Safeguarding IoT consumer devices: Deep learning with TinyML driven real-time anomaly detection for predictive maintenance

Internet of Things (IoT) security is paramount for enterprises, as it includes several strategies, techniques, actions, and protocols that aim to alleviate the high vulnerability of cutting-edge businesses. IoT consumer devices, from smart home appliances to wearable gadgets, have become ubiquitous...

Full description

Saved in:
Bibliographic Details
Published in:Ain Shams Engineering Journal Vol. 16; no. 2; p. 103281
Main Authors: Katib, Iyad, Albassam, Emad, Sharaf, Sanaa A., Ragab, Mahmoud
Format: Journal Article
Language:English
Published: Elsevier B.V 01.02.2025
Elsevier
Subjects:
ISSN:2090-4479
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Internet of Things (IoT) security is paramount for enterprises, as it includes several strategies, techniques, actions, and protocols that aim to alleviate the high vulnerability of cutting-edge businesses. IoT consumer devices, from smart home appliances to wearable gadgets, have become ubiquitous daily, facilitating automation and seamless connectivity. However, ensuring their reliability and security presents a tremendous challenge. Anomaly detection methods offer a promising solution, especially those powered by TinyML (Machine Learning (ML) on Tiny Devices). These IoT devices can autonomously identify unusual behaviours or patterns that diverge from regular operation by leveraging the proficiencies of deep learning (DL) techniques enhanced for resource-constraint environments, like neural networks. Incorporating DL, anomaly detection, and TinyML allows real-time monitoring and proactive mitigation of malfunctions or security breaches in IoT devices. This advanced technology ensures improved reliability, privacy, and overall user experience in the dynamic landscape of connected devices, whether identifying irregular health data or detecting unauthorized access attempts on a smart door lock from the wearable fitness tracker. Therefore, this study develops a new Deep Learning technique to secure IoT consumer devices with TinyML Driven Real-time Anomaly Detection for Predictive Maintenance (DLTML-RTADPM). The DLTML-RTADPM technique aims to recognize and categorize the anomalies in IoT consumer devices. At the primary phase, the DLTML-RTADPM model normalizes the input data using Z-score normalization. In the DLTML-RTADPM method, the Fennec Fox Optimization Algorithm (FFA) is used for a high dimensionality reduction process where the optimal feature set is chosen. The DLTML-RTADPM technique implements gradient least mean squares with a bidirectional long short-term memory (GLMS-BiLSTM) approach for anomaly detection. To further improve the detection results of the DLTML-RTADPM technique, the Jaya optimization algorithm (JOA)-based hyperparameter tuning process is utilized. A series of simulations are performed on the benchmark dataset to ensure better detection outcomes of the DLTML-RTADPM model. The investigational validation of the DLTML-RTADPM method portrayed a superior accuracy value of 98.11% over other techniques.
AbstractList Internet of Things (IoT) security is paramount for enterprises, as it includes several strategies, techniques, actions, and protocols that aim to alleviate the high vulnerability of cutting-edge businesses. IoT consumer devices, from smart home appliances to wearable gadgets, have become ubiquitous daily, facilitating automation and seamless connectivity. However, ensuring their reliability and security presents a tremendous challenge. Anomaly detection methods offer a promising solution, especially those powered by TinyML (Machine Learning (ML) on Tiny Devices). These IoT devices can autonomously identify unusual behaviours or patterns that diverge from regular operation by leveraging the proficiencies of deep learning (DL) techniques enhanced for resource-constraint environments, like neural networks. Incorporating DL, anomaly detection, and TinyML allows real-time monitoring and proactive mitigation of malfunctions or security breaches in IoT devices. This advanced technology ensures improved reliability, privacy, and overall user experience in the dynamic landscape of connected devices, whether identifying irregular health data or detecting unauthorized access attempts on a smart door lock from the wearable fitness tracker. Therefore, this study develops a new Deep Learning technique to secure IoT consumer devices with TinyML Driven Real-time Anomaly Detection for Predictive Maintenance (DLTML-RTADPM). The DLTML-RTADPM technique aims to recognize and categorize the anomalies in IoT consumer devices. At the primary phase, the DLTML-RTADPM model normalizes the input data using Z-score normalization. In the DLTML-RTADPM method, the Fennec Fox Optimization Algorithm (FFA) is used for a high dimensionality reduction process where the optimal feature set is chosen. The DLTML-RTADPM technique implements gradient least mean squares with a bidirectional long short-term memory (GLMS-BiLSTM) approach for anomaly detection. To further improve the detection results of the DLTML-RTADPM technique, the Jaya optimization algorithm (JOA)-based hyperparameter tuning process is utilized. A series of simulations are performed on the benchmark dataset to ensure better detection outcomes of the DLTML-RTADPM model. The investigational validation of the DLTML-RTADPM method portrayed a superior accuracy value of 98.11% over other techniques.
ArticleNumber 103281
Author Katib, Iyad
Ragab, Mahmoud
Albassam, Emad
Sharaf, Sanaa A.
Author_xml – sequence: 1
  givenname: Iyad
  surname: Katib
  fullname: Katib, Iyad
  email: iakatib@kau.edu.sa
– sequence: 2
  givenname: Emad
  surname: Albassam
  fullname: Albassam, Emad
  email: ealbassam@kau.edu.sa
– sequence: 3
  givenname: Sanaa A.
  surname: Sharaf
  fullname: Sharaf, Sanaa A.
  email: ssharaf@kau.edu.sa
– sequence: 4
  givenname: Mahmoud
  surname: Ragab
  fullname: Ragab, Mahmoud
  email: mragab@kau.edu.sa
BookMark eNp9kc2O0zAUhbMYJIZhXoCVXyDFdpzERmzQ8FepiAVlbd3YN-VWiV3ZmaLy9DgUNixmZfvK39E957yobkIMWFWvBN8ILrrXxw1kPG4kl20ZNFKLm-pWcsNrpXrzvLrPmQZe7lK3ur2tfn2DEQ-PkDyFA9vGPXMx5McZE_N4Jof5DXuPeGITQgrrn5-0_GB7CpcvO-YTnTGwhDDVC83IIMQZpkthF3QLxcDGmNgpoafyPCObgcKCAYLDl9WzEaaM93_Pu-r7xw_7h8_17uun7cO7Xe2U4EvtGq6hEQZbZVTjOm-cUV3fecV1g8WoGPseeu_bQRdnru34wMd2AOFAOuWbu2p71fURjvaUaIZ0sRHI_hnEdLCQFnITWm_kiE7L1shO9cCNcb5Xvu-0HlEMqmjpq5ZLMeeEo3W0wGp0SUCTFdyuNdijXWuwaw32WkNB5X_ov1WehN5eISwBnQmTzY6whOcplYCLA3oK_w0hgqa4
CitedBy_id crossref_primary_10_1016_j_iot_2025_101621
crossref_primary_10_1371_journal_pone_0329227
crossref_primary_10_3390_app15105640
crossref_primary_10_1016_j_micpro_2025_105172
crossref_primary_10_1016_j_asej_2025_103620
crossref_primary_10_3390_app15158704
Cites_doi 10.1109/EAIS51927.2022.9787703
10.1109/EAIS58494.2024.10570025
10.1109/ACCESS.2024.3362346
10.28991/HIJ-2024-05-02-012
10.1109/MetroInd4.0IoT54413.2022.9831517
10.1016/j.jksuci.2020.12.001
10.1109/IESES53571.2023.10253705
10.1109/TCE.2024.3376440
10.1016/j.jocs.2024.102426
10.1016/j.eswa.2022.119016
10.3390/electronics13061053
10.1109/OJSP.2023.3333756
10.1109/ACCESS.2023.3262702
10.3390/agriengineering5040139
10.1007/978-3-031-23633-4_22
10.1016/j.iot.2023.100848
10.28991/ESJ-2024-08-06-08
10.28991/ESJ-2024-08-01-018
10.3390/fi16020042
10.3390/s23125696
10.1007/s10922-023-09782-9
10.54216/IJWAC.060104
10.1109/JSSC.2023.3236566
10.3390/s23042344
10.2118/221928-MS
10.20944/preprints202403.0714.v1
10.1016/j.cgh.2023.08.042
10.3390/batteries10030087
10.3390/app12199572
10.1109/ACCESS.2024.3367357
10.3390/a16040202
10.1016/j.bcra.2024.100188
10.1109/ACCESS.2025.3557405
ContentType Journal Article
Copyright 2025 The Author(s)
Copyright_xml – notice: 2025 The Author(s)
DBID 6I.
AAFTH
AAYXX
CITATION
DOA
DOI 10.1016/j.asej.2025.103281
DatabaseName ScienceDirect Open Access Titles
Elsevier:ScienceDirect:Open Access
CrossRef
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
DatabaseTitleList

Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
DeliveryMethod fulltext_linktorsrc
ExternalDocumentID oai_doaj_org_article_d92fec82592647a099cd74d7688fe1b4
10_1016_j_asej_2025_103281
S209044792500022X
GroupedDBID 6I.
AAFTH
ALMA_UNASSIGNED_HOLDINGS
M~E
AAYXX
CITATION
GROUPED_DOAJ
ID FETCH-LOGICAL-c410t-c308a319e54943c6d9c94676d4083e2021f77a7dd5b8b04c560b0f5ba1ca2c4d3
IEDL.DBID DOA
ISICitedReferencesCount 10
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001423810800001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2090-4479
IngestDate Fri Oct 03 12:47:50 EDT 2025
Wed Oct 29 21:33:22 EDT 2025
Tue Nov 18 21:45:30 EST 2025
Sat Nov 22 16:51:42 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 2
Keywords Deep learning
Internet of things
Jaya optimization algorithm
Feature selection
TinyML
Anomaly detection
Language English
License This is an open access article under the CC BY-NC-ND license.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c410t-c308a319e54943c6d9c94676d4083e2021f77a7dd5b8b04c560b0f5ba1ca2c4d3
OpenAccessLink https://doaj.org/article/d92fec82592647a099cd74d7688fe1b4
ParticipantIDs doaj_primary_oai_doaj_org_article_d92fec82592647a099cd74d7688fe1b4
crossref_citationtrail_10_1016_j_asej_2025_103281
crossref_primary_10_1016_j_asej_2025_103281
elsevier_sciencedirect_doi_10_1016_j_asej_2025_103281
PublicationCentury 2000
PublicationDate February 2025
2025-02-00
2025-02-01
PublicationDateYYYYMMDD 2025-02-01
PublicationDate_xml – month: 02
  year: 2025
  text: February 2025
PublicationDecade 2020
PublicationTitle Ain Shams Engineering Journal
PublicationYear 2025
Publisher Elsevier B.V
Elsevier
Publisher_xml – name: Elsevier B.V
– name: Elsevier
References Saiyed, Al-Anbagi (b0210) 2024; 12
tu Zahra, Bostanci, Soyturk (b0050) 2024
Tareq, Elbagoury, El-Regaily, El-Horbaty (b0205) 2022; 12
Blockchain: Research and Applications; 2024, p.100188.
2022 IEEE International Conference on evolving and adaptive intelligent systems (EAIS)
Antonini M, Pincheira M, Vecchio M, Antonelli F. A TinyML approach to non-repudiable anomaly detection in extreme industrial environments. In
Singh, Rosak-Szyrocka, Lukàcs (b0095) 2024; 8
Banerjee R, Ghose A. A lightweight deep residual network for classification of abnormal heart rhythms on tiny devices. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases
Chaudhary, Srivastava, Khari (b0010) 2023; 6
Abu Dhabi International Petroleum Exhibition and Conference
(pp. 1-6). IEEE; 2023, July.
Sun, Qin, Yun (b0180) 2024; 10
Antonini, Pincheira, Vecchio, Antonelli (b0065) 2023; 23
2024 IEEE International Conference on Evolving and Adaptive Intelligent Systems (EAIS)
Anidjar, Barak, Ben-Moshe, Hagai, Tuvyahu (b0130) 2023; 11
Zulfiqar, Malik, Moqurrab, Zulfiqar, Yaseen, Srivastava (b0220) 2024; 83
Khatoon, Wang, Ullah, Li, Wang (b0105) 2024; 80
https://research.unsw.edu.au/projects/toniot-datasets.
(Vol. 2473, p. 4901); 2023.
de la Fuente R, Radrigan L, Morales AS. Enhancing predictive maintenance in mining mobile machinery through a TinyML-enabled hierarchical inference network; 2024, arXiv preprint arXiv:2411.07168.
(pp. 317-331). Cham: Springer Nature Switzerland; 2022, September.
Mishra, Pati, Majhi (b0195) 2022; 34
Srisang W, Jaroensutasinee K, Jaroensutasinee M, Khongthong C, Piamonte JRP, Sparrow EB. PM2. 5 IoT sensor calibration and implementation issues including machine learning. Emerging Sci J, 8(6) (2024) pp.2267-2277.
Kharche A, Badholia S, Upadhyay RK. Implementation of blockchain technology in integrated IoT networks for constructing scalable ITS systems in India.
Lee, Kim, Kim (b0150) 2023
Zhang, Suleiman, Alibasa, Farid (b0040) 2024; 32
Chen Z, Gao Y, Liang J. A self-powered sensing system with embedded TinyML for anomaly detection. In
(pp. 1-8). IEEE, 2024, May.
2022 IEEE International Workshop on Metrology for Industry 4.0 & IoT (MetroInd4. 0&IoT)
Hayajneh, Batayneh, Alzoubi, Alwedyan (b0090) 2023; 5
Chiurato S. Neural network-based classification of electric vehicle acceleration pedal signals: from training to microcontroller deployment
2023 IEEE 3rd International Conference on Industrial Electronics for Sustainable Energy Systems (IESES)
Tang, Long (b0190) 2024; 63
Karras, Giannaros, Karras, Theodorakopoulos, Mammassis, Krimpas (b0055) 2024; 16
Akram, Anaissi, Othman, Alabdulatif, Akram (b0070) 2024
Alajlan, Ibrahim (b0100) 2023; 23
Proceedings of the ISCAP Conference ISSN
Kontogiannis, Gkamas, Pikridas (b0035) 2023; 16
Medeiros M, Flores T, Silva M, Silva I. A multi-layered methodology for driver behavior analysis using TinyML and edge computing. In
Jain, Giraldo, De Roose, Mei, Boons, Verhelst (b0140) 2023; 58
Mafarja, Thaher, Al-Betar, Too, Awadallah, Abu Doush (b0185) 2023
Siddique, Mahmud (b0005) 2024
(Doctoral dissertation, Politecnico di Torino); 2023.
(pp. 1-8). IEEE; 2022, May.
Hammad, Iskandaryan, Trilles (b0045) 2023; 23
Le, Nguyen (b0125) 2024; 21
(pp. 397-402). IEEE; 2022, June.
Antonini M, Pincheira M, Vecchio M, Antonelli F. Tiny-MLOps: A framework for orchestrating ML applications at the far edge of IoT systems. In
Yaras, Dener (b0215) 2024; 13
Khan, Obaidat, Mahmood, Batool, Badar, Aamir (b0015) 2024
Barbieri, Brambilla, Stefanutti, Romano, De Carlo, Roveri (b0075) 2023; 4
Razak, Yogarayan, Ullah (b0145) 2024; 5
Ismail S, Moudoud H, Dawoud D, Reza H. Blockchain-based zero trust supply chain security integrated with deep reinforcement learning; 2024.
Asutkar, Chalke, Shivgan, Tallur (b0160) 2023; 213
(p. D011S014R003). SPE; 2024, November.
Yuan J, Elfrink S, Li Z, Cheng K, Han Q. An IoT based new platform for teaching tiny machine learning. In
Tharayil SM, Alrammah MM, Alghamdi MA, Aljohar FE, Otalvora WBC. Enhancing drilling equipment reliability: deep learning for predicting failure time and real-time anomaly detection. In
Bagheri, Farshforoush, Bagheri, Shemirani (b0020) 2023
Geem, Hercules, Pelia, Venkateswaran, Griffiths, Noe (b0175) 2024; 22
10.1016/j.asej.2025.103281_b0110
Razak (10.1016/j.asej.2025.103281_b0145) 2024; 5
Sun (10.1016/j.asej.2025.103281_b0180) 2024; 10
10.1016/j.asej.2025.103281_b0155
Anidjar (10.1016/j.asej.2025.103281_b0130) 2023; 11
Antonini (10.1016/j.asej.2025.103281_b0065) 2023; 23
Khatoon (10.1016/j.asej.2025.103281_b0105) 2024; 80
10.1016/j.asej.2025.103281_b0135
10.1016/j.asej.2025.103281_b0115
Chaudhary (10.1016/j.asej.2025.103281_b0010) 2023; 6
Jain (10.1016/j.asej.2025.103281_b0140) 2023; 58
Mishra (10.1016/j.asej.2025.103281_b0195) 2022; 34
Akram (10.1016/j.asej.2025.103281_b0070) 2024
Le (10.1016/j.asej.2025.103281_b0125) 2024; 21
tu Zahra (10.1016/j.asej.2025.103281_b0050) 2024
Hammad (10.1016/j.asej.2025.103281_b0045) 2023; 23
Mafarja (10.1016/j.asej.2025.103281_b0185) 2023
Siddique (10.1016/j.asej.2025.103281_b0005) 2024
Geem (10.1016/j.asej.2025.103281_b0175) 2024; 22
Zulfiqar (10.1016/j.asej.2025.103281_b0220) 2024; 83
10.1016/j.asej.2025.103281_b0170
10.1016/j.asej.2025.103281_b0030
Singh (10.1016/j.asej.2025.103281_b0095) 2024; 8
10.1016/j.asej.2025.103281_b0165
Tareq (10.1016/j.asej.2025.103281_b0205) 2022; 12
Lee (10.1016/j.asej.2025.103281_b0150) 2023
10.1016/j.asej.2025.103281_b0200
10.1016/j.asej.2025.103281_b0025
Karras (10.1016/j.asej.2025.103281_b0055) 2024; 16
Hayajneh (10.1016/j.asej.2025.103281_b0090) 2023; 5
Tang (10.1016/j.asej.2025.103281_b0190) 2024; 63
Bagheri (10.1016/j.asej.2025.103281_b0020) 2023
Barbieri (10.1016/j.asej.2025.103281_b0075) 2023; 4
Saiyed (10.1016/j.asej.2025.103281_b0210) 2024; 12
Asutkar (10.1016/j.asej.2025.103281_b0160) 2023; 213
Yaras (10.1016/j.asej.2025.103281_b0215) 2024; 13
10.1016/j.asej.2025.103281_b0080
Alajlan (10.1016/j.asej.2025.103281_b0100) 2023; 23
10.1016/j.asej.2025.103281_b0060
Kontogiannis (10.1016/j.asej.2025.103281_b0035) 2023; 16
10.1016/j.asej.2025.103281_b0085
Khan (10.1016/j.asej.2025.103281_b0015) 2024
Zhang (10.1016/j.asej.2025.103281_b0040) 2024; 32
10.1016/j.asej.2025.103281_b0120
References_xml – volume: 23
  start-page: 5696
  year: 2023
  ident: b0100
  article-title: DDD TinyML: a TinyML-based driver drowsiness detection model using deep learning
  publication-title: Sensors
– reference: Chen Z, Gao Y, Liang J. A self-powered sensing system with embedded TinyML for anomaly detection. In
– volume: 10
  start-page: 87
  year: 2024
  ident: b0180
  article-title: A state-of-health estimation method for lithium batteries based on fennec fox optimization algorithm–mixed extreme learning machine
  publication-title: Batteries
– reference: Abu Dhabi International Petroleum Exhibition and Conference
– volume: 12
  start-page: 9572
  year: 2022
  ident: b0205
  article-title: Analysis of ton-iot, unw-nb15, and edge-iiot datasets using dl in cybersecurity for iot
  publication-title: Appl Sci
– year: 2024
  ident: b0050
  article-title: LSTM-based jamming detection and forecasting model using transport and application layer parameters in Wi-Fi based IoT systems
  publication-title: IEEE Access
– reference: Tharayil SM, Alrammah MM, Alghamdi MA, Aljohar FE, Otalvora WBC. Enhancing drilling equipment reliability: deep learning for predicting failure time and real-time anomaly detection. In
– volume: 12
  start-page: 25623
  year: 2024
  end-page: 25641
  ident: b0210
  article-title: A genetic algorithm-and t-test-based system for DDoS attack detection in IoT networks
  publication-title: IEEE Access
– volume: 11
  start-page: 33336
  year: 2023
  end-page: 33353
  ident: b0130
  article-title: A stethoscope for drones: Transformers-based methods for UAVs acoustic anomaly detection
  publication-title: IEEE Access
– reference: Blockchain: Research and Applications; 2024, p.100188.
– reference: de la Fuente R, Radrigan L, Morales AS. Enhancing predictive maintenance in mining mobile machinery through a TinyML-enabled hierarchical inference network; 2024, arXiv preprint arXiv:2411.07168.
– reference: Banerjee R, Ghose A. A lightweight deep residual network for classification of abnormal heart rhythms on tiny devices. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases
– reference: (pp. 1-8). IEEE, 2024, May.
– reference: (Vol. 2473, p. 4901); 2023.
– volume: 63
  start-page: 403
  year: 2024
  end-page: 406
  ident: b0190
  article-title: Integration of gradient least mean squares in bidirectional long short-term (LSTM) memory networks for metallurgical bearing ball anomaly diagnosis
  publication-title: Metalurgija
– reference: Medeiros M, Flores T, Silva M, Silva I. A multi-layered methodology for driver behavior analysis using TinyML and edge computing. In
– reference: Proceedings of the ISCAP Conference ISSN
– volume: 21
  start-page: 187
  year: 2024
  end-page: 195
  ident: b0125
  article-title: Lightweight unsupervised model for anomaly detection on microcontroller platforms
  publication-title: J Maritime Res
– reference: Antonini M, Pincheira M, Vecchio M, Antonelli F. Tiny-MLOps: A framework for orchestrating ML applications at the far edge of IoT systems. In
– year: 2023
  ident: b0150
  article-title: Enhanced anomaly detection in manufacturing processes through hybrid deep learning techniques
  publication-title: IEEE Access
– start-page: 1
  year: 2023
  end-page: 43
  ident: b0185
  article-title: Classification framework for faulty-software using enhanced exploratory whale optimizer-based feature selection scheme and random forest ensemble learning
  publication-title: Appl Intell
– volume: 34
  start-page: 4914
  year: 2022
  end-page: 4930
  ident: b0195
  article-title: A dynamic load scheduling in IaaS cloud using binary JAYA algorithm
  publication-title: J King Saud Univ-Comput Inform Sci
– volume: 4
  start-page: 462
  year: 2023
  end-page: 478
  ident: b0075
  article-title: A tiny transformer-based anomaly detection framework for IoT solutions
  publication-title: IEEE Open Journal of Signal Processing
– reference: Antonini M, Pincheira M, Vecchio M, Antonelli F. A TinyML approach to non-repudiable anomaly detection in extreme industrial environments. In
– reference: https://research.unsw.edu.au/projects/toniot-datasets.
– year: 2024
  ident: b0015
  article-title: Real-time road damage detection and infrastructure evaluation leveraging unmanned aerial vehicles and tiny machine learning
  publication-title: IEEE Internet Things J
– reference: (pp. 317-331). Cham: Springer Nature Switzerland; 2022, September.
– reference: (pp. 1-6). IEEE; 2023, July.
– reference: Yuan J, Elfrink S, Li Z, Cheng K, Han Q. An IoT based new platform for teaching tiny machine learning. In
– reference: Ismail S, Moudoud H, Dawoud D, Reza H. Blockchain-based zero trust supply chain security integrated with deep reinforcement learning; 2024.
– reference: Srisang W, Jaroensutasinee K, Jaroensutasinee M, Khongthong C, Piamonte JRP, Sparrow EB. PM2. 5 IoT sensor calibration and implementation issues including machine learning. Emerging Sci J, 8(6) (2024) pp.2267-2277.
– volume: 32
  start-page: 20
  year: 2024
  ident: b0040
  article-title: Privacy-aware anomaly detection in IoT environments using fedgroup: a group-based federated learning approach
  publication-title: J Netw Syst Manag
– volume: 5
  start-page: 400
  year: 2024
  end-page: 409
  ident: b0145
  article-title: Preventing impaired driving using IoT on steering wheels approach
  publication-title: HighTech and Innovation Journal
– reference: 2022 IEEE International Conference on evolving and adaptive intelligent systems (EAIS)
– volume: 23
  start-page: 2344
  year: 2023
  ident: b0065
  article-title: An adaptable and unsupervised TinyML anomaly detection system for extreme industrial environments
  publication-title: Sensors
– reference: Chiurato S. Neural network-based classification of electric vehicle acceleration pedal signals: from training to microcontroller deployment
– reference: 2022 IEEE International Workshop on Metrology for Industry 4.0 & IoT (MetroInd4. 0&IoT)
– volume: 23
  year: 2023
  ident: b0045
  article-title: An unsupervised TinyML approach is applied to the detection of urban noise anomalies under the smart cities environment
  publication-title: Internet Things
– volume: 5
  start-page: 2266
  year: 2023
  end-page: 2283
  ident: b0090
  article-title: TinyML olive fruit variety classification by means of convolutional neural networks on IoT edge devices
  publication-title: AgriEngineering
– reference: (Doctoral dissertation, Politecnico di Torino); 2023.
– reference: (pp. 397-402). IEEE; 2022, June.
– year: 2023
  ident: b0020
  article-title: Applications of Artificial Intelligence Technologies in Water Environments: From Basic Techniques to Novel Tiny Machine Learning Systems
  publication-title: Process Safety and Environmental Protection
– reference: Kharche A, Badholia S, Upadhyay RK. Implementation of blockchain technology in integrated IoT networks for constructing scalable ITS systems in India.
– volume: 58
  start-page: 2360
  year: 2023
  end-page: 2371
  ident: b0140
  article-title: Tinyvers: A tiny versatile system-on-chip with state-retentive eMRAM for ML inference at the extreme edge
  publication-title: IEEE J Solid State Circuits
– reference: 2024 IEEE International Conference on Evolving and Adaptive Intelligent Systems (EAIS)
– reference: (pp. 1-8). IEEE; 2022, May.
– volume: 16
  start-page: 42
  year: 2024
  ident: b0055
  article-title: TinyML algorithms for big data management in large-scale IoT systems
  publication-title: Future Internet
– reference: (p. D011S014R003). SPE; 2024, November.
– year: 2024
  ident: b0070
  article-title: DroneSSL: self-supervised multimodal anomaly detection in internet of drone things
  publication-title: IEEE Trans Consum Electron
– volume: 22
  start-page: 368
  year: 2024
  end-page: 376
  ident: b0175
  article-title: Progression of pediatric crohn’s disease is associated with anti–tumor necrosis factor timing and body mass index Z-score normalization
  publication-title: Clinical Gastroenterology and Hepatology
– volume: 16
  start-page: 202
  year: 2023
  ident: b0035
  article-title: Deep learning stranded neural network model for the detection of sensory triggered events
  publication-title: Algorithms
– volume: 80
  year: 2024
  ident: b0105
  article-title: Optimized binary neural networks for road anomaly detection: a tinyML approach on edge devices
  publication-title: Computers, Materials & Continua
– volume: 8
  start-page: 251
  year: 2024
  end-page: 269
  ident: b0095
  article-title: Design and analysis of a bandwidth aware adaptive multipath N-channel routing protocol for 5G internet of things (IoT)
  publication-title: Emerging Sci J
– volume: 6
  year: 2023
  ident: b0010
  article-title: Generative edge intelligence for securing IoT-assisted smart grid against cyber-threats
  publication-title: Int J Wireless & Ad Hoc Commun
– year: 2024
  ident: b0005
  article-title: Physics-enhanced TinyML for real-time detection of ground magnetic anomalies
  publication-title: IEEE Access
– volume: 13
  start-page: 1053
  year: 2024
  ident: b0215
  article-title: IoT-based intrusion detection system using new hybrid deep learning algorithm
  publication-title: Electronics
– reference: 2023 IEEE 3rd International Conference on Industrial Electronics for Sustainable Energy Systems (IESES)
– volume: 213
  year: 2023
  ident: b0160
  article-title: TinyML-enabled edge implementation of transfer learning framework for domain generalization in machine fault diagnosis
  publication-title: Expert Syst Appl
– volume: 83
  year: 2024
  ident: b0220
  article-title: DeepDetect: An innovative hybrid deep learning framework for anomaly detection in IoT networks
  publication-title: J Comput Sci
– ident: 10.1016/j.asej.2025.103281_b0025
  doi: 10.1109/EAIS51927.2022.9787703
– ident: 10.1016/j.asej.2025.103281_b0135
  doi: 10.1109/EAIS58494.2024.10570025
– year: 2024
  ident: 10.1016/j.asej.2025.103281_b0005
  article-title: Physics-enhanced TinyML for real-time detection of ground magnetic anomalies
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2024.3362346
– volume: 21
  start-page: 187
  issue: 2
  year: 2024
  ident: 10.1016/j.asej.2025.103281_b0125
  article-title: Lightweight unsupervised model for anomaly detection on microcontroller platforms
  publication-title: J Maritime Res
– volume: 5
  start-page: 400
  issue: 2
  year: 2024
  ident: 10.1016/j.asej.2025.103281_b0145
  article-title: Preventing impaired driving using IoT on steering wheels approach
  publication-title: HighTech and Innovation Journal
  doi: 10.28991/HIJ-2024-05-02-012
– ident: 10.1016/j.asej.2025.103281_b0060
  doi: 10.1109/MetroInd4.0IoT54413.2022.9831517
– volume: 34
  start-page: 4914
  issue: 8
  year: 2022
  ident: 10.1016/j.asej.2025.103281_b0195
  article-title: A dynamic load scheduling in IaaS cloud using binary JAYA algorithm
  publication-title: J King Saud Univ-Comput Inform Sci
  doi: 10.1016/j.jksuci.2020.12.001
– ident: 10.1016/j.asej.2025.103281_b0170
  doi: 10.1109/IESES53571.2023.10253705
– year: 2024
  ident: 10.1016/j.asej.2025.103281_b0070
  article-title: DroneSSL: self-supervised multimodal anomaly detection in internet of drone things
  publication-title: IEEE Trans Consum Electron
  doi: 10.1109/TCE.2024.3376440
– volume: 63
  start-page: 403
  issue: 3–4
  year: 2024
  ident: 10.1016/j.asej.2025.103281_b0190
  article-title: Integration of gradient least mean squares in bidirectional long short-term (LSTM) memory networks for metallurgical bearing ball anomaly diagnosis
  publication-title: Metalurgija
– volume: 80
  issue: 1
  year: 2024
  ident: 10.1016/j.asej.2025.103281_b0105
  article-title: Optimized binary neural networks for road anomaly detection: a tinyML approach on edge devices
  publication-title: Computers, Materials & Continua
– volume: 83
  year: 2024
  ident: 10.1016/j.asej.2025.103281_b0220
  article-title: DeepDetect: An innovative hybrid deep learning framework for anomaly detection in IoT networks
  publication-title: J Comput Sci
  doi: 10.1016/j.jocs.2024.102426
– ident: 10.1016/j.asej.2025.103281_b0120
– volume: 213
  year: 2023
  ident: 10.1016/j.asej.2025.103281_b0160
  article-title: TinyML-enabled edge implementation of transfer learning framework for domain generalization in machine fault diagnosis
  publication-title: Expert Syst Appl
  doi: 10.1016/j.eswa.2022.119016
– volume: 13
  start-page: 1053
  issue: 6
  year: 2024
  ident: 10.1016/j.asej.2025.103281_b0215
  article-title: IoT-based intrusion detection system using new hybrid deep learning algorithm
  publication-title: Electronics
  doi: 10.3390/electronics13061053
– volume: 4
  start-page: 462
  year: 2023
  ident: 10.1016/j.asej.2025.103281_b0075
  article-title: A tiny transformer-based anomaly detection framework for IoT solutions
  publication-title: IEEE Open Journal of Signal Processing
  doi: 10.1109/OJSP.2023.3333756
– volume: 11
  start-page: 33336
  year: 2023
  ident: 10.1016/j.asej.2025.103281_b0130
  article-title: A stethoscope for drones: Transformers-based methods for UAVs acoustic anomaly detection
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2023.3262702
– year: 2024
  ident: 10.1016/j.asej.2025.103281_b0015
  article-title: Real-time road damage detection and infrastructure evaluation leveraging unmanned aerial vehicles and tiny machine learning
  publication-title: IEEE Internet Things J
– volume: 5
  start-page: 2266
  issue: 4
  year: 2023
  ident: 10.1016/j.asej.2025.103281_b0090
  article-title: TinyML olive fruit variety classification by means of convolutional neural networks on IoT edge devices
  publication-title: AgriEngineering
  doi: 10.3390/agriengineering5040139
– ident: 10.1016/j.asej.2025.103281_b0080
  doi: 10.1007/978-3-031-23633-4_22
– volume: 23
  year: 2023
  ident: 10.1016/j.asej.2025.103281_b0045
  article-title: An unsupervised TinyML approach is applied to the detection of urban noise anomalies under the smart cities environment
  publication-title: Internet Things
  doi: 10.1016/j.iot.2023.100848
– ident: 10.1016/j.asej.2025.103281_b0155
  doi: 10.28991/ESJ-2024-08-06-08
– ident: 10.1016/j.asej.2025.103281_b0200
– ident: 10.1016/j.asej.2025.103281_b0110
– volume: 8
  start-page: 251
  issue: 1
  year: 2024
  ident: 10.1016/j.asej.2025.103281_b0095
  article-title: Design and analysis of a bandwidth aware adaptive multipath N-channel routing protocol for 5G internet of things (IoT)
  publication-title: Emerging Sci J
  doi: 10.28991/ESJ-2024-08-01-018
– year: 2023
  ident: 10.1016/j.asej.2025.103281_b0150
  article-title: Enhanced anomaly detection in manufacturing processes through hybrid deep learning techniques
  publication-title: IEEE Access
– volume: 16
  start-page: 42
  issue: 2
  year: 2024
  ident: 10.1016/j.asej.2025.103281_b0055
  article-title: TinyML algorithms for big data management in large-scale IoT systems
  publication-title: Future Internet
  doi: 10.3390/fi16020042
– volume: 23
  start-page: 5696
  issue: 12
  year: 2023
  ident: 10.1016/j.asej.2025.103281_b0100
  article-title: DDD TinyML: a TinyML-based driver drowsiness detection model using deep learning
  publication-title: Sensors
  doi: 10.3390/s23125696
– volume: 32
  start-page: 20
  issue: 1
  year: 2024
  ident: 10.1016/j.asej.2025.103281_b0040
  article-title: Privacy-aware anomaly detection in IoT environments using fedgroup: a group-based federated learning approach
  publication-title: J Netw Syst Manag
  doi: 10.1007/s10922-023-09782-9
– volume: 6
  issue: 1
  year: 2023
  ident: 10.1016/j.asej.2025.103281_b0010
  article-title: Generative edge intelligence for securing IoT-assisted smart grid against cyber-threats
  publication-title: Int J Wireless & Ad Hoc Commun
  doi: 10.54216/IJWAC.060104
– year: 2024
  ident: 10.1016/j.asej.2025.103281_b0050
  article-title: LSTM-based jamming detection and forecasting model using transport and application layer parameters in Wi-Fi based IoT systems
  publication-title: IEEE Access
– volume: 58
  start-page: 2360
  issue: 8
  year: 2023
  ident: 10.1016/j.asej.2025.103281_b0140
  article-title: Tinyvers: A tiny versatile system-on-chip with state-retentive eMRAM for ML inference at the extreme edge
  publication-title: IEEE J Solid State Circuits
  doi: 10.1109/JSSC.2023.3236566
– start-page: 1
  year: 2023
  ident: 10.1016/j.asej.2025.103281_b0185
  article-title: Classification framework for faulty-software using enhanced exploratory whale optimizer-based feature selection scheme and random forest ensemble learning
  publication-title: Appl Intell
– volume: 23
  start-page: 2344
  issue: 4
  year: 2023
  ident: 10.1016/j.asej.2025.103281_b0065
  article-title: An adaptable and unsupervised TinyML anomaly detection system for extreme industrial environments
  publication-title: Sensors
  doi: 10.3390/s23042344
– ident: 10.1016/j.asej.2025.103281_b0115
  doi: 10.2118/221928-MS
– ident: 10.1016/j.asej.2025.103281_b0085
  doi: 10.20944/preprints202403.0714.v1
– year: 2023
  ident: 10.1016/j.asej.2025.103281_b0020
  article-title: Applications of Artificial Intelligence Technologies in Water Environments: From Basic Techniques to Novel Tiny Machine Learning Systems
– volume: 22
  start-page: 368
  issue: 2
  year: 2024
  ident: 10.1016/j.asej.2025.103281_b0175
  article-title: Progression of pediatric crohn’s disease is associated with anti–tumor necrosis factor timing and body mass index Z-score normalization
  publication-title: Clinical Gastroenterology and Hepatology
  doi: 10.1016/j.cgh.2023.08.042
– volume: 10
  start-page: 87
  issue: 3
  year: 2024
  ident: 10.1016/j.asej.2025.103281_b0180
  article-title: A state-of-health estimation method for lithium batteries based on fennec fox optimization algorithm–mixed extreme learning machine
  publication-title: Batteries
  doi: 10.3390/batteries10030087
– volume: 12
  start-page: 9572
  issue: 19
  year: 2022
  ident: 10.1016/j.asej.2025.103281_b0205
  article-title: Analysis of ton-iot, unw-nb15, and edge-iiot datasets using dl in cybersecurity for iot
  publication-title: Appl Sci
  doi: 10.3390/app12199572
– volume: 12
  start-page: 25623
  year: 2024
  ident: 10.1016/j.asej.2025.103281_b0210
  article-title: A genetic algorithm-and t-test-based system for DDoS attack detection in IoT networks
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2024.3367357
– volume: 16
  start-page: 202
  issue: 4
  year: 2023
  ident: 10.1016/j.asej.2025.103281_b0035
  article-title: Deep learning stranded neural network model for the detection of sensory triggered events
  publication-title: Algorithms
  doi: 10.3390/a16040202
– ident: 10.1016/j.asej.2025.103281_b0030
  doi: 10.1016/j.bcra.2024.100188
– ident: 10.1016/j.asej.2025.103281_b0165
  doi: 10.1109/ACCESS.2025.3557405
SSID ssib044728585
Score 2.3886676
Snippet Internet of Things (IoT) security is paramount for enterprises, as it includes several strategies, techniques, actions, and protocols that aim to alleviate the...
SourceID doaj
crossref
elsevier
SourceType Open Website
Enrichment Source
Index Database
Publisher
StartPage 103281
SubjectTerms Anomaly detection
Deep learning
Feature selection
Internet of things
Jaya optimization algorithm
TinyML
Title Safeguarding IoT consumer devices: Deep learning with TinyML driven real-time anomaly detection for predictive maintenance
URI https://dx.doi.org/10.1016/j.asej.2025.103281
https://doaj.org/article/d92fec82592647a099cd74d7688fe1b4
Volume 16
WOSCitedRecordID wos001423810800001&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: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  issn: 2090-4479
  databaseCode: M~E
  dateStart: 20100101
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://road.issn.org
  omitProxy: false
  ssIdentifier: ssib044728585
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1NT9wwELUQ6oELKiqIbWnlQ2_I4CTOOu6NtqAiAUJiQdwiezxeLdrNrpYFCQ797R07WbRc6IVLpET-SMZjz5t4_Iax70o7EwD7QoNFoUqUwtjSCeOsk6AMQCKrvjnTFxfV7a25XEn1FWPCWnrgVnCH3uQBgfwYQ6ZbWwI04LXyhJKrgJlLTKBSmxVnijRJKZ3HDa-YWU4aKejedCdm2uAushB35Bzm5UEilMteWaVE3r9inFYMzslHttkhRX7UvuEWW8PmE3u-sgGHaVibIT-dDjh0Zyi5xzTpf_DfiDPeZYMY8vijlQ9GzdP5GffzuLZxwoljEZPKc9tMJ3b8RHUXKSSr4YRh-Wwed2_iOsgnNvJJRFIO3GbXJ8eDX39Elz5BgMrkQkAhK0szDMkFVAX0vQFDy2LfK4JdSB-fBa2t9r50FYkMCPs4GUpnM7A5KF_ssPVm2uAu48qETAO5FgEK5aWrSol9kznMMRTGQY9lS_HV0HGLxxQX43oZRHZXR5HXUeR1K_Ie23-pM2uZNd4s_TOOykvJyIqdHpCu1J2u1P_TlR4rl2NadwCjBQ7U1OiNzj-_R-df2EZsso343mPri_kDfmUf4HExup9_S-pL1_O_x_8AIP31zw
linkProvider Directory of Open Access Journals
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=Safeguarding+IoT+consumer+devices%3A+Deep+learning+with+TinyML+driven+real-time+anomaly+detection+for+predictive+maintenance&rft.jtitle=Ain+Shams+Engineering+Journal&rft.au=Katib%2C+Iyad&rft.au=Albassam%2C+Emad&rft.au=Sharaf%2C+Sanaa+A.&rft.au=Ragab%2C+Mahmoud&rft.date=2025-02-01&rft.pub=Elsevier+B.V&rft.issn=2090-4479&rft.volume=16&rft.issue=2&rft_id=info:doi/10.1016%2Fj.asej.2025.103281&rft.externalDocID=S209044792500022X
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2090-4479&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2090-4479&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2090-4479&client=summon