Human Activity Recognition via Hybrid Deep Learning Based Model

• Published in: Sensors (Basel, Switzerland) Vol. 22; no. 1; p. 323
• Main Authors: Khan, Imran Ullah, Afzal, Sitara, Lee, Jong Weon
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 01.01.2022; MDPI
• Subjects: Ablation; Algorithms; Artificial Intelligence; Cameras; convolutional neural network; Coronaviruses; Datasets; Deep Learning; Exercise; Feature recognition; Human Activities; Human activity recognition; Humans; long short-term memory; Machine Learning; Moving object recognition; Neural networks; Neural Networks, Computer; Physical fitness; Sensors; skeleton data; United Kingdom; skeleton data; deep learning; machine learning; convolutional neural network; human activity recognition; long short-term memory
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s22010323

In recent years, Human Activity Recognition (HAR) has become one of the most important research topics in the domains of health and human-machine interaction. Many Artificial intelligence-based models are developed for activity recognition; however, these algorithms fail to extract spatial and temporal features due to which they show poor performance on real-world long-term HAR. Furthermore, in literature, a limited number of datasets are publicly available for physical activities recognition that contains less number of activities. Considering these limitations, we develop a hybrid model by incorporating Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) for activity recognition where CNN is used for spatial features extraction and LSTM network is utilized for learning temporal information. Additionally, a new challenging dataset is generated that is collected from 20 participants using the Kinect V2 sensor and contains 12 different classes of human physical activities. An extensive ablation study is performed over different traditional machine learning and deep learning models to obtain the optimum solution for HAR. The accuracy of 90.89% is achieved via the CNN-LSTM technique, which shows that the proposed model is suitable for HAR applications.