) vectors non-contiguously stored in a KV cache buffer. The method also includes multiplying the non-contiguous attention mask with the KV cache buffer to obtain token-specific KV vectors. The method further includes generating a new KV vector, with an artificial neural network transformer model during a current inference iteration, based on an input token and the token-specific KV vectors. The method may also append the new KV vector into an input buffer of the KV cache buffer adjacent to right-side padding during a next inference iteration with the artificial neural network transformer model.

Simulation and validation of neural network systems is provided. In various embodiments, a description of an artificial neural network is read. A directed graph is constructed comprising a plurality of edges and a plurality of nodes, each of the plurality of edges corresponding to a queue and each of the plurality of nodes corresponding to a computing function of the neural network system. A graph state is updated over a plurality of time steps according to the description of the neural network, the graph state being defined by the contents of each of the plurality of queues. Each of a plurality of assertions is tested at each of the plurality of time steps, each of the plurality of assertions being a function of a subset of the graph state. Invalidity of the neural network system is indicated for each violation of one of the plurality of assertions.

Block decoding in an artificial neural network is provided. An encoded block comprising a plurality of encoded values, each encoded value comprising a mantissa, is read. The encoded block's scaling information, which includes an exponent and a mantissa, is read. Each of the plurality of encoded values is decoded according to the scaling information to produce a plurality of decoded values.

The invention discloses a drilling pump pressure prediction method based on an artificial neural network, and the method comprises the following steps: S1, data collection; s2, data preprocessing; s3, constructing a neural network model; s4, model training and optimization; and S5, model verification and deployment. According to the method, multi-channel data fusion and time synchronization optimization are innovatively adopted, so that the data quality and consistency are improved; in combination with a deep neural network and a self-adaptive optimization strategy, the precision and generalization ability of pump pressure prediction of the drilling pump are improved; and an online updating mechanism is introduced, so that the model can be dynamically optimized according to real-time data, the defects of low prediction precision, poor adaptability and difficulty in real-time updating of a traditional method are overcome, and an efficient and reliable prediction means is provided for intelligent drilling control.

In a method, for training an artificial neural network (ANN) to reduce noise and / or artefacts in an electron microscopy image, a plurality of training image pairs is generated. For each pair, an undistorted synthetic specimen image and a distorted image are created by simulating additional noise and / or artefact features. The ANN is trained, in which the distorted images are used as input and the corresponding undistorted images as output. An adversarial training strategy is used in which the ANN is trained, as a generator network, in conjunction with concomitantly training a further ANN, as a discriminator network, to differentiate output produced by the generator network from synthetic images in the training set. In training, parameters of the ANN and further ANN are optimized using a generator loss function and a discriminator loss function, in which a dependency exists between said loss functions to train the networks in an adversarial manner.

A method of quantifying pulmonary function using a medical image includes acquiring or receiving a medical image including anatomical information for a lung region of a patient; segmenting at least one abnormal finding region in the lung region of the medical image using an artificial neural network; and predicting a quantification result related to pulmonary function based on a size of the at least one abnormal finding region.

Systems, methods and apparatuses of Artificial Neural Network (ANN) applications implemented via Memory as a Service (MaaS) are described. For example, a computing system can include a computing device and a remote device. The computing device can borrow memory from the remote device over a wired or wireless network. Through the borrowed memory, the computing device and the remote device can collaborate with each other in storing an artificial neural network and in processing based on the artificial neural network. Some layers of the artificial neural network can be stored in the memory loaned by the remote device to the computing device. The remote device can perform the computation of the layers stored in the borrowed memory on behalf of the computing device. When the network connection degrades, the computing device can use an alternative module to function as a substitute of the layers stored in the borrowed memory.

To provide a balance function management system for balance function state information generation and a balance function rehabilitation program.SOLUTION: A memory configured to store at least one processor and at least one artificial neural network model that stores instructions executable by the processor and is executed on a computing device, wherein the at least one processor is configured to input frame images of n (where n is a natural number) videos obtained by photographing a subject through n cameras to the at least one artificial neural network model, At least one of information related to the coordinates of the head, the coordinates of the center of the pupil, and the phase change of the eyeball of the subject according to the order of the frame images of the m-th (m is a natural number from 1 to n) moving image may be acquired, and information related to the movement of the head and the movement of the eyeball for generating the balance state information or performing the balance rehabilitation program may be generated using the acquired information.SELECTED DRAWING: Figure 1