基于卷积神经网络的活动识别分析系统及应用
Activity Recognition Analysis System and Application Based on Convolutional Neural Network

DOI: 10.12677/CSA.2020.109179, PP. 1690-1697

Keywords: 活动识别，卷积神经网络，卡路里消耗
Activity Recognition, Convolutional Neural Networks, Calorie Consumption

Full-Text   Cite this paper   Add to My Lib

Abstract:

活动识别技术在智能家居、运动评估和社交等领域得到广泛应用。本文设计了一种基于卷积神经网络的活动识别分析与应用系统，通过分析基于Android搭建的前端采所集的三向加速度传感器数据，对用户的当前活动进行识别。实验表明活动识别准确率满足了应用需求。本文基于识别的活动进行卡路里消耗计算，根据用户具体的活动、时间以及体重计算出相应活动在相应时间内具体消耗的卡路里消耗，有助于建立健康生活模式。
Activity recognition technology has got widely used in smart home, sports assessment, social contact and other fields. This paper designs an activity recognition analysis and application system based on convolution neural network. By analyzing the data of three-way accelerometer collected in Android devices, the current activities of a user are identified. Experiments show that the accuracy of activity recognition meets the requirement of application. This paper calculates calorie expenditure based on identified activities, and calculates calorie expenditure based on a user’s specific activities according to time and weight for the corresponding activities in the corresponding time, which helps to establish a healthy lifestyle.

References

[1]	张洋, 姚登峰. 人类的行为识别分类方法综述[C]. 中国计算机用户协会网络应用分会2019年第二十三届网络新技术与应用年会论文集. 2019.
[2]	Kao, H.-L., Ho, B.J., Lin, A.C. and Chu, H.H. (2012) Phone-Based Gait Analysis to Detect Alcohol Usage. Proceedings of the 2012 ACM Conference on Ubiquitous Computing, Pittsburgh, September 2012, 661-662. https://doi.org/10.1145/2370216.2370354
[3]	Ordó？ez, F.J. and Roggen, D. (2016) Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition. Sensors, 16, 115. https://doi.org/10.3390/s16010115
[4]	Zheng, J.C. and Li, N.M. (2013) An Unsupervised Learning Approach to Social Circles Detection in Ego Bluetooth Proximity Network. Proceedings of the 2013 ACM International Joint Con-ference on Pervasive and Ubiquitous Computing, Zurich, September 2013, 721-724. https://doi.org/10.1145/2493432.2493512
[5]	Xuan, B., Fan, S.C., et al. (2013) Your Reactions Suggest You Liked the Movie: Automatic Content Rating via Reaction Sensing. Proceedings of the 2013 ACM International Joint Conference on Pervasive and Ubiquitous Computing, Zurich, September 2013, 197-206. https://doi.org/10.1145/2493432.2493440
[6]	Hammerla, N.Y., et al. (2015) PD Disease State Assessment in Naturalistic Environments Using Deep Learning. Proceedings of the 29th AAAI Conference on Artificial Intelligence, Austin, January 2015, 1742-1748.
[7]	Pourbabaee, B., Roshtkhari, M.J. and Khorasani, K. (2017) Deep Convolution Neural Networks And Learning Ecg Features For Screening Paroxysmal Atrial Fibrillation Patients. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 48, 2095-2104.
[8]	Parlak, S., Marsic, I. and Burd, R. (2012) Activity Recognition for Emergency Care Using RFID. BODYNETS 2011—6th International ICST Conference on Body Area Networks, Brussels, November 2011, 40-46. https://doi.org/10.4108/icst.bodynets.2011.247213
[9]	Kwon, Y., Kang, K. and Bae, C. (2016) Evaluation of a Smartphone Human Activity Recognition Application with Able-Bodied and Stroke Participants. Journal of Neuro Engi-neering and Rehabilitation.
[10]	Capela, N.A., Lemaire, E.D., Baddour, N., Rudolf, M., Goljar, N. and Burger, H. (2016) Evaluation of a Smartphone Human Activity Recognition Application with Able-Bodied and Stroke Participants. Journal of NeuroEngineering and Rehabilitation, 13, Article No. 5. https://doi.org/10.1186/s12984-016-0114-0
[11]	Ghose, S., Mitra, J., et al. (2016) Human Activity Recognition from Smart-Phone Sensor Data Using a Multi-Class Ensemble Learning in Home Monitoring. IEEE International Con-ference on Healthcare Informatics, 214, 62-67.

Full-Text