Deep Learning based Activity Recognition for Sensor Data

Deep Learning based Activity Recognition for Sensor Data

游智翔(Chih-Hsiang Yu)

指導教授 ： 江振國

國立中正大學/工學院/資訊工程學系/碩士(2016年)

並列摘要

In our method, a Multipath Convolutional Neural Network (MP-CNN) is
proposed for activity recognition using sensor data. It consists of
two novel components: Dynamic Convolutional Neural Network (D-CNN)
and a State Transition Probabilities CNN (S-CNN). In D-CNN, Gaussian
Mixture Models (GMM) is exploited to capture the distribution of
sensor data for each activity. Then, input signal and the GMMs are
screened into different segments. These form multiple paths in the
CNN. S-CNN uses a modified LZW algorithm to extract the transition
probabilities of hidden states as discriminate features. Then, D-CNN
and S-CNN are combined to build the MP-CNN. Experimental results on
several activity recognition datasets demonstrate the superior
performance of MP-CNN.

並列關鍵字

Deep learning ； activity recognition ； sensor data

參考文獻

[2] S. Chennuru, P.-W. Chen, J. Zhu, and J. Zhang, Mobile lifelogger recording, index-

[3] P. Wu, J. Zhu, and J. Y. Zhang, Mobisens: A versatile mobile sensing platform for

tivity classi cation using realistic data from wearable sensors," IEEE Transactions

on Information Technology in Biomedicine, vol. 10, pp. 119{128, Jan 2006.

the IEEE Engineering in Medicine and Biology Society, pp. 4451{4454, Aug 2008.