Empirical Study and Improvement on Deep Transfer Learning for Human Activity Recognition
Open accessThe DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
Abstract
Human activity recognition (HAR) based on sensor data is a significant problem in pervasive computing. In recent years, deep learning has become the dominating approach in this field, due to its high accuracy. However, it is difficult to make accurate identification for the activities of one individual using a model trained on data from other users. The decline on the accuracy of recognition restricts activity recognition in practice. At present, there is little research on the transferring of deep learning model in this field. This is the first time as we known, an empirical study was carried out on deep transfer learning between users with unlabeled data of target. We compared several widely-used algorithms and found that Maximum Mean Discrepancy (MMD) method is most suitable for HAR. We studied the distribution of features generated from sensor data. We improved the existing method from the aspect of features distribution with center loss and get better results. The observations and insights in this study have deepened the understanding of transfer learning in the activity recognition field and provided guidance for further research.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Learning Transferable Features with Deep Adaptation Networks
Long, M., Cao, Y., Wang, J., & Jordan, M. I. (2015) · arXiv · doi:10.48550/arxiv.1502.02791 · Cited by 4,505
A Discriminative Feature Learning Approach for Deep Face Recognition
Wen, Y., Zhang, K., Li, Z., & Qiao, Y. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46478-7_31 · Cited by 4,077
Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks
Oquab, M., Bottou, L., Laptev, I., & Sivic, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.222 · Cited by 3,150 · cited 1×
“Finally, some methods [26,27] make use of pre-trained model which is trained on source data.”
MethodDeep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition
Ordóñez, F., & Roggen, D. (2016) · Sensors · doi:10.3390/s16010115 · Cited by 2,761
Deep learning for sensor-based activity recognition: A survey
Wang, J., Chen, Y., Hao, S., Peng, X., & Hu, L. (2019) · Pattern Recognition Letters · doi:10.1016/j.patrec.2018.02.010 · Cited by 2,014
Domain adaptation with structural correspondence learning
Blitzer, J., McDonald, R., & Pereira, F. (2006) · Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing - EMNLP '06 · doi:10.3115/1610075.1610094 · Cited by 1,543 · cited 1×
“Some researchers studied the switching of conversation models in different scenarios within NLP (Natural Language Processing), so that the dialogue system can satisfy the needs of users [15].”
BackgroundUSC-HAD: a daily activity dataset for ubiquitous activity recognition using wearable sensors
Zhang, M., & Sawchuk, A. A. (2012) · Proceedings of the 2012 ACM Conference on Ubiquitous Computing · doi:10.1145/2370216.2370438 · Cited by 554 · cited 6×
“With the USC-HAD, there are two kinds of activities which are really similar: elevator up and elevator down.”
MethodInfluentialA Deep Learning Approach to Human Activity Recognition Based on Single Accelerometer
Chen, Y., & Xue, Y. (2015) · 2015 IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2015.263 · Cited by 378 · cited 12×
“The MK-MMD Loss is defined as follows: Lm = 1 n n ∑ k=1 MMDHK 2 (14) so the total loss is combination of the Ls (Soft-max Loss), Lc(Center Loss) and LD(MMD Loss): L = Ls + λLc + βLm (15) This work uses two layers of CNN and one layer of fully connected layer.”
MethodInfluentialPD Disease State Assessment in Naturalistic Environments Using Deep Learning
Hammerla, N., Fisher, J., Andras, P., Rochester, L., Walker, R., & Ploetz, T. (2015) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v29i1.9484 · Cited by 179 · cited 1×
“In the medical field, researchers attached wearable sensors to shoes to reflect the speed and gait of people walking [10].”
BackgroundMorales, F. J. O., & Roggen, D. (2016) · Proceedings of the 2016 ACM International Symposium on Wearable Computers · doi:10.1145/2971763.2971764 · Cited by 136 · cited 3×
“For deep learning, the researchers used so e labeled data in target do ain to fine-tune the odel [7].”
MethodInfluential
Research works printed but not linked: 23
- Inoue, M., Inoue, S., and Nishida, T. (arXiv, 2016). Deep recurrent neural network for mobile human activity recognition with high throughput, arXiv. · DOI · Paper page
- Cao, L., Liu, Z., and Huang, T.S. (2010, January 13–18). Cross-dataset action detection. Proceedings of the IEEE Computer Vision and Pattern Recognition, San Francisco, CA, USA. · DOI · Paper page
- Zhao, Z., Chen, Y., Liu, J., Shen, Z., and Liu, M. (2011, January 16–22). Cross-people mobile-phone based activity recognition. Proceedings of the International Joint Conference on Artificial Intelligence, Barcelona, Spain.
- Edel, M., and Köppe, E. (2016, January 4–7). Binarized-BLSTM-RNN based Human Activity Recognition. Proceedings of the International Conference on Indoor Positioning and Indoor Navigation, Madrid, Spain. · DOI · Paper page
- Le, N.N.N., and Cavallaro, A. (2015, January 7–9). Basketball activity recognition using wearable inertial measurement units. Proceedings of the XVI International Conference on Human Computer Interaction, Vilanova i la Geltru, Spain.
- Ermes, 2008, Detection of Daily Activities and Sports with Wearable Sensors in Controlled and Uncontrolled Conditions, IEEE Trans. Inf. Technol. Biomed., 12, 20, 10.1109/TITB.2007.899496 · DOI · Paper page
- Subetha, T., and Chitrakala, S. (2016, January 25–26). A survey on human activity recognition from videos. Proceedings of the International Conference on Information Communication and Embedded Systems, Chennai, India. · DOI
- Gopalan, R., Li, R., Patel, V.M., and Chellappa, R. (2015). Domain Adaptation for Visual Recognition. Foundations and Trends in Computer Graphics, Now Publisher. · doi:10.1561/9781680830316
- Long, 2015, Domain Invariant Transfer Kernel Learning, IEEE Trans. Knowl. Data Eng., 27, 1519, 10.1109/TKDE.2014.2373376 · DOI · Paper page
- Pan, 2011, Domain adaptation via transfer component analysis, IEEE Trans. Neural Netw., 22, 199, 10.1109/TNN.2010.2091281 · DOI · Paper page
- Pan, S.J., Kwok, J.T., and Yang, Q. (2008, January 13–17). Transfer learning via dimensionality reduction. Proceedings of the 23rd National Conference on Artificial Intelligence, Chicago, IL, USA.
- Tzeng, E., Hoffman, J., Darrell, T., and Saenko, K. (arXiv, 2014). Deep Domain Confusion: Maximizing for Domain Invariance, arXiv.
- Dai, W., Yang, Q., Xue, G.R., and Yu, Y. (2007, January 20–24). Boosting for transfer learning. Proceedings of the 24th International Conference on Machine Learning, Corvalis, OR, USA. · DOI · Paper page
- Quiñonero-Candela, J., Sugiyama, M., Schwaighofer, A., and Lawrence, N. (2009). Covariate Shift by Kernel Mean Matching, MIT Press.
- Sugiyama, M., Suzuki, T., and Kanamori, T. (2012). Density Ratio Estimation in Machine Learning, Cambridge University Press. · DOI · Paper page
- Mihalkova, L., Huynh, T., and Mooney, R.J. (2007, January 22–26). Mapping and revising Markov logic networks for transfer learning. Proceedings of the 22nd National Conference on Artificial Intelligence, Vancouver, BC, Canada.
- Davis, J., and Domingos, P. (2009, January 14–18). Deep transfer via second-order Markov logic. Proceedings of the 26th Annual International Conference on Machine Learning, Montreal, QC, Canada. · DOI · Paper page
- Yao, Y., and Doretto, G. (2010, January 13–18). Boosting for transfer learning with multiple sources. Proceedings of the IEEE Computer Vision and Pattern Recognition, San Francisco, CA, USA. · DOI · Paper page
- Wang, J., Zheng, V.W., Chen, Y., and Huang, M. (2018, January 28–31). Deep Transfer Learning for Cross-domain Activity Recognition. Proceedings of the 3rd International Conference on Crowd Science and Engineering, Singapore. · DOI · Paper page
- Ganin, 2017, Domain-Adversarial Training of Neural Networks, J. Mach. Learn. Res., 17, 2096
- Shen, J., Qu, Y., and Zhang, W. (arXiv, 2017). Wasserstein Distance Guided Representation Learning for Domain Adaptation, arXiv. · DOI · Paper page
- Altun, 2010, Comparative study on classifying human activities with miniature inertial and magnetic sensors, Pattern Recognit., 43, 3605, 10.1016/j.patcog.2010.04.019 · DOI · Paper page
- Cui, J., and Xu, B. (October, January 30). Cost-Effective Activity Recognition on Mobile Devices. Proceedings of the BODYNETS 2013—8th International Conference on Body Area Networks, Boston, MA, USA.
Cited by
Alzubaidi, L., Bai, J., Al-Sabaawi, A., Santamaría, J., Albahri, A. S., Al-dabbagh, B. S. N., Fadhel, M. A., Manoufali, M., Zhang, J., Al-Timemy, A. H., et al. (2023) · Journal of Big Data · doi:10.1186/s40537-023-00727-2 · Cited by 907
A Review of Deep Transfer Learning and Recent Advancements
Iman, M., Arabnia, H. R., & Rasheed, K. (2023) · Technologies · doi:10.3390/technologies11020040 · Cited by 680
Qiu, S., Zhao, H., Jiang, N., Wang, Z., Liu, L., An, Y., Zhao, H., Miao, X., Liu, R., & Fortino, G. (2022) · Information Fusion · doi:10.1016/j.inffus.2021.11.006 · Cited by 671
Demrozi, F., Pravadelli, G., Bihorac, A., & Rashidi, P. (2020) · IEEE Access · doi:10.1109/access.2020.3037715 · Cited by 368
Human activity recognition in artificial intelligence framework: a narrative review
Gupta, N., Gupta, S. K., Pathak, R. K., Jain, V., Rashidi, P., & Suri, J. S. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-021-10116-x · Cited by 337
Chung, S., Lim, J., Noh, K. J., Kim, G., & Jeong, H. (2019) · Sensors · doi:10.3390/s19071716 · Cited by 215
“Deep learning model is renowned for its feature learning ability through neural networks, which accepts a large amount of raw data for training and identify unseen data through knowledge transfer methods [31].”
BackgroundHuman Activity Recognition Data Analysis: History, Evolutions, and New Trends
Ariza-Colpas, P. P., Vicario, E., Oviedo-Carrascal, A. I., Butt Aziz, S., Piñeres-Melo, M. A., Quintero-Linero, A., & Patara, F. (2022) · Sensors · doi:10.3390/s22093401 · Cited by 52
Hu, R., Chen, L., Miao, S., & Tang, X. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i5.25743 · Cited by 44
Cross-dataset deep transfer learning for activity recognition
Gjoreski, M., Kalabakov, S., Luštrek, M., Gams, M., & Gjoreski, H. (2019) · Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2019 ACM International Symposium on Wearable Computers · doi:10.1145/3341162.3344865 · Cited by 28
Metadata
- Authors
- Ding, R., Li, X., Nie, L., Li, J., Si, X., Chu, D., Liu, G., & Zhan, D.
- Venue
- Sensors
- Publisher
- MDPI AG
- Published
- 2018-12-24
- Volume
- 19
- Issue
- 1
- Pages
- 57
- ISSN
- 1424-8220 (ISSN-L)
- OpenAlex
- W2906031885
- Cited by
- 63
- References
- 11
- FWCI
- 3.12
- Type
- journal article
- Language
- en
- Open access
- gold
- Funders
- Natural Science Foundation of Shandong Province (ZR2017MF026)
- National Natural Science Foundation of China (61772159)
- Science and technology Special Project of National Regional Innovation Center (2017QYCX12)
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.