Abstract: A computer-implemented method for ordinal prediction is provided. The method includes encoding time series data with a temporal encoder to obtain latent space representations. The method includes optimizing the temporal encoder using semi-supervised learning to distinguish different classes in the labeled space using labeled data, and augment the latent space representations using unlabeled training data, to obtain semi-supervised representations. The method further includes discarding a linear layer after the temporal encoder and fixing the temporal encoder. The method also includes training k-1 binary classifiers on top of the semi-supervised representations to obtain k-1 binary predictions. The method additionally includes identifying and correcting inconsistent ones of the k-1 binary predictions by matching the inconsistent ones to consistent ones of the k-1 binary predictions. The method further includes aggregating the k-1 binary predictions to obtain an ordinal prediction.

Abstract: A display panel includes a display region and a photoelectric sensing region which includes a light transmitting region and a frame region surrounding the light transmitting region; the frame region includes a first region surrounding the light transmitting region, a second region on a side of the first region away from the light transmitting region and surrounding the first region, and a third region between the second region and the display region. The spacers are in an array and in the display region but not in the light transmitting region. A plurality of first support pillars are in the first region, arranged around the light transmitting region, and spaced from each other. A plurality of second support pillars are in the second region, around the second region, and spaced from each other. A plurality of third support pillars are in the third region in an array.

Abstract: A computer-implemented method for ordinal prediction is provided. The method includes encoding time series data with a temporal encoder to obtain latent space representations. The method includes optimizing the temporal encoder using semi-supervised learning to distinguish different classes in the labeled space using labeled data, and augment the latent space representations using unlabeled training data, to obtain semi-supervised representations. The method further includes discarding a linear layer after the temporal encoder and fixing the temporal encoder. The method also includes training k?1 binary classifiers on top of the semi-supervised representations to obtain k?1 binary predictions. The method additionally includes identifying and correcting inconsistent ones of the k?1 binary predictions by matching the inconsistent ones to consistent ones of the k?1 binary predictions. The method further includes aggregating the k?1 binary predictions to obtain an ordinal prediction.

Abstract: A dynamic side blind zone method includes determining that a host vehicle is approaching a first lane that is nonparallel to a second lane. The host vehicle is moving in the second lane. The method further includes activating an adaptive side blind zone alert system of the host vehicle in response to determining that the host vehicle is approaching the first lane that is nonparallel to the second lane, determining a warning zone in response to activating the adaptive side blind zone alert system of the host vehicle, and detecting a remote vehicle inside the warning zone after determining the warning zone. The remote vehicle is moving in the first lane. The method further includes providing an alert to a vehicle user of the host vehicle in response to detecting that the remote vehicle is inside the warning zone.

Abstract: An automated driving system includes an object detection system. A neural network image encoder generates image embeddings associated with an image including an object. A neural network text encoder generates concept embeddings associated with each of a plurality of concepts. Each of the plurality of concepts is associated with one of at least two object classes. A confidence score module generates a confidence score for each of the plurality of concepts based on the image embeddings and the concept embeddings associated with the concept. An object class prediction module generates a predicted object class of the object based on an association between a set of concepts of the plurality of concepts having at least two of the highest values of the generated confidence scores and the one of the at least two object classes associated with a majority of the set of concepts.

Abstract: A displaying base plate and a manufacturing method thereof, and a displaying device. The displaying base plate includes a substrate, and a first electrode layer disposed on one side of the substrate, wherein the first electrode layer includes a first electrode pattern; a first planarization layer disposed on one side of the first electrode layer that is away from the substrate, wherein the first planarization layer is provided with a through hole, and the through hole penetrates the first planarization layer, to expose the first electrode pattern; and a second electrode layer, a second planarization layer and a third electrode layer that are disposed in stack on one side of the first planarization layer that is away from the substrate, wherein the second electrode layer is disposed closer to the substrate, the second electrode layer is connected to the first electrode pattern and the third electrode layer.

Abstract: The present application provides a memory device having a word line with an improved adhesion between a work function member and a conductive layer. The memory device includes a semiconductor substrate defined with an active area and including a recess extending into the semiconductor substrate, and a word line disposed within the recess, wherein the word line includes a first insulating layer disposed within and conformal to the recess, a conductive layer surrounded by the first insulating layer, a conductive member enclosed by the conductive layer, and a second insulating layer disposed over the conductive layer and conformal to the first insulating layer. A method of manufacturing the memory device is also disclosed.

Abstract: A front light module includes a light guide sheet and a light bar. The light guide sheet has two light receiving laterals, a fold line, a first pattern area, and a second pattern area respectively located on two sides of the fold line. One light receiving lateral is protruded to form first taper sets, and the other is protruded to form second taper sets. The second pattern area is superimposed on the first pattern area, and the first and second tapers set are engaged and coplanar to form a light incident surface after folding along the fold line. The light bar provides light toward the light incident surface, the first pattern area is lit by the odd positions of the light bar via the first taper sets, and the second pattern area is lit by the even positions of the light bar via the second taper sets.

Abstract: A system and method for preparing epoxy chloropropane is provided in that by coupling three stages of high gravity reactors, the product epoxy chloropropane and water vapor are distilled from a reaction system in form of an azeotrope by adopting a water vapor steam stripping method. Further, by combining the azeotrope with the multiples stages of high gravity reactors, the gas phase mass transfer and the liquid phase mass transfer of the azeotrope are improved aiming at the features of the azeotrope in the reaction system, thus making the overall conversion rate higher. In addition, by combining steam stripping and high gravity, dichloropropanol and alkali solution are rapidly mixed for mass transfer, and the product epoxy chloropropane is rapidly distilled from the reaction system in the form of the azeotrope, such that the reaction proceeds continuously towards the direction of producing epoxy chloropropane, thus significantly improving the conversion rate.

Abstract: An automobile vehicle continuous validation system includes a backend collecting data from a vehicle fleet and wirelessly communicating with the vehicle fleet. The backend is in wireless communication with at least one client. A vehicle module is provided on-board individual ones of multiple automobile vehicles of the vehicle fleet and performing an on-board vehicle validation analysis. A fleet-based validation module provided either at the backend or cloud based manages data defining a configuration of and a capability of the multiple automobile vehicles of the vehicle fleet. A validation manager generates validation tasks based on a user's definition or a desired production of the validation tasks of the validation analysis and a fleet vehicle availability. A client-side module remote from the multiple automobile vehicles of the vehicle fleet has interface items applied by the at least one client seeking to perform the validation analysis.

Abstract: Methods and systems for training a model include determining class prototypes of time series samples from a training dataset. A task corresponding to the time series samples is encoded using the class prototypes and a task-level configuration. A likelihood value is determined based on outputs of a time series density model, a task-class distance from a task embedding model, and a task density model. Parameters of the time series density model, the task embedding model, and the task density model are adjusted responsive to the likelihood value.

Abstract: A method of manufacturing a semiconductor device is provided. The method includes providing a semiconductor substrate having a trench. The method also includes forming a first buffer layer in the trench. The method further includes forming a doped-polysilicon layer on the first buffer layer in the trench. The method also includes performing a thermal treatment on the doped-polysilicon layer.

Abstract: A system comprises a computer including a processor and a memory. The memory includes instructions such that the processor is programmed to determine a pairwise region of interest feature similarity based on features extracted from a first cropped image portion and corresponding point cloud data and features extracted from a second cropped image portion and corresponding point cloud data. The processor is also programmed to determine a loss using a loss function based on the pairwise region of interest feature similarity, wherein the loss function corresponds to at least one a first deep neural network or a second deep neural network. The processor is also programmed to update at least one weight of the at least one of the first deep neural network or the second deep neural network based on the loss.

Abstract: The present application provides a method of manufacturing a memory device having a word line (WL) with improved adhesion between a work function member and a conductive layer. The method includes steps of providing a semiconductor substrate defined with an active area and including an isolation structure surrounding the active area; forming a recess extending into the semiconductor substrate and across the active area; forming a first insulating layer conformal to the recess; disposing a first conductive material conformal to the first insulating layer; forming a conductive member surrounded by the first conductive material; disposing a second conductive material over the conductive member and removing a portion of the first conductive material above the second conductive material to form a conductive layer enclosing the conductive member; and forming a second insulating layer over the conductive layer and conformal to the first insulating layer.

Abstract: A system for an attention-based perception includes a camera device configured to provide an image of an operating environment of a vehicle. The system further includes a computerized device monitoring the image, analyzing sensor data to identify a feature in the image as corresponding to an object in the operating environment and assign a score for the feature based upon an identification, a location, or a behavior of the object. The computerized device is further operable to define candidate regions of interest upon the image, correlate the score for the feature to the candidate regions of interest to accrue a total region score, select some of the candidate regions for analysis based upon the total region scores, and analyze the portion of the candidate regions to generate a path of travel output. The system further includes a device controlling the vehicle based upon the output.

Abstract: An in-vehicle violence detection and fusion system includes a standard vehicle camera positioned within a vehicle capturing images of at least one occupant of the vehicle. An event camera positioned within the vehicle captures motion images of the at least one occupant. A standard vehicle camera-based region of interest (ROI) signal and an event camera-based ROI signal are received and fused by an ROI fusion module to generate a fused ROI signal. A threat evaluation module receives the fused ROI signal and augments the fused ROI signal with saved data to assist in differentiating normal events from threat events. An event camera-based violence indicator identifies the threat events to the at least one occupant of the vehicle.

Abstract: An in-vehicle violence detection system includes a speech and non-speech audio recognition module capturing occupant threat words and non-speech audio events. In-vehicle accelerometers generate data analyzed in a shaking movement recognition module. A heart rate and breathing rate detection module measures physiological changes in occupant heart rates and breathing rhythms. An in-vehicle semantic scene recognition module analyzes occupant non-verbal interactions. Occupant threat indicators including an audible threat indicator are generated by the speech and non-speech audio event recognition module. Visual threat indicators are generated by the in-vehicle semantic scene recognition module. Physiological threat indicators are generated by the heart rate and breathing rate detection module. Vibration-based threat indicators are generated by the shaking movement recognition module.

Abstract: A perception system includes a perception module configured to capture first sensor data that includes data from at least one of an external sensor and a camera captured in a first period, a prediction module configured to receive the first sensor data, generate, based on the first sensor data, predicted sensor data for a second period subsequent to the first period, receive second sensor data for the second period, and output results of a comparison between the predicted sensor data and the second sensor data, and a diagnostic module configured to selectively identify a fault in the perception system based on the results of the comparison.

Abstract: A method for validating an autonomous vehicle performance using nearby traffic patterns includes receiving remote vehicle data. The remote vehicle data includes at least one remote-vehicle motion parameter about a movement of a plurality of remote vehicles during a predetermined time interval. The method further includes determining a traffic pattern of the plurality of remote vehicles using the at least one remote-vehicle motion parameter. The method includes determining a similarity between the traffic pattern of the plurality of remote vehicles and movements of the host vehicle. Further, the method includes determining whether the similarity between the traffic pattern of the plurality of remote vehicles and movements of the host vehicle is less than a predetermined threshold. Also, the method includes commanding the host vehicle to adjust the movements thereof to match the traffic pattern of the plurality of remote vehicles.

Abstract: A system comprises a computer including a processor and a memory. The memory includes instructions such that the processor is programmed to: receive intermediate concept constraints at a neural network and train the neural network with training data, training labels, and the at least one of the data constraint, the feature constraint, or the intermediate concept constraint.