Abstract: A multiple-port bidirectional converter is provided. The multiple-port bidirectional converter includes a transformer, a primary full-bridge converter, a first high voltage (HV) power converting unit, a second HV power converting unit, a first low voltage (LV) power converting unit, a second LV power converting unit, a full-bridge diode rectifier, and a full-bridge inverter. The transformer includes a core, one primary winding and five secondary windings. The primary full-bridge converter is coupled to the first primary winding and receives an input voltage. The first/second HV power converting unit, coupled to the first/second secondary winding, outputs a first/second high DC voltage to a first/second HV battery. The first/second LV power converting unit, coupled to the third/fourth secondary winding, outputs a first/second low DC voltage to a first/second LV battery. The full-bridge diode rectifier is coupled to the fifth secondary winding and the full-bridge diode rectifier to output an AC output voltage.

Abstract: A transformer is provided. The transformer includes a core, a primary winding, and a number of secondary windings. The core has a first leg and a second leg. At least part of the primary winding is wound around the first leg of the core. The primary winding includes a first sub-primary winding. This first sub-primary winding comprises a first auxiliary sub-primary winding and a second auxiliary sub-primary winding. Both the first auxiliary sub-primary winding and the second auxiliary sub-primary winding are bifilar wound, and they are connected in parallel. Some of the secondary windings are wound around the first leg of the core, and some of the secondary windings are wound around the second leg of the core.

Abstract: Embodiments pertain to a computer-implemented method of identifying at least one facial micro-expression pattern of a face of a subject by (1) receiving a plurality of images of the face of the subject, where the plurality of images represent consecutive images of the face of the subject taken sequentially during a period of time; (2) feeding the plurality of images into a machine-learning algorithm, where the machine-learning algorithm includes a diagonal micro attention (DMA) module that identifies at least one facial micro-movement between the plurality of images and correlates the facial micro-movement to at least one facial micro-expression pattern; and (3) outputting the facial micro-expression pattern of the face of the subject. Additional embodiments pertain to computing devices for identifying at least one facial micro-expression pattern of a face of a subject in accordance with the aforementioned processes.

Abstract: In some embodiments, the present disclosure pertains to systems and methods for evaluating demographic bias of images in a model having multiple clusters of images. In some embodiments, the method may include the steps of: determining demographic bias of the images in each of the multiple clusters of the model via a cluster purity evaluation module, encouraging a demographic fairness consistency for each of the multiple clusters via a loss function module to maintain fairness of the model, identifying, via a cross-attention module, correlations between each of the multiple clusters, and strengthening, via the cross-attention module, samples to have a stronger relationship with a centroid of each of the multiple clusters.

Abstract: A computer-implemented method, system, and computer program product for automatically detecting missing annotations (false negative objects) in 2D material detection data sets. Feature maps of an input image (e.g., image of 2D material obtained from optical microscopic images) are extracted using a backbone of a neural network (e.g., Mask-RCNN). Upon receiving such extracted feature maps, a list of object proposals are outputted by a regional proposal network of the neural network. The list of object proposals refer to the list of objects (visual representation of something in the image) in the input image to be annotated. Such a list of object proposals includes positive proposals (indicating that such objects were annotated) and negative proposals (indicating that such objects were not annotated). The false negative proposals (missing annotations) are then predicted from such a list of object proposals by measuring a self-attention between the positive and negative proposals.

Abstract: A method of clustering using encoder-decoder model based on attention mechanism extracts image features, clusters to form image feature vector clusters, and based on the cosine similarity score between the image feature vectors to arrange each image feature vector cluster into an image feature vector sequence. The image feature vector sequence includes cosine distance encoding vectors concatenated with respective image feature vectors and is used as the input data sequence in encoder and decoder neural network models to generate an output data sequence from the input data sequence. The output data sequence is a binary sequence having values of 1 or 0 at a position denoting that the image corresponding to the position is or is not in the same cluster with respect to the center image of the cluster.