Cross-Country Skiing Gears Classification using Deep Learning

Human Activity Recognition has witnessed a significant progress in the last decade. Although a great deal of work in this field goes in recognizing normal human activities, few studies focused on identifying motion in sports. Recognizing human movements in different sports has high impact on understanding the different styles of humans in the play and on improving their performance. As deep learning models proved to have good results in many classification problems, this paper will utilize deep learning to classify cross-country skiing movements, known as gears, collected using a 3D accelerometer. It will also provide a comparison between different deep learning models such as convolutional and recurrent neural networks versus standard multi-layer perceptron. Results show that deep learning is more effective and has the highest classification accuracy.

[1]  Hiroki Tamura,et al.  Development of a motion analysis system using acceleration sensors for tennis and its evaluations , 2011, Artificial Life and Robotics.

[2]  Jürgen Schmidhuber,et al.  Learning Precise Timing with LSTM Recurrent Networks , 2003, J. Mach. Learn. Res..

[3]  Trevor Darrell,et al.  Long-term recurrent convolutional networks for visual recognition and description , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  M. Gams,et al.  Comparing Deep and Classical Machine Learning Methods for Human Activity Recognition using Wrist Accelerometer , 2016 .

[5]  Erik Andersson,et al.  Automatic Classification of the Sub-Techniques (Gears) Used in Cross-Country Ski Skating Employing a Mobile Phone , 2014, Sensors.

[6]  Ching-Yu Yang,et al.  A Sport Recognition Method with Utilizing Less Motion Sensors , 2014, ICGEC.

[7]  Billur Barshan,et al.  Recognizing Daily and Sports Activities in Two Open Source Machine Learning Environments Using Body-Worn Sensor Units , 2014, Comput. J..

[8]  Sung-Bae Cho,et al.  Mobile Gesture Recognition Using Hierarchical Recurrent Neural Network with Bidirectional Long Short-Term Memory , 2012 .

[9]  Zhaozheng Yin,et al.  Human Activity Recognition Using Wearable Sensors by Deep Convolutional Neural Networks , 2015, ACM Multimedia.

[10]  Jürgen Schmidhuber,et al.  Framewise phoneme classification with bidirectional LSTM and other neural network architectures , 2005, Neural Networks.

[11]  Xiaoli Li,et al.  Deep Convolutional Neural Networks on Multichannel Time Series for Human Activity Recognition , 2015, IJCAI.

[12]  Daniel Roggen,et al.  Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition , 2016, Sensors.

[13]  Thomas Plötz,et al.  Deep, Convolutional, and Recurrent Models for Human Activity Recognition Using Wearables , 2016, IJCAI.

[14]  Bo Yu,et al.  Convolutional Neural Networks for human activity recognition using mobile sensors , 2014, 6th International Conference on Mobile Computing, Applications and Services.

[15]  Nasser Kehtarnavaz,et al.  A survey of depth and inertial sensor fusion for human action recognition , 2015, Multimedia Tools and Applications.

[16]  Wei Xie,et al.  A Multi-classifier Combination Method Using SFFS Algorithm for Recognition of 19 Human Activities , 2016, ICCSA.

[17]  Anders Holst,et al.  Classification of movement patterns in skiing , 2013, SCAI.

[18]  Yuwen Chen,et al.  LSTM Networks for Mobile Human Activity Recognition , 2016 .

[19]  Sung-Bae Cho,et al.  Human activity recognition with smartphone sensors using deep learning neural networks , 2016, Expert Syst. Appl..