Research on Human Activity Recognition with Multiple Contexts by Using Random Forest

doi:10.13474/j.cnki.11-2246.2017.0218

Abstract

Abstract: Previous research has verified the effectiveness of a method which utilizes multiple contexts including temporal, spatial, spatiotemporal and user from smartphone sensors to recognize human activities. But it has limitation in classification accuracy performance when recognizing human activity on smartphones by using naïve Bayes. This paper presents an improving research work on recognizing activity by utilizing a random forest algorithm in ensemble learning instead of original naïve Bayes under the same framework. The result of a ten-fold cross-validation experiment on three subjects' datasets shows that the weighted average F1 measures are improved by using random forest. However, the training time efficiency measures are worse than naive Bayes because of the complex structure of random forest. Meanwhile, the confusion matrix shows that the main factors for classification error are activity definition and indoor positioning error.

Key words: activity recognition, context awareness, machine learning, random forest, smartphone sensors

CLC Number:

P237

LIU Keqiang, WANG Yunjia, CHEN Ruizhi, CHU Tianxing. Research on Human Activity Recognition with Multiple Contexts by Using Random Forest[J]. 测绘通报, 2017, 0(7): 29-33,44.

References

[1] LARA O D, LABRADOR M A. A Survey on Human Activity Recognition Using Wearable Sensors[J]. IEEE Communications Surveys & Tutorials, 2013, 15(3):1192-1209.
[2] INCEL O D, KOSE M, ERSOY C. A Review and Taxonomy of Activity Recognition on Mobile Phones[J]. BioNanoScience, 2013, 3(2):145-171.
[3] SU X, TONG H, JI P. Activity Recognition with Smartphone Sensors[J]. Tsinghua Science and Technology, 2014, 19(3):235-249.
[4] CHEN R, CHU T, LIU K, et al. Inferring Human Activity in Mobile Devices by Computing Multiple Contexts[J]. Sensors, 2015, 15(9):21219-21238.
[5] COSKUN D, INCEL O D, OZGOVDE A. Phone Position/Placement Detection Using Accelerometer:Impact on Activity Recognition[C]//IEEE Tenth International Conference on Intelligent Sensors, Sensor Networks and Information Processing.[S.l.]:IEEE, 2015:1-6.
[6] DASH Y, KUMAR S, PATLE V K. A Novel Data Mining Scheme for Smartphone Activity Recognition by Accelerometer Sensor[C]//Proceedings of the 4th International Conference on Frontiers in Intelligent Computing:Theory and Applications (FICTA) 2015.[S.l.]:Springer India, 2016.
[7] GUO J, ZHOU X, SUN Y, et al. Smartphone-based Patients' Activity Recognition by Using a Self-learning Scheme for Medical Monitoring[J]. Journal of medical systems, 2016, 40(6):1-14.
[8] 周博翔,李平,李莲.改进随机森林及其在人体姿态识别中的应用[J].计算机工程与应用,2015, 51(16):86-92.
[9] HO T K. Random Decision Forests[C]//International Conference on Document Analysis and Recognition.[S.l.]:IEEE, 1995:278-282.
[10] BREIMAN L. Random Forests[J]. Machine learning, 2001, 45(1):5-32.
[11] 郭玉宝, 池天河, 彭玲,等. 利用随机森林的高分一号遥感数据进行城市用地分类[J]. 测绘通报, 2016(5):73-76.
[12] HALL M, FRANK E, HOLMES G, et al. The Weka Data Mining Software:An Update[J]. ACM SIGKDD Explorations Newsletter, 2009, 11(1):10-18.

[1]	KONG Ruiyao, XIE Tao, MA Ming, KONG Ruilin. Application of CatBoost model in water depth inversion [J]. Bulletin of Surveying and Mapping, 2022, 0(7): 33-37.
[2]	WEN Yuxiao, Lü Jie, MA Qingxun, ZHANG Peng, XU Ruling. Study on inversion of forest biomass by LiDAR and hyperspectral [J]. Bulletin of Surveying and Mapping, 2022, 0(7): 38-42.
[3]	Lü Zheng, SUN Qun, WEN Bowei, MA Jingzhen. A self-global-best-fit road network Stroke generation method [J]. Bulletin of Surveying and Mapping, 2022, 0(7): 93-99.
[4]	YU Zongqiao, WANG Yuhong, LIU Wensong, ZUO Yufang, FENG Feng. Flood extent extraction method based on the texture features of GF-3 images [J]. Bulletin of Surveying and Mapping, 2022, 0(5): 26-31.
[5]	DOU Shiqing, CHEN Zhiyu, XU Yong, ZHENG Hegang, MIAO Linlin, SONG Yingying. Hyperspectral image classification based on multi-feature fusion and dimensionality reduction algorithms [J]. Bulletin of Surveying and Mapping, 2022, 0(4): 32-36,50.
[6]	ZHANG Chi, BAI Zhihui, LI Liang, CHEN Ranli, WU Kan. Deformation monitoring of bridge structure in mining area using 3D laser scanning technology [J]. Bulletin of Surveying and Mapping, 2022, 0(4): 122-129.
[7]	FENG Zhili, XIAO Feng, LU Xiaoping, HAO Bo, WANG Ruyi, ZHU Rui. Winter wheat classification method based on feature optimization of random forest [J]. Bulletin of Surveying and Mapping, 2022, 0(3): 70-75.
[8]	WANG Gang, DING Huaxiang. Recognition of vegetation types in Leizhou Peninsula based on Sentinel-2A data [J]. Bulletin of Surveying and Mapping, 2022, 0(3): 76-82.
[9]	ZHANG Ziqiang, LIU Tao, DU Ping, SUO Xuhong, YANG Guolin. Classification of building group patterns using graph residual neural network [J]. Bulletin of Surveying and Mapping, 2022, 0(1): 1-7.
[10]	GAO Yu, HU Zhaoling, FAN Ru. Effect of high-resolution image fusion algorithm on the classification precision of land utilization in coastal wetland [J]. Bulletin of Surveying and Mapping, 2022, 0(1): 116-120.
[11]	LI Jun, SANG Xiao, ZHANG Chengye, ZHAO Wei, LIU Xinhua, WANG Hongpeng, WANG Jinyang, LI Jiayao, YANG Ying. Analysis of soil moisture content changes in resource-based cities over a long time series: a case study of Xilinhot city [J]. Bulletin of Surveying and Mapping, 2021, 0(7): 17-22,38.
[12]	LIU Maohua, LI Manwen. Urban road extraction with fusion of high-resolution images and LiDAR data [J]. Bulletin of Surveying and Mapping, 2021, 0(6): 1-5,60.
[13]	GU Chunxia, LI Dacheng. Application of spatio-temporal fusion technology in time series classification of regional land cover [J]. Bulletin of Surveying and Mapping, 2021, 0(5): 20-24.
[14]	YE Yexing, YANG Fei. Caculation of traffic congestion index based on betweenness centrality [J]. Bulletin of Surveying and Mapping, 2021, 0(5): 86-90.
[15]	SU Meichen, WEI Xiaoyan, ZHOU Junsong, WANG Yiqin. Analysis and prediction of landslide susceptibility in Jinsha River [J]. Bulletin of Surveying and Mapping, 2021, 0(4): 13-16.