Abstract: Methods and systems for training a model include pre-training a backbone model with a pre-training decoder, using an unlabeled dataset with multiple distinct sensor data modalities that derive from different sensor types. The backbone model is fine-tuned with an output decoder after pre-training, using a labeled dataset with the multiple modalities.

Abstract: Smart vehicle-to-everything (V2X) preemptive connections for emergency and/or potential accident scenarios. A V2X-enabled vehicle may determine a current route of the vehicle and high-risk areas through which the vehicle may travel (e.g., a hospital zone, high pedestrian traffic area, etc.). The vehicle may determine a distance (d) from a beginning of the high-risk area and begin establishing a V2X connection upon reaching the determined distance. The V2X-enabled vehicle may also, or alternatively, pre-emptively establish a V2X connection upon detecting an event initiative of an emergency, a hazardous situation, or a potential emergency. Examples of such events may include a sharp turn, a vehicle speed exceeding a speed threshold, a sudden acceleration or declaration, etc. A preemptive V2X connection may, for example, enable vehicles to begin communicating with one another faster in case of a threat, emergency, or unsafe conditions for vehicles in the area.

Abstract: Apparatuses, systems, and methods for RACH procedures to avoid excessive handover/secondary cell group failures. A base station may declare a handover and/or secondary cell group (SCG) failure and may determine that a failure threshold has been met. The base station may perform a remedial action in response to meeting the failure threshold. The failure threshold may be multi-dimensional, where a first dimension is associated with a number of handover/SCG failures and where a second dimension is associated with a time period in which the number of handover/SCG failures occurred. Further, a third dimension may be associated with a UE mobility state and a fourth dimension may be associated with whether the UE is using FR1 or FR2. The remedial action in response to meeting the failure threshold may include the base station suspending transmission of measurement object configurations for a specified period of time.

Abstract: Disclosed herein is method and system for identifying one or more Places of Interest (PoI) in a natural language system. Word embedding representation for each word in the natural language input are retrieved from a knowledge repository. Further, for each word, Part-of-Speech (POS) tags are tagged, and dependency labels are generated. Subsequently, a PoI tag is assigned to each word based on the word embedding representation, the POS and the dependency labels of each word. Finally, the one or more PoI are identified based on PoI tag assigned to each word. In an embodiment, the method of present disclosure helps in dynamically identifying one or more PoI from natural language text utterances in interactive systems, thereby enhancing usability of interaction based intelligent systems.

Abstract: Disclosed herein is method and system for identifying one or more Places of Interest (PoI) in a natural language system. Word embedding representation for each word in the natural language input are retrieved from a knowledge repository. Further, for each word, Part-of-Speech (POS) tags are tagged, and dependency labels are generated. Subsequently, a PoI tag is assigned to each word based on the word embedding representation, the POS and the dependency labels of each word. Finally, the one or more PoI are identified based on PoI tag assigned to each word. In an embodiment, the method of present disclosure helps in dynamically identifying one or more PoI from natural language text utterances in interactive systems, thereby enhancing usability of interaction based intelligent systems.

Abstract: Systems and methods for identifying and learning emotions in conversation utterances are described. The system receives at least one of textual utterance data, audio utterance data and visual utterance data. A set of facial expressions are fetched from the visual utterance data. The system annotates the set of facial expressions with corresponding set of emotions using predictive modeling. Upon annotating, labelled data is generated by tagging the textual utterance data and the audio utterance data with the set of emotions. The labelled data along with non-labelled data is fed into self-learning model of the system. The non-labelled data is new textual utterance data. The self-learning model learns, from the labelled data, about the set of emotions. Further, the self-learning model also determines a new set of emotions corresponding to the new textual utterance data by using recurrent neural network. The self-learning model generates new labelled data and update itself accordingly.

Abstract: Systems and methods for identifying and learning emotions in conversation utterances are described. The system receives at least one of textual utterance data, audio utterance data and visual utterance data. A set of facial expressions are fetched from the visual utterance data. The system annotates the set of facial expressions with corresponding set of emotions using predictive modeling. Upon annotating, labelled data is generated by tagging the textual utterance data and the audio utterance data with the set of emotions. The labelled data along with non-labelled data is fed into self-learning model of the system. The non-labelled data is new textual utterance data. The self-learning model learns, from the labelled data, about the set of emotions. Further, the self-learning model also determines a new set of emotions corresponding to the new textual utterance data by using recurrent neural network. The self-learning model generates new labelled data and update itself accordingly.

Abstract: A computing device may generate, a graph that includes a plurality of nodes, wherein the plurality of nodes includes a plurality of entity nodes representing a plurality of entities and a plurality of feature nodes representing a plurality of features, and wherein each of the plurality of entity nodes is connected in the graph to one or more of the plurality of feature nodes. The computing device may perform label propagation to associate a distribution of labels with each of the plurality of nodes. The computing device may be configured to receive an indication of at least one of a feature of interest or an entity of interest. The computing device may further be configured to output an indication of one or more related entities that are related to the feature of interest or the entity of interest.

Abstract: Embodiments of the present disclosure disclose a method and a device for dynamically controlling quality of a video displaying on a display associated to an electronic device is provided. The method comprises detecting current eye position of a user and identifying at least one region of interest (ROI) on a display screen of the display device based on the current eye position of the user. Then, the method comprises predicting next position of the eye based on at least one of the current eye position of the user or the at least one ROI. Also, the method comprises converting the SD video in to a high definition (HD) video displayed on the ROI on the display screen associated with the current and next position of the eye. Further, the method comprises displaying the HD video on the ROI of the display screen.

Abstract: Embodiments of the present disclosure disclose a method and a device for dynamically controlling quality of a video displaying on a display associated to an electronic device is provided. The method comprises detecting current eye position of a user and identifying at least one region of interest (ROI) on a display screen of the display device based on the current eye position of the user. Then, the method comprises predicting next position of the eye based on at least one of the current eye position of the user or the at least one ROI. Also, the method comprises converting the SD video in to a high definition (HD) video displayed on the ROI on the display screen associated with the current and next position of the eye. Further, the method comprises displaying the HD video on the ROI of the display screen.

Abstract: A computer system for discount shifting includes a network server including a microprocessor, a memory and computer software, wherein the computer software is located in the memory and run by the microprocessor, the computer software including a database and an algorithm, wherein the algorithm includes the steps of: writing to the memory an acceptance of an offer from a seller having a retail value when the offer is accepted by a buyer; reading from the memory a buying power of the buyer; recalculating the buying power of the buyer by reducing the buying power of the buyer by an amount equal to the retail value; writing to the memory the reduced buying power of the buyer; transmitting from the network server to the buyer a voucher for the offer from the seller.

Abstract: A method and apparatus are provided for braking and stopping a vehicle whose powertrain includes an electric drive. The electric drive is used to generate braking torque which is used to decelerate the vehicle down to a full stop. The braking torque is achieved using any of several closed loop speed control systems. The system can be used as a substitute for or as a supplement to conventional friction bakes.

Abstract: A flush and fill process is used to ready a fuel cell cooling circuit for initial use. An external flushing system releasably connected to the cooling circuit circulates flushing coolant through the cooling circuit to remove contaminants from the wetted surfaces of the cooling circuit before the fuel cell is put into use. The flushing system includes a pump for circulating the flushing coolant through the cooling circuit, filters for removing contaminants from the coolant and a heater for elevating the temperature of the coolant. Following the flushing process to remove contaminants, the flushing system is disconnected from the cooling circuit and the cooling circuit is filled with fresh coolant.

Abstract: A prognostic method and system for testing and controlling various hybrid, fuel cell, and electric vehicle components. The tests generate test data for determining a state of the tested components. An operating strategy of the vehicle is controlled based on the state of its tested components.

Abstract: An alternative fuel vehicle having a fuel economy control module with associated logic that allows the vehicle to operate in a fuel economy mode based on a desired fuel economy preference. The fuel economy control logic is in electrical communication with a vehicle system controller (VSC) and may be integrally formed as a sub-module within the VSC. A fuel economy control switch controlled by the fuel economy control logic toggles between an on and an off position to enable or disable a fuel economy mode. A fuel economy control selector allows a user to select a desired fuel economy mode preference once the fuel economy control switch is on. The fuel economy mode selected represents a predefined desired fuel economy preference such as a distance per amount of fuel consumed, or alternatively, a percentage of a balance between a fuel economy operation and a fuel performance operation.

Abstract: An alternative fuel vehicle having a fuel economy control module with associated logic that allows the vehicle to operate in a fuel economy mode based on a desired fuel economy preference. The fuel economy control logic is in electrical communication with a vehicle system controller (VSC) and may be integrally formed as a sub-module within the VSC. A fuel economy control switch controlled by the fuel economy control logic toggles between an on and an off position to enable or disable a fuel economy mode. A fuel economy control selector allows a user to select a desired fuel economy mode preference once the fuel economy control switch is on. The fuel economy mode selected represents a predefined desired fuel economy preference such as a distance per amount of fuel consumed, or alternatively, a percentage of a balance between a fuel economy operation and a fuel performance operation.

Abstract: A flush and fill process is used to ready a fuel cell cooling circuit for initial use. An external flushing system relasably connected to the cooling circuit circulates flushing coolant through the cooling circuit to remove contaminants from the wetted surfaces of the cooling circuit before the fuel cell is put into use. The flushing system includes a pump for circulating the flushing coolant through the cooling circuit, filters for removing contaminants from the coolant and a heater for elevating the temperature of the coolant. Following the flushing process to remove contaminants, the flushing system is disconnected from the cooling circuit and the cooling circuit is filled with fresh coolant.

Abstract: A method and apparatus are provided for braking and stopping a vehicle whose powertrain includes an electric drive. The electric drive is used to generate braking torque which is used to decelerate the vehicle down to a full stop. The braking torque is achieved using any of several closed loop speed control systems. The system can be used as a substitute for or as a supplement to conventional friction bakes.

Abstract: The present invention can diagnose a potential discrepancy in electrical operating characteristics of a three phase electric motor by generating two independent torque estimates using a plurality of current sensors and a shaft position sensor. The invention provides a strategy to generate two independent torque estimates of a three phase electric motor comprising first and second systems to determine currents in two motor phases, first and second systems to generate a first and second estimate of motor shaft position, and first and second systems to generate first and second estimates of motor torque using the first and second systems to determine current in each motor phase and the first and second values of motor shaft position. The present invention detects also an electrical operating characteristic discrepancy in an electric motor-propelled vehicle's electrical components and subsystems, including single subsystem discrepancies between the two independent torque estimates.

Abstract: A system and method for diagnosing a potential electrical operating discrepancy in a polyphase electric motor by generating two independent torque estimates using a plurality of current sensors and, optionally, a shaft position sensor. Differences between the independent torque estimates are used to indicate potential discrepancies in electrical operating characteristics of the motor.