AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
Powered by AMiner. Clicking this button will take you away from SciOpen.
Home Journal of Computer Science and Technology Article
Article Link
Cite
EndNote(RIS) BibTeX
Collect
Submit Manuscript
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Regular Paper

FedIERF: Federated Incremental Extremely Random Forest for Wearable Health Monitoring

Chun-Yu Hu1,2,3,†, Li-Sha Hu4,†, Lin Yuan1,2, Dian-Jie Lu3,5, Lei Lyu3,5, Yi-Qiang Chen6( )
Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong ComputerScience Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academyof Sciences), Jinan 250353, China
Shandong Provincial Key Laboratory of Computer Networks, Shandong Fundamental Research Center for Computer Science, Jinan 250000, China
Shandong Provincial Key Laboratory for Novel Distributed Computer Software Technology, Jinan 250000, China
Institute of Information Technology, Hebei University of Economics and Business, Shijiazhuang 050061, China
School of Information Science and Engineering, Shandong Normal University, Jinan 250358, China
Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China

†Co-First Author (Chun-Yu Hu and Li-Sha Hu are both responsible for paper writing and algorithm design and implementation.)

Show Author Information

Abstract

Wearable health monitoring is a crucial technical tool that offers early warning for chronic diseases due to its superior portability and low power consumption. However, most wearable health data is distributed across different organizations, such as hospitals, research institutes, and companies, and can only be accessed by the owners of the data in compliance with data privacy regulations. The first challenge addressed in this paper is communicating in a privacy-preserving manner among different organizations. The second technical challenge is handling the dynamic expansion of the federation without model retraining. To address the first challenge, we propose a horizontal federated learning method called Federated Extremely Random Forest (FedERF). Its contribution-based splitting score computing mechanism significantly mitigates the impact of privacy protection constraints on model performance. Based on FedERF, we present a federated incremental learning method called Federated Incremental Extremely Random Forest (FedIERF) to address the second technical challenge. FedIERF introduces a hardness-driven weighting mechanism and an importance-based updating scheme to update the existing federated model incrementally. The experiments show that FedERF achieves comparable performance with non-federated methods, and FedIERF effectively addresses the dynamic expansion of the federation. This opens up opportunities for cooperation between different organizations in wearable health monitoring.

Keywords

federated learningincremental learningrandom forestwearable health monitoring

Electronic Supplementary Material

Download File(s)
JCST-2212-13009-Highlights.pdf (152.6 KB)

References

[1]
Chen Y Q, Huang M Y, Hu C Y, Zhu Y C, Han F, Miao C Y. A coarse-to-fine feature selection method for accurate detection of cerebral small vessel disease. In Proc. the 2016 International Joint Conference on Neural Networks, July 2016, pp.2609–2616. DOI: 10.1109/IJCNN.2016.7727 526.
Crossref
[2]

Chen Y Q, Hu C Y, Hu B, Hu L S, Yu H, Miao C Y. Inferring cognitive wellness from motor patterns. IEEE Trans. Knowledge and Data Engineering, 2018, 30(12): 2340–2353. DOI: 10.1109/TKDE.2018.2820024.
Crossref Google Scholar
[3]

Hu C Y, Chen Y Q, Peng X H, Yu H, Gao C L, Hu L S. A novel feature incremental learning method for sensor-based activity recognition. IEEE Trans. Knowledge and Data Engineering, 2019, 31(6): 1038–1050. DOI: 10.1109/TKDE.2018.2855159.
Crossref Google Scholar
[4]

Dias D, Cunha J P S. Wearable health devices-vital sign monitoring, systems and technologies. Sensors, 2018, 18(8): 2414. DOI: 10.3390/s18082414.
Crossref Google Scholar
[5]
Schauss G, Arquilla K, Anderson A. ARGONAUT: An inclusive design process for wearable health monitoring systems. In Proc. the 2022 CHI Conference on Human Factors in Computing Systems, Apr. 2022, Article No. 392. DOI: 10.1145/3491102.3517590.
Crossref
[6]

Zendehdel G A, Kaur R, Chopra I, Stakhanova N, Scheme E. Automated security assessment framework for wearable BLE-enabled health monitoring devices. ACM Trans. Internet Technology, 2022, 22(1): Article No. 14. DOI: 10.1145/ 3448649.
Crossref Google Scholar
[7]
Konečn y` J, McMahan H B, Yu F X, Richtárik P, Suresh A T, Bacon D. Federated learning: Strategies for improving communication efficiency. arXiv: 1610.05492, 2016. https://arxiv.org/abs/1610.05492, Sept. 2023.
[8]
Konečn y` J, McMahan H B, Ramage D, Richttárik P. Federated optimization: Distributed machine learning for on-device intelligence. arXiv: 1610.02527, 2016. https://arxiv.org/abs/1610.02527, Sept. 2023.
[9]

Nguyen D C, Pham Q V, Pathirana P N, Ding M, Seneviratne A, Lin Z H, Dobre O, Hwang W J. Federated learning for smart healthcare: A survey. ACM Computing Surveys, 2023, 55(3): Article No. 60. DOI: 10.1145/3501296.
Crossref Google Scholar
[10]
Ghods A. Creating interpretable data-driven approaches for remote health monitoring. In Proc. the 35th AAAI Conference on Artificial Intelligence, Feb. 2021, pp.15712–15713. DOI: 10.1609/aaai.v35i18.17853.
Crossref
[11]

Geurts P, Ernst D, Wehenkel L. Extremely randomized trees. Machine Learning, 2006, 63(1): 3–42. DOI: 10.1007/s10994-006-6226-1.
Crossref Google Scholar
[12]

Roebers C M, Röthlisberger M, Neuenschwander R, Cimeli P, Michel E, Jäger K. The relation between cognitive and motor performance and their relevance for children’s transition to school: A latent variable approach. Human Movement Science, 2014, 33: 284–297. DOI: 10.1016/j.humov.2013.08.011.
Crossref Google Scholar
[13]

Verlinden V J A, van der Geest J N, Hofman A, Ikram M A. Cognition and gait show a distinct pattern of association in the general population. Alzheimer’s & Dementia, 2014, 10(3): 328–335. DOI: 10.1016/j.jalz.2013.03.009.
Crossref Google Scholar
[14]

van der Fels I M J, te Wierike S C M, Hartman E, Elferink-Gemser M T, Smith J, Visscher C. The relationship between motor skills and cognitive skills in 4–16 year old typically developing children: A systematic review. Journal of Science and Medicine in Sport, 2015, 18(6): 697–703. DOI: 10.1016/j.jsams.2014.09.007.
Crossref Google Scholar
[15]

Tian X B, Deng Z H, Ying W H, Choi K S, Wu D R, Qin B, Wang J, Shen H B, Wang S T. Deep multi-view feature learning for EEG-based epileptic seizure detection. IEEE Trans. Neural Systems and Rehabilitation Engineering, 2019, 27(10): 1962–1972. DOI: 10.1109/TNSRE.2019.2940485.
Crossref Google Scholar
[16]
Jarchi D, Peters A, Lo B, Kalliolia E, Di Giulio I, Limousin P, Day B L, Yang G Z. Assessment of the e-AR sensor for gait analysis of Parkinson’s disease patients. In Proc. the 12th International Conference on Wearable and Implantable Body Sensor Networks, Jun. 2015. DOI: 10.1109/BSN.2015.7299396.
Crossref
[17]
Tian F, Fan X M, Fan J J, Zhu Y C, Gao J, Wang D K, Bi X J, Wang H A. What can gestures tell?: Detecting motor impairment in early Parkinson’s from common touch gestural interactions. In Proc. the 2019 CHI Conference on Human Factors in Computing Systems, May 2019, Article No. 83. DOI: 10.1145/3290605.3300313.
Crossref
[18]

Alberdi A, Weakley A, Schmitter-Edgecombe M, Cook D J, Aztiria A, Basarab A, Barrenechea M. Smart home-based prediction of multidomain symptoms related to Alzheimer’s disease. IEEE Journal of Biomedical and Health Informatics, 2018, 22(6): 1720–1731. DOI: 10.1109/JBHI.2018.2798062.
Crossref Google Scholar
[19]

Sun F M, Zang W L, Gravina R, Fortino G, Li Y. Gait-based identification for elderly users in wearable healthcare systems. Information Fusion, 2020, 53: 134–144. DOI: 10.1016/j.inffus.2019.06.023.
Crossref Google Scholar
[20]

Kos A, Umek A. Wearable sensor devices for prevention and rehabilitation in healthcare: Swimming exercise with real-time therapist feedback. IEEE Internet of Things Journal, 2019, 6(2): 1331–1341. DOI: 10.1109/JIOT.2018.2850664.
Crossref Google Scholar
[21]

EL Menshawy M, Benharref A, Serhani M. An automatic mobile-health based approach for EEG epileptic seizures detection. Expert Systems with Applications, 2015, 42(20): 7157–7174. DOI: 10.1016/j.eswa.2015.04.068.
Crossref Google Scholar
[22]

Hu C Y, Chen Y Q, Hu L S, Peng X H. A novel random forests based class incremental learning method for activity recognition. Pattern Recognition, 2018, 78: 277–290. DOI: 10.1016/j.patcog.2018.01.025.
Crossref Google Scholar
[23]

Qin Z, Zhang Y B, Meng S Y, Qin Z G, Choo K K R. Imaging and fusing time series for wearable sensor-based human activity recognition. Information Fusion, 2020, 53: 80–87. DOI: 10.1016/j.inffus.2019.06.014.
Crossref Google Scholar
[24]
Guo H D, Chen L, Peng L Y, Chen G C. Wearable sensor based multimodal human activity recognition exploiting the diversity of classifier ensemble. In Proc. the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing, Sept. 2016, pp.1112–1123. DOI: 10.1145/2971648.2971708.
Crossref
[25]

Xia Q X, Wada A, Korpela J, Maekawa T, Namioka Y. Unsupervised factory activity recognition with wearable sensors using process instruction information. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 2019, 3(2): Article No. 60. DOI: 10.1145/3328 931.
Crossref Google Scholar
[26]
McMahan H B, Moore E, Ramage D, Arcas B A Y. Federated learning of deep networks using model averaging. arXiv: 1602.05629, 2016. https://arxiv.org/abs/1602.05629v1, Sept. 2023.
[27]

Li Z, Bilal M, Xu X L, Jiang J L, Cui Y. Federated learning-based cross-enterprise recommendation with graph neural networks. IEEE Trans. Industrial Informatics, 2023, 19(1): 673–682. DOI: 10.1109/TII.2022.3203395.
Crossref Google Scholar
[28]

Chen H, Huang S C, Zhang D Y, Xiao M, Skoglund M, Poor H V. Federated learning over wireless IoT networks with optimized communication and resources. IEEE Internet of Things Journal, 2022, 9(17): 16592–16605. DOI: 10.1109/JIOT.2022.3151193.
Crossref Google Scholar
[29]

Yang Q, Liu Y, Chen T J, Tong Y X. Federated machine learning: Concept and applications. ACM Trans. Intelligent Systems and Technology, 2019, 10(2): Article No. 12. DOI: 10.1145/3298981.
Crossref Google Scholar
[30]
McMahan H B, Moore E, Ramage D, Hampson S, Arcas B A Y. Communication-efficient learning of deep networks from decentralized data. arXiv: 1602.05629, 2016. https://arxiv.org/abs/1602.05629, Sept. 2023.
[31]
Smith V, Chiang C K, Sanjabi M, Talwalkar A. Federated multi-task learning. In Proc. the 31st International Conference on Neural Information Processing Systems, Dec. 2017, pp.4427–4437. DOI: 10.5555/3294996.3295196.
[32]

Liu Y, Liu Y T, Liu Z J, Liang Y X, Meng C S, Zhang J B, Zheng Y. Federated forest. IEEE Trans. Big Data, 2022, 8(3): 843–854. DOI: 10.1109/TBDATA.2020.2992755.
Crossref Google Scholar
[33]

Cheng K W, Fan T, Jin Y L, Liu Y, Chen T J, Papadopoulos D, Yang Q. SecureBoost: A lossless federated learning framework. IEEE Intelligent Systems, 2021, 36(6): 87–98. DOI: 10.1109/MIS.2021.3082561.
Crossref Google Scholar
[34]

Chen Y Q, Qin X, Wang J D, Yu C H, Gao W. FedHealth: A federated transfer learning framework for wearable healthcare. IEEE Intelligent Systems, 2020, 35(4): 83–93. DOI: 10.1109/MIS.2020.2988604.
Crossref Google Scholar
[35]

Liu Y, Kang Y, Xing C P, Chen T J, Yang Q. A secure federated transfer learning framework. IEEE Intelligent Systems, 2020, 35(4): 70–82. DOI: 10.1109/MIS.2020.2988 525.
Crossref Google Scholar
[36]
Saffari A, Leistner C, Santner J, Godec M, Bischof H. On-line random forests. In Proc. the 12th International Conference on Computer Vision Workshops, Sept. 27–Oct. 4, 2009, pp.1393–1400. DOI: 10.1109/ICCVW.2009.5457447.
Crossref
[37]
Reiss A, Stricker D. Introducing a new benchmarked dataset for activity monitoring. In Proc. the 16th International Symposium on Wearable Computers, Jun. 2012, pp.108–109. DOI: 10.1109/ISWC.2012.13.
Crossref
[38]
Sztyler T, Stuckenschmidt H. On-body localization of wearable devices: An investigation of position-aware activity recognition. In Proc. the 2016 IEEE International Conference on Pervasive Computing and Communications, Mar. 2016. DOI: 10.1109/PERCOM.2016.7456521.
Crossref
[39]
Chavarriaga R, Sagha H, Calatroni A, Digumarti S T, Tröster, G, del R. Millán J, Roggen D. The Opportunity challenge: A benchmark database for on-body sensor-based activity recognition. Pattern Recognition Letters, 2013, 34(15): 2033–2042. DOI: 10.1016/j.patrec.2012.12.014.
Crossref
[40]
Reyes-Ortiz J, Anguita D, Ghio A, Oneto L, Parra X. Human activity recognition using smartphones. UCI Machine Learning Repository, 2012. DOI: 10.24432/C54S4K.
[41]

Barshan B, Yüksek M C. Recognizing daily and sports activities in two open source machine learning environments using body-worn sensor units. The Computer Journal, 2014, 57(11): 1649–1667. DOI: 10.1093/comjnl/bxt075.
Crossref Google Scholar
Journal of Computer Science and Technology
Volume 38 Issue 5,
September 2023
Pages 970-984
DOI: 10.1007/s11390-023-3009-0
Cite this article:
Hu C-Y, Hu L-S, Yuan L, et al. FedIERF: Federated Incremental Extremely Random Forest for Wearable Health Monitoring. Journal of Computer Science and Technology, 2023, 38(5): 970-984. https://doi.org/10.1007/s11390-023-3009-0

317

Views

1

Crossref

0

Web of Science

0

Scopus

0

CSCD

Altmetrics
Received: 05 December 2022
Accepted: 14 August 2023
Published: 30 September 2023
© Institute of Computing Technology, Chinese Academy of Sciences 2023
Return