围栏的人类活动识别优化算法

doi:10.19665/j.issn1001-2400.2019.01.015

摘要/Abstract

摘要：

为了有效地检测围栏上的人类活动,对已有的使用神经网络的围栏人类活动识别系统进行了优化,提出多级识别、多节点融合判断等优化算法。多级识别算法通过初级识别排除掉了大量无活动时的背景数据,降低了上传的数据量,提升了下一级的识别准确率;多节点融合算法通过融合地理位置相邻的节点的识别结果,提升了结果的可靠性。基于小型围栏环境的实地数据,通过实验仿真验证了算法的有效性。优化算法的数据传输速率、数据传输总量都远小于基准算法;多节点融合算法去除掉了67.7%的冗余识别结果。

关键词: 惯性传感器, 围栏, 人类活动检测, 神经网络

Abstract:

In order to effectively recognize the human activities on a fence, we optimize the original human activity recognition system by proposing two algorithms: multi-level classification and multi-node fusion. The multi-level classification algorithm eliminates background data without activities in first level classification, reduces the amount of transferred data, and improves the accuracy of the next level. The multi-node fusion algorithm improves the reliability of the results by merging the recognition results of the neighboring nodes. Based on the data of experimental environment, the effectiveness of the algorithm is verified. The data transfer rate and data transmission amount of the multi-level classification algorithm are much lower than those of the benchmark algorithm. The multi-node fusion algorithm removes the redundancy recognition results by up to 67.7%.

Key words: inertial sensor, fence, human activity recognition, neural network

中图分类号:

TP391

胡科路,王营冠. 围栏的人类活动识别优化算法[J]. 西安电子科技大学学报, 2019, 46(1): 93-97.

HU Kelu,WANG Yingguan. Fence human activity recognition optimized algorithm[J]. Journal of Xidian University, 2019, 46(1): 93-97.

图/表 5

参考文献 18

[1]	WITTENBURG G, TERFLOTH L, VILLAFUERTE F L, et al. Fence Monitoring: Experimental Evaluation of a Use Case for Wireless Sensor Networks [C]// Lecture Notes in Computer Science: 4373 LNCS. Heidelberg: Springer Verlag, 2007: 163-178.
[2]	YOUSEFI A, BERGER T W. Intelligent Fence Intrusion Detection System: Detection of Intentional Fence Breaching and Recognition of Fence Climbing [C]// Proceedings of the 2008 IEEE Conference on Technologies for Homeland Security. Piscataway: IEEE, 2008: 620-625.
[3]	DZIENGEL N, ZIEGERT M, ADLER S, et al. Energy-aware Distributed Fence Surveillance for Wireless Sensor Networks [C]// Proceedings of the 2011 7th International Conference on Intelligent Sensors, Sensor Networks and Information Processing. Washington: IEEE Computer Society, 2011: 353-358.
[4]	TAKAGI R, HORISAKI R, TANIDA J . Object Recognition through a Multi-mode Fiber[J]. Optical Review, 2017,24(2) : 117-120. doi: 10.1007/s10043-017-0303-5
[5]	PAVEY T G, GILSON N D, GOMERSALL S R , et al. Field Evaluation of a Random Forest Activity Classifier for Wrist-worn Accelerometer data[J]. Journal of Science & Medicine in Sport, 2017,20(1):75-80. doi: 10.1016/j.jsams.2016.06.003 pmid: 27372275
[6]	SHCHERBINA A , et al. Accuracy in Wrist-worn, Sensor-based Measurements of Heart Rate and Energy Expenditure in a Diverse Cohort[J]. Journal of Personalized Medicine, 2017,7(2):3. doi: 10.3390/jpm7020003 pmid: 28538708
[7]	RUEDA F M, GRZESZICK R, FINK G A , et al. Convolutional Neural Networks for Human Activity Recognition Using Body-worn Sensors[J/OL]. [2018-05-20]. DOI: 10.3390/informatics 5020026.
[8]	SINGH D, MERDIVAN E, PSYCHOULA I , et al. Human Activity Recognition Using Recurrent Neural Networks[M/OL]. [2018-05-20]. DOI: 10.1007/978-3-319-66808-6_18.
[9]	ZEBIN T, SCULLY P J, OZANYAN K B . Human Activity Recognition with Inertial Sensors Using a Deep Learning Approach[J/OL]. [2018-05-20]. DOI: 10.1109/ICSENS. 2016. 7808590.
[10]	RAVI D, WONG C, LO B, et al. Deep Learning for Human Activity Recognition: a Resource Efficient Implementation on Low-power Devices [C]//Proceedings of the 2016 IEEE International Conference on Wearable and Implantable Body Sensor Networks. Piscataway: IEEE, 2016: 71-76.
[11]	SCHEURER S, TEDESCO S, BROWN K N, et al. Human Activity Recognition for Emergency First Responders via Body-worn Inertial Sensors [C]//Proceedings of the 2017 IEEE 14th International Conference on Wearable and Implantable Body Sensor Networks. Piscataway: IEEE, 2017: 5-8.
[12]	LIU F T, WANG Y T, MA H P. Gesture Recognition with Wearable 9-axis Sensors [C]//Proceedings of the 2017 IEEE International Conference on Communications. Piscataway: IEEE, 2017: 1-6.
[13]	COOPER K, SANI S, CORRIGN L , et al. Accuracy of Physical Activity Recognition from a Wrist-worn Sensor[J]. Physiotherapy, 2017,103:e47.
[14]	CHENG L, GUAN Y, ZHU K C, et al. Recognition of Human Activities Using Machine Learning Methods with Wearable Sensors [C]//Proceedings of the 2017 IEEE 7th Annual Computing and Communication Workshop and Conference. Piscataway: IEEE, 2017: 1-7.
[15]	LIU L, LUO G, QIN K , et al. An Algorithm Based on Logistic Regression with Data Fusion in Wireless Sensor Networks[J]. Journal of Wireless Com Network, 2017,2017(1):10. doi: 10.1186/s13638-016-0793-z
[16]	JAVADI S H, PEIRAVI A . Fusion of Weighted Decisions in Wireless Sensor Networks[J/OL]. [2018-03-20]. DOI: 10.1049/iet-wss.2013.0116.
[17]	EL ABBASSI M A, JILBAB A, BOUROUHOU A . A Robust Model of Multi-sensor Data Fusion Applied in Wireless Sensor Networks for Fire Detection[J]. International Review on Modelling and Simulations, 2016,9:173. doi: 10.15866/iremos.v9i3.8558
[18]	LANDGREBE D . A Survey of Decision Tree Classifier Methodology[J]. IEEE Transactions on Systems Man and Cybernetics, 2002,21(3):660-674. doi: 10.1109/21.97458

活动类型	基准算法		优化算法
活动类型	准确率	召回率	准确率	召回率
踢	91.1	94.0	94.0	95.6
拍	91.1	90.0	95.4	94.6
靠	93.9	91.6	95.3	94.6
无	97.0	97.5	100.0	100.0