Attention-based Convolutional Neural Network for Weakly Labeled Human Activities Recognition with Wearable Sensors
This work addresses the time-consuming sensor data annotation process for human activity recognition, making data collection easier, though it is incremental as it builds on existing attention mechanisms.
The paper tackles the problem of human activity recognition from weakly labeled wearable sensor data by proposing an attention-based convolutional neural network that filters out background noise and focuses on labeled activities, achieving higher accuracy than classical deep learning methods.
Unlike images or videos data which can be easily labeled by human being, sensor data annotation is a time-consuming process. However, traditional methods of human activity recognition require a large amount of such strictly labeled data for training classifiers. In this paper, we present an attention-based convolutional neural network for human recognition from weakly labeled data. The proposed attention model can focus on labeled activity among a long sequence of sensor data, and while filter out a large amount of background noise signals. In experiment on the weakly labeled dataset, we show that our attention model outperforms classical deep learning methods in accuracy. Besides, we determine the specific locations of the labeled activity in a long sequence of weakly labeled data by converting the compatibility score which is generated from attention model to compatibility density. Our method greatly facilitates the process of sensor data annotation, and makes data collection more easy.