{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T20:00:42Z","timestamp":1775073642269,"version":"3.50.1"},"reference-count":41,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2025,2,14]],"date-time":"2025-02-14T00:00:00Z","timestamp":1739491200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001654","name":"German Academic Exchange Service (DAAD)","doi-asserted-by":"publisher","award":["57645446"],"award-info":[{"award-number":["57645446"]}],"id":[{"id":"10.13039\/501100001654","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001654","name":"German Academic Exchange Service (DAAD)","doi-asserted-by":"publisher","award":["57647374"],"award-info":[{"award-number":["57647374"]}],"id":[{"id":"10.13039\/501100001654","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001654","name":"German Academic Exchange Service (DAAD)","doi-asserted-by":"publisher","award":["416228727\u2013SFB 1410"],"award-info":[{"award-number":["416228727\u2013SFB 1410"]}],"id":[{"id":"10.13039\/501100001654","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Deutsche Forschungsgemeinschaft","award":["57645446"],"award-info":[{"award-number":["57645446"]}]},{"name":"Deutsche Forschungsgemeinschaft","award":["57647374"],"award-info":[{"award-number":["57647374"]}]},{"name":"Deutsche Forschungsgemeinschaft","award":["416228727\u2013SFB 1410"],"award-info":[{"award-number":["416228727\u2013SFB 1410"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Future Internet"],"abstract":"<jats:p>The rapid advancement of edge computing and Tiny Machine Learning (TinyML) has created new opportunities for deploying intelligence in resource-constrained environments. With the growing demand for intelligent Internet of Things (IoT) devices that can efficiently process complex data in real-time, there is an urgent need for innovative optimisation techniques that overcome the limitations of IoT devices and enable accurate and efficient computations. This study investigates a novel approach to optimising Convolutional Neural Network (CNN) models for Hand Gesture Recognition (HGR) based on Electrical Impedance Tomography (EIT), which requires complex signal processing, energy efficiency, and real-time processing, by simultaneously reducing input complexity and using advanced model compression techniques. By systematically reducing and halving the input complexity of a 1D CNN from 40 to 20 Boundary Voltages (BVs) and applying an innovative compression method, we achieved remarkable model size reductions of 91.75% and 97.49% for 40 and 20 BVs EIT inputs, respectively. Additionally, the Floating-Point operations (FLOPs) are significantly reduced, by more than 99% in both cases. These reductions have been achieved with a minimal loss of accuracy, maintaining the performance of 97.22% and 94.44% for 40 and 20 BVs inputs, respectively. The most significant result is the 20 BVs compressed model. In fact, at only 8.73 kB and a remarkable 94.44% accuracy, our model demonstrates the potential of intelligent design strategies in creating ultra-lightweight, high-performance CNN-based solutions for resource-constrained devices with near-full performance capabilities specifically for the case of HGR based on EIT inputs.<\/jats:p>","DOI":"10.3390\/fi17020089","type":"journal-article","created":{"date-parts":[[2025,2,17]],"date-time":"2025-02-17T12:36:57Z","timestamp":1739795817000},"page":"89","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Hybrid Solution Through Systematic Electrical Impedance Tomography Data Reduction and CNN Compression for Efficient Hand Gesture Recognition on Resource-Constrained IoT Devices"],"prefix":"10.3390","volume":"17","author":[{"given":"Salwa","family":"Sahnoun","sequence":"first","affiliation":[{"name":"National School of Electronics and Telecommunications of Sfax, University of Sfax, Sfax 3018, Tunisia"},{"name":"Laboratory of Signals, Systems, Artificial Intelligence and Networks (SM@RTS), Digital Research Center of Sfax (CRNS), Sfax University, Sfax 3021, Tunisia"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0294-0154","authenticated-orcid":false,"given":"Mahdi","family":"Mnif","sequence":"additional","affiliation":[{"name":"National School of Electronics and Telecommunications of Sfax, University of Sfax, Sfax 3018, Tunisia"},{"name":"Laboratory of Signals, Systems, Artificial Intelligence and Networks (SM@RTS), Digital Research Center of Sfax (CRNS), Sfax University, Sfax 3021, Tunisia"},{"name":"Measurements and Sensor Technology, Faculty of Electrical Engineering and Information Technology, Chemnitz University of Technology, 09126 Chemnitz, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1361-9688","authenticated-orcid":false,"given":"Bilel","family":"Ghoul","sequence":"additional","affiliation":[{"name":"National School of Electronics and Telecommunications of Sfax, University of Sfax, Sfax 3018, Tunisia"},{"name":"Laboratory of Signals, Systems, Artificial Intelligence and Networks (SM@RTS), Digital Research Center of Sfax (CRNS), Sfax University, Sfax 3021, Tunisia"},{"name":"Measurements and Sensor Technology, Faculty of Electrical Engineering and Information Technology, Chemnitz University of Technology, 09126 Chemnitz, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9500-3403","authenticated-orcid":false,"given":"Mohamed","family":"Jemal","sequence":"additional","affiliation":[{"name":"National School of Electronics and Telecommunications of Sfax, University of Sfax, Sfax 3018, Tunisia"},{"name":"Laboratory of Signals, Systems, Artificial Intelligence and Networks (SM@RTS), Digital Research Center of Sfax (CRNS), Sfax University, Sfax 3021, Tunisia"},{"name":"Measurements and Sensor Technology, Faculty of Electrical Engineering and Information Technology, Chemnitz University of Technology, 09126 Chemnitz, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3219-2371","authenticated-orcid":false,"given":"Ahmed","family":"Fakhfakh","sequence":"additional","affiliation":[{"name":"National School of Electronics and Telecommunications of Sfax, University of Sfax, Sfax 3018, Tunisia"},{"name":"Laboratory of Signals, Systems, Artificial Intelligence and Networks (SM@RTS), Digital Research Center of Sfax (CRNS), Sfax University, Sfax 3021, Tunisia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7166-1266","authenticated-orcid":false,"given":"Olfa","family":"Kanoun","sequence":"additional","affiliation":[{"name":"Measurements and Sensor Technology, Faculty of Electrical Engineering and Information Technology, Chemnitz University of Technology, 09126 Chemnitz, Germany"}]}],"member":"1968","published-online":{"date-parts":[[2025,2,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"31297","DOI":"10.1007\/s11042-023-16875-9","article-title":"Smart home for enhanced healthcare: Exploring human machine interface oriented digital twin model","volume":"83","author":"Shoukat","year":"2024","journal-title":"Multimed. Tools Appl."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"107541","DOI":"10.1016\/j.compag.2022.107541","article-title":"Human\u2013robot collaboration systems in agricultural tasks: A review and roadmap","volume":"204","author":"Adamides","year":"2023","journal-title":"Comput. Electron. Agric."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Mourtzis, D., Angelopoulos, J., and Panopoulos, N. (2023). The future of the human\u2013machine interface (HMI) in society 5.0. Future Internet, 15.","DOI":"10.3390\/fi15050162"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"85714","DOI":"10.1109\/ACCESS.2020.2991734","article-title":"An overview on edge computing research","volume":"8","author":"Cao","year":"2020","journal-title":"IEEE Access"},{"key":"ref_5","unstructured":"Warden, P., and Situnayake, D. (2019). TinyML: Machine learning with TensorFlow Lite on Arduino and Ultra-Low-Power Microcontrollers, O\u2019Reilly Media."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1109\/MCAS.2020.3005467","article-title":"Tinyml-enabled frugal smart objects: Challenges and opportunities","volume":"20","author":"Skarmeta","year":"2020","journal-title":"IEEE Circuits Syst. Mag."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"96892","DOI":"10.1109\/ACCESS.2023.3294111","article-title":"A comprehensive survey on tinyml","volume":"11","author":"Abadade","year":"2023","journal-title":"IEEE Access."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1146\/annurev.bioeng.8.061505.095716","article-title":"Bioimpedance tomography (electrical impedance tomography)","volume":"8","author":"Bayford","year":"2006","journal-title":"Annu. Rev. Biomed. Eng."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"300","DOI":"10.1109\/THMS.2021.3086003","article-title":"Human\u2013machine interaction sensing technology based on hand gesture recognition: A review","volume":"51","author":"Guo","year":"2021","journal-title":"IEEE Trans.-Hum.-Mach. Syst."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"nwad298","DOI":"10.1093\/nsr\/nwad298","article-title":"Machine-learned wearable sensors for real-time hand-motion recognition: Toward practical applications","volume":"11","author":"Pyun","year":"2024","journal-title":"Natl. Sci. Rev."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1581","DOI":"10.1007\/s40747-023-01173-6","article-title":"Computer vision-based hand gesture recognition for human\u2013robot interaction: A review","volume":"10","author":"Qi","year":"2024","journal-title":"Complex Intell. Syst."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"2300359","DOI":"10.1002\/aisy.202300359","article-title":"Multimodal Human\u2013Robot Interaction for Human-Centric Smart Manufacturing: A Survey","volume":"6","author":"Wang","year":"2024","journal-title":"Adv. Intell. Syst."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1729","DOI":"10.1109\/JSEN.2021.3130982","article-title":"Hand sign recognition system based on EIT imaging and robust CNN classification","volume":"22","author":"Atitallah","year":"2021","journal-title":"IEEE Sens. J."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Yao, T., Wu, Y., Jiang, D., Bayford, R., and Demosthenous, A. (2023, January 19\u201321). A compact neural network for high accuracy bioimpedancebased hand gesture recognition. Proceedings of the 2023 IEEE Biomedical Circuits and Systems Conference (BioCAS), Toronto, ON, Canada.","DOI":"10.1109\/BioCAS58349.2023.10388679"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Vaquero-Gallardo, N., and Mart\u00ednez-Garc\u00eda, H. (2022). Electrical impedance tomography for hand gesture recognition for hmi interaction applications. J. Low Power Electron. Appl., 12.","DOI":"10.3390\/jlpea12030041"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1515\/cdbme-2023-1111","article-title":"Design of a miniaturized wearable eit system for imaging and hand gesture recognition","volume":"9","author":"Liebing","year":"2023","journal-title":"Curr. Dir. Biomed. Eng."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3555308","article-title":"Edge-computing-driven internet of things: A survey","volume":"55","author":"Kong","year":"2022","journal-title":"ACM Comput. Surv."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"10706","DOI":"10.1109\/JSEN.2020.2994292","article-title":"Real-time radar-based gesture detection and recognition built in an edge-computing platform","volume":"20","author":"Sun","year":"2020","journal-title":"IEEE Sens. J."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"74406","DOI":"10.1109\/ACCESS.2021.3081353","article-title":"Analysis of edge-optimized deep learning classifiers for radar-based gesture recognition","volume":"9","author":"Chmurski","year":"2021","journal-title":"IEEE Access"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"38999","DOI":"10.1109\/ACCESS.2021.3064390","article-title":"Gesture recognition with ultrasounds and edge computing","volume":"9","author":"Saez","year":"2021","journal-title":"IEEE Access"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"19490","DOI":"10.1109\/JSEN.2022.3194678","article-title":"Neuromorphic edge computing for biomedical applications: Gesture classification using emg signals","volume":"22","author":"Vitale","year":"2022","journal-title":"IEEE Sens. J."},{"key":"ref_22","unstructured":"Venzke, M., Klisch, D., Kubik, P., Ali, A., Missier, J.D., and Turau, V. (2020). Artificial neural networks for sensor data classification on small embedded systems. arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Mnif, M., Sahnoun, S., Kaaniche, M., Atitallah, B.B., Fakhfakh, A., and Kanoun, O. (2024, January 20\u201321). Ultra-Fast Edge Computing Approach for Hand Gesture Classification Based on EIT Measurements. Proceedings of the 2024 IEEE International Symposium on Robotic and Sensors Environments (ROSE), Chemnitz, Germany.","DOI":"10.1109\/ROSE62198.2024.10591116"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Ghoul, B., Atitallah, B.B., Barioul, R., Fakhfakh, A., and Kanoun, O. (2024, January 20\u201321). Exploring the Real-Time Capability of Electrical Impedance Tomography for Hand Sign Recognition in Robotic Hand Control. Proceedings of the 2024 IEEE International Symposium on Robotic and Sensors Environments (ROSE), Chemnitz, Germany.","DOI":"10.1109\/ROSE62198.2024.10591166"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"572","DOI":"10.1016\/j.patrec.2010.11.013","article-title":"Sign language recognition using a combination of new vision based features","volume":"32","author":"Zaki","year":"2011","journal-title":"Pattern Recognit. Lett."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Martin-Gutierrez, J., and Del Rio Guerra, M.S. (2021). Analysing touchscreen gestures: A study based on individuals with down syndrome centred on design for all. Sensors, 21.","DOI":"10.3390\/s21041328"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"9929684","DOI":"10.1155\/2021\/9929684","article-title":"Reduce surface electromyography channels for gesture recognition by multitask sparse representation and minimum redundancy maximum relevance","volume":"2021","author":"Qu","year":"2021","journal-title":"J. Healthc. Eng."},{"key":"ref_28","first-page":"507","article-title":"Laplacian score for feature selection","volume":"18","author":"He","year":"2005","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_29","unstructured":"Hinton, G., Vinyals, O., and Dean, J. (2015). Distilling the knowledge in a neural network. arXiv."},{"key":"ref_30","unstructured":"Han, S., Mao, H., and Dally, W.J. (2015). Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv."},{"key":"ref_31","unstructured":"Courbariaux, M., Hubara, I., Soudry, D., El-Yaniv, R., and Bengio, Y. (2016). Binarized neural networks: Training deep neural networks with weights and activations constrained to+ 1 or-1. arXiv."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"101459","DOI":"10.1016\/j.jocs.2021.101459","article-title":"FLOPs-efficient filter pruning via transfer scale for neural network acceleration","volume":"55","author":"Guo","year":"2021","journal-title":"J. Comput. Sci."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Chen, J., Kao, S.H., He, H., Zhuo, W., Wen, S., Lee, C.H., and Chan, S.H.G. (2023, January 17\u201324). Run, do not walk: Chasing higher FLOPS for faster neural networks. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.01157"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Ding, X., Ding, G., Han, J., and Tang, S. (2018, January 2\u20137). Auto-balanced filter pruning for efficient convolutional neural networks. Proceedings of the AAAI Conference on Artificial Intelligence, New Orleans, LA, USA.","DOI":"10.1609\/aaai.v32i1.12262"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Wei, L., Ma, Z., Yang, C., and Yao, Q. (2024). Advances in the Neural Network Quantization: A Comprehensive Review. Appl. Sci., 14.","DOI":"10.20944\/preprints202407.0076.v1"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Rokh, B., Azarpeyvand, A., and Khanteymoori, A. (2022). A comprehensive survey on model quantization for deep neural networks. arXiv.","DOI":"10.1145\/3623402"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Tu, Z., Hu, J., Chen, H., and Wang, Y. (2023, January 17\u201324). Toward accurate post-training quantization for image super resolution. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.00567"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Ghoul, B., Atitallah, B.B., Sahnoun, S., Fakhfakh, A., and Kanoun, O. (2024, January 11\u201313). Comparative Study of Data Reduction Methods in Electrical Impedance Tomography For Hand Sign Recognition. Proceedings of the 2024 IEEE 7th International Conference on Advanced Technologies, Signal and Image Processing (ATSIP), Sousse, Tunisia.","DOI":"10.1109\/ATSIP62566.2024.10639011"},{"key":"ref_39","unstructured":"Wu, J. (2017). Introduction to Convolutional Neural Networks, National Key Lab for Novel Software Technology, Nanjing University."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"101403","DOI":"10.1016\/j.iot.2024.101403","article-title":"Combinative model compression approach for enhancing 1D CNN efficiency for EIT-based Hand Gesture Recognition on IoT edge devices","volume":"28","author":"Mnif","year":"2024","journal-title":"Internet Things"},{"key":"ref_41","unstructured":"Vakili, M., Ghamsari, M., and Rezaei, M. (2020). Performance analysis and comparison of machine and deep learning algorithms for IoT data classification. arXiv."}],"container-title":["Future Internet"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-5903\/17\/2\/89\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T16:34:45Z","timestamp":1760027685000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-5903\/17\/2\/89"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,14]]},"references-count":41,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,2]]}},"alternative-id":["fi17020089"],"URL":"https:\/\/doi.org\/10.3390\/fi17020089","relation":{},"ISSN":["1999-5903"],"issn-type":[{"value":"1999-5903","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,14]]}}}