{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T01:36:17Z","timestamp":1760060177697,"version":"build-2065373602"},"reference-count":37,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T00:00:00Z","timestamp":1754438400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Systems"],"abstract":"<jats:p>This study develops and validates an artificial intelligence (AI)-assisted internship learning platform for automotive electronics based on the Llama 3 large language model, aiming to enhance pedagogical effectiveness within vocational training contexts. Addressing critical issues such as the persistent theory\u2013practice gap and limited innovation capability prevalent in existing curricula, we leverage the natural language processing (NLP) capabilities of Llama 3 through fine-tuning based on transfer learning to establish a specialized knowledge base encompassing fundamental circuit principles and fault diagnosis protocols. The implementation employs the Hugging Face Transformers library with optimized hyperparameters, including a learning rate of 5 \u00d7 10\u22125 across five training epochs. Post-training evaluations revealed an accuracy of 89.7% on validation tasks (representing a 12.4% improvement over the baseline model), a semantic comprehension precision of 92.3% in technical question-and-answer assessments, a mathematical computation accuracy of 78.4% (highlighting this as a current limitation), and a latency of 6.3 s under peak operational workloads (indicating a system bottleneck). Although direct trials involving students were deliberately avoided, the platform\u2019s technical feasibility was validated through multidimensional benchmarking against established models (BERT-base and GPT-2), confirming superior domain adaptability (F1 = 0.87) and enhanced error tolerance (\u03c32 = 1.2). Notable limitations emerged in numerical reasoning tasks (Cohen\u2019s d = 1.15 compared to human experts) and in real-time responsiveness deterioration when exceeding 50 concurrent users. The study concludes that Llama 3 demonstrates considerable promise for automotive electronics skills development. Proposed future enhancements include integrating symbolic AI modules to improve computational reliability, implementing Kubernetes-based load balancing to ensure latency below 2 s at scale, and conducting longitudinal pedagogical validation studies with trainees. This research provides a robust technical foundation for AI-driven vocational education, especially suited to mechatronics fields that require close integration between theoretical knowledge and practical troubleshooting skills.<\/jats:p>","DOI":"10.3390\/systems13080668","type":"journal-article","created":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T13:25:11Z","timestamp":1754486711000},"page":"668","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Development of an Automotive Electronics Internship Assistance System Using a Fine-Tuned Llama 3 Large Language Model"],"prefix":"10.3390","volume":"13","author":[{"given":"Ying-Chia","family":"Huang","sequence":"first","affiliation":[{"name":"Department of Electrical and Mechanical Technology, National Changhua University of Education Bao-Shan Campus, No. 2, Shi-Da Road, Changhua City 500208, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hsin-Jung","family":"Tsai","sequence":"additional","affiliation":[{"name":"Department of Electrical and Mechanical Technology, National Changhua University of Education Bao-Shan Campus, No. 2, Shi-Da Road, Changhua City 500208, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui-Ting","family":"Liang","sequence":"additional","affiliation":[{"name":"Department of Finance, National Changhua University of Education, Bao-Shan Campus, No. 2, Shi-Da Road, Changhua City 500208, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2864-1593","authenticated-orcid":false,"given":"Bo-Siang","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Vehicle Engineering, Nan Kai University of Technology, No. 568, Zhongzheng Road, Caotun Township, Nantou City 542020, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tzu-Hsin","family":"Chu","sequence":"additional","affiliation":[{"name":"Department of Electrical and Mechanical Technology, National Changhua University of Education Bao-Shan Campus, No. 2, Shi-Da Road, Changhua City 500208, Taiwan"},{"name":"Department and Graduate Institute of Information Management, Yu Da University of Science and Technology, No. 168, Hsueh-fu Road, Tanwen Village, Chaochiao Township, Miaoli County 361027, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7591-8102","authenticated-orcid":false,"given":"Wei-Sho","family":"Ho","sequence":"additional","affiliation":[{"name":"Department of Electrical and Mechanical Technology, National Changhua University of Education Bao-Shan Campus, No. 2, Shi-Da Road, Changhua City 500208, Taiwan"},{"name":"NCUE Alumni Association, National Changhua University of Education Jin-De Campus, No. 1, Jinde Road, Changhua County, Changhua City 500207, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1286-4481","authenticated-orcid":false,"given":"Wei-Lun","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Mechanical Technology, National Changhua University of Education Bao-Shan Campus, No. 2, Shi-Da Road, Changhua City 500208, Taiwan"},{"name":"Medical Affairs Office, National Taiwan University Hospital, No. 7, Zhongshan S. Road, Taipei City 100225, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying-Ju","family":"Tseng","sequence":"additional","affiliation":[{"name":"Department of Electrical and Mechanical Technology, National Changhua University of Education Bao-Shan Campus, No. 2, Shi-Da Road, Changhua City 500208, Taiwan"},{"name":"Department of Child Care and Education, National Yuanlin Home-Economics and Commercial Vocational Senior High School, No. 56, Zhongzheng Road, Yuanlin City 510005, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,8,6]]},"reference":[{"key":"ref_1","first-page":"548","article-title":"AI-Assisted Personalized Learning System for Teaching Chassis Principles","volume":"41","author":"Liao","year":"2025","journal-title":"Int. J. Eng. Educ."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Liao, C.-W., Liao, H.-K., Chen, B.-S., Tseng, Y.-J., Liao, Y.-H., Wang, I.-C., Ho, W.-S., and Ko, Y.-Y. (2023). Inquiry Practice Capability and Students\u2019 Learning Effectiveness Evaluation in Strategies of Integrating Virtual Reality into Vehicle Body Electrical System Comprehensive Maintenance and Repair Services Practice: A Case Study. Electronics, 12.","DOI":"10.3390\/electronics12122576"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1589","DOI":"10.1002\/sd.3221","article-title":"AI-driven adaptive learning for sustainable educational transformation","volume":"33","author":"Strielkowski","year":"2025","journal-title":"Sustain. Dev."},{"key":"ref_4","unstructured":"Xu, H., Gan, W., Qi, Z., Wu, J., and Yu, P.S. (2024). Large language models for education: A survey. arXiv."},{"key":"ref_5","first-page":"1","article-title":"A survey on large language models: Applications, challenges, limitations, and practical usage","volume":"3","author":"Hadi","year":"2023","journal-title":"Authorea Prepr."},{"key":"ref_6","unstructured":"Gupta, A. (2025). Designing and Deploying Scalable Intelligent Tutoring Systems to Enhance Adult Education. [Doctoral Dissertation, Drexel University]. Available online: https:\/\/www.proquest.com\/openview\/10eecba5e602d412a0c9ff8fdf92ba23\/1?pq-origsite=gscholar&cbl=18750&diss=y."},{"key":"ref_7","unstructured":"Raimondi, B. (2023). Large Language Models for Education. [Master\u2019s Thesis, University of Bologna]. Available online: https:\/\/amslaurea.unibo.it\/id\/eprint\/29693."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1007\/s43621-025-01094-z","article-title":"The role of large language models in personalized learning: A systematic review of educational impact","volume":"6","author":"Sharma","year":"2025","journal-title":"Discov. Sustain."},{"key":"ref_9","first-page":"2813","article-title":"Smart Classrooms, Smarter Teachers: A Deep Dive into AI-Driven Educational Enhancement","volume":"3","author":"Chopra","year":"2023","journal-title":"J. Inform. Educ. Res."},{"key":"ref_10","first-page":"23","article-title":"Intelig\u00eancia artifical: Suas vantagens e limites em cursos \u00e0 dist\u00e2ncia","volume":"4","author":"Coelho","year":"2023","journal-title":"Rev. Ilus."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Song, C., Shin, S.-Y., and Shin, K.-S. (2024). Implementing the Dynamic Feedback-Driven Learning Optimization Framework: A Machine Learning Approach to Personalize Educational Pathways. Appl. Sci., 14.","DOI":"10.20944\/preprints202401.0811.v1"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1080\/00461520.2011.611369","article-title":"The relative effectiveness of human tutoring, intelligent tutoring systems, and other tutoring systems","volume":"46","author":"VanLehn","year":"2011","journal-title":"Educ. Psychol."},{"key":"ref_13","unstructured":"Koedinger, K.R., McLaughlin, E.A., and Stamper, J.C. (2012, January 19\u201321). Automated Student Model Improvement. Proceedings of the 5th International Conference on Educational Data Mining, Chania, Greece. Available online: https:\/\/eric.ed.gov\/?id=ED537201."},{"key":"ref_14","first-page":"147","article-title":"An effective metacognitive strategy: Learning by doing and explaining with a computer-based cognitive tutor","volume":"26","author":"Aleven","year":"2002","journal-title":"Cogn. Sci."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1007\/BF01099821","article-title":"Knowledge tracing: Modeling the acquisition of procedural knowledge","volume":"4","author":"Corbett","year":"1994","journal-title":"User Model. User-Adapt. Interact."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Tecson, C. (2018, January 26\u201330). Intelligent Learning System for Automata (ILSA) and the learners\u2019 achievement goal orientations. Proceedings of the 2018: ICCE 2018: The 26th International Conference on Computers in Education, Manila, Philippines. Available online: https:\/\/library.apsce.net.","DOI":"10.1109\/TALE.2018.8615234"},{"key":"ref_17","first-page":"61","article-title":"Integrating artificial intelligence in education: Impacts on student learning and innovation","volume":"10","author":"Treve","year":"2024","journal-title":"Int. J. Vocat. Educ. Train. Res."},{"key":"ref_18","first-page":"101401","article-title":"Harnessing artificial intelligence to revolutionize vocational education: Emerging trends, challenges, and contributions to SDGs 2030","volume":"11","author":"Prasetya","year":"2025","journal-title":"Soc. Sci. Humanit. Open"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1186\/s40561-023-00260-y","article-title":"Artificial intelligence in intelligent tutoring systems toward sustainable education: A systematic review","volume":"10","author":"Lin","year":"2023","journal-title":"Smart Learn. Environ."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"100001","DOI":"10.1016\/j.caeai.2020.100001","article-title":"Vision, challenges, roles and research issues of artificial intelligence in education","volume":"1","author":"Hwang","year":"2020","journal-title":"Comput. Educ. Artif. Intell."},{"key":"ref_21","first-page":"127","article-title":"Device-Cloud Collaborative Intelligent Computing: Key Problems, Methods, and Applications","volume":"26","author":"Zhang","year":"2024","journal-title":"Strateg. Study Chin. Acad. Eng."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Stavroulia, K.E., Baka, E., and Lanitis, A. (2025). VR-Based Teacher Training Environments: A Systematic Approach for Defining the Optimum Appearance of Virtual Classroom Environments. Virtual Worlds, 4.","DOI":"10.3390\/virtualworlds4010006"},{"key":"ref_23","first-page":"2375296","article-title":"Local large language models to simplify requirement engineering documents in the automotive industry","volume":"12","author":"Uygun","year":"2024","journal-title":"Prod. Manuf. Res."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Momodu, V. (2023). Using local large language models to simplify requirement engineering documents in the automotive industry. Logistics Engineering and Technologies Group-Working Paper Series 2023-04, Elsevier.","DOI":"10.2139\/ssrn.4574992"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"L\u00f3pez-Villanueva, D., Santiago, R., and Palau, R. (2024). Flipped Learning and Artificial Intelligence. Electronics, 13.","DOI":"10.20944\/preprints202407.2498.v1"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"100392","DOI":"10.1016\/j.caeai.2025.100392","article-title":"Integrating AI-based adaptive learning into the flipped classroom model to enhance engagement and learning outcomes","volume":"8","author":"Katona","year":"2025","journal-title":"Comput. Educ. Artif. Intell."},{"key":"ref_27","first-page":"2536382","article-title":"Integration of an AI-Based Platform and Flipped Classroom Instructional Model","volume":"2022","author":"Li","year":"2022","journal-title":"Sci. Program."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"122664","DOI":"10.1016\/j.techfore.2023.122664","article-title":"Digital transformation in education: A systematic review of education 4.0","volume":"194","author":"Mukul","year":"2023","journal-title":"Technol. Forecast. Soc. Chang."},{"key":"ref_29","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., and Polosukhin, I. (2017, January 4\u20139). Attention is all you need. Proceedings of the Advances in Neural Information Processing Systems 30 (NIPS 2017), Long Beach, CA, USA."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"e25383","DOI":"10.1016\/j.heliyon.2024.e25383","article-title":"A systematic literature review of knowledge graph construction and application in education","volume":"10","author":"Alotaibi","year":"2024","journal-title":"Heliyon"},{"key":"ref_31","unstructured":"Trajanoska, M., Stojanov, R., and Trajanov, D. (2023). Enhancing knowledge graph construction using large language models. arXiv."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Zhao, M., Wang, H., Guo, J., Liu, D., Xie, C., Liu, Q., and Cheng, Z. (2019). Construction of an Industrial Knowledge Graph for Unstructured Chinese Text Learning. Appl. Sci., 9.","DOI":"10.3390\/app9132720"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Kirchner, S., and Knoll, A.C. (2025). Generating Automotive Code: Large Language Models for Software Development and Verification in Safety-Critical Systems. arXiv.","DOI":"10.1109\/IV64158.2025.11097503"},{"key":"ref_34","unstructured":"Nouri, A., Cabrero-Daniel, B., Fei, Z., Ronanki, K., Sivencrona, H., and Berger, C. (2025). Large Language Models in Code Co-generation for Safe Autonomous Vehicles. arXiv."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Govea, J., Ocampo Edye, E., Revelo-Tapia, S., and Villegas-Ch, W. (2023). Optimization and Scalability of Educational Platforms: Integration of Artificial Intelligence and Cloud Computing. Computers, 12.","DOI":"10.3390\/computers12110223"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"274","DOI":"10.1080\/0194262X.2023.2247460","article-title":"Lightweight Cloud-Based Solution for Digital Education and Assessment","volume":"43","author":"Geetha","year":"2024","journal-title":"Sci. Technol. Libr."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Xu, X. (2025). AI optimization algorithms enhance higher education management and personalized teaching through empirical analysis. Sci. Rep., 15.","DOI":"10.1038\/s41598-025-94481-5"}],"container-title":["Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2079-8954\/13\/8\/668\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:24:40Z","timestamp":1760034280000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2079-8954\/13\/8\/668"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,6]]},"references-count":37,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2025,8]]}},"alternative-id":["systems13080668"],"URL":"https:\/\/doi.org\/10.3390\/systems13080668","relation":{},"ISSN":["2079-8954"],"issn-type":[{"type":"electronic","value":"2079-8954"}],"subject":[],"published":{"date-parts":[[2025,8,6]]}}}