{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T17:54:26Z","timestamp":1774720466632,"version":"3.50.1"},"reference-count":33,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2023,3,30]],"date-time":"2023-03-30T00:00:00Z","timestamp":1680134400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Wi-Fi-based human activity recognition (HAR) has gained considerable attention recently due to its ease of use and the availability of its infrastructures and sensors. Channel state information (CSI) captures how Wi-Fi signals are transmitted through the environment. Using channel state information of the received signals transmitted from Wi-Fi access points, human activity can be recognized with more accuracy compared with the received signal strength indicator (RSSI). However, in many scenarios and applications, there is a serious limit in the volume of training data because of cost, time, or resource constraints. In this study, multiple deep learning models have been trained for HAR to achieve an acceptable accuracy level while using less training data compared to other machine learning techniques. To do so, a pretrained encoder which is trained using only a limited number of data samples, is utilized for feature extraction. Then, by using fine-tuning, this encoder is utilized in the classifier, which is trained by a fraction of the rest of the data, and the training is continued alongside the rest of the classifier\u2019s layers. Simulation results show that by using only 50% of the training data, there is a 20% improvement compared with the case where the encoder is not used. We also showed that by using an untrainable encoder, an accuracy improvement of 11% using 50% of the training data is achievable with a lower complexity level.<\/jats:p>","DOI":"10.3390\/s23073591","type":"journal-article","created":{"date-parts":[[2023,3,30]],"date-time":"2023-03-30T02:23:46Z","timestamp":1680143026000},"page":"3591","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["CSI-Based Human Activity Recognition Using Multi-Input Multi-Output Autoencoder and Fine-Tuning"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8046-825X","authenticated-orcid":false,"given":"Mahnaz","family":"Chahoushi","sequence":"first","affiliation":[{"name":"Cognitive Telecommunication Research Group, Department of Telecommunications, Faculty of Electrical Engineering, Shahid Beheshti University, Tehran 19839 69411, Iran"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4847-9829","authenticated-orcid":false,"given":"Mohammad","family":"Nabati","sequence":"additional","affiliation":[{"name":"Cognitive Telecommunication Research Group, Department of Telecommunications, Faculty of Electrical Engineering, Shahid Beheshti University, Tehran 19839 69411, Iran"}]},{"given":"Reza","family":"Asvadi","sequence":"additional","affiliation":[{"name":"Cognitive Telecommunication Research Group, Department of Telecommunications, Faculty of Electrical Engineering, Shahid Beheshti University, Tehran 19839 69411, Iran"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2910-9208","authenticated-orcid":false,"given":"Seyed Ali","family":"Ghorashi","sequence":"additional","affiliation":[{"name":"Cognitive Telecommunication Research Group, Department of Telecommunications, Faculty of Electrical Engineering, Shahid Beheshti University, Tehran 19839 69411, Iran"},{"name":"Department of Computer Science & Digital Technologies, School of Architecture, Computing and Engineering, University of East London, London E16 2RD, UK"}]}],"member":"1968","published-online":{"date-parts":[[2023,3,30]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1629","DOI":"10.1109\/COMST.2019.2934489","article-title":"Wireless Sensing for Human Activity: A Survey","volume":"22","author":"Liu","year":"2019","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1192","DOI":"10.1109\/LCOMM.2020.3047352","article-title":"Joint Coordinate Optimization in Fingerprint-Based Indoor Positioning","volume":"25","author":"Nabati","year":"2020","journal-title":"IEEE Commun. Lett."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"107066","DOI":"10.1016\/j.asoc.2020.107066","article-title":"Device-free single-user activity recognition using diversified deep ensemble learning","volume":"102","author":"Cui","year":"2021","journal-title":"Appl. Soft Comput."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Wang, X., Yang, C., and Mao, S. (2017, January 4\u20138). ResBeat: Resilient Breathing Beats Monitoring with Realtime Bimodal CSI Data. Proceedings of the GLOBECOM 2017 IEEE Global Communications Conference, Singapore.","DOI":"10.1109\/GLOCOM.2017.8255021"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1109\/TMC.2020.3012784","article-title":"Attention-Based Gait Recognition and Walking Direction Estimation in Wi-Fi Networks","volume":"21","author":"Xu","year":"2020","journal-title":"IEEE Trans. Mob. Comput."},{"key":"ref_6","unstructured":"Hindawi (2022, September 15). A Framework for Human Activity Recognition Based on WiFi CSI Signal Enhancement. Available online: https:\/\/www.hindawi.com\/journals\/ijap\/2021\/6654752\/."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"5993","DOI":"10.1007\/s00521-021-06787-w","article-title":"Utilizing deep learning models in CSI-based human activity recognition","volume":"34","author":"Shalaby","year":"2022","journal-title":"Neural Comput. Appl."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Dua, N., Singh, S.N., Challa, S.K., and Semwal, V.B. (2022, January 21\u201322). A Survey on Human Activity Recognition Using Deep Learning Techniques and Wearable Sensor Data. Proceedings of the International Conference on Machine Learning, Image Processing, Network Security and Data Sciences, Virtual. Available online: https:\/\/link.springer.com\/chapter\/10.1007\/978-3-031-24352-3_5.","DOI":"10.1007\/978-3-031-24352-3_5"},{"key":"ref_9","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_10","doi-asserted-by":"crossref","first-page":"260","DOI":"10.1016\/j.neucom.2020.02.137","article-title":"Towards CSI-based diversity activity recognition via LSTM-CNN encoder-decoder neural network","volume":"444","author":"Guo","year":"2020","journal-title":"Neurocomputing"},{"key":"ref_11","unstructured":"Hindawi (2022, September 12). A Deep Learning-Based Framework for Human Activity Recognition in Smart Homes. Available online: https:\/\/www.hindawi.com\/journals\/misy\/2021\/6961343\/."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Vrskova, R., Kamencay, P., Hudec, R., and Sykora, P. (2023). A New Deep-Learning Method for Human Activity Recognition. Sensors, 23.","DOI":"10.3390\/s23052816"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Li, J., Xu, H., and Wang, Y. (2023). Multi-resolution Fusion Convolutional Network for Open Set Human Activity Recognition. IEEE Internet Things J., Early Access.","DOI":"10.1109\/JIOT.2023.3243476"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"340","DOI":"10.1016\/j.future.2023.01.006","article-title":"Human activity recognition using marine predators algorithm with deep learning","volume":"142","author":"Helmi","year":"2023","journal-title":"Futur. Gener. Comput. Syst."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"6000204","DOI":"10.1109\/LSENS.2020.2971555","article-title":"Using Synthetic Data to Enhance the Accuracy of Fingerprint-Based Localization: A Deep Learning Approach","volume":"4","author":"Nabati","year":"2020","journal-title":"IEEE Sensors Lett."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"17345","DOI":"10.1109\/JIOT.2021.3080401","article-title":"Multimodal CSI-Based Human Activity Recognition Using GANs","volume":"8","author":"Wang","year":"2021","journal-title":"IEEE Internet Things J."},{"key":"ref_17","unstructured":"(2022, December 05). Challenges and Corresponding Solutions of Generative Adversarial Networks (GANs): A Survey Study\u2014IOPscience. Available online: https:\/\/iopscience.iop.org\/article\/10.1088\/1742-6596\/1827\/1\/012066\/meta."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1007\/s10796-020-09992-5","article-title":"Atypical Sample Regularizer Autoencoder for Cross-Domain Human Activity Recognition","volume":"23","author":"Prabono","year":"2020","journal-title":"Inf. Syst. Front."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Moshiri, P.F., Shahbazian, R., Nabati, M., and Ghorashi, S.A. (2021). A CSI-Based Human Activity Recognition Using Deep Learning. Sensors, 21.","DOI":"10.3390\/s21217225"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"76592","DOI":"10.1109\/ACCESS.2021.3082627","article-title":"Device-Free Human Activity Recognition Based on GMM-HMM Using Channel State Information","volume":"9","author":"Cheng","year":"2021","journal-title":"IEEE Access"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"161502","DOI":"10.1007\/s11704-021-0407-8","article-title":"Cross-scene passive human activity recognition using commodity WiFi","volume":"16","author":"Fang","year":"2021","journal-title":"Front. Comput. Sci."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Su, J., Liao, Z., Sheng, Z., Liu, A.X., Singh, D., and Lee, H.-N. (IEEE Sens. J., 2022). Human Activity Recognition Using Self-powered Sensors Based on Multilayer Bi-directional Long Short-Term Memory Networks, IEEE Sens. J., Early Access.","DOI":"10.1109\/JSEN.2022.3195274"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1109\/MCOM.2017.1700082","article-title":"A Survey on Behavior Recognition Using WiFi Channel State Information","volume":"55","author":"Yousefi","year":"2017","journal-title":"IEEE Commun. Mag."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"166624","DOI":"10.1109\/ACCESS.2021.3134794","article-title":"CSI-IANet: An Inception Attention Network for Human-Human Interaction Recognition Based on CSI Signal","volume":"9","author":"Kabir","year":"2021","journal-title":"IEEE Access"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Ng, H.-W., Nguyen, V.D., Vonikakis, V., and Winkler, S. (2015, January 9). Deep Learning for Emotion Recognition on Small Datasets Using Transfer Learning. Proceedings of the 2015 ACM on International Conference on Multimodal Interaction, New York, NY, USA.","DOI":"10.1145\/2818346.2830593"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Geng, C., Huang, H., and Langerman, J. (2020, January 20\u201323). Multipoint Channel Charting with Multiple-Input Multiple-Output Convolutional Autoencoder. Proceedings of the 2020 IEEE\/ION Position, Location and Navigation Symposium (PLANS), Portland, OR, USA.","DOI":"10.1109\/PLANS46316.2020.9109875"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1007\/s42979-020-0070-4","article-title":"Literature Review on Transfer Learning for Human Activity Recognition Using Mobile and Wearable Devices with Environmental Technology","volume":"1","author":"Hernandez","year":"2020","journal-title":"SN Comput. Sci."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"202","DOI":"10.1016\/j.procs.2022.12.023","article-title":"Time Complexity in Deep Learning Models","volume":"215","author":"Shah","year":"2022","journal-title":"Procedia Comput. Sci."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_30","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_31","doi-asserted-by":"crossref","first-page":"17627","DOI":"10.1109\/ACCESS.2017.2746095","article-title":"Internal Transfer Learning for Improving Performance in Human Action Recognition for Small Datasets","volume":"5","author":"Wang","year":"2017","journal-title":"IEEE Access"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1565","DOI":"10.1007\/s11063-021-10695-4","article-title":"ORVAE: One-Class Residual Variational Autoencoder for Voice Activity Detection in Noisy Environment","volume":"54","author":"Khalid","year":"2022","journal-title":"Neural Process. Lett."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: Synthetic Minority Over-sampling Technique","volume":"16","author":"Chawla","year":"2002","journal-title":"J. Artif. Intell. Res."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/7\/3591\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T19:06:48Z","timestamp":1760123208000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/7\/3591"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,30]]},"references-count":33,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2023,4]]}},"alternative-id":["s23073591"],"URL":"https:\/\/doi.org\/10.3390\/s23073591","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,30]]}}}