Combinative model compression approach for enhancing 1D CNN efficiency for EIT-based Hand Gesture Recognition on IoT edge devices
Tiny Machine Learning is rapidly evolving in edge computing and intelligent Internet of Things (IoT) devices. This paper investigates model compression techniques with the aim of determining their compatibility when combined, and identifying an effective approach to improve inference speed and energ...
Uložené v:
| Vydané v: | Internet of things (Amsterdam. Online) Ročník 28; s. 101403 |
|---|---|
| Hlavní autori: | , , , , |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
Elsevier B.V
01.12.2024
|
| Predmet: | |
| ISSN: | 2542-6605, 2542-6605 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | Tiny Machine Learning is rapidly evolving in edge computing and intelligent Internet of Things (IoT) devices. This paper investigates model compression techniques with the aim of determining their compatibility when combined, and identifying an effective approach to improve inference speed and energy efficiency within IoT edge devices. The study is carried out on the application scenario of Hand Gesture Recognition (HGR) based on Electrical Impedance Tomography (EIT), which involves complex signal processing and needs real-time processing and energy efficiency. Therefore, a customized 1-Dimensional Convolutional Neural Network (1D CNN) HGR classification model has been designed. An approach based on strategically combining model compression techniques was then implemented resulting in a model customized for faster inference and improved energy efficiency for IoT embedded devices. The model size became compact at 10.42 kB, resulting in a substantial size reduction of 98.8%, and an inference gain of 94.73% on a personal computer with approximately 8.56% decrease in accuracy. The approach of combinative model compression techniques was applied to a wide range of edge-computing IoT devices with limited processing power, resulting in a significant improvement in model execution speed and energy efficiency for these devices. Specifically, there was an average power consumption gain of 52% for Arduino Nano BLE and 34.05% for Raspberry Pi 4. Inference time was halved for Arduino Nano BLE Sense, Nicla Sense, and Raspberry Pi 4, with a remarkable gain of 94% for ESP32. |
|---|---|
| AbstractList | Tiny Machine Learning is rapidly evolving in edge computing and intelligent Internet of Things (IoT) devices. This paper investigates model compression techniques with the aim of determining their compatibility when combined, and identifying an effective approach to improve inference speed and energy efficiency within IoT edge devices. The study is carried out on the application scenario of Hand Gesture Recognition (HGR) based on Electrical Impedance Tomography (EIT), which involves complex signal processing and needs real-time processing and energy efficiency. Therefore, a customized 1-Dimensional Convolutional Neural Network (1D CNN) HGR classification model has been designed. An approach based on strategically combining model compression techniques was then implemented resulting in a model customized for faster inference and improved energy efficiency for IoT embedded devices. The model size became compact at 10.42 kB, resulting in a substantial size reduction of 98.8%, and an inference gain of 94.73% on a personal computer with approximately 8.56% decrease in accuracy. The approach of combinative model compression techniques was applied to a wide range of edge-computing IoT devices with limited processing power, resulting in a significant improvement in model execution speed and energy efficiency for these devices. Specifically, there was an average power consumption gain of 52% for Arduino Nano BLE and 34.05% for Raspberry Pi 4. Inference time was halved for Arduino Nano BLE Sense, Nicla Sense, and Raspberry Pi 4, with a remarkable gain of 94% for ESP32. |
| ArticleNumber | 101403 |
| Author | Fakhfakh, Ahmed Ben Saad, Yasmine Sahnoun, Salwa Mnif, Mahdi Kanoun, Olfa |
| Author_xml | – sequence: 1 givenname: Mahdi orcidid: 0009-0002-0294-0154 surname: Mnif fullname: Mnif, Mahdi organization: National School of Electronics and Telecommunications of Sfax, University of Sfax, Tunisia – sequence: 2 givenname: Salwa surname: Sahnoun fullname: Sahnoun, Salwa organization: National School of Electronics and Telecommunications of Sfax, University of Sfax, Tunisia – sequence: 3 givenname: Yasmine surname: Ben Saad fullname: Ben Saad, Yasmine organization: National School of Electronics and Telecommunications of Sfax, University of Sfax, Tunisia – sequence: 4 givenname: Ahmed surname: Fakhfakh fullname: Fakhfakh, Ahmed organization: Laboratory of Signals, Systems, Artificial Intelligence and Networks (SM@RTS), Digital Research Center of Sfax (CRNS), Tunisia – sequence: 5 givenname: Olfa orcidid: 0000-0002-7166-1266 surname: Kanoun fullname: Kanoun, Olfa email: olfa.kanoun@etit.tu-chemnitz.de organization: Measurements and Sensor Technology, Faculty of Electrical Engineering and Information Technology, Chemnitz University of Technology, Germany |
| BookMark | eNp9kM1KAzEQgIMoWGsfwFteYGuy_8WTrLUtlAqy95CfSZvSTZZkLfTom7vbehAPhcBkmPmGme8B3VpnAaEnSqaU0Px5PzWum8YkToc8JckNGsVZGkd5TrLbP_97NAlhTwiJZ3kSJ8UIfVeuEcbyzhwBN07BAUvXtB5CMM5i3rbecbnD2nkMdsetNHaL6RuuNhsMWhtpwMrTuT5f1ZHgARRecqvwAkL35QF_gnRba7phXv9WrsagtoAVHI2E8IjuND8EmPzGMarf53W1jNYfi1X1uo5kkpIuEmLG06yYJZATXoo0K4sikVqVgmazgotcE0myolQCaFxklKRKyb431UITgGSMistY6V0IHjSTpuPDUp3n5sAoYYNLtme9Sza4ZBeXPUn_ka03Dfenq8zLhYH-oqMBz8JZFCjjQXZMOXOF_gHuiY-K |
| CitedBy_id | crossref_primary_10_1109_ACCESS_2025_3545827 crossref_primary_10_3390_s25020475 |
| Cites_doi | 10.1145/3555802 10.1007/s13042-022-01530-w 10.1109/JSEN.2021.3130982 10.1007/s44196-024-00518-4 10.1016/j.ergon.2017.02.004 10.3390/jimaging6080073 10.1145/3665278 10.1109/ICIP.2017.8297033 10.1109/ACCESS.2023.3294111 10.51594/csitrj.v5i3.929 10.1109/MCAS.2020.3005467 10.1007/s10209-021-00823-1 10.1109/JSTSP.2022.3222910 10.1145/3180155.3180220 10.1109/ACCESS.2021.3081353 10.3390/s24030920 10.1109/TWC.2024.3435017 10.1007/s10489-020-01894-y 10.3390/s21217298 10.3390/computers11020026 10.1109/ACCESS.2020.2991734 10.1109/ICIP.2018.8451766 10.3389/fnbot.2021.659311 |
| ContentType | Journal Article |
| Copyright | 2024 The Authors |
| Copyright_xml | – notice: 2024 The Authors |
| DBID | 6I. AAFTH AAYXX CITATION |
| DOI | 10.1016/j.iot.2024.101403 |
| DatabaseName | ScienceDirect Open Access Titles Elsevier:ScienceDirect:Open Access CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 2542-6605 |
| ExternalDocumentID | 10_1016_j_iot_2024_101403 S2542660524003445 |
| GroupedDBID | 0R~ 6I. AACTN AAEDW AAFTH AAKOC AALRI AAQFI AAXUO AAYFN ABMAC ACDAQ ACHRH ACRLP AEBSH AFJKZ AFKWA AFTJW AGUBO AGUMN AIALX AIEXJ AIKHN AITUG AKRWK ALMA_UNASSIGNED_HOLDINGS AMRAJ AOUOD AXJTR BELTK BJAXD BKOJK EBS EFJIC EJD FDB KOM M41 ROL SPC SPCBC SSB SSL SSR SST SSV SSZ T5K ~G- AATTM AAYWO AAYXX ABJNI ACLOT ACVFH ADCNI AEIPS AEUPX AFPUW AIGII AIIUN AKBMS AKYEP ANKPU APXCP CITATION EFKBS EFLBG FYGXN |
| ID | FETCH-LOGICAL-c340t-bb9a45793e60a8b458773cfd8b1597ab6f0c0578dbe1275104ddce604fbf0ee3 |
| ISICitedReferencesCount | 5 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001350151300001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 2542-6605 |
| IngestDate | Sat Nov 29 05:26:39 EST 2025 Tue Nov 18 22:25:53 EST 2025 Wed Dec 04 16:48:09 EST 2024 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | EIT Tiny ML Hand Gesture Recognition Lightweight models IoT devices Energy efficiency Inference time 1D CNN Model compression techniques Edge computing |
| Language | English |
| License | This is an open access article under the CC BY license. |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c340t-bb9a45793e60a8b458773cfd8b1597ab6f0c0578dbe1275104ddce604fbf0ee3 |
| ORCID | 0000-0002-7166-1266 0009-0002-0294-0154 |
| OpenAccessLink | https://dx.doi.org/10.1016/j.iot.2024.101403 |
| ParticipantIDs | crossref_citationtrail_10_1016_j_iot_2024_101403 crossref_primary_10_1016_j_iot_2024_101403 elsevier_sciencedirect_doi_10_1016_j_iot_2024_101403 |
| PublicationCentury | 2000 |
| PublicationDate | December 2024 2024-12-00 |
| PublicationDateYYYYMMDD | 2024-12-01 |
| PublicationDate_xml | – month: 12 year: 2024 text: December 2024 |
| PublicationDecade | 2020 |
| PublicationTitle | Internet of things (Amsterdam. Online) |
| PublicationYear | 2024 |
| Publisher | Elsevier B.V |
| Publisher_xml | – sequence: 0 name: Elsevier B.V |
| References | Ding, Feng, Lu, Zheng, Zhao, Meng (b10) 2022; 17 Mnif, Atitallah, El Houssaini, Sahnoun, Fakhfakh, Kanoun (b1) 2022 Liu, Fang, Zhao, Wang, Zhang (b37) 2015 Kumar, Shaikh, Li, Bilal, Yin (b40) 2021; 51 Geng, Niu (b28) 2024; 17 Oudah, Al-Naji, Chahl (b17) 2020; 6 Z. Ni, J. Chen, N. Sang, C. Gao, L. Liu, Light YOLO for high-speed gesture recognition, in: 2018 25th IEEE International Conference on Image Processing, ICIP, 2018, pp. 3099–3103. Hua, Li, Wang, Dong, Li, Cao (b7) 2023; 55 He, Xiao (b27) 2023 Kahlon, Singh (b20) 2023; 22 Li, Zhang, Cao (b23) 2022 Cao, Liu, Meng, Sun (b8) 2020; 8 Modupe, Otitoola, Oladapo, Abiona, Oyeniran, Adewusi (b9) 2024; 5 Li, Kadav, Durdanovic, Samet, Graf (b29) 2016 Yuan, Liu, Wu, Yang, Wu, Sun (b30) 2023 Liu, Wang (b16) 2018; 68 Chmurski, Zubert, Bierzynski, Santra (b4) 2021 Zhu, Li, Liu, Ma, Wang (b26) 2023 Atitallah, Hu, Bouchaala, Hussain, Ismail, Derbel, Kanoun (b34) 2021; 22 Abadade, Temouden, Bamoumen, Benamar, Chtouki, Hafid (b15) 2023 Ren, Anicic, Li, Runkler (b14) 2024; 23 K. Mullick, A.M. Namboodiri, Learning deep and compact models for gesture recognition, in: 2017 IEEE International Conference on Image Processing, ICIP, 2017, pp. 3998–4002. Ding, Zhang, Lu, Zhao, Nallanathan, Wang, Yang (b11) 2024 Wu (b38) 2017; vol. 5 Yao, Wang, Xia, Guo, Liu, Han (b19) 2024; 24 Shen, Xia, Cai, Zhang, Zhan (b24) 2023 Li, Wu, Su, Wang (b25) 2020; vol. 16 Wu, Yao, Zhang, Li, He (b32) 2022; 35 Kuang, Shao, Wang, Zuo, Ding (b39) 2022; 13 Ha, Withanachchi, Yihun (b18) 2018; 40789 Leins, Gibas, Brück, Haschke (b35) 2021; 15 Sanchez-Iborra, Skarmeta (b13) 2020; 20 Yao, Yazdani Aminabadi, Zhang, Wu, Li, He (b31) 2022; 35 Chmurski, Mauro, Santra, Zubert, Dagasan (b6) 2021; 21 Y. Tian, K. Pei, S. Jana, B. Ray, Deeptest: Automated testing of deep-neural-network-driven autonomous cars, in: The 40th International Conference on Software Engineering, 2018, pp. 303–314. Mohandas, Bhattacharya, Penica, Van Camp, Hayes (b33) 2020 Warden, Situnayake (b12) 2019 S. (b36) 2015 Yu, de Antonio, Villalba-Mora (b2) 2022; 11 Venzke, Klisch, Kubik, Ali, Missier, Turau (b5) 2020 Cao (10.1016/j.iot.2024.101403_b8) 2020; 8 Ding (10.1016/j.iot.2024.101403_b11) 2024 Venzke (10.1016/j.iot.2024.101403_b5) 2020 Chmurski (10.1016/j.iot.2024.101403_b6) 2021; 21 Ding (10.1016/j.iot.2024.101403_b10) 2022; 17 Hua (10.1016/j.iot.2024.101403_b7) 2023; 55 Warden (10.1016/j.iot.2024.101403_b12) 2019 10.1016/j.iot.2024.101403_b22 Ren (10.1016/j.iot.2024.101403_b14) 2024; 23 10.1016/j.iot.2024.101403_b21 10.1016/j.iot.2024.101403_b3 Leins (10.1016/j.iot.2024.101403_b35) 2021; 15 Geng (10.1016/j.iot.2024.101403_b28) 2024; 17 Ha (10.1016/j.iot.2024.101403_b18) 2018; 40789 Zhu (10.1016/j.iot.2024.101403_b26) 2023 Li (10.1016/j.iot.2024.101403_b25) 2020; vol. 16 Wu (10.1016/j.iot.2024.101403_b38) 2017; vol. 5 Wu (10.1016/j.iot.2024.101403_b32) 2022; 35 Abadade (10.1016/j.iot.2024.101403_b15) 2023 S. (10.1016/j.iot.2024.101403_b36) 2015 Modupe (10.1016/j.iot.2024.101403_b9) 2024; 5 He (10.1016/j.iot.2024.101403_b27) 2023 Li (10.1016/j.iot.2024.101403_b23) 2022 Chmurski (10.1016/j.iot.2024.101403_b4) 2021 Sanchez-Iborra (10.1016/j.iot.2024.101403_b13) 2020; 20 Yao (10.1016/j.iot.2024.101403_b19) 2024; 24 Kahlon (10.1016/j.iot.2024.101403_b20) 2023; 22 Oudah (10.1016/j.iot.2024.101403_b17) 2020; 6 Atitallah (10.1016/j.iot.2024.101403_b34) 2021; 22 Yao (10.1016/j.iot.2024.101403_b31) 2022; 35 Mnif (10.1016/j.iot.2024.101403_b1) 2022 Yu (10.1016/j.iot.2024.101403_b2) 2022; 11 Liu (10.1016/j.iot.2024.101403_b37) 2015 Liu (10.1016/j.iot.2024.101403_b16) 2018; 68 Kumar (10.1016/j.iot.2024.101403_b40) 2021; 51 Yuan (10.1016/j.iot.2024.101403_b30) 2023 Li (10.1016/j.iot.2024.101403_b29) 2016 Mohandas (10.1016/j.iot.2024.101403_b33) 2020 Kuang (10.1016/j.iot.2024.101403_b39) 2022; 13 Shen (10.1016/j.iot.2024.101403_b24) 2023 |
| References_xml | – volume: 17 start-page: 54 year: 2022 end-page: 65 ident: b10 article-title: Online edge learning offloading and resource management for UAV-assisted MEC secure communications publication-title: IEEE J. Sel. Top. Sign. Proces. – year: 2023 ident: b30 article-title: Benchmarking the reliability of post-training quantization: a particular focus on worst-case performance – year: 2023 ident: b24 article-title: Real-time gesture detection in complex multi-person scenarios – volume: 22 start-page: 1729 year: 2021 end-page: 1737 ident: b34 article-title: Hand sign recognition system based on EIT imaging and robust CNN classification publication-title: IEEE Sens. J. – year: 2023 ident: b26 article-title: A survey on model compression for large language models – volume: 51 start-page: 1152 year: 2021 end-page: 1160 ident: b40 article-title: Pruning filters with L1-norm and capped L1-norm for CNN compression publication-title: Appl. Intell. – reference: Y. Tian, K. Pei, S. Jana, B. Ray, Deeptest: Automated testing of deep-neural-network-driven autonomous cars, in: The 40th International Conference on Software Engineering, 2018, pp. 303–314. – volume: 8 start-page: 85714 year: 2020 end-page: 85728 ident: b8 article-title: An overview on edge computing research publication-title: IEEE Access – volume: vol. 16 start-page: 639 year: 2020 end-page: 654 ident: b25 article-title: Eagleeye: Fast sub-net evaluation for efficient neural network pruning publication-title: Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August (2020) 23–28, Proceedings, Part II – year: 2023 ident: b27 article-title: Structured pruning for deep convolutional neural networks: A survey publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – year: 2019 ident: b12 article-title: TinyML: Machine Learning with TensorFlow Lite on Arduino and Ultra-Low-Power Microcontrollers – volume: 6 start-page: 73 year: 2020 ident: b17 article-title: Hand gesture recognition based on computer vision: a review of techniques publication-title: J. Imaging – start-page: 74406 year: 2021 end-page: 74421 ident: b4 article-title: Analysis of edge-optimized deep learning classifiers for radar-based gesture recognition publication-title: IEEE Access – volume: 35 start-page: 3217 year: 2022 end-page: 3231 ident: b32 article-title: Xtc: Extreme compression for pre-trained transformers made simple and efficient publication-title: Adv. Neural Inf. Process. Syst. – volume: vol. 5 start-page: 495 year: 2017 ident: b38 article-title: Introduction to convolutional neural networks publication-title: National Key Lab for Novel Software Technology – volume: 68 start-page: 355 year: 2018 end-page: 367 ident: b16 article-title: Gesture recognition for human–robot collaboration: A review publication-title: Int. J. Ind. Ergon. – volume: 35 start-page: 27168 year: 2022 end-page: 27183 ident: b31 article-title: Efficient and affordable post-training quantization for large-scale transformers publication-title: Adv. Neural Inf. Process. Syst. – volume: 13 start-page: 2403 year: 2022 end-page: 2414 ident: b39 article-title: Network pruning via probing the importance of filters publication-title: Int. J. Mach. Learn. Cybern. – volume: 5 start-page: 693 year: 2024 end-page: 702 ident: b9 article-title: Reviewing the transformational impact of edge computing on real-time data processing and analytics publication-title: Comput. Sci. IT Res. J. – reference: Z. Ni, J. Chen, N. Sang, C. Gao, L. Liu, Light YOLO for high-speed gesture recognition, in: 2018 25th IEEE International Conference on Image Processing, ICIP, 2018, pp. 3099–3103. – year: 2022 ident: b23 article-title: MyoTac: Real-time recognition of tactical sign language based on lightweight deep neural network publication-title: Wirel. Commun. Mob. Comput. – volume: 17 start-page: 1 year: 2024 end-page: 27 ident: b28 article-title: APSSF: Adaptive CNN pruning based on structural similarity of filters publication-title: Int. J. Comput. Intell. Syst. – volume: 24 start-page: 920 year: 2024 ident: b19 article-title: Effects of training and calibration data on surface electromyogram-based recognition for upper limb amputees publication-title: Sensors – volume: 11 start-page: 26 year: 2022 ident: b2 article-title: Deep learning (CNN, RNN) applications for smart homes: a systematic review publication-title: Computers – year: 2023 ident: b15 article-title: A comprehensive survey on tinyml publication-title: IEEE Access – year: 2015 ident: b37 article-title: Implementation of training convolutional neural networks – volume: 55 start-page: 1 year: 2023 end-page: 35 ident: b7 article-title: Edge computing with artificial intelligence: A machine learning perspective publication-title: ACM Comput. Surv. – volume: 15 year: 2021 ident: b35 article-title: Toward more robust hand gesture recognition on EIT data publication-title: Front. Neurorobotics – start-page: 857 year: 2022 end-page: 863 ident: b1 article-title: Design of a wearable multi-sensor node for human movement identification based on RSSI measurements publication-title: 19th International Multi-Conference on Systems, Signals & Devices – volume: 21 start-page: 7298 year: 2021 ident: b6 article-title: Highly-optimized radar-based gesture recognition system with depthwise expansion module publication-title: Sensors – volume: 20 start-page: 4 year: 2020 end-page: 18 ident: b13 article-title: Tinyml-enabled frugal smart objects: Challenges and opportunities publication-title: IEEE Circuits Syst. Mag. – year: 2016 ident: b29 article-title: Pruning filters for efficient convnets – year: 2015 ident: b36 article-title: Instrumentierung der Bioimpedanzmessung: Optimierung mit Fokus auf die Elektroimpedanztomographie – year: 2020 ident: b5 article-title: Artificial neural networks for sensor data classification on small embedded systems – start-page: 157 year: 2020 end-page: 168 ident: b33 article-title: TensorFlow enabled deep learning model optimization for enhanced realtime person detection using raspberry pi operating at the edge publication-title: AICS – volume: 22 start-page: 1 year: 2023 end-page: 35 ident: b20 article-title: Machine translation from text to sign language: a systematic review publication-title: Univers. Access Inf. Soc. – year: 2024 ident: b11 article-title: Collaborative communication and computation for secure UAV-enabled MEC against active aerial eavesdropping publication-title: IEEE Trans. Wireless Commun. – volume: 23 start-page: 1 year: 2024 end-page: 32 ident: b14 article-title: On-device online learning and semantic management of TinyML systems publication-title: ACM Trans. Embed. Comput. Syst. – reference: K. Mullick, A.M. Namboodiri, Learning deep and compact models for gesture recognition, in: 2017 IEEE International Conference on Image Processing, ICIP, 2017, pp. 3998–4002. – volume: 40789 year: 2018 ident: b18 article-title: Force myography signal-based hand gesture classification for the implementation of real-time control system to a prosthetic hand publication-title: Front. Biomed. Dev. – year: 2023 ident: 10.1016/j.iot.2024.101403_b27 article-title: Structured pruning for deep convolutional neural networks: A survey publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: vol. 5 start-page: 495 year: 2017 ident: 10.1016/j.iot.2024.101403_b38 article-title: Introduction to convolutional neural networks – year: 2020 ident: 10.1016/j.iot.2024.101403_b5 – volume: 55 start-page: 1 issue: 9 year: 2023 ident: 10.1016/j.iot.2024.101403_b7 article-title: Edge computing with artificial intelligence: A machine learning perspective publication-title: ACM Comput. Surv. doi: 10.1145/3555802 – year: 2015 ident: 10.1016/j.iot.2024.101403_b36 – year: 2015 ident: 10.1016/j.iot.2024.101403_b37 – volume: 13 start-page: 2403 issue: 9 year: 2022 ident: 10.1016/j.iot.2024.101403_b39 article-title: Network pruning via probing the importance of filters publication-title: Int. J. Mach. Learn. Cybern. doi: 10.1007/s13042-022-01530-w – volume: 22 start-page: 1729 issue: 2 year: 2021 ident: 10.1016/j.iot.2024.101403_b34 article-title: Hand sign recognition system based on EIT imaging and robust CNN classification publication-title: IEEE Sens. J. doi: 10.1109/JSEN.2021.3130982 – year: 2023 ident: 10.1016/j.iot.2024.101403_b26 – volume: 17 start-page: 1 issue: 1 year: 2024 ident: 10.1016/j.iot.2024.101403_b28 article-title: APSSF: Adaptive CNN pruning based on structural similarity of filters publication-title: Int. J. Comput. Intell. Syst. doi: 10.1007/s44196-024-00518-4 – volume: 68 start-page: 355 year: 2018 ident: 10.1016/j.iot.2024.101403_b16 article-title: Gesture recognition for human–robot collaboration: A review publication-title: Int. J. Ind. Ergon. doi: 10.1016/j.ergon.2017.02.004 – volume: vol. 16 start-page: 639 year: 2020 ident: 10.1016/j.iot.2024.101403_b25 article-title: Eagleeye: Fast sub-net evaluation for efficient neural network pruning – volume: 6 start-page: 73 issue: 8 year: 2020 ident: 10.1016/j.iot.2024.101403_b17 article-title: Hand gesture recognition based on computer vision: a review of techniques publication-title: J. Imaging doi: 10.3390/jimaging6080073 – volume: 23 start-page: 1 issue: 4 year: 2024 ident: 10.1016/j.iot.2024.101403_b14 article-title: On-device online learning and semantic management of TinyML systems publication-title: ACM Trans. Embed. Comput. Syst. doi: 10.1145/3665278 – ident: 10.1016/j.iot.2024.101403_b22 doi: 10.1109/ICIP.2017.8297033 – year: 2023 ident: 10.1016/j.iot.2024.101403_b15 article-title: A comprehensive survey on tinyml publication-title: IEEE Access doi: 10.1109/ACCESS.2023.3294111 – year: 2023 ident: 10.1016/j.iot.2024.101403_b30 – volume: 5 start-page: 693 issue: 3 year: 2024 ident: 10.1016/j.iot.2024.101403_b9 article-title: Reviewing the transformational impact of edge computing on real-time data processing and analytics publication-title: Comput. Sci. IT Res. J. doi: 10.51594/csitrj.v5i3.929 – volume: 20 start-page: 4 issue: 3 year: 2020 ident: 10.1016/j.iot.2024.101403_b13 article-title: Tinyml-enabled frugal smart objects: Challenges and opportunities publication-title: IEEE Circuits Syst. Mag. doi: 10.1109/MCAS.2020.3005467 – start-page: 157 year: 2020 ident: 10.1016/j.iot.2024.101403_b33 article-title: TensorFlow enabled deep learning model optimization for enhanced realtime person detection using raspberry pi operating at the edge publication-title: AICS – volume: 22 start-page: 1 issue: 1 year: 2023 ident: 10.1016/j.iot.2024.101403_b20 article-title: Machine translation from text to sign language: a systematic review publication-title: Univers. Access Inf. Soc. doi: 10.1007/s10209-021-00823-1 – volume: 17 start-page: 54 issue: 1 year: 2022 ident: 10.1016/j.iot.2024.101403_b10 article-title: Online edge learning offloading and resource management for UAV-assisted MEC secure communications publication-title: IEEE J. Sel. Top. Sign. Proces. doi: 10.1109/JSTSP.2022.3222910 – ident: 10.1016/j.iot.2024.101403_b3 doi: 10.1145/3180155.3180220 – start-page: 74406 year: 2021 ident: 10.1016/j.iot.2024.101403_b4 article-title: Analysis of edge-optimized deep learning classifiers for radar-based gesture recognition publication-title: IEEE Access doi: 10.1109/ACCESS.2021.3081353 – volume: 35 start-page: 27168 year: 2022 ident: 10.1016/j.iot.2024.101403_b31 article-title: Efficient and affordable post-training quantization for large-scale transformers publication-title: Adv. Neural Inf. Process. Syst. – volume: 24 start-page: 920 issue: 3 year: 2024 ident: 10.1016/j.iot.2024.101403_b19 article-title: Effects of training and calibration data on surface electromyogram-based recognition for upper limb amputees publication-title: Sensors doi: 10.3390/s24030920 – year: 2023 ident: 10.1016/j.iot.2024.101403_b24 – start-page: 857 year: 2022 ident: 10.1016/j.iot.2024.101403_b1 article-title: Design of a wearable multi-sensor node for human movement identification based on RSSI measurements – year: 2024 ident: 10.1016/j.iot.2024.101403_b11 article-title: Collaborative communication and computation for secure UAV-enabled MEC against active aerial eavesdropping publication-title: IEEE Trans. Wireless Commun. doi: 10.1109/TWC.2024.3435017 – year: 2022 ident: 10.1016/j.iot.2024.101403_b23 article-title: MyoTac: Real-time recognition of tactical sign language based on lightweight deep neural network publication-title: Wirel. Commun. Mob. Comput. – year: 2019 ident: 10.1016/j.iot.2024.101403_b12 – year: 2016 ident: 10.1016/j.iot.2024.101403_b29 – volume: 51 start-page: 1152 year: 2021 ident: 10.1016/j.iot.2024.101403_b40 article-title: Pruning filters with L1-norm and capped L1-norm for CNN compression publication-title: Appl. Intell. doi: 10.1007/s10489-020-01894-y – volume: 21 start-page: 7298 issue: 21 year: 2021 ident: 10.1016/j.iot.2024.101403_b6 article-title: Highly-optimized radar-based gesture recognition system with depthwise expansion module publication-title: Sensors doi: 10.3390/s21217298 – volume: 35 start-page: 3217 year: 2022 ident: 10.1016/j.iot.2024.101403_b32 article-title: Xtc: Extreme compression for pre-trained transformers made simple and efficient publication-title: Adv. Neural Inf. Process. Syst. – volume: 11 start-page: 26 issue: 2 year: 2022 ident: 10.1016/j.iot.2024.101403_b2 article-title: Deep learning (CNN, RNN) applications for smart homes: a systematic review publication-title: Computers doi: 10.3390/computers11020026 – volume: 8 start-page: 85714 year: 2020 ident: 10.1016/j.iot.2024.101403_b8 article-title: An overview on edge computing research publication-title: IEEE Access doi: 10.1109/ACCESS.2020.2991734 – volume: 40789 year: 2018 ident: 10.1016/j.iot.2024.101403_b18 article-title: Force myography signal-based hand gesture classification for the implementation of real-time control system to a prosthetic hand publication-title: Front. Biomed. Dev. – ident: 10.1016/j.iot.2024.101403_b21 doi: 10.1109/ICIP.2018.8451766 – volume: 15 year: 2021 ident: 10.1016/j.iot.2024.101403_b35 article-title: Toward more robust hand gesture recognition on EIT data publication-title: Front. Neurorobotics doi: 10.3389/fnbot.2021.659311 |
| SSID | ssj0002963237 |
| Score | 2.3094146 |
| Snippet | Tiny Machine Learning is rapidly evolving in edge computing and intelligent Internet of Things (IoT) devices. This paper investigates model compression... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 101403 |
| SubjectTerms | 1D CNN Edge computing EIT Energy efficiency Hand Gesture Recognition Inference time IoT devices Lightweight models Model compression techniques Tiny ML |
| Title | Combinative model compression approach for enhancing 1D CNN efficiency for EIT-based Hand Gesture Recognition on IoT edge devices |
| URI | https://dx.doi.org/10.1016/j.iot.2024.101403 |
| Volume | 28 |
| WOSCitedRecordID | wos001350151300001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 2542-6605 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002963237 issn: 2542-6605 databaseCode: AIEXJ dateStart: 20180901 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9NAEF6FlAMcEE9RXtoDJyxHfiVeH6M2pUEoQiiHcLL2ZZI22VRtaHvtj-N_MbO7dkxpET0gJZa1sTeW59vZ2dmZbwh5L5jKY6nSMJWFCLOYw5hLRA5LFR4xkfQ5l5Zn9nM-mbDZrPjS6fysc2HOl7kx7PKyOPmvooY2EDamzt5B3E2n0ADnIHQ4gtjh-E-ChxEOq13H523r3NiwcRfuahoOcUf1beZIt2G-B_F-sDeZYHTHwg52F8Y5Gk9DnOZUcIj-9Y8wg-B-w9c66AhtTROM19MAvXKYgIVqp23vOoej3rhQBFsiFEza4QrpGRRf9YI21amTvFlULolorhaN_4fPDagl58JeXmydCBq0E3co_cbPVq0ggQN-PK_ga5XffOVzuLx_I8lasSJWDcIKNgkHg8jtfesb2rwe90nmThFjCWJLnvDnHOHcFUe9xRpjaZOst732dz7ua_NkE71YB8YdldBFiV2Urot7ZCfJ-wXrkp3heDT71Dj7ElBzieVvbZ683mG3sYbXHuVmG6ll90wfk0d-wUKHDmhPSEebp-Rhi8byGblqQY5ayNEW5GgNOQqQog3kaLxPAXJ0Czn7ewM5ipCjHnK0BTkKH4AcRchRD7nnZHowmu4dhr60RyjTLNqEQhQ868PcoAcRZyLrszxPZaWYAPM652JQRRJWEkwJjRUI4ihTSsK1WSWqSOv0BematdEvCY15VcD7rSSrGO7xw4KFacVxHiqUlvEuiep3WUpPe4_VV5blrWLcJR-aW04c58vfLs5qAZXeaHXGaAl4u_22V3f5j9fkwXZkvCHdzekP_Zbcl-ebxdnpOw-2X_Z7tvA |
| linkProvider | Elsevier |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Combinative+model+compression+approach+for+enhancing+1D+CNN+efficiency+for+EIT-based+Hand+Gesture+Recognition+on+IoT+edge+devices&rft.jtitle=Internet+of+things+%28Amsterdam.+Online%29&rft.au=Mnif%2C+Mahdi&rft.au=Sahnoun%2C+Salwa&rft.au=Ben+Saad%2C+Yasmine&rft.au=Fakhfakh%2C+Ahmed&rft.date=2024-12-01&rft.issn=2542-6605&rft.eissn=2542-6605&rft.volume=28&rft.spage=101403&rft_id=info:doi/10.1016%2Fj.iot.2024.101403&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_iot_2024_101403 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2542-6605&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2542-6605&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2542-6605&client=summon |