Embedded Inter-Subject Variability in Adversarial Learning for Inertial Sensor-Based Human Activity Recognition
Open accessAbstract
This paper addresses the problem of Human Activity Recognition (HAR) using data from wearable inertial sensors. An important challenge in HAR is the model's generalization capabilities to new unseen individuals due to inter-subject variability, i.e., the same activity is performed differently by different individuals. To address this problem, we propose a novel deep adversarial framework that integrates the concept of inter-subject variability in the adversarial task, thereby encouraging subject-invariant feature representations and enhancing the classification performance in the HAR problem. Our approach outperforms previous methods in three well-established HAR datasets using a leave-one-subject-out (LOSO) cross-validation. Further results indicate that our proposed adversarial task effectively reduces inter-subject variability among different users in the feature space, and it outperforms adversarial tasks from previous works when integrated into our framework. Code: https://github.com/FranciscoCalatrava/EmbeddedSubjectVariability.git
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In inertial-based HAR, data distribution shift is produced by inter-person variability, sensor position, and hardware differences.
“In inertial-based HAR, this shift is produced by the way different individuals implement the same activity (inter-person variability), the sensor position (placement variability), and hardware differences between sensors18,19,37, among others.”
From Siamese masked reconstruction with temporal rotation consistency for inertial-based human activity recognition (2026) · cites this paper as [37]
Supervised HAR methods often require large labeled datasets and may generalise poorly under realistic deployment conditions.
“Despite substantial improvements in recognition accuracy, supervised HAR methods often require large labeled datasets and may generalise poorly under realistic deployment conditions.”
From Siamese masked reconstruction with temporal rotation consistency for inertial-based human activity recognition (2026) · cites this paper as [37]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Deep 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 · see citing works
NIPS 2016 Tutorial: Generative Adversarial NetworksPreprint
Goodfellow, I. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1701.00160 · Cited by 1,735 · see citing works
Introducing a New Benchmarked Dataset for Activity Monitoring
Reiss, A., & Stricker, D. (2012) · 2012 16th International Symposium on Wearable Computers · doi:10.1109/iswc.2012.13 · Cited by 1,456 · cited 2× · see citing works
“In this section, we first compare our proposed method with previous works in the HAR field.”
mHealthDroid: A Novel Framework for Agile Development of Mobile Health Applications
Banos, O., Garcia, R., Holgado-Terriza, J. A., Damas, M., Pomares, H., Rojas, I., Saez, A., & Villalonga, C. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-13105-4_14 · Cited by 583 · see citing works
A survey of video datasets for human action and activity recognition
Chaquet, J. M., Carmona, E. J., & Fernández-Caballero, A. (2013) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2013.01.013 · Cited by 455 · see citing works
Monitoring Activities of Daily Living in Smart Homes: Understanding human behavior
Debes, C., Merentitis, A., Sukhanov, S., Niessen, M. E., Frangiadakis, N., & Bauer, A. (2016) · IEEE Signal Processing Magazine · doi:10.1109/msp.2015.2503881 · Cited by 299 · see citing works
Let's (not) stick together: pairwise similarity biases cross-validation in activity recognition
Hammerla, N. Y., & Plötz, T. (2015) · Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing · doi:10.1145/2750858.2807551 · Cited by 91 · see citing works
Human Activity Recognition on Smartphones Using a Bidirectional LSTM Network
Castrillón, F., Suárez, L. F. D., Villamizar, J., & Altuve, M. (2019) · Symposium on Image, Signal Processing and Artificial Vision (STSIVA) · doi:10.1109/stsiva.2019.8730249 · Cited by 87 · see citing works
Ling, C. (2020) · doi:10.1145/3381012 · Cited by 72 · see citing works
Human Activity Recognition for Domestic Robots
Piyathilaka, L., & Kodagoda, S. (2014) · Springer tracts in advanced robotics · doi:10.1007/978-3-319-07488-7_27 · Cited by 66 · see citing works
Iwasawa, Y., Nakayama, K., Yairi, I., & Matsuo, Y. (2017) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2017/268 · Cited by 44 · see citing works
Adversarial Multi-view Networks for Activity Recognition
Bai, L., Yao, L., Wang, X., Kanhere, S. S., Guo, B., & Yu, Z. (2020) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3397323 · Cited by 40 · see citing works
Qin, X., Wang, J., Ma, S., Lu, W., Zhu, Y., Xie, X., & Chen, Y. (2023) · Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining · doi:10.1145/3580305.3599360 · Cited by 29 · see citing works
Barshan, B., & Yurtman, A. (2015) · The Computer Journal · doi:10.1093/comjnl/bxv093 · Cited by 25 · see citing works
Adversarial Deep Feature Extraction Network for User Independent Human Activity Recognition
Suh, S., Rey, V. F., & Lukowicz, P. (2022) · 2022 IEEE International Conference on Pervasive Computing and Communications (PerCom) · doi:10.1109/percom53586.2022.9762387 · Cited by 25 · see citing works
Self-citationLight Residual Network for Human Activity Recognition using Wearable Sensor Data
Calatrava-Nicolás, F. M., & Mozos, O. M. (2023) · IEEE Sensors Letters · doi:10.1109/lsens.2023.3311623 · Cited by 22 · see citing works
Self-citationSTranGAN: Adversarially-learnt Spatial Transformer for scalable human activity recognition
Faridee, A. Z. M., Chakma, A., Misra, A., & Roy, N. (2021) · Smart Health · doi:10.1016/j.smhl.2021.100226 · Cited by 18 · see citing works
If only we had more data!: Sensor-Based Human Activity Recognition in Challenging Scenarios
Plötz, T. (2023) · 2023 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops) · doi:10.1109/percomworkshops56833.2023.10150267 · Cited by 16 · see citing works
Flagged first, then by citations
Research works printed but not linked: 6
- Eshed Ohn-Bar and Mohan Manubhai Trivedi, "Looking at hu- mans in the age of self-driving and highly automated vehicles," IEEE T. Intell. Veh., vol. 1, no. 1, pp. 90-104, 2016.
- Tiago Fernandes Tavares and Lucas Bertoloto, "Air drums, and bass: Anticipating musical gestures in accelerometer signals with a lightweight cnn," in IEEE International Workshop on Machine Learning for Signal Processing, 2023, pp. 1-5.
- Jianbo Yang, Minh Nhut Nguyen, Phyo Phyo San, Xiaoli Li, and Shonali Krishnaswamy, "Deep convolutional neural net- works on multichannel time series for human activity recogni- tion.," in International Joint Conference on Artificial Intelli- gence, 2015, vol. 15, pp. 3995-4001.
- Yang Wang, Hongji Xu, Yunxia Liu, Mengmeng Wang, Yuhao Wang, Yang Yang, Shuang Zhou, Jiaqi Zeng, Jie Xu, Shijie Li, and Jianjun Li, "A novel deep multi-feature extraction frame- work based on attention mechanism using wearable sensor data for human activity recognition," IEEE Sensors Journal, vol. 23, no. 7, pp. 7188-7198, 2023.
- Oresti Banos, Mate Toth, and Oliver Amft, "REALDISP Ac- tivity Recognition Dataset," UCI Machine Learning Reposi- tory, 2014, DOI: doi.org/10.24432/C5GP6D. · DOI · Paper page
- Charlie Frogner, Chiyuan Zhang, Hossein Mobahi, Mauricio Araya, and Tomaso A Poggio, "Learning with a wasserstein loss," Advances in neural information processing systems, vol. 28, 2015.
Cited by
Sorted by citations
Calatrava-Nicolás, F. M., Stoyanov, T., & Martinez Mozos, O. (2026) · Scientific Reports · doi:10.1038/s41598-026-64846-5
Self-citation
- Authors
- Calatrava-Nicolás, F. M., Miyauchi, S., Rey, V. F., Lukowicz, P., Stoyanov, T., & Mozos, O. M.
- Affiliations
- Örebro University (SE)
- Kyushu University (JP)
- RPTU,Kaiserslautern,Germany
- Rheinland-Pfälzische Technische Universität Kaiserslautern-Landau (DE)
- Escuela Técnica Superior de Ingeniería y Diseño Industrial, Universidad Politécnica de Madrid,Madrid,Spain
- Venue
- 2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)
- Publisher
- IEEE
- Published
- 2025-08-31
- Pages
- 1-6
- ISSN
- 1551-2541 (ISSN-L)
- OpenAlex
- W4415524292
- Cited by
- 2
- References
- 18
- Citations by year
- 2026: 2
- FWCI
- 1.50
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- Machine learning for signal processing ... (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Carl-Zeiss-Stiftung (P2021-02-009)
- Knut och Alice Wallenbergs Stiftelse
- Vetenskapsrådet (2022-06725)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Physical Sciences › Engineering › Biomedical Engineering › Gait Recognition and Analysis
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Keywords
- human activity recognition, interindividual variability, adversarial learning, inertial sensors, wearable sensors, leave-one-subject-out cross-validation
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
