{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T08:30:33Z","timestamp":1778142633837,"version":"3.51.4"},"reference-count":37,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T00:00:00Z","timestamp":1752624000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["MAKE"],"abstract":"<jats:p>Fault detection and remaining useful life (RUL) prediction are critical tasks in self-healing network (SHN) environments and industrial cyber\u2013physical systems. These domains demand intelligent systems capable of handling dynamic, high-dimensional sensor data. However, existing optimization-based approaches often struggle with imbalanced datasets, noisy signals, and delayed convergence, limiting their effectiveness in real-time applications. This study utilizes two benchmark datasets\u2014EFCD and SFDD\u2014which represent electrical and sensor fault scenarios, respectively. These datasets pose challenges due to class imbalance and complex temporal dependencies. To address this, we propose a novel hybrid framework combining Attention-Augmented Convolutional Neural Networks (AACNN) with transformer encoders, enhanced through Enhanced Ensemble-SMOTE for balancing the minority class. The model captures spatial features and long-range temporal patterns and learns effectively from imbalanced data streams. The novelty lies in the integration of attention mechanisms and adaptive oversampling in a unified fault-prediction architecture. Model evaluation is based on multiple performance metrics, including accuracy, F1-score, MCC, RMSE, and score*. The results show that the proposed model outperforms state-of-the-art approaches, achieving up to 97.14% accuracy and a score* of 0.419, with faster convergence and improved generalization across both datasets.<\/jats:p>","DOI":"10.3390\/make7030067","type":"journal-article","created":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T15:48:22Z","timestamp":1752680902000},"page":"67","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Transformer-Driven Fault Detection in Self-Healing Networks: A Novel Attention-Based Framework for Adaptive Network Recovery"],"prefix":"10.3390","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8903-6664","authenticated-orcid":false,"given":"Parul","family":"Dubey","sequence":"first","affiliation":[{"name":"Symbiosis Institute of Technology, Nagpur Campus, Symbiosis International (Deemed University), Pune 440008, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9929-6002","authenticated-orcid":false,"given":"Pushkar","family":"Dubey","sequence":"additional","affiliation":[{"name":"Department of Management, Pandit Sundarlal Sharma (Open) University, Bilaspur 495009, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9178-2700","authenticated-orcid":false,"given":"Pitshou N.","family":"Bokoro","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering Technology, University of Johannesburg, Johannesburg 2006, South Africa"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,7,16]]},"reference":[{"key":"ref_1","unstructured":"(2025, February 15). Cisco Annual Internet Report (2018\u20132023) White Paper. 2022. Cisco. 23 January 2022. Available online: https:\/\/www.cisco.com\/c\/en\/us\/solutions\/collateral\/executive-perspectives\/annual-internet-report\/white-paper-c11-741490.html."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s42162-024-00460-x","article-title":"Realization and Research of Self-healing Technology of Power Communication Equipment Based on Power Safety and Controllability","volume":"8","author":"Liu","year":"2025","journal-title":"Energy Inform."},{"key":"ref_3","first-page":"10081","article-title":"Machine Learning Based Automatic Diagnosis in Mobile Communication Networks","volume":"68","author":"Chen","year":"2019","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref_4","unstructured":"Mateo, S., Dusaric, I., and Cardozo, N. (2024, January 14\u201315). Learning Recovery Strategies for Dynamic Self-healing in Reactive Systems. Proceedings of the 19th International Symposium on Software Engineering for Adaptive and Self-Managing Systems (SEAMS \u201924), Lisbon, Portugal."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1109\/MNET.2024.3416850","article-title":"Self-Healing in Knowledge-Driven Autonomous Networks: Context, Challenges, and Future Directions","volume":"38","author":"Fang","year":"2024","journal-title":"IEEE Netw."},{"key":"ref_6","unstructured":"Devi, S.K., Thenmozhi, R., and Kumar, D.S. (2024, January 14\u201316). Self-Healing IoT Sensor Networks with Isolation Forest Algorithm for Autonomous Fault Detection and Recovery. Proceedings of the 2024 International Conference on Automation and Computation (AUTOCOM), S\u00e3o Paulo Expo, Brazil."},{"key":"ref_7","first-page":"2441","article-title":"Fault Diagnosis and Self-healing for Smart Manufacturing: A Review","volume":"35","author":"Joma","year":"2023","journal-title":"J. Intell. Manuf."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"e8246","DOI":"10.1002\/cpe.8246","article-title":"Proactive Self-healing Techniques for Cloud Computing: A Systematic Review","volume":"36","author":"Rouholamini","year":"2024","journal-title":"Concurr. Comput. Pract. Exp."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"2295","DOI":"10.1039\/D4SC06855F","article-title":"Chemodynamic Covalent Adaptable Network-induced Robust, Self-healing, and Degradable Fluorescent Elastomers for Multicolor Information Encryption","volume":"16","author":"Li","year":"2024","journal-title":"Chem. Sci."},{"key":"ref_10","first-page":"84","article-title":"ImageNet Classification with Deep Convolutional Neural Networks","volume":"60","author":"Krizhevsky","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Andronie, M., L\u0103z\u0103roiu, G., \u0218tef\u0103nescu, R., U\u021b\u0103, C., and Dijm\u0103rescu, I. (2021). Sustainable, Smart, and Sensing Technologies for Cyber-Physical Manufacturing Systems: A Systematic Literature Review. Sustainability, 13.","DOI":"10.3390\/su13105495"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"103880","DOI":"10.1016\/j.compind.2023.103880","article-title":"Petri nets-based digital twin drives dual-arm cooperative manipulation","volume":"147","author":"Hu","year":"2023","journal-title":"Comput. Ind."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Hsieh, F.-S. (2024). A Self-Adaptive Neighborhood Search Differential Evolution Algorithm for planning sustainable sequential Cyber\u2013Physical production systems. Appl. Sci., 14.","DOI":"10.3390\/app14178044"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"125662","DOI":"10.1109\/ACCESS.2019.2925566","article-title":"An Ensemble Learning Approach for Fault Diagnosis in Self-Organizing Heterogeneous Networks","volume":"7","author":"Wang","year":"2019","journal-title":"IEEE Access"},{"key":"ref_15","first-page":"6","article-title":"A Decentralised Self-healing Approach for Network Topology Maintenance","volume":"35","author":"Arles","year":"2020","journal-title":"Auton. Agents Multi-Agent Syst."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"375","DOI":"10.1007\/s12083-020-00926-1","article-title":"Improved Self-healing Technique for 5G Networks Using Predictive Analysis","volume":"14","author":"Reshmi","year":"2020","journal-title":"Peer Netw. Appl."},{"key":"ref_17","unstructured":"Liang, X., He, M., and Chen, H. (2021, January 27\u201328). Multiple Adaptive Strategies-based Rat Swarm Optimizer. Proceedings of the 2022 IEEE 8th International Conference on Cloud Computing and Intelligent Systems (CCIS), Chengdu, China."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"18725","DOI":"10.1007\/s11227-022-04614-0","article-title":"A Distributed Formal-based Model for Self-healing Behaviors in Autonomous Systems: From Failure Detection to Self-recovery","volume":"78","author":"Hafaiedh","year":"2022","journal-title":"J. Supercomput."},{"key":"ref_19","first-page":"1145","article-title":"An Adaptive Fault Detection Scheme Using Optimized Self-healing Ensemble Machine Learning Algorithm","volume":"8","author":"Yavuz","year":"2021","journal-title":"CSEE J. Power Energy Syst."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"66828","DOI":"10.1109\/ACCESS.2023.3287896","article-title":"Quantum Dwarf Mongoose Optimization With Ensemble Deep Learning Based Intrusion Detection in Cyber-Physical Systems","volume":"11","author":"Almutairi","year":"2023","journal-title":"IEEE Access"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"112732","DOI":"10.1016\/j.knosys.2024.112732","article-title":"Revolutionizing Fault Detection in Self-Healing Network via Multi-Serial Cascaded and Adaptive Network","volume":"309","author":"Caleb","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"ref_22","unstructured":"(2025, February 15). Electrical Fault Detection and Classification. Kaggle. 22 May 2021. Available online: https:\/\/www.kaggle.com\/datasets\/esathyaprakash\/electrical-fault-detection-and-classification."},{"key":"ref_23","unstructured":"(2025, February 15). Sensor Fault Detection Data, Kaggle. 4 November 2020. Available online: https:\/\/www.kaggle.com\/datasets\/arashnic\/sensor-fault-detection-data."},{"key":"ref_24","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., and Polosukhin, I. (2017). Attention is All You Need. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Dolo, K.M., and Mnkandla, E. (2022). Modifying the SMOTE and Safe-Level SMOTE Oversampling Method to Improve Performance. Lecture Notes on Data Engineering and Communications Technologies, Springer Nature.","DOI":"10.1007\/978-3-030-89776-5_4"},{"key":"ref_26","first-page":"1310","article-title":"Addressing Class Imbalance of Health Data: A Systematic Literature Review on Modified Synthetic Minority Oversampling Technique (SMOTE) Strategies","volume":"8","author":"Hairani","year":"2024","journal-title":"JOIV Int. J. Inform. Vis."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1016\/j.ins.2020.07.014","article-title":"RCSMOTE: Range-Controlled Synthetic Minority Over-sampling Technique for Handling the Class Imbalance Problem","volume":"542","author":"Soltanzadeh","year":"2020","journal-title":"Inf. Sci."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"158742","DOI":"10.1109\/ACCESS.2024.3480848","article-title":"FADA-SMOTE-Ms: Fuzzy Adaptative Smote Based Methods","volume":"12","author":"Mouhamed","year":"2024","journal-title":"IEEE Access"},{"key":"ref_29","first-page":"135","article-title":"Optimal Feature Selection for Imbalanced Text Classification","volume":"4","author":"Anshu","year":"2022","journal-title":"IEEE Trans. Artif. Intell."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Tan, J.S., Yee, H.J., Boo, I., Tan, I.K.T., and Zakariah, H. (2023). Investigating the Stability of SMOTE-Based Oversampling on COVID-19 Data. Lecture Notes in Networks and Systems, Springer Nature.","DOI":"10.1007\/978-3-031-37963-5_33"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"501","DOI":"10.1142\/S1793351X24300085","article-title":"LLMs: Their Past, Promise, and Problems","volume":"18","author":"Luger","year":"2024","journal-title":"Int. J. Semant. Comput."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"100078","DOI":"10.1016\/j.metrad.2024.100078","article-title":"The General Intelligence of GPT\u20134, Its Knowledge Diffusive and Societal Influences, and Its Governance","volume":"2","author":"Yekta","year":"2024","journal-title":"Meta-Radiol."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Naik, D., Naik, I., and Naik, N. (2024). Decoder-Only Transformers: The Brains Behind Generative AI, Large Language Models and Large Multimodal Models. Lecture Notes in Networks and Systems, Springer Nature.","DOI":"10.36227\/techrxiv.173198819.91727188\/v1"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Yang, Z., and Buehler, M.J. (2021). Words to Matter: De Novo Architected Materials Design Using Transformer Neural Networks. Front. Mater., 8.","DOI":"10.3389\/fmats.2021.740754"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1592","DOI":"10.1109\/TVLSI.2023.3299509","article-title":"H3DAtten: Heterogeneous 3-D Integrated Hybrid Analog and Digital Compute-in-Memory Accelerator for Vision Transformer Self-Attention","volume":"31","author":"Li","year":"2023","journal-title":"IEEE Trans. Very Large Scale Integr. (VLSI) Syst."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Sajun, A.R., Zualkernan, I., and Sankalpa, D. (2024). A Historical Survey of Advances in Transformer Architectures. Appl. Sci., 14.","DOI":"10.3390\/app14104316"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1007\/s10462-022-10173-w","article-title":"Fire Hawk Optimizer: A Novel Metaheuristic Algorithm","volume":"56","author":"Azizi","year":"2022","journal-title":"Artif. Intell. Rev."}],"container-title":["Machine Learning and Knowledge Extraction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-4990\/7\/3\/67\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:11:00Z","timestamp":1760033460000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-4990\/7\/3\/67"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,16]]},"references-count":37,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["make7030067"],"URL":"https:\/\/doi.org\/10.3390\/make7030067","relation":{},"ISSN":["2504-4990"],"issn-type":[{"value":"2504-4990","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,16]]}}}