Internet of Things-Based Human Movement Monitoring System: Prospect for Conceptual Digital Twin

Abstract

The growing popularity of smart healthcare and novel innovations in human movement monitoring systems (HMMS) open doors for diagnosing various health conditions, including neurological disorders, musculoskeletal system problems, mobility limitations associated with aging, and the oversight of rehabilitation programs. This paper discusses the technical challenges, potential applications, and prospects for conceptual Digital Twin (DT) technology in Internet of Things (IoT)-based human monitoring systems, underscoring its role in revolutionizing rehabilitation strategies. Current studies emphasize the possibilities of the IoT and Digital Twin technologies across various sectors, including healthcare. However, given its use in real-time monitoring and follow-up of end-to-end rehabilitation programs, it is still emerging. Integrating Digital Twin into the existing IoT-based human movement monitoring system facilitates the handling of large amounts of data, supports analytics, and provides a platform for integrating additional services. This proposed framework incorporates inertia or wearable sensors to collect data on human activities during rehabilitation, utilizes fast Fourier transform for feature extraction, and employs advanced machine learning (ML) algorithms for activity recognition along with artificial intelligence (AI) for predictive analytics. Furthermore, it implements a data-driven virtual model at the cloud services that mirror the physical behaviors of IoT systems for enhanced real-time monitoring and tuning of the system based on personal requirements.