Deep activity recognition on imaging sensor data.

Inspired by the recent success of deep learning (DL) approaches in computer vision domain, this Letter proposes a framework to encode the sensor data into an image representation for the activity recognition task. The signal from sensors is encoded based on the Gramian Angular Field. The encoding technique increases the dimension of the data, captures a local temporal relationship in terms of temporal correlation between time intervals on the geometric interpretation, and can be easily applied to the pre-trained DL architecture. The proposed framework is examined with respect to six popular sensor-based activity recognition datasets. Using the authors' framework, the results show that their approach outperforms most of the state-of-the-art approaches. [ABSTRACT FROM AUTHOR]