A rider state modification system for improving a state of a rider in a vehicle includes a first neural network that operates to classify a state of the vehicle through analysis of information about the vehicle captured by an Internet-of-things device during operation of the vehicle. The rider state modification system further includes a second neural network that operates to optimize at least one operating parameter of the vehicle based on the classified state of the vehicle, information about a state of a rider occupying the vehicle, and information that correlates vehicle operation with an effect on rider state.

The invention relates to a method for generating disturbed input data for a neural network for analyzing sensor data, in particular digital images, of a driver assistance system, in which a first metric is defined which indicates how the magnitude of a change in sensor data is measured, a second metric is defined which indicates where a disturbance of sensor data is directed, an optimization problem is generated from a combination of the first metric and second metric, the optimization problem is solved by means of at least one solution algorithm, wherein the solution indicates a target disturbance of the input data, and disturbed input data is generated from sensor data for the neural network by means of the target disturbance.

A method, a system, and a computer program product for detecting fake news based on a multi-task learning model. In an embodiment, a multi-task learning model is used to perform joint training on authenticity detection and topic classification of news to be detected, and authenticity of the news to be detected and a topic of the news to be detected are returned simultaneously. Through the implementation of the embodiment of the present invention, the authenticity of the news and the topic of the news can be detected simultaneously, and the accuracy of fake news detection and topic classification is improved.

Fusion of trained artificial intelligence (AI) neural networks to produce more accurate classifications is disclosed. Concatenation from each network being merged may be performed. The new set of features, which includes the concatenated layers, is then fed through a new classifier to form a single final classifier that uses the best parts of each input classifier.

A system for transportation includes a vehicle interface for gathering physiological sensed data of a rider in the vehicle. The system includes an artificial intelligence-based circuit that is trained on a set of outcomes related to rider in-vehicle experience and that induces, responsive to the sensed rider physiological data, variation in one or more of the user experience parameters to achieve at least one desired outcome in the set of outcomes. The inducing variation includes control of timing and extent of the variation.

A method including: for each image forming part of a plurality of images showing an individual, applying processing to the image so as to produce a biometric template relating to the individual; calculating an average template constituting an average of the biometric templates produced; modifying a chosen image from the plurality of images into a modified image, the modification being adapted so that an error between the average template and a biometric template produced by applying the processing to the modified image is smaller than an error between the average template and the biometric template that has been produced by applying the processing to the chosen image.

A method for surveying an environment includes segmenting a plurality of nodes into a plurality of communities. The method includes identifying a plurality of community centroids based on the plurality of communities, where each community centroid from among the plurality of community centroids is associated with one community from among the plurality of communities. The method includes determining, for each community centroid from among the plurality of community centroids, a community type of the community centroid, where the community type is one of a primary type and an auxiliary type, and where the community type is based on a distance between the community centroid and one or more charging stations. The method includes generating a plurality of intercommunity routes based on the plurality of community centroids, the one or more charging stations, the community type, and one or more performance constraints.

A method for identifying, locating, and mapping targets of interest using unmanned aerial vehicle (UAV) camera footage in GPS-denied environments. In one embodiment, the method comprises obtaining UAV visual data, passing the UAV visual data through a convolutional neural network (CNN) in order to detect targets of interest based on visual features disposed in the UAV visual data, wherein the detection by the CNN defines reference points and pixel coordinates for the UAV visual data, applying a geometric transformation to known and defined pixel coordinates to obtain real-world orthogonal positions; and projecting the detected targets of interest onto an orthogonal map based on the obtained real-world orthogonal positions, all without GPS data.

Systems and methods are disclosed for performing event timing detection for DNA sequencing. In certain embodiments, a method may comprise generating a signal based on a DNA strand passed through a nanopore sensor, sampling the signal to generate a plurality of sample values, and detecting one or more event boundaries based on the sample values, an event representing a movement of a single DNA base of the DNA strand through the nanopore sensor. Detecting the one or more event boundaries may include segmenting the plurality of sample values into multiple events to calculate an optimal total score, assigning an event value to a selected event from the multiple events based on sample values of the selected event, and providing the event value to a base caller to determine a sequence of DNA bases.

Described herein are embodiments of a unified neural network framework to integrate Topic modeling, Word embedding and Entity Embedding (TWEE) for representation learning of inputs. In one or more embodiments, a novel topic sparse autoencoder is introduced to incorporate discriminative topics into the representation learning of the input. Topic distributions of inputs are generated from a global viewpoint and are utilized to enable autoencoder to learn topical representations. A sparsity constraint may be added to ensure that the most discriminative representations are related to topics. In addition, both words and entity related information may be embedded into the network to help learn a more comprehensive input representation. Extensive empirical experiments show that embodiments of the TWEE framework outperform the state-of-the-art methods on different datasets.