Abstract
Human activity recognition using smartphone has been attracting great interest. Since collecting large amount of labeled data is expensive and time-consuming for conventional machine learning techniques, transfer learning techniques have been proposed for activity recognition. However, existing transfer learning techniques typically rely on feature matching based on global domain shift and lack considering the intra-class knowledge transfer. In this paper, a novel transfer learning technique is proposed for cross-domain activity recognition, which can properly integrate feature matching and instance reweighting across the source and target domain in principled dimensionality reduction. The experiments using three real datasets demonstrate that the proposed scheme can achieve much higher precision (92%), recall (91%), and F1-score (92%), in comparison with the existing schemes.
Similar content being viewed by others
References
Cao L et al., (2017) “ActiRecognizer: Design and implementation of a real-time human activity recognition system,” In: International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, pp. 266–271
Malwade S (2018) Mobile and wearable technologies in healthcare for the ageing population. Comput Methods Progr Biomed 161:233–237
Incel OD, Ozgovde A (2018) ARService: A smartphone based crowd-sourced data collection and activity recognition framework. Procedia computer sci 130:1019–1024
Ahmadi-Karvigh S (2018) Real-time activity recognition for energy efficiency in buildings. Appl Energ 2110:146–160
Hsu YL et al (2018) Human daily and sport activity recognition using a wearable inertial sensor network. IEEE Access 6:31715–31728
Weiss GM et al., (2016) Smartwatch-based activity recognition: A machine learning approach, In: IEEE-EMBS International Conference on Biomedical and Health Informatics, pp. 426–429
Cvetković B et al (2018) Real-time activity monitoring with a wristband and a smartphone. Inf Fusion 43:77–93
Li F et al (2018) Comparison of feature learning methods for human activity recognition using wearable sensors. Sensors 18(3):679. https://doi.org/10.3390/s18020679
Yuan G et al (2019) An overview of human activity recognition based on smartphone. Sens Rev 39:288–306
Suresh S, Jain M, Ramadoss R, (2019) “Fall classification based on sensor data from smartphone and smartwatch,” In: AIP Conference Proceedings, vol. 2112, pp. 020075
Mejia-Ricart LF, Helling P, Olmsted A, (2017) “Evaluate action primitives for human activity recognition using unsupervised learning approach,” In: 12th International Conference for Internet Technology and Secured Transactions, pp. 186–188
Ahmed N, Rafiq JI, Islam MR (2020) Enhanced human activity recognition based on smartphone sensor data using hybrid feature selection model. Sensors 20(1):317
Tiwary M et al (2018) Response time optimization for cloudlets in Mobile Edge Computing. J Parallel Distrib Comput 119:81–91
Chen X, Xue H, Kim M, Wang C, and Youn HY, (2019) Detection of falls with smartphone using machine learning technique, In: 8th International Congress on Advanced Applied Informatics, pp. 611–616
Zhao Z, Chen Y, Liu J, Shen Z, Liu M (2011) Cross-people mobilephone based activity recognition. IJCAI 11:2545–2550
Khan MAAH, and Roy N, (2017) Transact: Transfer learning enabled activity recognition, In: PerCom Workshops, pp. 545– 550
Feuz KD, and Cook DJ, (2017) Collegial activity learning between heterogeneous sensors, Knowledge and Information Systems, pp. 1–28
Nater F et al (2011) Transferring activities: Updating human behavior analysis, In IEEE International Conference on Computer Vision Workshops, pp. 1737–1744
Yang J, Yan R, Hauptmann AG (2007) “Cross-domain video concept detection using adaptive svms,” In Proceedings of the 15th ACM International Conference on Multimedia, pp. 188–197
Bruzzone L, Marconcini M (2009) Domain adaptation problems: A DASVM classification technique and a circular validation strategy. IEEE trans pattern analysis machine intelligence 32(5):770–787. https://doi.org/10.1109/TPAMI.2009.57
Chen M, Weinberger KQ, Blitzer J (2011) “Co-training for domain adaptation,” In Advances in neural information processing systems, pp. 2456–2464
Chu WS, De la Torre F, Cohn JF (2013) “Selective transfer machine for personalized facial action unit detection,” In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3515–3522
Duan L, Xu D, Tsang IWH, Luo J (2011) Visual event recognition in videos by learning from web data. IEEE Trans Pattern Anal Mach Intell 34(9):1667–1680
D. H. Hu, and Q. Yang, (2011) “Transfer learning for activity recognition via sensor mapping,” In Twenty-Second International Joint Conference on Artificial Intelligence
Hachiya H, Sugiyama M, Ueda N (2012) Importance-weighted least-squares probabilistic classifier for covariate shift adaptation with application to human activity recognition. Neurocomputing 80:93–101
Venkatesan A, Krishnan NC, and Panchanathan S, (2010) “Cost-sensitive boosting for concept drift,” In: International workshop on handling concept drift in adaptive information systems, pp. 41–47
Freund Y, Schapire RE (1997) A decision-theoretic generalization of on-line learning and an application to boosting. J Comput Syst Sci 55:119–139
Zheng VW , Hu DH, Yang Q, (2009) “Cross-domain activity recognition,” In: Proceedings of the 11th International Conference on Ubiquitous Computing, pp. 61–70
Long M, et al., (2014) Transfer Feature Learning with Joint Distribution Adaptation, In: IEEE International Conference on Computer Vision, pp. 2200–2207
Wang J et al., (2017) Balanced Distribution Adaptation for Transfer Learning, In: IEEE International Conference on Data Mining. IEEE Computer Society, pp. 1129–1134
Pan SJ et al (2010) Domain adaptation via transfer component analysis. IEEE Trans Neural Netw 22:199–210
J. Wang, et al., (2018) Stratified transfer learning for cross-domain activity recognition, In: IEEE International Conference on Pervasive Computing and Communications, pp. 1–10
Long M, Wang J, Ding X, Sun J, Yu PS (2014) “Transfer joint matching for unsupervised domain adaptation,” In Proceedings of the IEEE Conference On Computer Vision And Pattern Recognition, pp. 1410–1417
Reyes-Ortiz JL, Oneto L, Samà A, Parra X, Anguita D (2015) UCI public dataset. https://archive.ics.uci.edu/ml/datasets/SmartphoneBased+Recognition+of+Human+Activities+and+Postural+Transitions
Vavoulas G, Pediaditis M, Chatzaki C, Spanakis EG, Tsiknakis M (2014) The mobifall dataset: Fall detection and classification with a smartphone. Int J Monit Surveill Technol Res 2(1):44–56
Figueiredo IN et al (2016) Exploring smartphone sensors for fall detection. mUX: The Journal Of Mobile User Experience 5(1):1–7. https://doi.org/10.1186/s13678-016-0004-1
Vallabh P et al., (2016) Fall detection using machine learning algorithms, In: 24th International Conference on Software, Telecommunications and Computer Networks , pp. 1–9
Sousa Lima W (2019) Human activity recognition using inertial sensors in a smartphone: An overview. Sensors 19(14):3213. https://doi.org/10.3390/s19143213
Liang S et al (2018) Research on recognition of nine kinds of fine gestures based on adaptive AdaBoost algorithm and multi-feature combination. IEEE Access 7:3235–3246
Entropy (2020) In Wikipedia. https://en.wikipedia.org/w/index.php?title=Entropy&oldid=952435473
Gretton A et al (2012) A kernel two-sample test. J Mach Learn Res 13(1):723–773
Borgwardt KM et al (2006) Integrating structured biological data by kernel maximum mean discrepancy. Bioinformatics 22:e49–e57
Schölkopf B, Smola A, Müller KR (1998) Nonlinear component analysis as a kernel eigenvalue problem. Neural Comput 10:1299–1319
Frobenius Norm (2018) In Wikipedia. https://en.wikipedia.org/w/index.php?title=Frobenius_norm&oldid=829464654
Centroid (2020) In Wikipedia. https://en.wikipedia.org/w/index.php?title=Centroid&oldid=949341879
Euclidean Distance (2020) In Wikipedia. https://en.wikipedia.org/w/index.php?title=Euclidean_distance&oldid=953821598
Wang J, Chen Y, Hao S, (2017) Balanced distribution adaptation for transfer learning, In: IEEE International Conference on Data Mining, pp. 1129–1134
Oguntala GA et al (2019) SmartWall: Novel RFID-enabled ambient human activity recognition using machine learning for unobtrusive health monitoring. IEEE Access 7:68022–68033. https://doi.org/10.1109/ACCESS.2019.2917125
Medrano C, Igual R, Plaza I, Castro M (2014) Detecting falls as novelties in acceleration patterns acquired with smartphones. PLoS ONE 9(4):e94811
Acknowledgements
This work was partly supported by Institute for Information & communications Technology Promotion(IITP) grant funded by the Korea government(MSIT) (No.2016-000133, Research on Edge computing via collective intelligence of hyper-connection IoT nodes), Korea, under the National Program for Excellence in SW supervised by the IITP (Institute for Information & communications Technology Promotion)(2015-0-00914), Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education, Science and Technology (2017R1A2B2009095, Research on SDN-based WSN Supporting Real-time Stream Data Processing and Multi-connectivity, 2019R1I1A1A01058780, Efficient Management of SDN-based Wireless Sensor Network Using Machine Learning Technique), the second Brain Korea 21 PLUS project.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Chen, X., Kim, K. & Youn, H. Feature matching and instance reweighting with transfer learning for human activity recognition using smartphone. J Supercomput 78, 712–739 (2022). https://doi.org/10.1007/s11227-021-03844-y
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11227-021-03844-y