School of Electronic Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China.
Beijing Vocational College of Transport, Beijing 102618, China.
Sensors (Basel). 2024 Aug 22;24(16):5450. doi: 10.3390/s24165450.
This study introduces an innovative approach by incorporating statistical offset features, range profiles, time-frequency analyses, and azimuth-range-time characteristics to effectively identify various human daily activities. Our technique utilizes nine feature vectors consisting of six statistical offset features and three principal component analysis network (PCANet) fusion attributes. These statistical offset features are derived from combined elevation and azimuth data, considering their spatial angle relationships. The fusion attributes are generated through concurrent 1D networks using CNN-BiLSTM. The process begins with the temporal fusion of 3D range-azimuth-time data, followed by PCANet integration. Subsequently, a conventional classification model is employed to categorize a range of actions. Our methodology was tested with 21,000 samples across fourteen categories of human daily activities, demonstrating the effectiveness of our proposed solution. The experimental outcomes highlight the superior robustness of our method, particularly when using the Margenau-Hill Spectrogram for time-frequency analysis. When employing a random forest classifier, our approach outperformed other classifiers in terms of classification efficacy, achieving an average sensitivity, precision, F1, specificity, and accuracy of 98.25%, 98.25%, 98.25%, 99.87%, and 99.75%, respectively.
本研究提出了一种创新方法，将统计偏移特征、距离-方位-时间剖面图、时频分析和方位-距离-时间特征相结合，以有效识别各种人类日常活动。我们的技术利用了由六个统计偏移特征和三个主成分分析网络（PCANet）融合属性组成的九个特征向量。这些统计偏移特征是从俯仰和方位的组合数据中提取的，考虑了它们的空间角度关系。融合属性是通过同时使用 CNN-BiLSTM 的一维网络生成的。该过程从 3D 距离-方位-时间数据的时间融合开始，然后进行 PCANet 集成。随后，使用传统的分类模型对各种动作进行分类。我们的方法在十四个人类日常活动类别中，使用了 21000 个样本进行了测试，验证了我们提出的解决方案的有效性。实验结果突出了我们方法的卓越鲁棒性，特别是在使用 Margenau-Hill 频谱进行时频分析时。当使用随机森林分类器时，我们的方法在分类效果方面优于其他分类器，其平均灵敏度、精度、F1 值、特异性和准确性分别为 98.25%、98.25%、98.25%、99.87%和 99.75%。
