Deep learning based fall detection using smartwatches for healthcare applications

• Published in: Biomedical signal processing and control Vol. 71; p. 103242
• Main Authors: Şengül, Gökhan, Karakaya, Murat, Misra, Sanjay, Abayomi-Alli, Olusola O., Damaševičius, Robertas
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.01.2022
• Subjects: Activity recognition; Digital health; Fall detection; Smartwatch; Activity recognition; Digital health; Fall detection; Smartwatch
• ISSN: 1746-8094; 1746-8108
• DOI: 10.1016/j.bspc.2021.103242

•Bica cubic Hermite interpolation based data augmentation method allows to handle imbalanced data problem.•A fusion accelerometer and gyroscope data features allows achieving higher performance.•Bi-directional long short-term memory neural network allows effective recognition of human activities. We implement a smart watch-based system to predict fall detection. We differentiate fall detection from four common daily activities: sitting, squatting, running, and walking. Moreover, we separate falling into falling from a chair and falling from a standing position. We develop a mobile application that collects the acceleration and gyroscope sensor data and transfers them to the cloud. In the cloud, we implement a deep learning algorithm to classify the activity according to the given classes. To increase the number of data samples available for training, we use the Bica cubic Hermite interpolation, which allows us to improve the accuracy of the neural network. The 38 statistical data features were calculated using the rolling update approach and used as input to the classifier. For activity classification, we have adopted the bi-directional long short-term memory (BiLSTM) neural network. The results demonstrate that our system can detect falling with an accuracy of 99.59% (using leave-one-activity-out cross-validation) and 97.35% (using leave-one-subject-out cross-validation) considering all activities. When considering only binary classification (falling vs. all other activities), perfect accuracy is achieved.