A Novel Fall Detection Framework Using Skip-DSCGAN Based on Inertial Sensor Data

作     者：Kun Fang Julong Pan Lingyi Li Ruihan Xiang 

作者机构：College of Information EngineeringChina Jiliang UniversityHangzhou310018China 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2024年第78卷第1期

页      面：493-514页

核心收录：

学科分类：08[工学] 0837[工学-安全科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported partly by the Natural Science Foundation of Zhejiang Province China(LGF21F020017) 

主　　题：Fall detection skip-connection depthwise separable convolution generative adversarial networks inertial sensor 

摘      要：With the widespread use of Internet of Things(IoT)technology in daily life and the considerable safety risks of falls for elderly individuals,research on IoT-based fall detection systems has gainedmuch *** paper proposes an IoT-based spatiotemporal data processing framework based on a depthwise separable convolution generative adversarial network using skip-connection(Skip-DSCGAN)for fall *** method uses spatiotemporal data from accelerometers and gyroscopes in inertial sensors as input data.A semisupervised learning approach is adopted to train the model using only activities of daily living(ADL)data,which can avoid data imbalance ***,a quantile-based approach is employed to determine the fall threshold,which makes the fall detection frameworkmore *** proposed fall detection framework is evaluated against four other generative adversarial network(GAN)models with superior anomaly detection performance using two fall public datasets(SisFall&MobiAct).The test results show that the proposed method achieves better results,reaching 96.93% and 92.75% accuracy on the above two test datasets,*** the same time,the proposed method also achieves satisfactory results in terms ofmodel size and inference delay time,making it suitable for deployment on wearable devices with limited *** addition,this paper also compares GAN-based semisupervised learning methods with supervised learning methods commonly used in fall *** clarifies the advantages of GAN-based semisupervised learning methods in fall detection.