Evaluation of Deep Convolutional Neural Network Architectures for Human Activity Recognition with Smartphone Sensors

Feature extraction is the most vital and critical stage in performing effective activity recognition. On the other hand, deep learning, most especially convolutional neural networks (convnets), have garnered a lot of attention in recent years with its success in the image and speech domains because of its powerful feature extraction mechanism. In this paper, we utilize convnets to classify activities using time-series data collected from smartphone sensors and evaluate its different architectures. Experiments show that increasing the number of convolutional layers increases performance, but the complexity of the derived features decreases with every additional layer. Moreover, as opposed to blindly increasing the number of feature maps to improve performance, preserving the information passed from layer to layer is more important.

[1]  Dong Yu,et al.  Exploring convolutional neural network structures and optimization techniques for speech recognition , 2013, INTERSPEECH.

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

[3]  Yoshua Bengio,et al.  Convolutional networks for images, speech, and time series , 1998 .

[4]  Yoshua Bengio,et al.  Practical Recommendations for Gradient-Based Training of Deep Architectures , 2012, Neural Networks: Tricks of the Trade.

[5]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[6]  Yi Zheng,et al.  Time Series Classification Using Multi-Channels Deep Convolutional Neural Networks , 2014, WAIM.

[7]  Patrick Olivier,et al.  Feature Learning for Activity Recognition in Ubiquitous Computing , 2011, IJCAI.

[8]  Samuel Berlemont,et al.  3D gesture classification with convolutional neural networks , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[9]  Jesse Hoey,et al.  Sensor-Based Activity Recognition , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).