EGTCN: An Efficient Graph and Temporal Convolution Network for Sensor-Based Human Activity Recognition in Federated Learning

Technology advancements have led to the emergence of edge devices, wearable sensors, and the Internet of Things (IoT) that have revolutionized how we interact with technology. These devices enable real-time monitoring and analysis of human activities, leading to wearable sensor-based human activity recognition (HAR). Several recognition models are proposed for federated learning to protect users’ privacy and improve the efficiency of activity recognition predictive models. However, these models have large parameters, yet their prediction results require improvement. In addition, these previous federated learning works do not consider the framewise classification of activity sensor data. This work presents an efficient graph and temporal convolution network (EGTCN) model that guarantees better recognition performance with less computation cost. In addition, EGTCN parallelly predicts activities of sensor segments just as other state-of-the-art (SOTA) methods and performs framewise prediction of the sensor data. EGTCN comprises the encoder, decoder, and classifier modules. The encoder, constructed from multigraph convolution (MGC) and multitemporal convolution (MTC) modules, mines essential features from the segment input. The decoder takes the encoder output to reconstruct and predict the activities of each frame within a segment. Similarly, the classifier module uses the encoder output to predict the activity category of the segment input as a whole. Moreover, we design a federated learning system (FLS) that ensures user privacy and improves the performance of activity recognition models. Benchmark sensor datasets, namely, WISDM, UCI-HAR, PAMAP2, RealWorld, and USCHAD, are utilized to evaluate the performance of our method. The results indicate that our EGTCN and FLS outperform SOTA methods.