Dynamic convolutional neural network for activity recognition

In this paper, a novel Dynamic Convolutional Neural Network (D-CNN) is proposed using sensor data for activity recognition. Sensor data collected for activity recognition is usually not well-aligned. It may also contains noises and variations from different persons. To overcome these challenges, Gaussian Mixture Models (GMM) is exploited to capture the distribution of each activity. Then, sensor data and the GMMs are screened into different segments. These segments form multiple paths in the Convolutional Neural Network. During testing, Gaussian Mixture Regression (GMR) is applied to dynamically fit segments of test signals into corresponding paths in the CNN. Experimental results demonstrate the superior performance of D-CNN to other learning methods.