We present a convolutional neural network- and long short-term memory-based method to classify the valence level of a computer user based on functional near infrared spectroscopy data. Convolutional neural networks are well suited for capturing the spatial characteristics of functional near infrared spectroscopy data. And long short-term memories are demonstrated to be good at learning temporal patterns of unknown length in time series data. We explore these methods in a combined layered architecture in order to improve classification accuracy. We conducted an experiment with 20 participants, wherein they were subjected to emotion inducing stimuli while their brain activity was measured using functional near infrared spectroscopy. Self-report surveys were administered after each stimulus to gauge participants' self-assessment of their valence. The resulting classification using these survey labels as ground truth provided a three-class classification accuracy 77.89% in across subject cross-validation. This method also shows promise for generalization to other classification tasks using functional near infrared spectroscopy data.

This study explores the genetic risk associations with autism spectrum disorder (ASD) using graph neural networks (GNNs), leveraging the Sfari dataset and protein interaction network (PIN) data. We built a gene network with genes as nodes, chromosome band location as node features, and gene interactions as edges. Graph models were employed to classify the autism risk associated with newly introduced genes (test set). Three classification tasks were undertaken to test the ability of our models: binary risk association, multi-class risk association, and syndromic gene association. We tested graph convolutional networks, Graph Sage, graph transformer, and Multi-Layer Perceptron (Baseline) architectures on this problem. The Graph Sage model consistently outperformed the other models, showcasing its utility in classifying ASD-related genes. Our ablation studies show that the chromosome band location and protein interactions contain useful information for this problem. The models achieved 85.80% accuracy on the binary risk classification, 81.68% accuracy on the multi-class risk classification, and 90.22% on the syndromic classification.

Few-shot human action recognition, a prominent area in computer vision, has garnered increasing attention and broader use in real-life scenarios. Extracting spatio-temporal skeletal information from human movement videos offers interpretable and data-efficient features. However, existing spatio-temporal feature encoders face challenges such as handling sequence boundaries and coping with noise. In order to solve the above problems, this paper proposes a temporal complement method to optimize the Dynamic Time Warping (DTW) algorithm based on the feature representation of the human skeleton sequence. DTW helps to find optimal alignment between sequences by warping them in the time domain. This is quite useful specially in scenarios where training data is limited. However, DTW has the drawback that the optimal alignment path is highly sensitive to errors in the time series distance matrix. Therefore, we apply a Virtual Adversarial Training method to improve the anti-noise capability of the algorithm. Here, We introduce adversarial perturbations in the training phase to the time series distance matrix, thus incentivizing the model to be resilient to such noise. Our method achieves highest accuracy among protonet, DTW and DASTM methods for the 5-way-1-shot setting for the NTU-S (77.7%), and Kinetics (41.2%) datasets. For the 5-way-5-shot setting, our method achieves highest accuracy of 51.8% for Kinetics dataset when compared with the other approaches.