Abstract: A vehicle, system and a method of predicting a thermal runaway event in a battery pack. The vehicle includes a battery pack having a plurality of battery cells. The system includes a sensor and a processor. The measures a parameter of a battery cell of a battery pack of the vehicle. The processor is configured to determine a charging response of the battery cell from the parameter, determine a likelihood of the thermal runaway event from the charging response, and control an operation of the vehicle to prevent the thermal runaway event based on the likelihood.

Abstract: Systems and methods are disclosed that relate to testing processing elements of an integrated processing system. A first system test may be performed on a first processing element of an integrated processing system. The first system test may be based at least on accessing a test node associated with the first processing element. The first system test may be accessed using a first local test controller. A second system test may be performed on a second processing element of the integrated processing system. The second system test may be based at least on accessing a second test node associated with the second processing element. The second system test may be accessed using a second local test controller.

Abstract: A method for trajectory generation based on player tracking is described herein. The method includes determining a temporal association for a first player in a captured field of view and determining a spatial association for the first player. The method also includes deriving a global player identification based on the temporal association and the spatial association and generating a trajectory based on the global player identification.

Abstract: An intelligent analysis system applied to ethology of various kinds of high-density minimal polypides is provided, including an operating platform subsystem and an analysis subsystem; the operating platform subsystem is used for providing an activity medium capable of obtaining behaviors of the minimal polypides and shooting the behaviors of the minimal polypides; the behavior collecting module in the analysis subsystem is used for obtaining an ethology video of the high-density minimal polypides through the operating platform subsystem; the analysis modeling module is used for obtaining ethology big data of various kinds of high-density minimal insects according to the ethology video, and establishing an ethology model; the simulation predicting module is used for dynamically predicting comprehensive control strategies and control effects of minimal pests in a field ecosystem according to the ethology model; the visual demonstrating module is used for displaying the above behavior data.

Abstract: A vehicle operates a system and method of predicting a thermal runaway event in a battery pack of the vehicle. The battery pack includes a battery cell. The sensor obtains measurements of a parameter of the battery cell at a plurality of times. The processor is configured to determine a value of at least one feature of the battery cell from the measurements of the parameter, determine a likelihood of the thermal runaway event from the value of the at least one feature, and take an action to prevent the thermal runaway event from occurring based on the likelihood.

Abstract: A decoding method, a memory storage device and a memory control circuit unit are disclosed. The method includes: activating a decoding circuit which supports a plurality of decoding modes each corresponding to a threshold value, wherein a distribution of the threshold value corresponds to error correction abilities of the decoding modes; reading first data from a rewritable non-volatile memory module; performing, by the decoding circuit, a first decoding operation on the first data; obtaining a decoding parameter according to an execution result of the first decoding operation; and performing, by the decoding circuit, a second decoding operation on the first data based on a first decoding mode among the decoding modes according to a relative numerical relationship between the decoding parameter and the threshold value.

Abstract: A decoding method, a memory storage device and a memory control circuit unit are disclosed. The method includes: activating a decoding circuit which supports a plurality of decoding modes each corresponding to a threshold value, wherein a distribution of the threshold value corresponds to error correction abilities of the decoding modes; reading first data from a rewritable non-volatile memory module; performing, by the decoding circuit, a first decoding operation on the first data; obtaining a decoding parameter according to an execution result of the first decoding operation; and performing, by the decoding circuit, a second decoding operation on the first data based on a first decoding mode among the decoding modes according to a relative numerical relationship between the decoding parameter and the threshold value.

Abstract: A mechanism is described for facilitating real-time multi-view detection of objects in multi-camera environments, according to one embodiment. A method of embodiments, as described herein, includes mapping first lines associated with objects to a ground plane; and forming clusters of second lines corresponding to the first lines such that an intersection point in a cluster represents a position of an object on the ground plane.

Abstract: The invention relates to a smart card, which includes: a card body, having an accommodating recess extending along its own thickness direction of the card body; a decorative part, at least part of the decorative part being embedded in the accommodating recess; in which the decorative part includes a base layer and decorative pieces, more than two decorative pieces are arranged on the base layer, the base layer is connected to the card body, the decorative pieces correspond to the accommodating recess along the thickness direction and are exposed to an external environment. The smart card of the invention can improve the stereoscopic sense, individuation and noble sense of the smart card by arranging the decorative parts with decorative pieces on the card body.

Abstract: The present invention provides a long-acting glucagon derivative whose amino acid sequence includes a sequence as shown in SEQ ID NO. 9. The long-acting glucagon derivative of the present invention shows in animal experiments that, compared with a similar fatty acid-modified GLP-1R single agonist Semaglutide (see J Med Chem. 2015, 58 (18): 7370-80), its glucose tolerance and activity of reducing weight in mice are both stronger and can maintain for a longer time.

Abstract: A trip energy estimation system includes a memory and a control module. The memory stores average traffic speed, average traffic acceleration, driver speed, and driver acceleration data. The control module executes an algorithm to estimate an amount of energy for an electric vehicle to travel between two locations. The algorithm includes: determining, based on the average traffic speed data and the average traffic acceleration data, a baseline amount of energy for the electric vehicle to travel between the two locations; determining, based on the driver speed data and the driver acceleration data, a dynamic amount of energy corresponding to at least one of stop and go events, over speeding, or under speeding; and determining a total amount of energy based on the baseline amount of energy and the dynamic amount of energy. The control module, based on the total amount of energy, performs an operation including indicating a trip estimate.

Abstract: A system in an electric or hybrid vehicle includes two or more battery packs to power one or more motors of the vehicle to move the vehicle. A controller dynamically activates an operational mode of the vehicle during vehicle operation, the operational mode being one of a plurality of possible operational modes. Each of the possible operational modes defines which of the two or more battery packs are connected to the one or more motors and, based on two or more of the two or more battery packs being connected to the one or more motors, also defines an interconnection among the two or more of the two or more battery packs. The plurality of possible operational modes includes a first operational mode defining a series connection between the two or more battery packs and second operational mode defining a parallel connection between the two or more battery packs.

Abstract: Some embodiments involve a reinforcement learning based framework for training a natural media agent to learn a rendering policy without human supervision or labeled datasets. The reinforcement learning based framework feeds the natural media agent a training dataset to implicitly learn the rendering policy by exploring a canvas and minimizing a loss function. Once trained, the natural media agent can be applied to any reference image to generate a series (or sequence) of continuous-valued primitive graphic actions, e.g., sequence of painting strokes, that when rendered by a synthetic rendering environment on a canvas, reproduce an identical or transformed version of the reference image subject to limitations of an action space and the learned rendering policy.

Abstract: An electric vehicle, an electric drive system and method of operating the electric vehicle. The electric drive system provides a torque to a wheel of the electric vehicle. The processor is configured to obtain a value of the torque at which the electric drive system of the vehicle is operating, determine an optimal speed for the vehicle for the torque based on an efficiency model of the electric drive system, wherein the optimal speed corresponds to an optimal drive efficiency for the electric drive system, and operate the vehicle at the optimal speed.

Abstract: An intelligent analysis system applied to ethology of various kinds of high-density minimal polypides is provided, including an operating platform subsystem and an analysis subsystem; the operating platform subsystem is used for providing an activity medium capable of obtaining behaviors of the minimal polypides and shooting the behaviors of the minimal polypides; the behavior collecting module in the analysis subsystem is used for obtaining an ethology video of the high-density minimal polypides through the operating platform subsystem; the analysis modeling module is used for obtaining ethology big data of various kinds of high-density minimal insects according to the ethology video, and establishing an ethology model; the simulation predicting module is used for dynamically predicting comprehensive control strategies and control effects of minimal pests in a field ecosystem according to the ethology model; the visual demonstrating module is used for displaying the above behavior data.

Abstract: The present disclosure relates to a fashion recommendation system that employs a task-guided learning framework to jointly train a visually-aware personalized preference ranking network. In addition, the fashion recommendation system employs implicit feedback and generated user-based triplets to learn variances in the user's fashion preferences for items with which the user has not yet interacted. In particular, the fashion recommendation system uses triplets generated from implicit user data to jointly train a Siamese convolutional neural network and a personalized ranking model, which together produce a user preference predictor that determines personalized fashion recommendations for a user.

Abstract: Embodiments of the present invention provide an automated image tagging system that can predict a set of tags, along with relevance scores, that can be used for keyword-based image retrieval, image tag proposal, and image tag auto-completion based on user input. Initially, during training, a clustering technique is utilized to reduce cluster imbalance in the data that is input into a convolutional neural network (CNN) for training feature data. In embodiments, the clustering technique can also be utilized to compute data point similarity that can be utilized for tag propagation (to tag untagged images). During testing, a diversity based voting framework is utilized to overcome user tagging biases. In some embodiments, bigram re-weighting can down-weight a keyword that is likely to be part of a bigram based on a predicted tag set.

Abstract: The present invention provides for lithium battery comprising (a) a cathode or an anode, or both, comprising an additive, or (b) an electrolyte composition comprising optionally an ether solvent, optionally an amphiphilic molecule, an additive, an electrolyte solvent, and a lithium salt; wherein the additive is a silicic acid, silicate, metasilicate, or salt thereof, or a mixture thereof. The present invention also provides for particles in lithium ion-battery electrolytes to improve low temperature performance.

Abstract: Methods and systems are provided for transforming sketches into stylized electronic paintings. A neural network system is trained where the training includes training a first neural network that converts input sketches into output images and training a second neural network that converts images into output paintings. Similarity for the first neural network is evaluated between the output image and a reference image and similarity for the second neural network is evaluated between the output painting, the output image, and a reference painting. The neural network system is modified based on the evaluated similarity. The trained neural network is used to generate an output painting from an input sketch where the output painting maintains features from the input sketch utilizing an extrapolated intermediate image and reflects a designated style from the reference painting.