Rahemtulla Zahra, Turner Alexander, Oliveira Carlos, Kaner Jake, Dias Tilak, Hughes-Riley Theodore
Nottingham School of Art & Design, Nottingham Trent University, Bonington Building, Dryden Street, Nottingham NG1 4GG, UK.
School of Computer Science, University of Nottingham, Jubilee Campus, Wollaton Road, Nottingham NG8 1BB, UK.
Materials (Basel). 2023 Feb 25;16(5):1920. doi: 10.3390/ma16051920.
Falls can be detrimental to the quality of life of older people, and therefore the ability to detect falls is beneficial, especially if the person is living alone and has injured themselves. In addition, detecting near falls (when a person is imbalanced or stumbles) has the potential to prevent a fall from occurring. This work focused on the design and engineering of a wearable electronic textile device to monitor falls and near-falls and used a machine learning algorithm to assist in the interpretation of the data. A key driver behind the study was to create a comfortable device that people would be willing to wear. A pair of over-socks incorporating a single motion sensing electronic yarn each were designed. The over-socks were used in a trial involving 13 participants. The participants performed three types of activities of daily living (ADLs), three types of falls onto a crash mat, and one type of near-fall. The trail data was visually analyzed for patterns, and a machine learning algorithm was used to classify the data. The developed over-socks combined with the use of a bidirectional long short-term memory (Bi-LSTM) network have been shown to be able to differentiate between three different ADLs and three different falls with an accuracy of 85.7%, ADLs and falls with an accuracy of 99.4%, and ADLs, falls, and stumbles (near-falls) with an accuracy of 94.2%. In addition, results showed that the motion sensing E-yarn only needs to be present in one over-sock.
跌倒会对老年人的生活质量产生不利影响，因此具备检测跌倒的能力是有益的，尤其是当老人独自生活且已受伤时。此外，检测险些跌倒（即人失去平衡或绊倒的情况）有可能预防跌倒的发生。这项工作聚焦于可穿戴电子织物设备的设计与工程，用于监测跌倒和险些跌倒情况，并使用机器学习算法辅助数据解读。该研究背后的一个关键驱动力是打造一款人们愿意佩戴的舒适设备。设计了一双每只都包含一根运动感应电子纱线的套袜。这双套袜在一项涉及13名参与者的试验中使用。参与者进行了三种日常生活活动（ADL）、三种在防撞垫上的跌倒类型以及一种险些跌倒类型。对试验数据进行了可视化模式分析，并使用机器学习算法对数据进行分类。已证明，所开发的套袜结合双向长短期记忆（Bi-LSTM）网络，能够以85.7%的准确率区分三种不同的日常生活活动和三种不同的跌倒情况，以99.4%的准确率区分日常生活活动和跌倒情况，以及以94.2%的准确率区分日常生活活动、跌倒和绊倒（险些跌倒）情况。此外，结果表明运动感应电子纱线只需存在于一只套袜中。
