The increasing demand for motion tracking systems has been accelerated by advancements in virtual reality (VR) and motion reconstruction technologies. Combined with emerging innovations in the Internet of Things (IoT), these systems have unlocked transformative applications, from immersive user experiences to personalized healthcare solutions. However, conventional motion tracking systems often fall short of delivering sophisticated tracking and feedback capabilities, while systems designed for detailed motion analysis are typically costly and limited to controlled environments. This study introduces a cost-effective motion tracking system that integrates full-body motion analysis with real-time, bidirectional haptic feedback. Utilizing flexible, patch-type epidermal haptic devices alongside a remote machine‑learning framework, the system captures full‑body motion and delivers personalized, time‑synchronized feedback. Its closed‑loop design lays the groundwork for real‑time bidirectional haptic cues that accommodate user responsiveness and engagement.

Epidermally mounted sensors using triaxial accelerometers have been previously used to monitor physiological processes with the implementation of machine learning (ML) algorithm interfaces. The findings from these previous studies have established a strong foundation for the analysis of high-resolution, intricate signals, typically through frequency domain conversion. In this study we integrate a wireless mechano-acoustic sensor with a multi-modal deep learning system for the real-time analysis of signals emitted by the laryngeal prominence area of the thyroid cartilage at frequency ranges up to 1 kHz. This interface provides real-time data visualization and communication with the ML server, creating a system that assesses severity of chronic obstructive pulmonary disease and analyzes the user’s speech patterns.