{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T14:18:12Z","timestamp":1784557092248,"version":"3.55.0"},"reference-count":52,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100000104","name":"National Aeronautics and Space Administration","doi-asserted-by":"publisher","award":["80NSSCM0029"],"award-info":[{"award-number":["80NSSCM0029"]}],"id":[{"id":"10.13039\/100000104","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000104","name":"National Aeronautics and Space Administration","doi-asserted-by":"publisher","award":["1-511123-OU2 RIG"],"award-info":[{"award-number":["1-511123-OU2 RIG"]}],"id":[{"id":"10.13039\/100000104","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007069","name":"Oklahoma State University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007069","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007926","name":"University of Oklahoma","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007926","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.eswa.2026.132963","type":"journal-article","created":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T16:14:32Z","timestamp":1779725672000},"page":"132963","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":3,"special_numbering":"C","title":["Improving aviation safety analysis: Automated HFACS classification using reinforcement learning with group relative policy optimization"],"prefix":"10.1016","volume":"329","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0369-7387","authenticated-orcid":false,"given":"Arash","family":"Ahmadi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4667-6650","authenticated-orcid":false,"given":"Sarah S.","family":"Sharif","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7339-810X","authenticated-orcid":false,"given":"Yaser M.","family":"Banad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.132963_bib0001","unstructured":"Babaeizadeh, M., Frosio, I., Tyree, S., Clemons, J., & Kautz, J. (2016). Reinforcement learning through asynchronous advantage actor-critic on a GPU. arXiv preprint arXiv: 1611.06256."},{"key":"10.1016\/j.eswa.2026.132963_bib0002","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.132963_bib0003","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"Smote: Synthetic minority over-sampling technique","volume":"16","author":"Chawla","year":"2002","journal-title":"Journal of Artificial Intelligence Research"},{"key":"10.1016\/j.eswa.2026.132963_bib0004","unstructured":"Chen, Z., Deng, Y., Yuan, H., Ji, K., & Gu, Q. (2024). Self-play fine-tuning converts weak language models to strong language models. arXiv preprint arXiv: 2401.01335."},{"key":"10.1016\/j.eswa.2026.132963_bib0005","unstructured":"Chollet, F., Knoop, M., Kamradt, G., Landers, B., & Pinkard, H. (2025). Arc-agi-2: A new challenge for frontier ai reasoning systems. arXiv preprint arXiv: 2505.11831."},{"key":"10.1016\/j.eswa.2026.132963_bib0006","series-title":"2017 6th Mediterranean conference on embedded computing (MECO)","first-page":"1","article-title":"SVM classification: Optimization with the smote algorithm for the class imbalance problem","author":"Demidova","year":"2017"},{"key":"10.1016\/j.eswa.2026.132963_bib0007","series-title":"Proceedings of the 2019 Conference of the north american chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers)","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.eswa.2026.132963_bib0008","unstructured":"Gunjal, A., Wang, A., Lau, E., Nath, V., He, Y., Liu, B., & Hendryx, S. (2025). Rubrics as rewards: Reinforcement learning beyond verifiable domains. arXiv preprint arXiv: 2507.17746."},{"issue":"8081","key":"10.1016\/j.eswa.2026.132963_bib0009","doi-asserted-by":"crossref","first-page":"633","DOI":"10.1038\/s41586-025-09422-z","article-title":"Deepseek-r1 incentivizes reasoning in llms through reinforcement learning","volume":"645","author":"Guo","year":"2025","journal-title":"Nature"},{"issue":"1","key":"10.1016\/j.eswa.2026.132963_bib0010","doi-asserted-by":"crossref","first-page":"258","DOI":"10.30630\/joiv.7.1.1069","article-title":"Improvement performance of the random forest method on unbalanced diabetes data classification using smote-tomek link","volume":"7","author":"Hairani","year":"2023","journal-title":"JOIV: International Journal on Informatics Visualization"},{"key":"10.1016\/j.eswa.2026.132963_bib0011","series-title":"2024 11th International symposium on telecommunications (IST)","first-page":"697","article-title":"Modified double-DQN: Addressing stability","author":"Halat","year":"2024"},{"key":"10.1016\/j.eswa.2026.132963_bib0012","series-title":"International conference on intelligent computing","first-page":"878","article-title":"Borderline-SMOTE: A new over-sampling method in imbalanced data sets learning","author":"Han","year":"2005"},{"issue":"2","key":"10.1016\/j.eswa.2026.132963_bib0013","first-page":"84","article-title":"Reinforcement learning: Advanced techniques for LLM behavior optimization","volume":"2","author":"Hariharan","year":"2025","journal-title":"ESP International Journal of Advancements in Computational Technology (ESP-IJACT)"},{"issue":"2","key":"10.1016\/j.eswa.2026.132963_bib0014","doi-asserted-by":"crossref","first-page":"86","DOI":"10.29099\/ijair.v4i2.152","article-title":"Random and synthetic over-sampling approach to resolve data imbalance in classification","volume":"4","author":"Hayaty","year":"2020","journal-title":"International Journal of Artificial Intelligence Research"},{"key":"10.1016\/j.eswa.2026.132963_bib0015","unstructured":"Jaech, A., Kalai, A., Lerer, A., Richardson, A., El-Kishky, A., Low, A., Helyar, A., Madry, A., Beutel, A., Carney, A. et al. (2024). Openai o1 system card. arXiv preprint arXiv: 2412.16720."},{"key":"10.1016\/j.eswa.2026.132963_bib0016","unstructured":"Jimenez, C. E., Yang, J., Wettig, A., Yao, S., Pei, K., Press, O., & Narasimhan, K. (2023). Swe-bench: Can language models resolve real-world github issues?arXiv preprint arXiv: 2310.06770."},{"key":"10.1016\/j.eswa.2026.132963_bib0017","unstructured":"Khandelwal, A., Yun, T., Nayak, N. V., Merullo, J., Bach, S. H., Sun, C., & Pavlick, E. (2024). $100 k or 100 days: Trade-offs when pre-training with academic resources. arXiv preprint arXiv: 2410.23261."},{"key":"10.1016\/j.eswa.2026.132963_bib0018","doi-asserted-by":"crossref","first-page":"31504","DOI":"10.52202\/079017-0990","article-title":"Epic: Effective prompting for imbalanced-class data synthesis in tabular data classification via large language models","volume":"37","author":"Kim","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.132963_bib0019","series-title":"17th AIAA Aviation technology, integration, and operations conference","first-page":"3439","article-title":"In search of general aviation flight data monitoring: Lightweight recording system","author":"Kuo","year":"2017"},{"key":"10.1016\/j.eswa.2026.132963_bib0020","series-title":"Proceedings of the 29th Symposium on operating systems principles","first-page":"611","article-title":"Efficient memory management for large language model serving with pagedattention","author":"Kwon","year":"2023"},{"key":"10.1016\/j.eswa.2026.132963_bib0021","series-title":"Advances on smart and soft computing: Proceedings of ICACIn 2020","first-page":"37","article-title":"Smote\u2013enn-based data sampling and improved dynamic ensemble selection for imbalanced medical data classification","author":"Lamari","year":"2020"},{"key":"10.1016\/j.eswa.2026.132963_bib0022","unstructured":"Li, Y. (2017). Deep reinforcement learning: An overview. arXiv preprint arXiv: 1701.07274."},{"key":"10.1016\/j.eswa.2026.132963_bib0023","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.126422","article-title":"Accident investigation via LLMs reasoning: HFACS-guided chain-of-thoughts enhance general aviation safety","volume":"269","author":"Liu","year":"2025","journal-title":"Expert Systems with Applications"},{"issue":"2","key":"10.1016\/j.eswa.2026.132963_bib0024","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1007\/BF02295996","article-title":"Note on the sampling error of the difference between correlated proportions or percentages","volume":"12","author":"McNemar","year":"1947","journal-title":"Psychometrika"},{"key":"10.1016\/j.eswa.2026.132963_bib0025","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., & Riedmiller, M. (2013). Playing atari with deep reinforcement learning. arXiv preprint arXiv: 1312.5602."},{"issue":"1","key":"10.1016\/j.eswa.2026.132963_bib0026","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1108\/JHLSCM-01-2014-0008","article-title":"Managing airborne relief during international disasters","volume":"5","author":"Morales","year":"2015","journal-title":"Journal of Humanitarian Logistics and Supply Chain Management"},{"issue":"5","key":"10.1016\/j.eswa.2026.132963_bib0027","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3744746","article-title":"A comprehensive overview of large language models","volume":"16","author":"Naveed","year":"2025","journal-title":"ACM Transactions on Intelligent Systems and Technology"},{"key":"10.1016\/j.eswa.2026.132963_bib0028","series-title":"Technical Report","article-title":"GPT-5 System Card","author":"OpenAI","year":"2025"},{"key":"10.1016\/j.eswa.2026.132963_bib0029","series-title":"International conference on medical image computing and computer-assisted intervention","first-page":"337","article-title":"Medvlm-r1: Incentivizing medical reasoning capability of vision-language models (VLMS) via reinforcement learning","author":"Pan","year":"2025"},{"key":"10.1016\/j.eswa.2026.132963_bib0030","unstructured":"Pennino, F., Raimondi, B., Rondelli, M., Gurioli, A., & Gabbrielli, M. (2025). From reasoning to code: GRPO optimization for underrepresented languages. arXiv preprint arXiv: 2506.11027."},{"key":"10.1016\/j.eswa.2026.132963_bib0031","doi-asserted-by":"crossref","unstructured":"Petruzzellis, F., Testolin, A., & Sperduti, A. (2024). Benchmarking GPT-4 on algorithmic problems: A systematic evaluation of prompting strategies. arXiv preprint arXiv: 2402.17396.","DOI":"10.63317\/2zoyujcagmhp"},{"key":"10.1016\/j.eswa.2026.132963_bib0032","unstructured":"Pham, T.-H., & Ngo, C. (2025). Rarl: Improving medical vlm reasoning and generalization with reinforcement learning and lora under data and hardware constraints. arXiv preprint arXiv: 2506.06600."},{"key":"10.1016\/j.eswa.2026.132963_bib0033","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., & Klimov, O. (2017). Proximal policy optimization algorithms. arXiv preprint arXiv: 1707.06347."},{"key":"10.1016\/j.eswa.2026.132963_bib0034","doi-asserted-by":"crossref","first-page":"43000","DOI":"10.52202\/079017-1361","article-title":"Rl on incorrect synthetic data scales the efficiency of llm math reasoning by eight-fold","volume":"37","author":"Setlur","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.132963_bib0035","unstructured":"Shao, Z., Wang, P., Zhu, Q., Xu, R., Song, J., Bi, X., Zhang, H., Zhang, M., Li, Y. K., Wu, Y. et al. (2024). Deepseekmath: Pushing the limits of mathematical reasoning in open language models. arXiv preprint arXiv: 2402.03300."},{"key":"10.1016\/j.eswa.2026.132963_bib0036","series-title":"The Report of Office of Aviation Medicine Federal Aviation Administration","first-page":"20","article-title":"The Human Factors Analysis and Classification System\u2014HFACS","author":"Shappell","year":"2000"},{"issue":"4","key":"10.1016\/j.eswa.2026.132963_bib0037","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1016\/j.amj.2022.04.011","article-title":"A statistical overview of fixed wing air medical transportation operations in the united states (2019-2020)","volume":"41","author":"Sherry","year":"2022","journal-title":"Air Medical Journal"},{"key":"10.1016\/j.eswa.2026.132963_bib0038","article-title":"The geographical characteristics of subsidized air routes serving as lifelines","volume":"104","author":"e Silva","year":"2022","journal-title":"Journal of Air Transport Management"},{"issue":"7676","key":"10.1016\/j.eswa.2026.132963_bib0039","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of go without human knowledge","volume":"550","author":"Silver","year":"2017","journal-title":"Nature"},{"key":"10.1016\/j.eswa.2026.132963_bib0040","series-title":"Reinforcement learning: An introduction","volume":"vol. 1","author":"Sutton","year":"1998"},{"key":"10.1016\/j.eswa.2026.132963_bib0041","unstructured":"Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozi\u00e8re, B., Goyal, N., Hambro, E., Azhar, F. et al. (2023). Llama: Open and efficient foundation language models. arXiv preprint arXiv: 2302.13971."},{"key":"10.1016\/j.eswa.2026.132963_bib0042","unstructured":"Unsloth, A. I., Han-Chen, D., & Han-Chen, M. (2024). unsloth\/llama-3.1-8b-instruct. https:\/\/huggingface.co\/unsloth\/Llama-3.1-8B-Instruct."},{"key":"10.1016\/j.eswa.2026.132963_bib0043","series-title":"Proceedings of the AAAI Conference on artificial intelligence","article-title":"Deep reinforcement learning with double Q-learning","volume":"vol. 30","author":"Van Hasselt","year":"2016"},{"key":"10.1016\/j.eswa.2026.132963_bib0044","unstructured":"Wang, J., Meng, F., & Zhou, J. (2025). Deep reasoning translation via reinforcement learning. arXiv preprint arXiv: 2504.10187."},{"issue":"9","key":"10.1016\/j.eswa.2026.132963_bib0045","doi-asserted-by":"crossref","first-page":"2184","DOI":"10.1016\/j.engappai.2013.06.016","article-title":"Backward Q-learning: The combination of sarsa algorithm and q-learning","volume":"26","author":"Wang","year":"2013","journal-title":"Engineering Applications of Artificial Intelligence"},{"issue":"3","key":"10.1016\/j.eswa.2026.132963_bib0046","first-page":"279","article-title":"Q-learning","volume":"8","author":"Watkins","year":"1992","journal-title":"Machine Learning"},{"key":"10.1016\/j.eswa.2026.132963_bib0047","doi-asserted-by":"crossref","first-page":"24824","DOI":"10.52202\/068431-1800","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.132963_bib0048","doi-asserted-by":"crossref","unstructured":"Wu, K., Li, W., & Xiao, X. (2024). AccidentGPT: Large multi-modal foundation model for traffic accident analysis. arXiv preprint arXiv: 2401.03040.","DOI":"10.5220\/0012422100003636"},{"key":"10.1016\/j.eswa.2026.132963_bib0049","series-title":"2016 International conference on industrial informatics-computing technology, intelligent technology, industrial information integration (ICIICII)","first-page":"356","article-title":"Emergency management capability evaluation system in civil aviation industry","author":"Wu","year":"2016"},{"key":"10.1016\/j.eswa.2026.132963_bib0050","unstructured":"Xu, Z., Jain, S., & Kankanhalli, M. (2024). Hallucination is inevitable: An innate limitation of large language models. arXiv preprint arXiv: 2401.11817."},{"key":"10.1016\/j.eswa.2026.132963_bib0051","unstructured":"Zheng, L., Chiang, W.-L., Sheng, Y., Li, T., Zhuang, S., Wu, Z., Zhuang, Y., Li, Z., Lin, Z., Xing, E. P. et al. (2023a). Lmsys-chat-1m: A large-scale real-world llm conversation dataset. arXiv preprint arXiv: 2309.11998."},{"key":"10.1016\/j.eswa.2026.132963_bib0052","doi-asserted-by":"crossref","first-page":"46595","DOI":"10.52202\/075280-2020","article-title":"Judging LLM-as-a-judge with mt-bench and chatbot arena","volume":"36","author":"Zheng","year":"2023","journal-title":"Advances in Neural Information Processing Systems"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426018750?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426018750?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T23:17:06Z","timestamp":1783120626000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426018750"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":52,"alternative-id":["S0957417426018750"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132963","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Improving aviation safety analysis: Automated HFACS classification using reinforcement learning with group relative policy optimization","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132963","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"132963"}}