An IoT-based framework for remote fall monitoring. (May 2021)

• Record Type: Journal Article
• Authors: Al-Kababji, Ayman; Amira, Abbes; Bensaali, Faycal; Jarouf, Abdulah; Shidqi, Lisan; Djelouat, Hamza
• Is Part Of: Biomedical signal processing and control. Volume 67(2021)
• Publication Date: 2021-05
• Subjects: 00-01 -- 99-00; Wearable sensing device -- 3-axis accelerometer -- Feature extraction algorithm selection -- CWT -- Mobile application; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2021.102532
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: Thorough literature review on previously implemented systems. Presentation of a novel system accompanied by mobile application development. Investigation of multiple feature extraction and machine learning algorithms. A focus on Continuous Wavelet Transform (CWT) and its significance. Classifiers implemented on MATLAB where KNN and ENN are showing excellent results. Abstract: Fall detection is a serious healthcare issue that needs to be solved. Falling without quick medical intervention would lower elderly's chances of survival, especially if living alone. Hence, the need is there for developing fall detection algorithms with high accuracy. This paper presents a novel IoT-based system for fall detection that includes a sensing device transmitting data to a mobile application through a cloud-connected gateway device. Then, the focus is shifted to the algorithmic aspect where multiple features are extracted from 3-axis accelerometer data taken from existing datasets. The results emphasize on the significance of Continuous Wavelet Transform (CWT) as an influential feature for determining falls. CWT, Signal Energy (SE), Signal Magnitude Area (SMA), and Signal Vector Magnitude (SVM) features have shown promising classification results using K-Nearest Neighbors (KNN) and E-Nearest Neighbors (ENN). For all performance metrics (accuracy, recall, precision, specificity, and F 1 score), the achieved results are higher than 95% for a dataset of small size, while more than 98.47% score is achieved in the aforementioned criteria over the UniMiB-SHAR dataset by the same algorithms, where the classification time for a single test record is extremely efficient and is real-time.