{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:59:06Z","timestamp":1760230746267,"version":"build-2065373602"},"reference-count":51,"publisher":"MDPI AG","issue":"16","license":[{"start":{"date-parts":[[2022,8,12]],"date-time":"2022-08-12T00:00:00Z","timestamp":1660262400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Ministry of Trade, Industry &amp; Energy of the Republic of Korea as an AI Home Platform Development Project","award":["20009496"],"award-info":[{"award-number":["20009496"]}]},{"name":"Kwangwoon University","award":["20009496"],"award-info":[{"award-number":["20009496"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Nowadays WiFi based human activity recognition (WiFi-HAR) has gained much attraction in an indoor environment due to its various benefits, including privacy and security, device free sensing, and cost-effectiveness. Recognition of human-human interactions (HHIs) using channel state information (CSI) signals is still challenging. Although some deep learning (DL) based architectures have been proposed in this regard, most of them suffer from limited recognition accuracy and are unable to support low computation resource devices due to having a large number of model parameters. To address these issues, we propose a dynamic method using a lightweight DL model (HHI-AttentionNet) to automatically recognize HHIs, which significantly reduces the parameters with increased recognition accuracy. In addition, we present an Antenna-Frame-Subcarrier Attention Mechanism (AFSAM) in our model that enhances the representational capability to recognize HHIs correctly. As a result, the HHI-AttentionNet model focuses on the most significant features, ignoring the irrelevant features, and reduces the impact of the complexity on the CSI signal. We evaluated the performance of the proposed HHI-AttentionNet model on a publicly available CSI-based HHI dataset collected from 40 individual pairs of subjects who performed 13 different HHIs. Its performance is also compared with other existing methods. These proved that the HHI-AttentionNet is the best model providing an average accuracy, F1 score, Cohen\u2019s Kappa, and Matthews correlation coefficient of 95.47%, 95.45%, 0.951%, and 0.950%, respectively, for recognition of 13 HHIs. It outperforms the best existing model\u2019s accuracy by more than 4%.<\/jats:p>","DOI":"10.3390\/s22166018","type":"journal-article","created":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T23:44:03Z","timestamp":1660607043000},"page":"6018","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["HHI-AttentionNet: An Enhanced Human-Human Interaction Recognition Method Based on a Lightweight Deep Learning Model with Attention Network from CSI"],"prefix":"10.3390","volume":"22","author":[{"given":"Islam Md","family":"Shafiqul","sequence":"first","affiliation":[{"name":"Department of Electronic Engineering, Kwangwoon University, Seoul 01897, Korea"}]},{"given":"Mir Kanon Ara","family":"Jannat","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Kwangwoon University, Seoul 01897, Korea"}]},{"given":"Jin-Woo","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Kwangwoon University, Seoul 01897, Korea"}]},{"given":"Soo-Wook","family":"Lee","sequence":"additional","affiliation":[{"name":"Kwangwoon Academy, Kwangwoon University, Seoul 01897, Korea"}]},{"given":"Sung-Hyun","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Kwangwoon University, Seoul 01897, Korea"}]}],"member":"1968","published-online":{"date-parts":[[2022,8,12]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"31715","DOI":"10.1109\/ACCESS.2018.2839766","article-title":"Human daily and sport activity recognition using a wearable inertial sensor network","volume":"6","author":"Hsu","year":"2018","journal-title":"IEEE Access"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Blank, M., Gorelick, L., Shechtman, E., Irani, M., and Basri, R. (2005, January 17\u201321). Actions as space-time shapes. Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV\u201905), Beijing, China.","DOI":"10.1109\/ICCV.2005.28"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Ahad, M.A.R. (2018, January 8\u201312). Activity recognition for health-care and related works. Proceedings of the 2018 ACM International Joint Conference and 2018 International Symposium on Pervasive and Ubiquitous Computing and Wearable Computers, Singapore.","DOI":"10.1145\/3267305.3277813"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Uddin, M.H., Ara, J.M.K., Rahman, M.H., and Yang, S.H. (2021, January 17\u201319). A Study of Real-Time Physical Activity Recognition from Motion Sensors via Smartphone Using Deep Neural Network. Proceedings of the 2021 5th International Conference on Electrical Information and Communication Technology (EICT), Khulan, Bangladesh.","DOI":"10.1109\/EICT54103.2021.9733607"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.patrec.2018.02.010","article-title":"Deep learning for sensor-based activity recognition: A survey","volume":"119","author":"Wang","year":"2019","journal-title":"Pattern Recognit. Lett."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"M\u00fcnzner, S., Schmidt, P., Reiss, A., Hanselmann, M., Stiefelhagen, R., and D\u00fcrichen, R. (2017, January 11\u201315). CNN-based sensor fusion techniques for multimodal human activity recognition. Proceedings of the 2017 ACM International Symposium on Wearable Computers, Maui, Hawaii.","DOI":"10.1145\/3123021.3123046"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"106970","DOI":"10.1016\/j.knosys.2021.106970","article-title":"A review of multimodal human activity recognition with special emphasis on classification, applications, challenges and future directions","volume":"223","author":"Yadav","year":"2021","journal-title":"Knowl.-Based Syst."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3310194","article-title":"WiFi sensing with channel state information: A survey","volume":"52","author":"Ma","year":"2019","journal-title":"ACM Comput. Surv."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Youssef, M., Mah, M., and Agrawala, A. (2007, January 25\u201329). Challenges: Device-free passive localization for wireless environments. Proceedings of the 13th Annual ACM international Conference on Mobile Computing and Networking, New Orleans, LA, USA.","DOI":"10.1145\/1287853.1287880"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"612","DOI":"10.1109\/TMC.2010.175","article-title":"See-through walls: Motion tracking using variance-based radio tomography networks","volume":"10","author":"Wilson","year":"2010","journal-title":"IEEE Trans. Mob. Comput."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"621","DOI":"10.1109\/TMC.2009.174","article-title":"Radio tomographic imaging with wireless networks","volume":"9","author":"Wilson","year":"2010","journal-title":"IEEE Trans. Mob. Comput."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"153287","DOI":"10.1109\/ACCESS.2019.2948102","article-title":"Wi-Motion: A robust human activity recognition using WiFi signals","volume":"7","author":"Li","year":"2019","journal-title":"IEEE Access"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1016\/j.neunet.2021.11.011","article-title":"CSITime: Privacy-preserving human activity recognition using WiFi channel state information","volume":"146","author":"Yadav","year":"2022","journal-title":"Neural Netw."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"2907","DOI":"10.1109\/TMC.2016.2517630","article-title":"We Can Hear You with Wi-Fi!","volume":"15","author":"Wang","year":"2016","journal-title":"IEEE Trans. Mob. Comput."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Hao, Z., Duan, Y., Dang, X., Liu, Y., and Zhang, D. (2020). Wi-SL: Contactless Fine-Grained Gesture Recognition Uses Channel State Information. Sensors, 20.","DOI":"10.3390\/s20144025"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"80058","DOI":"10.1109\/ACCESS.2019.2923743","article-title":"Joint Activity Recognition and Indoor Localization with WiFi Fingerprints","volume":"7","author":"Wang","year":"2019","journal-title":"IEEE Access"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1007\/s10776-018-0389-0","article-title":"WiDriver: Driver activity recognition system based on WiFi CSI","volume":"25","author":"Duan","year":"2018","journal-title":"Int. J. Wireless Inf. Netw."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"10483","DOI":"10.1109\/JIOT.2020.2997053","article-title":"WiReader: Adaptive Air Handwriting Recognition Based on Commercial WiFi Signal","volume":"7","author":"Guo","year":"2020","journal-title":"IEEE Internet Things J."},{"key":"ref_19","unstructured":"Wang, F., Panev, S., Dai, Z., Han, J., and Huang, D. (2019). Can WiFi estimate person pose?. arXiv."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"581","DOI":"10.1109\/TMC.2016.2557792","article-title":"Wifall: Device-free fall detection by wireless networks","volume":"16","author":"Wang","year":"2016","journal-title":"IEEE Trans. Mob. Comput."},{"key":"ref_21","first-page":"1653","article-title":"Adapted Long Short-Term Memory (LSTM) for concurrent Human Activity Recognition","volume":"69","author":"Thapa","year":"2021","journal-title":"Comput. Mater."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Kim, S.C., Tae, G.K., and Sung, H.K. (2019, January 11\u201313). Human activity recognition and prediction based on Wi-Fi channel state information and machine learning. Proceedings of the 2019 International Conference on Artificial Intelligence in Information and Communication (ICAIIC), Okinawa, Japan.","DOI":"10.1109\/ICAIIC.2019.8669046"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Alsaify, B.A., Almazari, M.M., Alazrai, R., Alouneh, S., and Daoud, M.I. (2022). A CSI-Based Multi-Environment Human Activity Recognition Framework. Appl. Sci., 12.","DOI":"10.3390\/app12020930"},{"key":"ref_24","first-page":"1550147718772541","article-title":"Log-Viterbi algorithm applied on second-order hidden Markov model for human activity recognition","volume":"14","author":"Thapa","year":"2018","journal-title":"Int. J. Distrib. Sens. Netw."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"4560365","DOI":"10.1155\/2016\/4560365","article-title":"Two-layer hidden Markov model for human activity recognition in home environments","volume":"12","author":"Kabir","year":"2016","journal-title":"Int. J. Distrib. Sens. Netw."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"7293","DOI":"10.1109\/JIOT.2019.2915989","article-title":"Wi-multi: A three-phase system for multiple human activity recognition with commercial wifi devices","volume":"6","author":"Feng","year":"2019","journal-title":"IEEE Internet Things J."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1618","DOI":"10.1109\/TMC.2011.43","article-title":"Recognizing multiuser activities using wireless body sensor networks","volume":"10","author":"Gu","year":"2011","journal-title":"IEEE Trans. Mob. Comput."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"2346","DOI":"10.1016\/j.patcog.2015.03.002","article-title":"Anatomical-plane-based representation for human-human interactions analysis","volume":"48","author":"Alazrai","year":"2015","journal-title":"Pattern Recognit."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Hsieh, C.F., Chen, Y.C., Hsieh, C.Y., and Ku, M.L. (2020, January 28\u201330). Device-free indoor human activity recognition using Wi-Fi RSSI: Machine learning approaches. Proceedings of the 2020 IEEE International Conference on Consumer Electronics-Taiwan (ICCE-Taiwan), Taoyuan, Taiwan.","DOI":"10.1109\/ICCE-Taiwan49838.2020.9258097"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Sigg, S., Blanke, U., and Troster, G. (2014, January 24\u201328). The telepathic phone: Frictionless activity recognition from WiFi-RSSI. Proceedings of the 2014 IEEE International Conference on Pervasive Computing and Communications (PerCom), Budapest, Hungary.","DOI":"10.1109\/PerCom.2014.6813955"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Chen, J., Huang, X., Jiang, H., and Miao, X. (2021). Low-cost and device-free human activity recognition based on hierarchical learning model. Sensors, 21.","DOI":"10.3390\/s21072359"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1659","DOI":"10.1109\/TVT.2016.2555986","article-title":"Device-free simultaneous wireless localization and activity recognition with wavelet feature","volume":"66","author":"Wang","year":"2016","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1016\/j.comcom.2019.09.016","article-title":"WiDet: Wi-Fi based device-free passive person detection with deep convolutional neural networks","volume":"150","author":"Huang","year":"2020","journal-title":"Comput. Commun."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"796","DOI":"10.1109\/JIOT.2015.2511805","article-title":"Paws: Passive human activity recognition based on wifi ambient signals","volume":"3","author":"Gu","year":"2015","journal-title":"IEEE Internet Things J."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"6654752","DOI":"10.1155\/2021\/6654752","article-title":"A framework for human activity recognition based on WiFi CSI signal enhancement","volume":"2021","author":"Yang","year":"2021","journal-title":"Int. J. Antennas Propag."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Damodaran, N., and Sch\u00e4fer, J. (2019, January 19\u201323). Device free human activity recognition using WiFi channel state information. Proceedings of the 2019 IEEE Smart World, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation, Leicester, UK.","DOI":"10.1109\/SmartWorld-UIC-ATC-SCALCOM-IOP-SCI.2019.00205"},{"key":"ref_37","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_38","doi-asserted-by":"crossref","first-page":"1118","DOI":"10.1109\/JSAC.2017.2679658","article-title":"Device-Free Human Activity Recognition Using Commercial WiFi Devices","volume":"35","author":"Wang","year":"2017","journal-title":"IEEE J. Sel. Areas Commun."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"296","DOI":"10.1109\/JSEN.2019.2938245","article-title":"WiAct: A passive WiFi-based human activity recognition system","volume":"20","author":"Yan","year":"2019","journal-title":"IEEE Sens. J."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Muaaz, M., Chelli, A., and P\u00e4tzold, M. (2021). Wi-Fi-based human activity recognition using convolutional neural network. Innovative and Intelligent Technology-Based Services for Smart Environments\u2013Smart Sensing and Artificial Intelligence, CRC Press.","DOI":"10.1201\/9781003181545-11"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"197695","DOI":"10.1109\/ACCESS.2020.3034849","article-title":"An end-to-end deep learning framework for recognizing human-to-human interactions using Wi-Fi signals","volume":"8","author":"Alazrai","year":"2020","journal-title":"IEEE Access"},{"key":"ref_42","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_43","doi-asserted-by":"crossref","first-page":"105668","DOI":"10.1016\/j.dib.2020.105668","article-title":"A dataset for Wi-Fi-based human-to-human interaction recognition","volume":"31","author":"Alazrai","year":"2020","journal-title":"Data Brief"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1145\/1925861.1925870","article-title":"Tool release: Gathering 802.11 n traces with channel state information","volume":"41","author":"Halperin","year":"2011","journal-title":"ACM SIGCOMM Comput. Commun. Rev."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Chollet, F. (2017, January 21\u201326). Xception: Deep learning with depthwise separable convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1111\/j.2517-6161.1974.tb00994.x","article-title":"Cross-validatory choice and assessment of statistical predictions","volume":"36","author":"Stone","year":"1974","journal-title":"J. R. Stat. Soc. Ser. B"},{"key":"ref_47","unstructured":"Kingma, D.P., and Ba, J. (2015, January 7\u20139). Adam: A method for stochastic optimization. Proceedings of the 3rd International Conference on Learning Representations, San Diego, CA, USA."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Janocha, K., and Wojciech, M.C. (2017). On loss functions for deep neural networks in classification. arXiv.","DOI":"10.4467\/20838476SI.16.004.6185"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Islam, M., Shafiqul, K.T., and Sung-Hyun, Y. (2022). Epileptic-Net: An Improved Epileptic Seizure Detection System Using Dense Convolutional Block with Attention Network from EEG. Sensors, 22.","DOI":"10.3390\/s22030728"},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Alazrai, R., Awad, A., Alsaify, B.A., and Daoud, M.I. (2021, January 24\u201326). A wi-fi-based approach for recognizing human-human interactions. Proceedings of the 2021 12th International Conference on Information and Communication Systems (ICICS), Valencia, Spain.","DOI":"10.1109\/ICICS52457.2021.9464570"},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Yao, L., Nie, F., Sheng, Q.Z., Gu, T., Li, X., and Wang, S. (2016, January 12\u201316). Learning from less for better: Semi-supervised activity recognition via shared structure discovery. Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing, Heidelberg, Germany.","DOI":"10.1145\/2971648.2971701"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/16\/6018\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:07:42Z","timestamp":1760141262000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/16\/6018"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,12]]},"references-count":51,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2022,8]]}},"alternative-id":["s22166018"],"URL":"https:\/\/doi.org\/10.3390\/s22166018","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2022,8,12]]}}}