Motion Sequence Recognition with Multi-sensors Using Deep Convolutional Neural Network

With the rapid development of intelligent devices, motion recognition methods are broadly used in many different occasions. Most of them are based on several traditional machine learning models or their variants, such as Dynamic Time Warping, Hidden Markov Model or Support Vector Machine. Some of them could achieve a relatively high classification accuracy but with a time-consuming training process. Some other models are just the opposite. In this paper, we propose a novel designed deep Convolutional Neural Network (DBCNN) model using "Data-Bands" as input to solve the motion sequence recognition task with a higher accuracy in less training time. Contrast experiments were conducted between DBCNN and several baseline methods and the results demonstrated that our model could outperform these state-of-art models.