{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T05:02:38Z","timestamp":1768885358285,"version":"3.49.0"},"reference-count":31,"publisher":"MDPI AG","issue":"15","license":[{"start":{"date-parts":[[2022,7,28]],"date-time":"2022-07-28T00:00:00Z","timestamp":1658966400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Samsung-UFAM Project for Education and Research (SUPER)","award":["n\u00b06.008\/2006 (SU-FRAMA)"],"award-info":[{"award-number":["n\u00b06.008\/2006 (SU-FRAMA)"]}]},{"name":"Samsung-UFAM Project for Education and Research (SUPER)","award":["n\u00b08.387\/1991"],"award-info":[{"award-number":["n\u00b08.387\/1991"]}]},{"name":"Samsung Electronics of Amazonia Ltd.","award":["n\u00b06.008\/2006 (SU-FRAMA)"],"award-info":[{"award-number":["n\u00b06.008\/2006 (SU-FRAMA)"]}]},{"name":"Samsung Electronics of Amazonia Ltd.","award":["n\u00b08.387\/1991"],"award-info":[{"award-number":["n\u00b08.387\/1991"]}]},{"name":"CAPES","award":["n\u00b06.008\/2006 (SU-FRAMA)"],"award-info":[{"award-number":["n\u00b06.008\/2006 (SU-FRAMA)"]}]},{"name":"CAPES","award":["n\u00b08.387\/1991"],"award-info":[{"award-number":["n\u00b08.387\/1991"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Due to wearables\u2019 popularity, human activity recognition (HAR) plays a significant role in people\u2019s routines. Many deep learning (DL) approaches have studied HAR to classify human activities. Previous studies employ two HAR validation approaches: subject-dependent (SD) and subject-independent (SI). Using accelerometer data, this paper shows how to generate visual explanations about the trained models\u2019 decision making on both HAR and biometric user identification (BUI) tasks and the correlation between them. We adapted gradient-weighted class activation mapping (grad-CAM) to one-dimensional convolutional neural networks (CNN) architectures to produce visual explanations of HAR and BUI models. Our proposed networks achieved 0.978 and 0.755 accuracy, employing both SD and SI. The proposed BUI network achieved 0.937 average accuracy. We demonstrate that HAR\u2019s high performance with SD comes not only from physical activity learning but also from learning an individual\u2019s signature, as in BUI models. Our experiments show that CNN focuses on larger signal sections in BUI, while HAR focuses on smaller signal segments. We also use the grad-CAM technique to identify database bias problems, such as signal discontinuities. Combining explainable techniques with deep learning can help models design, avoid results overestimation, find bias problems, and improve generalization capability.<\/jats:p>","DOI":"10.3390\/s22155644","type":"journal-article","created":{"date-parts":[[2022,7,28]],"date-time":"2022-07-28T22:43:26Z","timestamp":1659048206000},"page":"5644","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Explaining One-Dimensional Convolutional Models in Human Activity Recognition and Biometric Identification Tasks"],"prefix":"10.3390","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3299-3337","authenticated-orcid":false,"given":"Gustavo","family":"Aquino","sequence":"first","affiliation":[{"name":"R&D Center in Electronic and Information Technology, Federal University of Amazonas, Manaus 69077-000, Brazil"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6839-1402","authenticated-orcid":false,"given":"Marly G. F.","family":"Costa","sequence":"additional","affiliation":[{"name":"R&D Center in Electronic and Information Technology, Federal University of Amazonas, Manaus 69077-000, Brazil"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3325-5715","authenticated-orcid":false,"given":"Cicero F. F.","family":"Costa Filho","sequence":"additional","affiliation":[{"name":"R&D Center in Electronic and Information Technology, Federal University of Amazonas, Manaus 69077-000, Brazil"}]}],"member":"1968","published-online":{"date-parts":[[2022,7,28]]},"reference":[{"key":"ref_1","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_2","unstructured":"Meticulous Research (2022, July 24). Wearable Devices Market by Product Type (Smartwatch, Earwear, Eyewear, and others), End-Use Industry(Consumer Electronics, Healthcare, Enterprise and Industrial, Media and Entertainment), Connectivity Medium, and Region\u2014Global Forecast to 2025. Available online: https:\/\/www.meticulousresearch.com\/product\/wearable-devices-market-5050."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1143","DOI":"10.1002\/cphy.c110025","article-title":"Lack of exercise is a major cause of chronic diseases","volume":"2","author":"Booth","year":"2012","journal-title":"Compr. Physiol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1007\/s40860-021-00147-0","article-title":"Trends in human activity recognition using smartphones","volume":"7","author":"Ferrari","year":"2021","journal-title":"J. Reliab. Intell. Environ."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Medrano, C., Igual, R., Plaza, I., and Castro, M. (2014). Detecting falls as novelties in acceleration patterns acquired with smartphones. PLoS ONE, 9.","DOI":"10.1371\/journal.pone.0094811"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1007\/s41050-021-00028-8","article-title":"Human Activity Recognition from Accelerometer with Convolutional and Recurrent Neural Networks","volume":"4","author":"Aquino","year":"2021","journal-title":"Polytechnica"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Micucci, D., Mobilio, M., and Napoletano, P. (2017). UniMiB SHAR: A Dataset for Human Activity Recognition Using Acceleration Data from Smartphones. Appl. Sci., 7.","DOI":"10.20944\/preprints201706.0033.v2"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1016\/j.maturitas.2018.04.012","article-title":"From A to Z: Wearable technology explained","volume":"113","author":"Godfrey","year":"2018","journal-title":"Maturitas"},{"key":"ref_9","first-page":"361","article-title":"Development of cnn-based visual recognition air conditioner for smart buildings","volume":"25","author":"Huang","year":"2020","journal-title":"J. Inf. Technol. Constr."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Bragan\u00e7a, H., Colonna, J.G., Oliveira, H.A.B.F., and Souto, E. (2022). How Validation Methodology Influences Human Activity Recognition Mobile Systems. Sensors, 22.","DOI":"10.3390\/s22062360"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Mekruksavanich, S., and Jitpattanakul, A. (2021). Biometric user identification based on human activity recognition using wearable sensors: An experiment using deep learning models. Electronics, 10.","DOI":"10.3390\/electronics10030308"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017, January 22\u201329). Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization. Proceedings of the 2017 IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"2059","DOI":"10.3390\/s150102059","article-title":"A survey of online activity recognition using mobile phones","volume":"15","author":"Shoaib","year":"2015","journal-title":"Sensors"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Vavoulas, G., Chatzaki, C., Malliotakis, T., Pediaditis, M., and Tsiknakis, M. (2016, January 21\u201322). The MobiAct Dataset: Recognition of Activities of Daily Living using Smartphones. Proceedings of the ICT4AgeingWell, Rome, Italy.","DOI":"10.5220\/0005792401430151"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Sadiq, S., Massie, S., Wiratunga, N., and Cooper, K. (2017, January 19\u201320). Learning, Deep and Shallow Features for Human Activity Recognition. Proceedings of the Knowledge Science, Engineering and Management, Melbourne, VIC, Australia.","DOI":"10.1007\/978-3-319-63558-3_40"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1109\/TST.2014.6838194","article-title":"Activity Recognition with Smartphone Sensors","volume":"19","author":"Su","year":"2014","journal-title":"Tsinghua Sci. Technol."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Rad, N.M., van Laarhoven, T., Furlanello, C., and Marchiori, E. (2018). Novelty detection using deep normative modeling for imu-based abnormal movement monitoring in parkinson\u2019s disease and autism spectrum disorders. Sensors, 18.","DOI":"10.3390\/s18103533"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"32066","DOI":"10.1109\/ACCESS.2020.2973425","article-title":"On the Personalization of Classification Models for Human Activity Recognition","volume":"8","author":"Ferrari","year":"2020","journal-title":"IEEE Access"},{"key":"ref_19","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., and Torralba, A. (2022, July 24). Learning Deep Features for Discriminative Localization. Available online: http:\/\/cnnlocalization.csail.mit.edu."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Li, F., Shirahama, K., Nisar, M.A., K\u00f6ping, L., and Grzegorzek, M. (2018). Comparison of feature learning methods for human activity recognition using wearable sensors. Sensors, 18.","DOI":"10.3390\/s18020679"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"18063","DOI":"10.1109\/JSEN.2021.3085360","article-title":"Block-Wise Training Residual Networks on Multi-Channel Time Series for Human Activity Recognition","volume":"21","author":"Teng","year":"2021","journal-title":"IEEE Sens. J."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Juefei-Xu, F., Bhagavatula, C., Jaech, A., Prasad, U., and Savvides, M. (2012, January 23\u201327). Gait-ID on the Move: Pace Independent Human Identification Using Cell Phone Accelerometer Dynamics. Proceedings of the 2012 IEEE Fifth International Conference on Biometrics: Theory, Applications and Systems (BTAS), Arlington, VA, USA.","DOI":"10.1109\/BTAS.2012.6374552"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1016\/j.eswa.2016.04.032","article-title":"Human activity recognition with smartphone sensors using deep learning neural networks","volume":"59","author":"Ronao","year":"2016","journal-title":"Expert Syst. Appl."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"31663","DOI":"10.1007\/s11042-020-09537-7","article-title":"EnsemConvNet: A deep learning approach for human activity recognition using smartphone sensors for healthcare applications","volume":"79","author":"Mukherjee","year":"2020","journal-title":"Multimed. Tools Appl."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"581","DOI":"10.1109\/JSEN.2020.3015521","article-title":"Layer-Wise Training Convolutional Neural Networks with Smaller Filters for Human Activity Recognition Using Wearable Sensors","volume":"21","author":"Tang","year":"2020","journal-title":"IEEE Sens. J."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"68320","DOI":"10.1109\/ACCESS.2020.2986246","article-title":"A Hybrid Network Based on Dense Connection and Weighted Feature Aggregation for Human Activity Recognition","volume":"8","author":"Lv","year":"2020","journal-title":"IEEE Access"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"5889","DOI":"10.1109\/JSEN.2022.3149337","article-title":"Real-time Human Activity Recognition Using Conditionally Parametrized Convolutions on Mobile and Wearable Devices","volume":"22","author":"Cheng","year":"2022","journal-title":"IEEE Sens. J."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"de Sousa, I.P., Vellasco, M.M.B.R., and da Silva, E.C. (2021). Explainable artificial intelligence for bias detection in covid ct-scan classifiers. Sensors, 21.","DOI":"10.3390\/s21165657"},{"key":"ref_29","unstructured":"Bengio, Y., Courville, A., and Vincent, P. (2022, July 24). Representation Learning: A Review and New Perspectives. Available online: http:\/\/www.image-net.org\/challenges\/LSVRC\/2012\/results.html."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"2839","DOI":"10.1016\/j.patcog.2015.03.009","article-title":"Performance evaluation of classification algorithms by k-fold and leave-one-out cross validation","volume":"48","author":"Wong","year":"2015","journal-title":"Pattern Recognit."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Shen, C., Chen, Y., and Yang, G. (March, January 29). On motion-sensor behavior analysis for human-activity recognition via smartphones. Proceedings of the 2016 IEEE International Conference on Identity, Security and Behavior Analysis (ISBA), Sendai, Japan.","DOI":"10.1109\/ISBA.2016.7477231"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/15\/5644\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T23:58:06Z","timestamp":1760140686000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/15\/5644"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,28]]},"references-count":31,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2022,8]]}},"alternative-id":["s22155644"],"URL":"https:\/\/doi.org\/10.3390\/s22155644","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7,28]]}}}