{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T20:17:47Z","timestamp":1779913067948,"version":"3.53.1"},"reference-count":74,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2024,1,21]],"date-time":"2024-01-21T00:00:00Z","timestamp":1705795200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Johannes Kepler Open Access Publishing Fund","award":["881844"],"award-info":[{"award-number":["881844"]}]},{"name":"FFG","award":["881844"],"award-info":[{"award-number":["881844"]}]},{"name":"Austrian Federal Ministry for Digital and Economic Affairs and of the Provinces of Upper Austria and Styria","award":["881844"],"award-info":[{"award-number":["881844"]}]},{"name":"Austrian Research Promotion Agency FFG","award":["881844"],"award-info":[{"award-number":["881844"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Learning underlying patterns from sensory data is crucial in the Human Activity Recognition (HAR) task to avoid poor generalization when coping with unseen data. A key solution to such an issue is representation learning, which becomes essential when input signals contain activities with similar patterns or when patterns generated by different subjects for the same activity vary. To address these issues, we seek a solution to increase generalization by learning the underlying factors of each sensor signal. We develop a novel multi-channel asymmetric auto-encoder to recreate input signals precisely and extract indicative unsupervised futures. Further, we investigate the role of various activation functions in signal reconstruction to ensure the model preserves the patterns of each activity in the output. Our main contribution is that we propose a multi-task learning model to enhance representation learning through shared layers between signal reconstruction and the HAR task to improve the robustness of the model in coping with users not included in the training phase. The proposed model learns shared features between different tasks that are indeed the underlying factors of each input signal. We validate our multi-task learning model using several publicly available HAR datasets, UCI-HAR, MHealth, PAMAP2, and USC-HAD, and an in-house alpine skiing dataset collected in the wild, where our model achieved 99%, 99%, 95%, 88%, and 92% accuracy. Our proposed method shows consistent performance and good generalization on all the datasets compared to the state of the art.<\/jats:p>","DOI":"10.3390\/s24020681","type":"journal-article","created":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T12:01:13Z","timestamp":1705924873000},"page":"681","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Robust Feature Representation Using Multi-Task Learning for Human Activity Recognition"],"prefix":"10.3390","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6160-341X","authenticated-orcid":false,"given":"Behrooz","family":"Azadi","sequence":"first","affiliation":[{"name":"Pro2Future GmbH, Altenberger Strasse 69, 4040 Linz, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6817-9639","authenticated-orcid":false,"given":"Michael","family":"Haslgr\u00fcbler","sequence":"additional","affiliation":[{"name":"Pro2Future GmbH, Altenberger Strasse 69, 4040 Linz, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bernhard","family":"Anzengruber-Tanase","sequence":"additional","affiliation":[{"name":"Pro2Future GmbH, Altenberger Strasse 69, 4040 Linz, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5527-4161","authenticated-orcid":false,"given":"Georgios","family":"Sopidis","sequence":"additional","affiliation":[{"name":"Pro2Future GmbH, Altenberger Strasse 69, 4040 Linz, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alois","family":"Ferscha","sequence":"additional","affiliation":[{"name":"Institute of Pervasive Computing, Johannes Kepler University, Altenberger Stra\u00dfe 69, 4040 Linz, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2024,1,21]]},"reference":[{"key":"ref_1","first-page":"23","article-title":"Human Activity Recognition From Sensorised Patient\u2019s Data in Healthcare: A Streaming Deep Learning-Based Approach","volume":"8","author":"Requena","year":"2023","journal-title":"Int. J. Interact. Multimed. Artif. Intell."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3552434","article-title":"Domain generalization for activity recognition via adaptive feature fusion","volume":"14","author":"Qin","year":"2022","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Hoelzemann, A., Romero, J.L., Bock, M., Laerhoven, K.V., and Lv, Q. (2023). Hang-Time HAR: A Benchmark Dataset for Basketball Activity Recognition Using Wrist-Worn Inertial Sensors. Sensors, 23.","DOI":"10.3390\/s23135879"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Moreno-P\u00e9rez, J.A., Ruiz-Garc\u00eda, I., Navarro-Marchal, I., L\u00f3pez-Ruiz, N., G\u00f3mez-L\u00f3pez, P.J., Palma, A.J., and Carvajal, M.A. (2023). System Based on an Inertial Measurement Unit for Accurate Flight Time Determination in Vertical Jumps. Sensors, 23.","DOI":"10.3390\/s23136022"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Azadi, B., Haslgr\u00fcbler, M., Sopidis, G., Murauer, M., Anzengruber, B., and Ferscha, A. (2019, January 5\u20137). Feasibility analysis of unsupervised industrial activity recognition based on a frequent micro action. Proceedings of the 12th ACM International Conference on PErvasive Technologies Related to Assistive Environments, Island of Rhodes, Greece.","DOI":"10.1145\/3316782.3322749"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Thomay, C., Gollan, B., Haslgr\u00fcbler, M., Ferscha, A., and Heftberger, J. (2019, January 5\u20137). A multi-sensor algorithm for activity and workflow recognition in an industrial setting. Proceedings of the 12th ACM International Conference on PErvasive Technologies Related to Assistive Environments, Island of Rhodes, Greece.","DOI":"10.1145\/3316782.3321523"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Sopidis, G., Haslgr\u00fcbler, M., and Ferscha, A. (2023). Counting Activities Using Weakly Labeled Raw Acceleration Data: A Variable-Length Sequence Approach with Deep Learning to Maintain Event Duration Flexibility. Sensors, 23.","DOI":"10.3390\/s23115057"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1016\/j.eswa.2019.04.057","article-title":"A survey on wearable sensor modality centred human activity recognition in health care","volume":"137","author":"Wang","year":"2019","journal-title":"Expert Syst. Appl."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Zhang, H.B., Zhang, Y.X., Zhong, B., Lei, Q., Yang, L., Du, J.X., and Chen, D.S. (2019). A comprehensive survey of vision-based human action recognition methods. Sensors, 19.","DOI":"10.3390\/s19051005"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Ahmad, A., Haslgr\u00fcbler, M., Sopidis, G., Azadi, B., and Ferscha, A. (2021, January 8\u201312). Privacy Preserving Workflow Detection for Manufacturing Using Neural Networks based Object Detection. Proceedings of the 11th International Conference on the Internet of Things, St. Gallen, Switzerland.","DOI":"10.1145\/3494322.3494339"},{"key":"ref_11","unstructured":"Anzengruber-Tanase, B., Sopidis, G., Haslgr\u00fcbler, M., and Ferscha, A. (July, January 29). Determining Best Hardware, Software and Data Structures for Worker Guidance during a Complex Assembly Task. Proceedings of the 15th International Conference on PErvasive Technologies Related to Assistive Environments, Corfu Island, Greece."},{"key":"ref_12","unstructured":"Sopidis, G., Haslgr\u00fcbler, M., Azadi, B., Anzengruber-T\u00e1nase, B., Ahmad, A., Ferscha, A., and Baresch, M. (July, January 29). Micro-activity recognition in industrial assembly process with IMU data and deep learning. Proceedings of the 15th International Conference on PErvasive Technologies Related to Assistive Environments, Corfu Island, Greece."},{"key":"ref_13","unstructured":"Laube, M., Haslgr\u00fcbler, M., Azadi, B., Anzengruber-T\u00e1nase, B., and Ferscha, A. (July, January 29). Skill Level Detection in Arc Welding towards an Assistance System for Workers. Proceedings of the 15th International Conference on PErvasive Technologies Related to Assistive Environments, Corfu Island, Greece."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2499621","article-title":"A tutorial on human activity recognition using body-worn inertial sensors","volume":"46","author":"Bulling","year":"2014","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"ref_15","first-page":"1","article-title":"Deep learning for sensor-based human activity recognition: Overview, challenges, and opportunities","volume":"54","author":"Chen","year":"2021","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Islam, M.M., Nooruddin, S., Karray, F., and Muhammad, G. (2022). Human activity recognition using tools of convolutional neural networks: A state of the art review, data sets, challenges, and future prospects. Comput. Biol. Med., 149.","DOI":"10.1016\/j.compbiomed.2022.106060"},{"key":"ref_17","unstructured":"Antar, A.D., Ahmed, M., and Ahad, M.A.R. (June, January 30). Challenges in sensor-based human activity recognition and a comparative analysis of benchmark datasets: A review. Proceedings of the 2019 Joint 8th International Conference on Informatics, Electronics & Vision (ICIEV) and 2019 3rd International Conference on Imaging, Vision & Pattern Recognition (icIVPR), Spokane, WA, USA."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1798","DOI":"10.1109\/TPAMI.2013.50","article-title":"Representation learning: A review and new perspectives","volume":"35","author":"Bengio","year":"2013","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Haresamudram, H., Anderson, D.V., and Pl\u00f6tz, T. (2019, January 9\u201313). On the role of features in human activity recognition. Proceedings of the 2019 ACM International Symposium on Wearable Computers, London, UK.","DOI":"10.1145\/3341163.3347727"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1126\/science.1127647","article-title":"Reducing the dimensionality of data with neural networks","volume":"313","author":"Hinton","year":"2006","journal-title":"Science"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"271","DOI":"10.1016\/j.neucom.2020.01.125","article-title":"An ensemble of autonomous auto-encoders for human activity recognition","volume":"439","author":"Garcia","year":"2021","journal-title":"Neurocomputing"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"102640","DOI":"10.1016\/j.media.2022.102640","article-title":"Multi-channel auto-encoders for learning domain invariant representations enabling superior classification of histopathology images","volume":"83","author":"Moyes","year":"2023","journal-title":"Med. Image Anal."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Elhalwagy, A., and Kalganova, T. (2022). Multi-channel LSTM-capsule autoencoder network for anomaly detection on multivariate data. Appl. Sci., 12.","DOI":"10.3390\/app122211393"},{"key":"ref_24","unstructured":"Crawshaw, M. (2020). Multi-task learning with deep neural networks: A survey. arXiv."},{"key":"ref_25","unstructured":"Le, L., Patterson, A., and White, M. (2018). Supervised autoencoders: Improving generalization performance with unsupervised regularizers. Adv. Neural Inf. Process. Syst., 31."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"5586","DOI":"10.1109\/TKDE.2021.3070203","article-title":"A survey on multi-task learning","volume":"34","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_27","unstructured":"Ruder, S. (2017). An overview of multi-task learning in deep neural networks. arXiv."},{"key":"ref_28","unstructured":"Smith, V., Chiang, C.K., Sanjabi, M., and Talwalkar, A.S. (2017). Federated multi-task learning. Adv. Neural Inf. Process. Syst., 30."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3214277","article-title":"Aroma: A deep multi-task learning based simple and complex human activity recognition method using wearable sensors","volume":"2","author":"Peng","year":"2018","journal-title":"Proc. ACM Interact. Mob. Wearable Ubiquitous Technol."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3328932","article-title":"Multi-task self-supervised learning for human activity detection","volume":"3","author":"Saeed","year":"2019","journal-title":"Proc. ACM Interact. Mob. Wearable Ubiquitous Technol."},{"key":"ref_31","first-page":"1","article-title":"Metier: A deep multi-task learning based activity and user recognition model using wearable sensors","volume":"4","author":"Chen","year":"2020","journal-title":"Proc. ACM Interact. Mob. Wearable Ubiquitous Technol."},{"key":"ref_32","first-page":"160","article-title":"An effective deep autoencoder approach for online smartphone-based human activity recognition","volume":"17","author":"Almaslukh","year":"2017","journal-title":"Int. J. Comput. Sci. Netw. Secur."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Gao, X., Luo, H., Wang, Q., Zhao, F., Ye, L., and Zhang, Y. (2019). A human activity recognition algorithm based on stacking denoising autoencoder and lightGBM. Sensors, 19.","DOI":"10.3390\/s19040947"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"4137","DOI":"10.1109\/ACCESS.2022.3140373","article-title":"Convae-lstm: Convolutional autoencoder long short-term memory network for smartphone-based human activity recognition","volume":"10","author":"Thakur","year":"2022","journal-title":"IEEE Access"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Balabka, D. (2019, January 9\u201313). Semi-supervised learning for human activity recognition using adversarial autoencoders. Proceedings of the 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, London, UK.","DOI":"10.1145\/3341162.3344854"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Campbell, C., and Ahmad, F. (2020, January 28\u201330). Attention-augmented convolutional autoencoder for radar-based human activity recognition. Proceedings of the 2020 IEEE International Radar Conference (RADAR), Washington, DC, USA.","DOI":"10.1109\/RADAR42522.2020.9114787"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"2157","DOI":"10.1007\/s11042-018-6273-1","article-title":"Stacked sparse autoencoder and history of binary motion image for human activity recognition","volume":"78","author":"Gnouma","year":"2019","journal-title":"Multimed. Tools Appl."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Zou, H., Zhou, Y., Yang, J., Jiang, H., Xie, L., and Spanos, C.J. (2018, January 20\u201324). Deepsense: Device-free human activity recognition via autoencoder long-term recurrent convolutional network. Proceedings of the 2018 IEEE International Conference on Communications (ICC), Kansas City, MO, USA.","DOI":"10.1109\/ICC.2018.8422895"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Wang, A., Chen, G., Shang, C., Zhang, M., and Liu, L. (2016, January 3\u20135). Human activity recognition in a smart home environment with stacked denoising autoencoders. Proceedings of the Web-Age Information Management: WAIM 2016 International Workshops, MWDA, SDMMW, and SemiBDMA, Nanchang, China. Revised Selected Papers 17.","DOI":"10.1007\/978-3-319-47121-1_3"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Varamin, A.A., Abbasnejad, E., Shi, Q., Ranasinghe, D.C., and Rezatofighi, H. (2018, January 5\u20137). Deep auto-set: A deep auto-encoder-set network for activity recognition using wearables. Proceedings of the 15th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services, New York, NY, USA.","DOI":"10.1145\/3286978.3287024"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Ord\u00f3\u00f1ez, F.J., and Roggen, D. (2016). Deep convolutional and lstm recurrent neural networks for multimodal wearable activity recognition. Sensors, 16.","DOI":"10.3390\/s16010115"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3448074","article-title":"Unsupervised human activity representation learning with multi-task deep clustering","volume":"5","author":"Ma","year":"2021","journal-title":"Proc. ACM Interact. Mob. Wearable Ubiquitous Technol."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Suh, S., Rey, V.F., and Lukowicz, P. (2022, January 21\u201325). Adversarial deep feature extraction network for user independent human activity recognition. Proceedings of the 2022 IEEE International Conference on Pervasive Computing and Communications (PerCom), Pisa, Italy.","DOI":"10.1109\/PerCom53586.2022.9762387"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Abbaspour, S., Fotouhi, F., Sedaghatbaf, A., Fotouhi, H., Vahabi, M., and Linden, M. (2020). A comparative analysis of hybrid deep learning models for human activity recognition. Sensors, 20.","DOI":"10.3390\/s20195707"},{"key":"ref_45","unstructured":"Mahmud, S., Tonmoy, M., Bhaumik, K.K., Rahman, A.M., Amin, M.A., Shoyaib, M., Khan, M.A.H., and Ali, A.A. (2020). Human activity recognition from wearable sensor data using self-attention. arXiv."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"107728","DOI":"10.1016\/j.asoc.2021.107728","article-title":"DanHAR: Dual attention network for multimodal human activity recognition using wearable sensors","volume":"111","author":"Gao","year":"2021","journal-title":"Appl. Soft Comput."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3448083","article-title":"Attend and discriminate: Beyond the state-of-the-art for human activity recognition using wearable sensors","volume":"5","author":"Abedin","year":"2021","journal-title":"Proc. ACM Interact. Mob. Wearable Ubiquitous Technol."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1016\/j.neucom.2020.04.151","article-title":"Human activity recognition based on smartphone and wearable sensors using multiscale DCNN ensemble","volume":"444","author":"Sena","year":"2021","journal-title":"Neurocomputing"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Li, Y., and Wang, L. (2022). Human activity recognition based on residual network and BiLSTM. Sensors, 22.","DOI":"10.3390\/s22020635"},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"6164","DOI":"10.1109\/JSEN.2022.3148431","article-title":"A novel deep learning Bi-GRU-I model for real-time human activity recognition using inertial sensors","volume":"22","author":"Tong","year":"2022","journal-title":"IEEE Sens. J."},{"key":"ref_51","unstructured":"EK, S., Portet, F., and Lalanda, P. (2022). Lightweight Transformers for Human Activity Recognition on Mobile Devices. arXiv."},{"key":"ref_52","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2020). An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale. arXiv."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"94173","DOI":"10.1109\/ACCESS.2023.3310269","article-title":"Attention-based Residual BiLSTM Networks for Human Activity Recognition","volume":"11","author":"Zhang","year":"2023","journal-title":"IEEE Access"},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Wang, W., An, A., Qin, Y., and Yang, F. (2023). A human activity recognition method using wearable sensors based on convtransformer model. Evol. Syst., 939\u2013955.","DOI":"10.1007\/s12530-022-09480-y"},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"628574","DOI":"10.3389\/fspor.2021.628574","article-title":"Health and performance assessment in winter sports","volume":"3","author":"Aminian","year":"2021","journal-title":"Front. Sport. Act. Living"},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1136\/bjsports-2016-096502","article-title":"Reducing the risks for traumatic and overuse injury among competitive alpine skiers","volume":"51","author":"Supej","year":"2017","journal-title":"Br. J. Sport. Med."},{"key":"ref_57","doi-asserted-by":"crossref","unstructured":"Neuwirth, C., Snyder, C., Kremser, W., Brunauer, R., Holzer, H., and St\u00f6ggl, T. (2020). Classification of alpine skiing styles using GNSS and inertial measurement units. Sensors, 20.","DOI":"10.3390\/s20154232"},{"key":"ref_58","unstructured":"Anguita, D., Ghio, A., Oneto, L., Parra, X., and Reyes-Ortiz, J.L. (2013, January 24\u201326). A public domain dataset for human activity recognition using smartphones. Proceedings of the ESANN: European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Bruges, Belgium."},{"key":"ref_59","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_60","unstructured":"Huber, P.J. (1992). Breakthroughs in Statistics: Methodology and Distribution, Springer."},{"key":"ref_61","doi-asserted-by":"crossref","first-page":"111626","DOI":"10.1109\/ACCESS.2020.3001531","article-title":"Approximating the gradient of cross-entropy loss function","volume":"8","author":"Li","year":"2020","journal-title":"IEEE Access"},{"key":"ref_62","doi-asserted-by":"crossref","unstructured":"Banos, O., Garcia, R., Holgado-Terriza, J.A., Damas, M., Pomares, H., Rojas, I., Saez, A., and Villalonga, C. (2014, January 2\u20135). mHealthDroid: A novel framework for agile development of mobile health applications. Proceedings of the Ambient Assisted Living and Daily Activities: 6th International Work-Conference, IWAAL 2014, Belfast, UK. Proceedings 6.","DOI":"10.1007\/978-3-319-13105-4_14"},{"key":"ref_63","doi-asserted-by":"crossref","unstructured":"Reiss, A., and Stricker, D. (2012, January 18\u201322). Introducing a new benchmarked dataset for activity monitoring. Proceedings of the 2012 16th International Symposium on Wearable Computers, Newcastle, UK.","DOI":"10.1109\/ISWC.2012.13"},{"key":"ref_64","doi-asserted-by":"crossref","unstructured":"Zhang, M., and Sawchuk, A.A. (2012, January 5\u20138). USC-HAD: A daily activity dataset for ubiquitous activity recognition using wearable sensors. Proceedings of the 2012 ACM Conference on Ubiquitous Computing, Pittsburgh, PA, USA.","DOI":"10.1145\/2370216.2370438"},{"key":"ref_65","doi-asserted-by":"crossref","unstructured":"Zhang, S., Li, Y., Zhang, S., Shahabi, F., Xia, S., Deng, Y., and Alshurafa, N. (2022). Deep learning in human activity recognition with wearable sensors: A review on advances. Sensors, 22.","DOI":"10.3390\/s22041476"},{"key":"ref_66","doi-asserted-by":"crossref","unstructured":"Azadi, B., Haslgr\u00fcbler, M., Anzengruber-Tanase, B., Gr\u00fcnberger, S., and Ferscha, A. (2022). Alpine skiing activity recognition using smartphone\u2019s IMUs. Sensors, 22.","DOI":"10.3390\/s22155922"},{"key":"ref_67","unstructured":"Grosse, R. (2018). Lecture 9: Generalization, University of Toronto."},{"key":"ref_68","unstructured":"Powers, D.M. (2020). Evaluation: From precision, recall and F-measure to ROC, informedness, markedness and correlation. arXiv."},{"key":"ref_69","unstructured":"Agarap, A.F. (2018). Deep learning using rectified linear units (relu). arXiv."},{"key":"ref_70","unstructured":"Klambauer, G., Unterthiner, T., Mayr, A., and Hochreiter, S. (2017). Self-normalizing neural networks. Adv. Neural Inf. Process. Syst., 30."},{"key":"ref_71","unstructured":"Clevert, D.A., Unterthiner, T., and Hochreiter, S. (2015). Fast and accurate deep network learning by exponential linear units (elus). arXiv."},{"key":"ref_72","unstructured":"Ramachandran, P., Zoph, B., and Le, Q.V. (2017). Searching for activation functions. arXiv."},{"key":"ref_73","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1016\/j.neucom.2022.09.099","article-title":"Two-stream transformer network for sensor-based human activity recognition","volume":"512","author":"Xiao","year":"2022","journal-title":"Neurocomputing"},{"key":"ref_74","unstructured":"Standley, T., Zamir, A., Chen, D., Guibas, L., Malik, J., and Savarese, S. (2020, January 13\u201318). Which tasks should be learned together in multi-task learning?. Proceedings of the International Conference on Machine Learning, Virtual."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/2\/681\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T13:46:39Z","timestamp":1760103999000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/2\/681"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,21]]},"references-count":74,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2024,1]]}},"alternative-id":["s24020681"],"URL":"https:\/\/doi.org\/10.3390\/s24020681","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,21]]}}}