The present invention provides a method, system and storage medium for load dispatch optimization for residential microgrid. The method includes collecting environmental data and time data of residential microgrid in preset future time period; obtaining power load data of residential microgrid in future time period by inputting environmental data and time data into pre-trained load forecasting model; obtaining photovoltaic output power data of residential microgrid in future time period by inputting environmental data and time data into pre-trained photovoltaic output power forecasting model; determining objective function and corresponding constraint condition of residential microgrid in future time period, where optimization objective of objective function is to minimize total cost of residential microgrid; obtaining load dispatch scheme of residential microgrid in future time period by solving objective function with particle swarm algorithm. The invention can provide load dispatch scheme suitable for current microgrid and reduce operating cost of residential microgrid.

Two major treatment strategies employed in fighting non-small cell lung cancer (NSCLC) are tyrosine kinase inhibitors (TKIs) and immune checkpoint inhibitors (ICIs). The choice of strategy is based on heterogeneous biomarkers expressed by the lung tumor tissue. A major challenge for molecular testing of these biomarkers is the insufficiency of biopsy specimens from patients with advanced NSCLC. Disclosed herein is a method for predicting a response to immune-checkpoint blockade immunotherapy. The method generally involves imaging the subject with positron emission tomography with 2-deoxy-2-[fluorine-18] fluoro-D-glucose integrated with computed tomography to produce .sup.18F-FDG PET/CT images of the tumor, analyzing the images using PET, CT, and Kulbek Leibler Divergence statistical (KLD) features or, alternatively using deep leaning such as Neural Networks; generating a radiomic signature from the identified features or Network characteristics; and computing a radiomic score based on the radiomic signature that is predictive of responsiveness to ICIs or TKIs.

A model compression device includes a compression unit and a determination unit. The compression unit is configured to create a compression model arrived at by compressing a first prediction model created by machine learning. The determination unit is configured to determine whether or not a second prediction model created by re-learning the compression model can be further compressed on the basis of an index related to the performance of the second prediction model.

A method is disclosed for reducing computation of a differentiable architecture search. An output node is formed having a channel dimension that is one-fourth of a channel dimension of a normal cell of a neural network architecture by averaging channel outputs of intermediate nodes of the normal cell. The output node is preprocessed using a 1×1 convolution to form channels of input nodes for a next layer of the cells in the neural network architecture. Forming the output node includes forming s groups of channel outputs of the intermediate nodes by dividing the channel outputs of the intermediate nodes by a splitting parameter s. An average channel output for each group of channel outputs is formed, and the output node is formed by concatenating the average channel output for each group of channels with channel outputs of the intermediate nodes of the normal cell.

A system includes inputs, outputs, and nodes between the inputs and the outputs. The nodes include hidden nodes. Connections between the nodes are determined based on a gradient computable using symmetric solution submatrices.

Embodiments of the present disclosure relate to a method, a device, and a computer program product for user behavior prediction. In some embodiments, at a client, a first user behavior embedding engine in the client generates behavior prediction information of a target user based on feature information of the target user. The client sends the behavior prediction information of the target user to a server, and receives information about a target item recommended for the target user from the server. Such method enables user privacy-related information to be processed only locally, thereby not only ensuring user privacy and security, but also significantly reducing overall resource overhead.

A method for providing a neural network system includes performing contrastive learning to the neural network system to generate a trained neural network system. The performing the contrastive learning includes performing first model augmentation to a first encoder of the neural network system to generate a first embedding of a sample, performing second model augmentation to the first encoder to generate a second embedding of the sample, and optimizing the first encoder using a contrastive loss based on the first embedding and the second embedding. The trained neural network system is provided to perform a task.

A method is provided for generating a visualization for explaining a behavior of a machine learning (ML) model. In the method, an image is input to the ML model for an inference operation. The input image has an increased resolution compared to an image resolution the ML model was intended to receive as an input. A resolution of a plurality of resolution-independent convolutional layers of the neural network are adjusted because of the increased resolution of the input image. A resolution-independent convolutional layer of the neural network is selected. The selected resolution-independent convolutional layer is used to generate a plurality of activation maps. The plurality of activation maps is used in a visualization method to show what features of the image were important for the ML model to derive an inference conclusion. The method may be implemented in a computer program having instructions executable by a processor.

A computing device for training an artificial neural network model includes: a model analyzer configured to receive a first artificial neural network model and split the first artificial neural network model into a plurality of layers; a training logic configured to calculate first sensitivity data varying as the first artificial neural network model is pruned, calculate a target sensitivity corresponding to a target pruning rate based on the first sensitivity data, calculate second sensitivity data varying as each of the plurality of layers is pruned, and output, based on the second sensitivity data, an optimal pruning rate of each of the plurality of layers, the optimal pruning rate corresponding to the target pruning rate; and a model updater configured to prune the first artificial neural network model based on the optimal pruning rate to obtain a second artificial neural network model, and output the second artificial neural network model.

A system monitors an individual for conditions indicating a possibility of occurrence of irregular heart events. A database includes a plurality of combinations of at least a first signature and a second signature. A first portion of the plurality of combinations is associated with a normal heartbeat and a second portion of the plurality of combinations is associated with an irregular heart event. A wearable heart monitor that is worn on a body of the patient includes a heart sensor for generating a heart signal responsive to monitoring a beating of a heart of the individual. The monitor further includes a processor for receiving the heart signal from the heart sensor. The processor is configured to analyze the heart signal using a plurality of different processes. Each of the plurality of different processes generates at least one of the first signature and the second signature. The plurality of different processes provide a unique combination including at least the first signature and the second signature for the generated heart signal. The processor compares the unique combination with the plurality of combinations in the database, locates a combination of the plurality of combinations that substantially matches the unique combination and generates a first indication if the unique combination substantially matches one of the first portion of the plurality of combinations and a second indication if the unique combination substantially matches one of the second portion of the plurality of combinations.