A computer-implemented method is provided for improving live video quality. The method comprises: acquiring, using a medical imaging apparatus, a stream of consecutive image frames of a subject, and the stream of consecutive image frames are acquired with reduced amount of radiation dose; applying a deep learning network model to the stream of consecutive image frames to generate an image frame with improved quality; and displaying the image frame with improved quality in real-time on a display.

Videos captured in low light conditions can be processed in order to identify an activity being performed in the video. The processing may use both the video and audio streams for identifying the activity in the low light video. The video portion is processed to generate a darkness-aware feature which may be used to modulate the features generated from the audio and video features. The audio features may be used to generate a video attention feature and the video features may be used to generate an audio attention feature. The audio and video attention features may also be used in modulating the audio video features. The modulated audio and video features may be used to predict an activity occurring in the video.

A method, system, and computer program product for visualizing a machine learning model are provided. A confusion matrix and model performance metric data are received from a classification model. For each data point in the confusion matrix, a corresponding pixel is generated. The pixels are grouped into clusters. Each cluster represents a label in the confusion matrix. A centroid is generated for each cluster. Using the model performance metric data, a misclassification indicator arrow is generated for each misclassified data point. The misclassification indicator arrow indicates both the predicted class and the actual class. The clusters, the centroids, and the misclassification indicator arrow are displayed as a graphical visualization of the machine learning model.

A data processing server may receive a set of data objects for frequent pattern (FP) analysis. The set of data objects may be analyzed using an attribute diversity technique. For the set of data attributes of the set of data objects, the server may arrange the attributes in one or more dimensions. The server may initialize a set of centroids on data points and identify mean values of nearby data points. Based on an iteration of the mean value calculation, the server may identify a set of attributes corresponding to final mean values as being groups of similarly frequent attributes. These groups of similarly frequent attributes may be analyzed using an FP analysis procedure to identify frequent patterns of data attributes.

An embodiment of a method 100 for predicting a future state of a biological system is provided. The method 100 comprises receiving 101a microscope image depicting the biological system at an associated time and receiving 102 metadata corresponding to the microscope image. The method 100 further comprises extracting 103 features from the microscope image having information on a state of the biological system and using 104 the features and the metadata to predict the future state of the biological system.

A client device configured with a neural network includes a processor, a memory, a user interface, a communications interface, a power supply and an input device, wherein the memory includes a trained neural network received from a server system that has trained and configured the neural network for the client device. A server system and a method of training a neural network are disclosed.

A method and system for predicting complex electric field images with a parameterized model are described. A latent space representation of a complex electric field image is determined based on dimensional data in a latent space of the parameterized model for a given input to the parameterized model. The given input may be a measured amplitude (e.g., intensity) associated with the complex electric field image. The complex electric field image is predicted based on the latent space representation of the complex electric field image. The predicted complex electric field image includes an amplitude and a phase. The parameterized model comprises encoder-decoder architecture. In some embodiments, determining the latent space representation of the electric field image comprises minimizing a function constrained by a set of electric field images that could be predicted by the parameterized model based on the dimensional data in the latent space and the given input.

A method of generating an image recognition model for recognising an input image and a system thereof are provided. The method includes appending at least one feature extraction layer to the image recognition model, extracting a plurality of feature vectors from a set of predetermined images, grouping the plurality of feature vectors into a plurality of categories, clustering the plurality of feature vectors of each of the plurality of categories into at least one cluster, determining at least one centroid for each of the at least one cluster, such that each of the at least one cluster comprises at least one centroid, such that each of the at least one centroid is represented by a feature vector, generating a classification layer based on the feature vector of the at least one centroid of the plurality of categories, and appending the classification layer to the image recognition model. In addition, a method of classifying an input image and a system thereof are provided.

Disclosed is multi-modal few-shot learning device for user identification using a walking pattern based on deep learning ensemble. The device includes: a walking data collector configured to collect walking data of a user from a smart insole including any one or more of a pressure sensor, an acceleration sensor, and a gyro sensor; a preprocessor configured to convert a series of time series walking data obtained from each of the sensors included in the smart insole into a unit format data set; and an ensemble learner configured to apply an ensemble learning model that provides one final prediction by training CNN series learning and RNN series learning respectively and independently based on the unit-format data set generated by the preprocessor.

A method for training a neural network for triggering an input signal in a measurement device is provided. The method comprises the steps of providing a trigger type and/or trigger parameter from a cloud server hosting the neural network via a network to the measurement device, triggering the input signal based on the trigger type and/or trigger parameter received in the measurement device, and collecting trigger feedback information from the measurement device at the neural network to train the neural network.