Enhanced Complex Human Activity Recognition System: A Proficient Deep Learning Framework Exploiting Physiological Sensors and Feature Learning

Human activity recognition is the process of identifying daily living activities of a person using sensor attributes and intelligent learning algorithms. Identifying complex human activities is tedious, as capturing long-term dependencies and extracting efficient features from the raw sensor data is challenging. This letter proposes an efficient and lightweight hybrid deep learning model for recognizing complex human activities using physiological electromyography (EMG) sensors and enhanced feature learning. The proposed convolutional neural networks - long short-term memory (CNN-LSTM) incorporates multiple 1-D convolution layers for spatial feature extraction and then feeds the generated feature maps to the recurrent layers to identify long-term temporal dependencies. Incorporating a physiological sensor-based raw EMG dataset and minimal preprocessing, we trained and tested our proposed model and achieved the highest accuracy of 84.12% and an average accuracy of 83%. The proposed model outperformed the benchmark models with optimal performance margins and generalized the patterns in significantly less computational time than other deep learning models.