Beijing Kupei Sports Culture Corporation Limited, Beijing, China.
Institute of Artificial Intelligence in Sports, Capital University of Physical Education and Sports, Beijing, China.
J Med Internet Res. 2024 Aug 5;26:e56750. doi: 10.2196/56750.
Fall detection is of great significance in safeguarding human health. By monitoring the motion data, a fall detection system (FDS) can detect a fall accident. Recently, wearable sensors-based FDSs have become the mainstream of research, which can be categorized into threshold-based FDSs using experience, machine learning-based FDSs using manual feature extraction, and deep learning (DL)-based FDSs using automatic feature extraction. However, most FDSs focus on the global information of sensor data, neglecting the fact that different segments of the data contribute variably to fall detection. This shortcoming makes it challenging for FDSs to accurately distinguish between similar human motion patterns of actual falls and fall-like actions, leading to a decrease in detection accuracy.
This study aims to develop and validate a DL framework to accurately detect falls using acceleration and gyroscope data from wearable sensors. We aim to explore the essential contributing features extracted from sensor data to distinguish falls from activities of daily life. The significance of this study lies in reforming the FDS by designing a weighted feature representation using DL methods to effectively differentiate between fall events and fall-like activities.
Based on the 3-axis acceleration and gyroscope data, we proposed a new DL architecture, the dual-stream convolutional neural network self-attention (DSCS) model. Unlike previous studies, the used architecture can extract global feature information from acceleration and gyroscope data. Additionally, we incorporated a self-attention module to assign different weights to the original feature vector, enabling the model to learn the contribution effect of the sensor data and enhance classification accuracy. The proposed model was trained and tested on 2 public data sets: SisFall and MobiFall. In addition, 10 participants were recruited to carry out practical validation of the DSCS model. A total of 1700 trials were performed to test the generalization ability of the model.
The fall detection accuracy of the DSCS model was 99.32% (recall=99.15%; precision=98.58%) and 99.65% (recall=100%; precision=98.39%) on the test sets of SisFall and MobiFall, respectively. In the ablation experiment, we compared the DSCS model with state-of-the-art machine learning and DL models. On the SisFall data set, the DSCS model achieved the second-best accuracy; on the MobiFall data set, the DSCS model achieved the best accuracy, recall, and precision. In practical validation, the accuracy of the DSCS model was 96.41% (recall=95.12%; specificity=97.55%).
This study demonstrates that the DSCS model can significantly improve the accuracy of fall detection on 2 publicly available data sets and performs robustly in practical validation.
跌倒检测对于保障人类健康具有重要意义。通过监测运动数据，跌倒检测系统（FDS）可以检测到跌倒事故。最近，基于可穿戴传感器的 FDS 已成为研究的主流，可分为基于经验的阈值 FDS、基于手动特征提取的机器学习 FDS 和基于自动特征提取的深度学习（DL）FDS。然而，大多数 FDS 主要关注传感器数据的全局信息，忽略了数据的不同段对跌倒检测的贡献程度不同这一事实。这一缺点使得 FDS 难以准确区分实际跌倒和类似跌倒的动作之间的相似人类运动模式，从而降低了检测精度。
本研究旨在开发和验证一种基于可穿戴传感器的加速度计和陀螺仪数据的 DL 框架，以准确检测跌倒。我们旨在探索从传感器数据中提取的区分跌倒与日常生活活动的基本贡献特征。本研究的意义在于通过设计使用 DL 方法的加权特征表示来改革 FDS，从而有效地区分跌倒事件和类似跌倒的活动。
基于三轴加速度计和陀螺仪数据，我们提出了一种新的 DL 架构，即双流卷积神经网络自注意力（DSCS）模型。与以往的研究不同，所使用的架构可以从加速度计和陀螺仪数据中提取全局特征信息。此外，我们还引入了自注意力模块，为原始特征向量分配不同的权重，使模型能够学习传感器数据的贡献效果，提高分类精度。该模型在两个公共数据集上进行了训练和测试：SisFall 和 MobiFall。此外，还招募了 10 名参与者对 DSCS 模型进行实际验证。共进行了 1700 次试验，以测试模型的泛化能力。
DSCS 模型在 SisFall 和 MobiFall 测试集上的跌倒检测准确率分别为 99.32%（召回率=99.15%；准确率=98.58%）和 99.65%（召回率=100%；准确率=98.39%）。在消融实验中，我们将 DSCS 模型与最先进的机器学习和 DL 模型进行了比较。在 SisFall 数据集上，DSCS 模型的准确率排名第二；在 MobiFall 数据集上，DSCS 模型的准确率、召回率和精度均为最佳。在实际验证中，DSCS 模型的准确率为 96.41%（召回率=95.12%；特异性=97.55%）。
本研究表明，DSCS 模型可以显著提高两个公开可用数据集上的跌倒检测准确性，并在实际验证中表现稳健。
