Enabling IoT for In-Home Rehabilitation: Accelerometer Signals Classification Methods for Activity and Movement Recognition

Abstract

Rehabilitation and elderly monitoring for active aging can benefit from Internet of Things (IoT) capabilities in particular for in-home treatments. In this paper, we consider two functions useful for such treatments: 1) activity recognition (AR) and 2) movement recognition (MR). The former is aimed at detecting if a patient is idle, still, walking, running, going up/down the stairs, or cycling; the latter individuates specific movements often required for physical rehabilitation, such as arm circles, arm presses, arm twist, curls, seaweed, and shoulder rolls. Smartphones are the reference platforms being equipped with an accelerometer sensor and elements of the IoT. The work surveys and compares accelerometer signals classification methods to enable IoT for the aforementioned functions. The considered methods are support vector machines (SVMs), decision trees, and dynamic time warping. A comparison of the methods has been proposed to highlight their performance: all the techniques have good recognition accuracies and, among them, the SVM-based approaches show an accuracy above 90% in the case of AR and above 99% in the case of MR

Healthcare 4.0: A review of frontiers in digital health

“…IoT wearable monitoring is an emerging area in Healthcare 4.0 and it is changing the way we capture and process our biological data. The application domain includes remote patient monitoring services, smart home (Alaa, Zaidan, Zaidan, Talal, & Kiah, 2017), hospital patient monitoring, rehabilitation (Bisio, Delfino, Lavagetto, & Sciarrone, 2017), self-tracking, performance sports (Camomilla, Bergamini, Fantozzi, & Vannozzi, 2018), and children, youths and elderly care (Misra, Mukherjee, & Roy, 2018). IoT wearable devices supported by AI-driven intelligent data processing techniques have great potential for early detection of physiological and behavioral changes and identify clinical episodes of several chronic diseases (A. R. M. Forkan, Khalil, Tari, Foufou, & Bouras, 2015).…”

Data Analytics in the Internet of Things: A Survey

“…Decision tree follows a greedy strategy to classify data items by arranging them based on attribute values. Example of IoT use case that utilized decision tree is activity and movement recognition [66].…”

Sensor‐based activity recognition independent of device placement and orientation

“…With the rapid development of microelectromechanical systems, sensor‐based human activity recognition (HAR) has been widely applied in many fields, such as medical, entertainment, military, education, etc . These applications take advantage of devices with variety of sensors on human body to obtain information of human behavior and action, then recognize human activity using preprocessed data and machine learning algorithms .…”