With advances in spatial–temporal Internet of Things (IoT) technologies, human activity recognition (HAR) has played a major role in human safety and medical health. Recently, most works focus on activity deep feature extraction, offering promising alternatives to manually engineered features. However, how to extract the effective and distinguishable continuity activity features and meanwhile reduce the heavy dependence on labels still remains the key challenge for HAR. This article proposes the human continuity activity semisupervised recognizing method in multiview IoT network scenarios. Our innovation combines supervised activity feature extraction with unsupervised encoder–decoder modules, which can capture continuity activity features from sensor data streams. To be more specific, our work applies a convolutional neural network (CNN) to capture the local dependence of sensor data and designs an encoder–decoder architecture to extract temporal features in an unsupervised manner. Then, we fuse these two features to recognize activities and train them with manual labels, thereby refining the temporal feature extraction and training CNN module. Experiments on five public data sets demonstrate the exceptional performance of our proposed method, which can achieve a higher recognition accuracy on almost all the data sets and is more robust and adaptive among different data sets.

中文翻译：

---

多视图物联网网络的人体连续性活动半监督识别模型


随着时空物联网（IoT）技术的进步，人类活动识别（HAR）在人类安全和医疗健康方面发挥了重要作用。最近，大多数工作都集中在活动深度特征提取上，为手动设计的特征提供了有前途的替代方案。然而，如何提取有效且可区分的连续性活动特征，同时减少对标签的严重依赖仍然是 HAR 的关键挑战。本文提出了多视图物联网网络场景下的人体连续性活动半监督识别方法。我们的创新将监督活动特征提取与无监督编码器解码器模块相结合，可以从传感器数据流中捕获连续性活动特征。更具体地说，我们的工作应用卷积神经网络（CNN）来捕获传感器数据的局部依赖性，并设计一个编码器-解码器架构来以无监督的方式提取时间特征。然后，我们融合这两个特征来识别活动并使用手动标签对其进行训练，从而改进时间特征提取和训练 CNN 模块。在五个公共数据集上的实验证明了我们提出的方法的卓越性能，它可以在几乎所有数据集上实现更高的识别精度，并且在不同数据集之间具有更强的鲁棒性和适应性。