Smart Plug Hub: A Sensor Fusion-Based Approach to Non-Invasive Activities of Daily Living Estimation

This paper presents Smart Plug Hub (SPH), a non-invasive system for accurately estimating a patient's Activities of Daily Living (ADL). Traditional methods for measuring ADL include interviews, remote video systems, and behavior-tracking wearable devices. However, these approaches have limitations, such as patient memory dependency, privacy violations, and device management issues. To overcome these limitations, SPH utilizes sensor fusion to analyze time-series environmental signals and accurately estimate a patient's ADL. We also efficiently utilized computing resources by implementing "device collaboration" in SPH to receive event data and segment a portion of the time-series environmental signal. By segmenting the data into small segments, we extracted an analyzable dataset, which was processed by an edge device. We conducted several experiments with SPH and successfully classified a patient's ADL by visualizing different activities. This study proposes an effective approach to analyzing both emergency situations and ADL, which is critical for accurate clinical decision-making.