Abstract: Motion windows are generated from a query activity sequence. For each of the motion windows in the query activity sequence, a corresponding motion window in the reference activity sequence is found. One or more difference calculations are performed between the motion windows of the query activity sequence and the corresponding motion windows in the reference activity sequence based on at least one criterion associated with physical meaning. Abnormality of the motion windows is determined based on the one or more difference calculations. A standardized evaluation result of the query activity sequence is output based on the detected abnormal motion windows in the query activity sequence.

Abstract: Various embodiments of a systems and methods for a triplet network having speaker diarization are disclosed.

Abstract: An operation method of a robot for leading a follower to a destination within an open space includes: calculating a distance between the follower and the robot; when it is determined that the distance is not greater than a threshold, determining a pre-movement location of the robot in the open space and an orientation of the robot, and calculating a linear speed and an angular speed for the robot based on the pre-movement location and the orientation of the robot and the destination; moving according to the linear speed and the angular speed; determining whether the robot has arrived at the destination according to the current position; and repeating the previous steps when it is determined that the robot has not arrived at the destination.

Abstract: A system and method for domain adaptation involves a first domain and a second domain. A machine learning system is trained with first sensor data and first label data of the first domain. Second sensor data of a second domain is obtained. Second label data is generated via the machine learning system based on the second sensor data. Inter-domain sensor data is generated by interpolating the first sensor data of the first domain with respect to the second sensor data of the second domain. Inter-domain label data is generated by interpolating first label data of the first domain with respect to second label data of the second domain. The machine learning system is operable to generate inter-domain output data in response to the inter-domain sensor data. Inter-domain loss data is generated based on the inter-domain output data with respect to the inter-domain label data. Parameters of the machine learning system are updated upon optimizing final loss data that includes at least the inter-domain loss data.

Abstract: Few-shot learning of repetitive human tasks is performed. Sliding window-based temporal segmentation is performed of sensor data for a plurality of cycles of a repetitive task. Motion alignment is performed of the plurality of cycles, the motion alignment mapping portions of the plurality of cycles to corresponding portions of other of the plurality of cycles. Categories are constructed for each of the corresponding portions of the plurality of cycles according to the motion alignment. Meta-training is performed to teach a model according to data sampled from a labeled set of human motions and the categories for each of the corresponding portions, the model utilizing a bidirectional long short-term memory (LSTM) network to account for length variation between the plurality of cycles. The model is used to perform temporal segmentation on a data stream of sensor data in real time for predicting motion windows within the data stream.

Abstract: Abnormal motions are detected in sensor data collected with respect to performance of repetitive human activities. An autoencoder network model is trained based on a set of standard activity. Repetitive activity is extracted from sensor data. A first score is generated indicative of distance of a repetition of the repetitive activity from the standard activity. The repetitive activity is used to retrain the autoencoder network model, using weights of the autoencoder network model as initial values, the weights being based on the training of the autoencoder network model using the set of standard activity. A second score is generated indicative of whether the repetition is an outlier as compared to other repetitions of the repetitive activity. A final score is generated based on a weighting of the first score and the second score.

Abstract: A power supply system with hydrogen fuel cell is provided, comprising a hydrogen fuel cell module converting hydrogen fuel into electrical power for outputting. A boost charging module electrically connected to the hydrogen fuel cell module receives, boosts and converts the electric power into charging power. At least two battery packs connected in parallel are electrically connected to the boost charging module and an external load respectively. When one of the battery packs discharges the external load, the other selectively receives charging power from the boost charging module. A control module electrically connected to the above controls the boost charging module to receive electrical power and convert it into charging power and controls the battery packs to alternate performing discharging the external load and charging from the boost charging module repeatedly by turns. The present invention combines hydrogen fuel cells to provide an innovative power supply system.

Abstract: A system for time series analysis using attention models is disclosed. The system may capture dependencies across different variables through input embedding and may map the order of a sample appearance to a randomized lookup table via positional encoding. The system may capture capturing dependencies within a single sequence through a self-attention mechanism and determine a range of dependency to consider for each position being analyzed. The system may obtain an attention weighting to other positions in the sequence through computation of an inner product and utilize the attention weighting to acquire a vector representation for a position and mask the sequence to enable causality. The system may employ a dense interpolation technique for encoding partial temporal ordering to obtain a single vector representation and a linear layer to obtain logits from the single vector representation. The system may use a type dependent final prediction layer.

Abstract: Various embodiments of systems and methods for attention models with random features for multi-layered graph embeddings are disclosed.

Abstract: Various embodiments of systems and methods for attention models with random features for multi-layered graph embeddings are disclosed.

Abstract: Motion windows are generated from a query activity sequence. For each of the motion windows in the query activity sequence, a corresponding motion window in the reference activity sequence is found. One or more difference calculations are performed between the motion windows of the query activity sequence and the corresponding motion windows in the reference activity sequence based on at least one criterion associated with physical meaning. Abnormality of the motion windows is determined based on the one or more difference calculations. A standardized evaluation result of the query activity sequence is output based on the detected abnormal motion windows in the query activity sequence.

Abstract: A quickly-mountable housing of an electronic device includes the holding member and a main body. The main body includes a lateral panel having a first edge, a second edge, a first groove, a second groove, a hooking structure, and two blocks. The first groove extends along a traversal axis and the second groove extends along a longitudinal axis. The hooking structure extends toward the traversal axis from a lower side wall adjacent to the second edge. The two blocks on two sides of the longitudinal axis extend from side walls of the second groove toward the longitudinal axis. The holding member in the second groove is in a closed position where a holding part of the holding member is within the first groove.

Abstract: A quickly-mountable housing of an electronic device includes the holding member and a main body. The main body includes a lateral panel having a first edge, a second edge, a first groove, a second groove, a hooking structure, and two blocks. The first groove extends along a traversal axis and the second groove extends along a longitudinal axis. The hooking structure extends toward the traversal axis from a lower side wall adjacent to the second edge. The two blocks on two sides of the longitudinal axis extend from side walls of the second groove toward the longitudinal axis. The holding member in the second groove is in a closed position where a holding part of the holding member is within the first groove.

Abstract: Various embodiments of a systems and methods for a triplet network having speaker diarization are disclosed.

Abstract: An operation method of a robot for leading a follower to a destination within an open space includes: calculating a distance between the follower and the robot; when it is determined that the distance is not greater than a threshold, determining a pre-movement location of the robot in the open space and an orientation of the robot, and calculating a linear speed and an angular speed for the robot based on the pre-movement location and the orientation of the robot and the destination; moving according to the linear speed and the angular speed; determining whether the robot has arrived at the destination according to the current position; and repeating the previous steps when it is determined that the robot has not arrived at the destination.

Abstract: A power supply system with hydrogen fuel cell is provided, comprising a hydrogen fuel cell module converting hydrogen fuel into electrical power for outputting. A boost charging module electrically connected to the hydrogen fuel cell module receives, boosts and converts the electric power into charging power. At least two battery packs connected in parallel are electrically connected to the boost charging module and an external load respectively. When one of the battery packs discharges the external load, the other selectively receives charging power from the boost charging module. A control module electrically connected to the above controls the boost charging module to receive electrical power and convert it into charging power and controls the battery packs to alternate performing discharging the external load and charging from the boost charging module repeatedly by turns. The present invention combines hydrogen fuel cells to provide an innovative power supply system.

Abstract: A method including receiving an input data set. The input data set can include one of a feature domain set or a kernel matrix. The method also can include constructing dense embeddings using: (i) Nyström approximations on the input data set when the input data set comprises the kernel matrix, and (ii) clustered Nyström approximations on the input data set when the input data set comprises the feature domain set. The method additionally can include performing representation learning on each of the dense embeddings using a multi-layer fully-connected network for each of the dense embeddings to generate latent representations corresponding to each of the dense embeddings. The method further can include applying a fusion layer to the latent representations corresponding to the dense embeddings to generate a combined representation. The method additionally can include performing classification on the combined representation. Other embodiments of related systems and methods are also disclosed.

Abstract: One embodiment of the present invention provides a computing system. The computing system includes a packet processor, a buffer management module, a data monitoring module, and a flow control module. The packet processor identifies a class of service indicating priority-based flow control associated with a remote computing system from a notification message. The buffer management module creates a buffer dedicated for frames belonging to the class of service from the remote computing system in response to identifying the class of service. The data monitoring module detects a potential overflow of the buffer. The flow control module operates in conjunction with the packet processor to generate a pause frame in response to detecting a potential overflow.

Abstract: A system for introducing telephone number related information, a method for introducing telephone number related information and a program product using the system and method are disclosed. An electronic communication device transmits a telephone number to a remote system for introducing telephone number related information when dialing or receiving a call, and the system searches the telephone number related information from a database stored in the system and provides the information to the electronic communication device, such that the electronic communication device can display the related information corresponding to the telephone number to let users know about the telephone number related information before receiving or dialing a call.

Abstract: One embodiment of the present invention provides a computing system. The computing system includes a packet processor, a buffer management module, a data monitoring module, and a flow control module. The packet processor identifies a class of service indicating priority-based flow control associated with a remote computing system from a notification message. The buffer management module creates a buffer dedicated for frames belonging to the class of service from the remote computing system in response to identifying the class of service. The data monitoring module detects a potential overflow of the buffer. The flow control module operates in conjunction with the packet processor to generate a pause frame in response to detecting a potential overflow.