ONTOLOGIYA, NLP VA CBR ASOSIDA METRO AVARIYALARIDA QAROR QABUL QILISHNI QO‘LLAB-QUVVATLASH
DOI:
https://doi.org/10.5281/Keywords:
metro xavfsizligi, ontologiya, tabiiy tilni qayta ishlash, CBR, RBR, SWRL, qarorlarni qo‘llab-quvvatlash.Abstract
Tezisda metro va temir yo‘l hodisalarida tezkor qaror tayyorlash uchun ontologiya, tabiiy tilni qayta ishlash, pretsedentlarga asoslangan xulosalash (Case-Based Reasoning — CBR) va qoidalarga asoslangan xulosalashni (Rule-Based Reasoning — RBR) birlashtiruvchi yondashuv tahlil qilinadi. NLP hodisa matnidan ontologiyada belgilangan tushunchalarni ajratadi, CBR o‘xshash tarixiy holatlarni topadi, RBR esa o‘xshash holat yetarli bo‘lmaganda reglament va favqulodda rejalar asosida choralarni taklif qiladi. Wu va hammualliflar tadqiqotida 120 ta metro hodisasi asosida yaratilgan bazani ekspertlar baholagan va o‘xshash holatlarni qidirish bo‘yicha o‘rtacha precision 91 foizni tashkil etgan. Mazkur qiymat umumiy accuracy emas, aynan ekspert baholashiga asoslangan o‘rtacha precision ko‘rsatkichidir.
References
1. Aamodt A., Plaza E. Case-Based Reasoning: Foundational Issues, Methodological Variations, and System Approaches // AI Communications. – 1994. – Vol. 7, No. 1. – P. 39–59.
2. Wu H., Zhong B., Medjdoub B., Xing X., Jiao L. An Ontological Metro Accident Case Retrieval Using CBR and NLP // Applied Sciences. – 2020. – Vol. 10, No. 15. – Article 5298. DOI: 10.3390/app10155298.
3. Blei D. M., Ng A. Y., Jordan M. I. Latent Dirichlet Allocation // Journal of Machine Learning Research. – 2003. – Vol. 3. – P. 993–1022.
4. Grootendorst M. BERTopic: Neural topic modeling with a class-based TF-IDF procedure. – arXiv:2203.05794, 2022. DOI: 10.48550/arXiv.2203.05794.
5. Bridgelall R., Tolliver D. D. Railroad accident analysis by machine learning and natural language processing // Journal of Rail Transport Planning & Management. – 2024. – Vol. 29. – Article 100429. DOI: 10.1016/j.jrtpm.2023.100429.
