Human Postures Recognition by Accelerometer Sensor and ML Architecture Integrated in Embedded Platforms: Benchmarking and Performance Evaluation

• Published in: Sensors (Basel, Switzerland) Vol. 23; no. 2; p. 1039
• Main Authors: Leone, Alessandro, Rescio, Gabriele, Caroppo, Andrea, Siciliano, Pietro, Manni, Andrea
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 16-01-2023; MDPI
• Subjects: Accelerometers; Accelerometry; Accuracy; Aged; ageing adults; Algorithms; Benchmarking; Cameras; Classification; Eigenvalues; embedded platform; Embedded systems; Energy consumption; Experimentation; Humans; Lifestyles; machine learning; Neural networks; Older people; Performance evaluation; Personal computers; Portability; Posture; posture classification; Power management; Pressure distribution; Recognition; Sensors; Software; Support vector machines; Wearable computers; Wearable Electronic Devices; wearable sensor; Wearable technology; embedded platform; ageing adults; wearable sensor; machine learning; posture classification
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s23021039

Embedded hardware systems, such as wearable devices, are widely used for health status monitoring of ageing people to improve their well-being. In this context, it becomes increasingly important to develop portable, easy-to-use, compact, and energy-efficient hardware-software platforms, to enhance the level of usability and promote their deployment. With this purpose an automatic tri-axial accelerometer-based system for postural recognition has been developed, useful in detecting potential inappropriate behavioral habits for the elderly. Systems in the literature and on the market for this type of analysis mostly use personal computers with high computing resources, which are not easily portable and have high power consumption. To overcome these limitations, a real-time posture recognition Machine Learning algorithm was developed and optimized that could perform highly on platforms with low computational capacity and power consumption. The software was integrated and tested on two low-cost embedded platform (Raspberry Pi 4 and Odroid N2+). The experimentation stage was performed on various Machine Learning pre-trained classifiers using data of seven elderly users. The preliminary results showed an activity classification accuracy of about 98% for the four analyzed postures (Standing, Sitting, Bending, and Lying down), with similar accuracy and a computational load as the state-of-the-art classifiers running on personal computers.