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.

[1]  Geoffrey E. Hinton.  Learning multiple layers of representation , 2007, Trends in Cognitive Sciences.

[2]  Niels Henze,et al.  Gesture recognition with a Wii controller , 2008, TEI.

[3]  Geoffrey E. Hinton.  A Practical Guide to Training Restricted Boltzmann Machines , 2012, Neural Networks: Tricks of the Trade.

[4]  Daqing Zhang,et al.  Gesture Recognition with a 3-D Accelerometer , 2009, UIC.

[5]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[6]  Yoshua Bengio,et al.  Greedy Layer-Wise Training of Deep Networks , 2006, NIPS.

[7]  Jeen-Shing Wang,et al.  An Accelerometer-Based Digital Pen With a Trajectory Recognition Algorithm for Handwritten Digit and Gesture Recognition , 2012, IEEE Transactions on Industrial Electronics.

[8]  Yoshua. Bengio,et al.  Learning Deep Architectures for AI , 2007, Found. Trends Mach. Learn..

[9]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[10]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[11]  Jani Mäntyjärvi,et al.  Online gesture recognition system for mobile interaction , 2003, SMC'03 Conference Proceedings. 2003 IEEE International Conference on Systems, Man and Cybernetics. Conference Theme - System Security and Assurance (Cat. No.03CH37483).

[12]  Razvan Pascanu,et al.  Theano: Deep Learning on GPUs with Python , 2012 .

[13]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[14]  Irccyn,et al.  Tenth international workshop on frontiers in handwriting recognition , 2006 .

[15]  Timo Pylvänäinen,et al.  Accelerometer Based Gesture Recognition Using Continuous HMMs , 2005, IbPRIA.

[16]  Biing-Hwang Juang,et al.  A new 6D motion gesture database and the benchmark results of feature-based statistical recognition , 2012, 2012 IEEE International Conference on Emerging Signal Processing Applications.

[17]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[18]  Tanja Schultz,et al.  Airwriting recognition using wearable motion sensors , 2010, AH.

[19]  Dong Yoon Kim,et al.  Two-stage Recognition of Raw Acceleration Signals for 3-D Gesture-Understanding Cell Phones , 2005 .

[20]  Zhen Wang,et al.  uWave: Accelerometer-based Personalized Gesture Recognition and Its Applications , 2009, PerCom.