[논문]Development of a Hybrid Deep-Learning Model for the Human Activity Recognition based on the Wristband Accelerometer Signals

Jeong, Seungmin; Oh, Dongik

doi:10.7472/jksii.2021.22.3.9

Development of a Hybrid Deep-Learning Model for the Human Activity Recognition based on the Wristband Accelerometer Signals 원문보기

Journal of Internet Computing and Services = 인터넷정보학회논문지, v.22 no.3, 2021년, pp.9 - 16

Jeong, Seungmin (Department of Software Convergence, Soonchunhyang University) , Oh, Dongik (Department of Medical IT Engineering, Soonchunhyang University)

Abstract ▼ AI-Helper

This study aims to develop a human activity recognition (HAR) system as a Deep-Learning (DL) classification model, distinguishing various human activities. We solely rely on the signals from a wristband accelerometer worn by a person for the user's convenience. 3-axis sequential acceleration signal data are gathered within a predefined time-window-slice, and they are used as input to the classification system. We are particularly interested in developing a Deep-Learning model that can outperform conventional machine learning classification performance. A total of 13 activities based on the laboratory experiments' data are used for the initial performance comparison. We have improved classification performance using the Convolutional Neural Network (CNN) combined with an auto-encoder feature reduction and parameter tuning. With various publically available HAR datasets, we could also achieve significant improvement in HAR classification. Our CNN model is also compared against Recurrent-Neural-Network(RNN) with Long Short-Term Memory(LSTM) to demonstrate its superiority. Noticeably, our model could distinguish both general activities and near-identical activities such as sitting down on the chair and floor, with almost perfect classification accuracy.

주제어

표/그림 (4)

그림 (Figure 1) The outline of Typical HAR Machine Learning Process and our Best-performing Method
그림 (Figure 2) The structure of the AAE+CNN hybrid Deep Learning model
표 (Table 1) Brief introduction of datasets usedin this study.
표 (Table 2) The result of experiments

AI 본문요약
AI-Helper

제안 방법

We tested three DL methods (DNN, RNN, and CNN) combined with AAE against four datasets made for the human activity classification; one lab dataset and three publically available datasets. Our experiment result shows that the hybrid-DL model outperforms models using only the DL classifier (average accuracy: 98.

대상 데이터

The elevator-up and elevator-down are treated as the same activity; with the acceleration sensor only, it is impossible to detect ascent and descent in an elevator moving at a constant speed. A total of 9057 windows data are collected.
The UCI-mobile dataset provides data from six activities; walking, sitting, standing, lying, walking upstairs/downstairs. Data are collected for a total of 10299 windows. A smartphone mounted on the wrist is used for data collection.
In this experiment, we measured the performance of a total of 6 DL models, including DNN, CNN, RNN, and their AAE hybrid models, against four datasets. For each dataset, train, validation, and test data are divided into the ratio of 6:2:2.
The UCI-mobile dataset provides data from six activities; walking, sitting, standing, lying, walking upstairs/downstairs. Data are collected for a total of 10299 windows.
We use only the data obtained from the wrist-mounted sensor. The dataset consists of a total of 6346 windows.
The pamap2 dataset is collected while subjects wear an IMU (Inertial Measurement Unit) on their wrists, chest, and knees. It contains 12 activity data.
This study evaluates the DL models' classification performance mentioned in Section 3.3, namely the DNN, CNN, RNN, and their AAE hybrid versions.
The data are transmitted to the artificial intelligence server. Through this experiment, a total of 7185 windows of data are collected for the 13 activities, which consist of stationary, walking, running, stair-up/down, sitting/standing on floor/chair, lying/getting up on floor/bed.
To obtain the lab dataset, six subjects wearing a smartwatch-type sensor with a built-in 3-axis acceleration sensor on their left wrist naturally performed 13 types of activities. The sensor collected 3-axis acceleration data 40 times per second.

성능/효과

Features extracted by AAE have low dimensionality, essential information that can be useful for classification. Hence, we could significantly improve classification accuracy by using these crucial features from the AAE dimensionality reduction model as an input for DL classification models.
In this study, we developed an efficient hybrid DL classification model for HAR. In most CML methods, collected data must undergo preprocessing step (e.
6%). Notably, the hybrid deep learning model using AAE and CNN produces near-perfect classification performance (average accuracy: 99.3%), which is the best performance in the literature as far as we know.
We tested three DL methods (DNN, RNN, and CNN) combined with AAE against four datasets made for the human activity classification; one lab dataset and three publically available datasets. Our experiment result shows that the hybrid-DL model outperforms models using only the DL classifier (average accuracy: 98.3% versus 86.6%). Notably, the hybrid deep learning model using AAE and CNN produces near-perfect classification performance (average accuracy: 99.

후속연구

In the future study, we plan to apply our hybrid-DL model to domains other than HAR to demonstrate its applicability and superiority.

참고문헌 (19)

Guan Yuan, Zhaohui Wang, Fanrong Meng, Qiuyan Yan, Shixiong Xia, "An overview of human activity recognition based on smartphone," Sensor Review, 2018. https://doi.org/10.1108/SR-11-2017-0245

상세보기
Yassine, Abdulsalam, Shailendra Singh, and Atif Alamri. "Mining human activity patterns from smart home big data for health care applications," IEEE Access 5, 13131-13141, 2017. https://doi.org/10.1109/ACCESS.2017.2719921

상세보기
Donahue, J., Anne Hendricks, L., Guadarrama, S., Rohrbach, M., Venugopalan, S., Saenko, K., and Darrell, T., "Long-term recurrent convolutional networks for visual recognition and description," In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2625-2634, 2015. https://doi.org/10.1109/cvpr.2015.7298878
Yan Wang, Shuang Cang, Hongnian Yu, "A survey on wearable sensor modality centred human activity recognition in health care," Journal of Expert Systems With Applications, Vol. 137, pp. 167-190, 2019. https://doi.org/10.1016/j.eswa.2019.04.057

상세보기
O. D. Lara and M. A. Labrador, "A Survey on Human Activity Recognition using Wearable Sensors," IEEE Communications Surveys & Tutorials, Vol. 15, no. 3, pp. 1192-1209, Third Quarter 2013. https://doi.org/10.1109/SURV.2012.110112.00192

상세보기
S. Jeong, C. Choi, D. Oh, "Development of a MachineLearning based Human Activity Recognition System including Eastern-Asian Specific Activities," Journal of Internet Computing and Services, Vol. 21, No. 4, pp. 127-135, Aug. 2020. https://doi.org/10.1109/ACCESS.2017.2719921

상세보기
Florenc Demrozi, Graziano Pravadelli, Azra Bihorac, Parisa Rashidi, "Human Activity Recognition using Inertial, Physiological and Environmental Sensors: A Comprehensive Survey," Preprint http://arxiv.org (arXiv:2004.08821v1) Apr. 2020.
Jindong Wang, Yiqiang Chen, Huji Hao, Xiaohui Peng, Lisha Hu, "Deep learning for sensor-based activity recognition: A survey," Pattern Recognition Letters, Volume 119, Pages 3-11, ISSN 0167-8655, 2019. https://doi.org/10.1016/j.patrec.2018.02.010

상세보기
Hinton, Geoffrey E., and Ruslan R. Salakhutdinov. "Reducing the dimensionality of data with neural networks," Science 28, 504-507, 2006. https://doi.org/10.1126/science.1127647

상세보기
Wang, Yasi, Hongxun Yao, and Sicheng Zhao. "Auto-encoder based dimensionality reduction," Neurocomputing 184, pp. 232-242, 2016. https://doi.org/10.1016/j.neucom.2015.08.104

상세보기
Makhzani, Alireza, et al. Adversarial Autoencoders, 2016. https://arxiv.org/abs/1511.05644
Abbaspour, Saedeh, et al. "A comparative analysis of hybrid deep learning models for human activity recognition," Sensors 20.19, 5707, 2020. https://doi.org/10.3390/s20195707

상세보기
Ronao, Charissa Ann, and Sung-Bae Cho. "Human activity recognition with smartphone sensors using deep learning neural networks," Expert systems with applications 59, pp. 235-244, 2016. https://doi.org/10.1016/j.eswa.2016.04.032

상세보기
Murad, Abdulmajid, and Jae-Young Pyun. "Deep recurrent neural networks for human activity recognition," Sensors 17.11, 2556, 2017. https://doi.org/10.3390/s17112556

상세보기
O'Shea, Keiron, and Ryan Nash. "An introduction to convolutional neural networks," preprint arXiv: 1511.08458, 2015. https://arxiv.org/abs/1511.08458
Albawi, Saad, Tareq Abed Mohammed, and Saad Al-Zawi. "Understanding of a convolutional neural network," International Conference on Engineering and Technology (ICET). IEEE, 2017. https://doi.org/10.1109/ICEngTechnol.2017.8308186
Reiss, Attila, and Didier Stricker. "Introducing a new benchmarked dataset for activity monitoring," 2012 16th International Symposium on Wearable Computers. IEEE, 2012. https://doi.org/10.1109/ISWC.2012.13
Anguita, Davide, et al. "A public domain dataset for human activity recognition using smartphones," Esann Vol. 3. 2013. https://doi.org/10.1109/ICEngTechnol.2017.8308186
Zhang, Mi, and Alexander A. Sawchuk. "USC-HAD: a daily activity dataset for ubiquitous activity recognition using wearable sensors," Proceedings of the 2012 ACM Conference on Ubiquitous Computing. 2012. https://doi.org/10.1145/2370216.2370438

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증