基于智能手机感知的人体运动状态深度识别

doi:10.13190/j.jbupt.2018-221

北京邮电大学学报 ›› 2019, Vol. 42 ›› Issue (3): 43-50.doi: 10.13190/j.jbupt.2018-221

基于智能手机感知的人体运动状态深度识别

殷晓玲^1,2, 夏启寿^1,2, 陈晓江¹, 何娟¹, 陈峰¹

1. 西北大学信息科学与技术学院, 西安 710127;
2. 池州学院数学与计算机学院, 安徽 247000

收稿日期:2018-09-09 出版日期:2019-06-28 发布日期:2019-06-20
作者简介:殷晓玲(1975-),女,副教授,E-mail:xqs@czu.edu.cn.
基金资助:
国家自然科学基金青年基金项目（61602382）；陕西省创新团队基金项目（2018TD-026）；安徽省高校自然科学研究资助项目（KJ2015A290，KJ2017A579）

In-Depth Recognition of Human Motion States Based on Smart Phone Perception

YIN Xiao-ling^1,2, XIA Qi-shou^1,2, CHEN Xiao-jiang¹, HE Juan¹, CHEN Feng¹

1. School of Information Science and Technology, Northwest University, Xi'an 710127, China;
2. College of Mathematics and Computer Science, Chizhou University, Chizhou 247000, China

Received:2018-09-09 Online:2019-06-28 Published:2019-06-20

摘要/Abstract

摘要： 为提高智能手机对人体运动状态识别的准确率，提出一种基于并联卷积神经网络（PCNN）的深度识别方法.首先，使用三维数据矩阵规范传感器数据输入格式；其次，使用2个PCNN分别对人体运动的加速度传感器和陀螺仪数据进行卷积和池化操作，实现部分权重共享；最后，在全连接层对两组卷积神经网络进行合并，并使用softmax函数对人体运动状态进行分类.实验结果表明，采用该方法可以从传感器原始数据中提取人体运动状态的深层特征，与传统的机器学习方法相比较，提高了运动状态的识别率.

关键词: 运动状态, 深度识别, 智能手机, 并联卷积神经网络

Abstract: In order to improve the accuracy of recognition of human motion states by smart phones, an in-depth recognition method based on parallel convolution neural network (PCNN) is proposed. Firstly, the sensor data input format is standardized by using 3D data matrix. Secondly, two PCNNs are used to carry out convolution and pool operation to the acceleration sensor and gyroscope data of human body motion respectively, realizing partial weight sharing. Finally, the two PCNNs are merged in the full-connected layer, and the softmax function is used to classify the human motion states. Experiments show that this method can extract the deep features of human motion states from the original data of the sensor, which can improve the recognition rate of the motion state by comparing with the traditional machine learning method.

Key words: motion states, in-depth recognition, smart phones, parallel convolution neural network

中图分类号:

殷晓玲, 夏启寿, 陈晓江, 何娟, 陈峰. 基于智能手机感知的人体运动状态深度识别[J]. 北京邮电大学学报, 2019, 42(3): 43-50.

YIN Xiao-ling, XIA Qi-shou, CHEN Xiao-jiang, HE Juan, CHEN Feng. In-Depth Recognition of Human Motion States Based on Smart Phone Perception[J]. JOURNAL OF BEIJING UNIVERSITY OF POSTS AND TELECOM, 2019, 42(3): 43-50.

参考文献

[1] Cornacchia M, Ozcan K, Zheng Y, et al.A survey on activity detection and classification using wearable sensors[J].IEEE Sensors Journal, 2016, 17(2):386-403.
[2] Matthews C E, George S M, Moore S C, et al.Amount of time spent in sedentary behaviors and cause-specific mortality in us adults[J].American Journal of Clinical Nutrition, 2012, 95(2):437.
[3] Katzmarzyk P T, Lee I.Sedentary behaviour and life expectancy in the USA:a cause-deleted life table analysis[J].BMJ Open, 2012, 2(4):808-816.
[4] Camhi S M, Sisson S B, Johnson W D, et al.Accelerometer-determined moderate intensity lifestyle activity and cardiometabolic health[J].Preventive Medicine, 2011, 52(5):358-360.
[5] Figo D, Diniz P C, Ferreira D R, et al.Preprocessing techniques for context recognition from accelerometer data[J].Personal & Ubiquitous Computing, 2010, 14(7):645-662.
[6] Chen Z H, Zhu Q C, Yeng C S, et al.Robust human activity recognition using smartphone sensors via CT-PCA and online SVM[J].IEEE Transactions on Industrial Informatics, 2017, 13(6):3070-3080.
[7] Wang Aiguo, Chen Guilin, Yang Jing, et al.A comparative study on human activity recognition using inertial sensors in a smartphone[J].IEEE Sensors Journal, 2016, 16(11):4566-4578.
[8] 李亚, 王广润, 王青.基于深度卷积神经网络的跨年龄人脸识别[J].北京邮电大学学报, 2017, 40(1):84-88.Li Ya, Wang Guangrun, Wang Qing.A deep joint learning approach for age invariant face verification[J].Journal of Beijing University of Posts and Telecommunications, 2017, 40(1):84-88.
[9] Sheeba P T, Murugan S.Hybrid features-enabled dragon deep belief neural network for activity recognition[J].The Imaging Science Journal, 2018, 66(6):355-371.
[10] Cheng F C, Zhang H, Fan W J, et al.Image recognition technology based on deep learning[J].Wireless Personal Communications, 2018(C):1-17.
[11] Ronao C A, Cho S B.Human activity recognition with smartphone sensors using deep learning neural networks[J].Expert Systems with Applications, 2016(59):235-244.
[12] Tao Dapeng, Wen Y G, Hong Richang.Multi-column bi-directional long short-term memory for mobile devices-based human activity recognition[J].IEEE Internet of Things Journal, 2016, 3(6):1124-1134.
[13] Ordóñez F J, Roggen D.Deep convolutional and lstm recurrent neural networks for multimodal wearable activity recognition[J].Sensors, 2016, 16(1):115-140.
[14] Chen Z H, Zhang L, Cao Z G, et al.Distilling the knowledge from handcrafted features for human activity recognition[J].IEEE Transactions on Industrial Informatics, 2018, 14(10):4334-4342.
[15] Alejandro B, Yago S, Pedro I.Evolutionary design of convolutional neural networks for human activity recognition in sensor-rich environments[J].Sensors, 2018, 18(4):1288-1312.
[16] Sheng Min, Jiang Jing, Su Benyue, et al.Short-time activity recognition with wearable sensors using convolutional neural network[C]//ACM SIGGRAPH Conference on Virtual-Reality Continuum and Its Applications in Industry.New York:ACM, 2016:413-416.
[17] Lee S M, Yoon S M, Cho H.Human activity recognition from accelerometer data using convolutional neural network[C]//IEEE International Conference on Big Data and Smart Computing.Jeju:IEEE, 2017:131-134.
[18] 沈延斌, 陈岭, 郭浩东, 等.基于深度学习的放置方式和位置无关运动识别[J].浙江大学学报(工学版), 2016, 50(6):1141-1148.Shen Yanbin, Chen Ling, Guo Haodong, et al.Deep learning based activity recognition independent of device orientation and placement[J].Journal of Zhejiang University (Engineering Science), 2016, 50(6):1141-1148.
[19] Bagct U, Bai L.A comparison of daubechies and gabor wavelets for classification of MR images[C]//IEEE International Conference on Signal Processing and Communications.Dubai:IEEE, 2008:676-679.
[20] Liu Cihang, Zhang Lan, Liu Zongqian, et al.Lasagna:towards deep hierarchical understanding and searching over mobile sensing data[C]//International Conference on Mobile Computing and Networking.New York:ACM, 2016:334-347.
[21] Simonyan K, Zisserman A.Very deep convolutional networks for large-scale image recognition[EB/OL].(2015-04-10)[2018-08-20].https://arxiv.org/pdf/1409.1556.pdf.
[22] Kwapisz J R, Weiss G M, Moore S A.Activity recognition using cell phone accelerometers[J].ACM Sigkdd Explorations Newsletter, 2011, 12(2):74-82.
[23] 李锋, 潘敬奎.基于三轴加速度传感器的人体运动识别[J].计算机研究与发展, 2016, 53(3):621-631.Li Feng, Pan Jingkui.Human motion recognition based on triaxial accelerometer[J].Journal of Computer Research and Development, 2016, 53(3):621-631.
[24] Xia Qishou, Ying Xiaoling, He Juan, et al.Real-time recognition of human daily motion with smartphone sensor[J].International Journal of Performability Engineering, 2018, 14(4):593-602.

基于智能手机感知的人体运动状态深度识别

In-Depth Recognition of Human Motion States Based on Smart Phone Perception

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	张天魁蔡昌利骆晓亮朱禹涛. 基于多尺度特征Transformer的细粒度图像分类方法[J]. 北京邮电大学学报, 2023, 46(4): 70-75.
[2]	包乾辉文娟石淑珍董萌萍刘雪. 融合句法依存与 BERT-Att-BiLSTM 的属性分类[J]. 北京邮电大学学报, 2023, 46(4): 123-128.
[3]	周雨昊孙哲吴晓非禹可. 基于门控特征融合的中文错别字纠正模型[J]. 北京邮电大学学报, 2023, 46(4): 91-96,122.
[4]	苏兴禹可吴晓非. 基于层次门控交互融合网络的谣言检测方法[J]. 北京邮电大学学报, 2023, 46(4): 97-102.
[5]	张涛马春梅. 面向异构时序数据基于关键帧动态采样的行为识别研究[J]. 北京邮电大学学报, 0, (): 0-0.
[6]	杨杰张书杰. 基于密集YOLOv3的印刷电路板缺陷识别[J]. 北京邮电大学学报, 2022, 45(5): 42-48.
[7]	刘绍华孙靖凯王奕苏刘海波毛天露. 一种多精度交互的行人轨迹预测[J]. 北京邮电大学学报, 2022, 45(5): 1-6.
[8]	刘金桐, 杨国兴, 刘晓鸿, 王光宇. 针对心电图分类模型的平滑攻击算法[J]. 北京邮电大学学报, 2022, 45(4): 44-50.
[9]	黄柳婷, 刘可欣, 牛凯, 常春, 贺志强. 基于深度学习的哮喘患者CT影像黏液栓自动识别[J]. 北京邮电大学学报, 2022, 45(4): 58-63.
[10]	武兴坤, 罗涛, 刘爱军, 杨明, 张文静. 面向主动脉缩窄辅助诊断的神经网络模型设计[J]. 北京邮电大学学报, 2022, 45(4): 1-6.
[11]	谢攀, 彭才静, 何志慧, 张远. 一种融合分组卷积和半监督的睡眠分期方法[J]. 北京邮电大学学报, 2022, 45(4): 7-12.
[12]	李星原, 汪鹏, 申牧, 李蕾, 张琳. 癫痫病相关论文多模态知识图谱的构建初探[J]. 北京邮电大学学报, 2022, 45(4): 19-24.
[13]	武兴坤罗涛刘爱军杨明张文静李剑峰李文秀. 面向主动脉缩窄辅助诊断的神经网络模型设计[J]. 北京邮电大学学报, 2022, 45(4): 1-6.
[14]	李星原汪鹏申牧李蕾张琳. 癫痫领域多模态知识图谱的构建初探[J]. 北京邮电大学学报, 2022, 45(4): 21-27.
[15]	田亮, 潘鹏, 刘玉敏. 基于神经网络的纳米光子结构逆设计[J]. 北京邮电大学学报, 2022, 45(3): 112-116.