A temporal Human Activity Recognition Based on Stacked Auto Encoder and Extreme Learning Machine

Human Activity Recognition (HAR) is one of the most important research areas in the fields of health and human-machine interaction. The creation of several artificial intelligence-based models for activity identification has resulted in poor long-term performance in the actual world since these methods are unable to extract spatial and temporal information. Though, Deep learning is starting to replace well-established hand-crafted techniques that rely on expertly built feature extraction and classification techniques in the field of HAR. Nevertheless, it is challenging to acquire an overview of the suitability of these discrete implementations of custom deep architectures for issues ranging from the recognition of manipulative gestures to the identification and segmentation of physical activities. Given these constraints, we develop an innovative Stacked Auto Encoder (SAE) and Extreme Learning Machine (ELM) architecture based on temporal feature to produce a new model for HAR.. This feature is connected to speed of movement and fed to a new neural network architecture as temporal stream. A key step in this approach is the selection of features that characterize the complexity of human actions in time. Results show that the proposed model outperforms many of the existing deep and machine learning techniques.