Wandering is a significant indicator in the clinical diagnosis of dementia and other related diseases for elders. Reliable monitoring of long-term continuous movement in indoor setting for detection of wandering movement is challenging because most elders are prone to forget to carry or wear sensors that collect motion information daily due to their declining memory. Wi-Fi as an emerging sensing modality has been widely used to monitor human indoor movement in a non-invasive manner. In order to continuously monitor individuals’ indoor motion and reliably identify wandering movement in a non-invasive manner, in this work, we develop a LSTM-based deep classification method that is able to differentiate the wandering-caused Wi-Fi signal change from the others. Specifically, we first use the off-the-shelf Wi-Fi devices to capture a resident’s indoor motion information, enabling to collect a group of Wi-Fi signal streams, which will be split into variable-size segments. Second, the deep network LSTM is adopted to develop wandering detection method that is able to classify every variable-size segment of Wi-Fi signals into categories according to the well-known wandering spatiotemporal patterns. Last, experimental evaluation conducted on a group of real-world Wi-Fi signal streams shows that our proposed LSTM-based detection method is workable and effective to identify indoor wandering behavior, obtaining an average value of 0.9286, 0.9618, 0.9634 and 0.9619 for accuracy, precision, recall and F-1 score, respectively.

流浪是老年痴呆症及其他相关疾病临床诊断的重要指标。在室内环境中对长期连续运动进行可靠监测以检测游走运动具有挑战性，因为大多数老年人由于记忆力下降而容易忘记携带或佩戴每天收集运动信息的传感器。Wi-Fi 作为一种新兴的传感方式，已被广泛用于以非侵入性方式监测人体室内运动。为了持续监测个人的室内运动并以非侵入性的方式可靠地识别游走运动，在这项工作中，我们开发了一种基于 LSTM 的深度分类方法，能够区分游走引起的 Wi-Fi 信号变化和其他。具体来说，我们首先使用现成的 Wi-Fi 设备来捕获居民的室内运动信息，从而能够收集一组 Wi-Fi 信号流，这些信号流将被分成可变大小的段。其次，采用深度网络 LSTM 开发了漫游检测方法，该方法能够根据众所周知的漫游时空模式将 Wi-Fi 信号的每个可变大小段分类。最后，对一组真实世界的 Wi-Fi 信号流进行的实验评估表明，我们提出的基于 LSTM 的检测方法在识别室内游走行为方面是可行且有效的，准确率的平均值为 0.9286、0.9618、0.9634 和 0.9619 、准确率、召回率和 F-1 分数。这将被分成可变大小的段。其次，采用深度网络 LSTM 开发了漫游检测方法，该方法能够根据众所周知的漫游时空模式将 Wi-Fi 信号的每个可变大小段分类。最后，对一组真实世界的 Wi-Fi 信号流进行的实验评估表明，我们提出的基于 LSTM 的检测方法在识别室内游走行为方面是可行且有效的，准确率的平均值为 0.9286、0.9618、0.9634 和 0.9619 、准确率、召回率和 F-1 分数。这将被分成可变大小的段。其次，采用深度网络 LSTM 开发了漫游检测方法，该方法能够根据众所周知的漫游时空模式将 Wi-Fi 信号的每个可变大小段分类。最后，对一组真实世界的 Wi-Fi 信号流进行的实验评估表明，我们提出的基于 LSTM 的检测方法在识别室内游走行为方面是可行且有效的，准确率的平均值为 0.9286、0.9618、0.9634 和 0.9619 、准确率、召回率和 F-1 分数。