Department of Computer Engineering, Mashhad Branch, Islamic Azad University, Mashhad 9187147578, Iran.
Int J Environ Res Public Health. 2022 Oct 22;19(21):13762. doi: 10.3390/ijerph192113762.
Many studies have used sensors attached to adults in order to collect signals by which one can carry out analyses to predict falls. In addition, there are research studies in which videos and photographs were used to extract and analyze body posture and body kinematics. The present study proposes an integrated approach consisting of body kinematics and machine learning. The model data consist of video recordings collected in the UP-Fall Detection dataset experiment. Three models based on long-short-term memory (LSTM) network-4p-SAFE, 5p-SAFE, and 6p-SAFE for four, five, and six parameters-were developed in this work. The parameters needed for these models consist of some coordinates and angles extracted from videos. These models are easy to apply to the sequential images collected by ordinary cameras, which are installed everywhere, especially on aged-care premises. The accuracy of predictions was as good as 98%. Finally, the authors discuss that, by applying these models, the health and wellness of adults and elderlies will be considerably promoted.
许多研究都使用成年人佩戴的传感器来收集信号，从而进行分析以预测跌倒。此外，还有一些研究使用视频和照片来提取和分析身体姿势和身体运动学。本研究提出了一种集成的方法，包括身体运动学和机器学习。模型数据由 UP-Fall Detection 数据集实验中的视频记录组成。这项工作中开发了三个基于长短期记忆 (LSTM) 网络的模型 - 4p-SAFE、5p-SAFE 和 6p-SAFE，用于四个、五个和六个参数。这些模型所需的参数包括从视频中提取的一些坐标和角度。这些模型易于应用于普通相机拍摄的连续图像，这些相机无处不在，特别是在老年人护理场所。预测的准确率高达 98%。最后，作者讨论了通过应用这些模型，可以极大地促进成年人和老年人的健康和福利。
