علوم رایانش و فناوری اطلاعات

عدالت‌یار هوشمند با استفاده از شبکه‌های عصبی بازگشتی

نویسنده

دانشکده فنی و مهندسی، دانشگاه ارومیه، ارومیه، ایران

چکیده

این مقاله، با بسط مفهوم تمرکز بر ویژگی‌ها، در استفاده از شبکه حافظه کوتاه- ماندگار دوطرفه (biLSTM)، یک معماری جدید برای مسائل کاربردی پیشنهاد می‌دهد. biLSTM، فرایند گذشته و آینده ویژگی‌ها را به‌طور کامل می‌تواند منعکس کند. سیستم پیشنهادی به مطالعه موردی در مسائل قضایی اعمال‌شده است. در سیستم عدالت‌یار هوشمند پیشنهادشده، برای تصمیم مؤثرتر بعد از biLSTM از دو رمزگذار استفاده‌شده است و دارای لایه‌ای مبتنی بر دانش خبرگان  می‌باشد. در این روش با مشاهده اجزای پرونده ابتدا نوع مؤلفه‌ها بررسی می‌شود، سپس کلیدی بودن مؤلفه در اصلاح وزن‌ها موردتوجه قرار می‌گیرد. روش پیشنهادی در دو طرح مختلف ارائه‌شده است، در هر دو طرح ابتدا biLSTM هم بر روی مؤلفه‌های پرونده و هم بر روی حکم که دو بخش تبرئه و محکوم است اعمال می‌شود. دقت عملکرد بر اساس تمرکز بر روی مؤلفه‌های مؤثرتر مشخص می‌شود. طراحی این معماری بر اساس اشتراک‌گذاری وزن‌ها در زمان آموزش توسط رمزگذارها می‌باشد در طرح اول ابتدا مفهوم تمرکز بر ویژگی‌ها اعمال می‌شود و سپس در لایه‌های بعد هوش جمعی اعمال می‌شود. در طرح دوم هوش جمعی خبرگان در قالب یک تابع عضویت فازی به آن اعمال می‌شود. نتایج سیستم مشاور پیشنهادی در مورد مطالعاتی قضایی با روش‌های دیگر مقایسه شده‌اند که برتری روش پیشنهادی مشخص‌شده است. روش پیشنهادی با طراحی یک الگوی مناسب و به‌کارگیری اکثر عامل‌های دخیل و شناخت تأثیرگذاری آن‌ها درگرفتن یک تصمیم درست‌تر در زمان کوتاه‌تر می‌تواند بسیار کمک‌کننده باشد و متعاقباً هزینه‌های تشکیل دادگاه‌های تجدیدنظر و اطاله دادرسی را کاهش می‌دهد و حس اعتماد جامعه به سیستم قضا را افزایش می‌دهد.

کلیدواژه‌ها

  • [1] H. A. Dehabadi "The Necessity of Philosophy of Criminology," fegh and hoghogh ( in Persian), vol. 11, pp. 5-6, 2006.
  • [2] J. Drobak, N. and C. North, D., "Understanding judicial decision-Making: The importance of constraints on non-rational deliberations," J. Law Policy, vol. 134, pp. 26-131, 2008.
  • [3] C. Guthrie, J. J. Rachlinski, and A. J. Wistrich, "Blinking on the bench: How judges decide cases," Cornell Law Review, Forthcoming; Vanderbilt Public Law Research Paper No. 07-25; Vanderbilt Law and Economics Research Paper No. 07-32, 2007.
  • [4] G. Gigerenzer, Gut feelings: The intelligence of the unconscious: Viking Adult, 2007.
  • [5] M. M. Hall , D. Calabro , T. Sourdin , A. Stranieri , and J. Zeleznikow, "Supporting Discretionary Decision-Making with Information Technology: A Case Study in the Criminal Sentencing Jurisdiction," University of Ottawa Law and Technology Journal vol. 2, pp. 1-36, 2005.
  • [6] V. Aleven "Using background knowledge in case-based legal reasoning: A computational model and an intelligent learning environment," Artif Intell, vol. 150, pp. 183-237, 2003.
  • [7] C. Tata, "The Application of Judicial Intelligence and ‘Rules’ to Systems Supporting Discretionary Judicial Decision-Making," in Judicial Applications of Artificial Intelligence, G. Sartor and K. Branting, Eds., ed Dordrecht: Springer Netherlands, pp. 99-126, 1998.
  • [8] A. Valente, J. Breuker, and B. O. B. Brouwer, "Legal modeling and automated reasoning with ON-LINE," International Journal of Human-Computer Studies, vol. 51, pp. 1079-1125, 1999/12/01/ 1999.
  • [9] A. Wyner, "An ontology in OWL for legal case-based reasoning," Artificial Intelligence and Law, vol. 16, pp. 361-387, 2008/12/01 2008.
  • [10] J. Keppens, "Argument diagram extraction from evidential Bayesian networks," Artificial Intelligence and Law, vol. 20, pp. 109-143, 2012.
  • [11] C. Li, Y. Hu, and Z. Zhong, "An event ontology construction approach to web crime mining," in 2010 Seventh International Conference on Fuzzy Systems and Knowledge Discovery, pp. 2441-2445, 2010.
  • [12] T. Abraham and O. d. Vel, "Investigative profiling with computer forensic log data and association rules," in Proceedings of IEEE International Conference on Data Mining, pp. 11-18, 2002.
  • [13] S. Thammaboosadee and U. Silparcha, "A framework for criminal judicial reasoning system using data mining techniques," in 2nd IEEE International Conference on Digital Ecosystems and Technologies, pp. 518-523, 2008.
  • [14] S. C. Naves, "Analytic hierarchy process integrated hybrid agent system for intelligent legal assistance," in 2011 2nd International Conference on Intelligent Agent & Multi-Agent Systems, pp. 41-45, 2011.
  • [15] P. Wang and X. Zhu, "The Reliability Assessment of Legal Reasoning with Evidence Theory," in Second International Workshop on Knowledge Discovery and Data Mining, pp. 582-585, 2009.
  • [16] E. H. Haeusler, V. d. Paiva, and A. Rademaker, "Intuitionistic Description Logic and Legal Reasoning," in 22nd International Workshop on Database and Expert Systems Applications, pp. 345-349, 2011.
  • [17] F. Sabahi and M.-R. Akbarzadeh-T, "Introducing validity in fuzzy probability for judicial decision-making," International Journal of Approximate Reasoning, vol. 55, pp. 1383-1403, 2014.
  • [18] F. Sabahi, On the Theory of Imprecise Logic and Reasoning based on Extended Fuzzy Logic: Application to Judicial and Medical Decision Making, Partial Fulfillment of the Requirements of the Degree Doctor of Philosophy (Control Engineering), Faculty of Engineering, Ferdowsi University of Mashhad, 2013.
  • [19] M. M. J. Theresa and V. J. Raj, "Analogy making in criminal law with neural network," in International Conference on Emerging Trends in Electrical and Computer Technology, pp. 772-775, 2011.
  • [20] K. Zhang, X. Geng, and X. Yan, "Prediction of 3-D Ocean Temperature by Multilayer Convolutional LSTM," IEEE Geoscience and Remote Sensing Letters, pp. 1-5, 2020.
  • [21] J. Han, H. Liu, M. Wang, Z. Li, and Y. Zhang, "ERA-LSTM: An Efficient ReRAM-Based Architecture for Long Short-Term Memory," IEEE Transactions on Parallel and Distributed Systems, vol. 31, pp. 1328-1342, 2020.
  • [22] S. D. Kumar and D. Subha, "Prediction of Depression from EEG Signal Using Long Short Term Memory(LSTM)," in 3rd International Conference on Trends in Electronics and Informatics (ICOEI), pp. 1248-1253, 2019.
  • [23] S. Ye, J. Jiang, J. Li, Y. Liu, Z. Zhou, and C. Liu, "Fault Diagnosis and Tolerance Control of Five-Level Nested NPP Converter Using Wavelet Packet and LSTM," IEEE Transactions on Power Electronics, vol. 35, pp. 1907-1921, 2020.
  • [24] B. Chen, Y. Li, S. Zhang, H. Lian, and T. He, "A Deep Learning Method for Judicial Decision Support," in IEEE 19th International Conference on Software Quality, Reliability and Security Companion (QRS-C), pp. 145-149, 2019.
  • [25] J. L. Kane "Judging credibility," Litigation Mag., Am. Bar Assoc, vol. 33, pp. 1-8, 2007.
  • [26] L. A. Zadeh, "Probability theory and fuzzy logic are complementary rather than competitive," Technometrics, vol. 37, 1995.
  • [27] Y. Bengio, P. Simard, and P. Frasconi, "Learning long-term dependencies with gradient descent is difficult," IEEE Transactions on Neural Networks, vol. 5, pp. 157-166, 1994.
  • [28] S. Hochreiter and J. Schmidhuber, "Long Short-Term Memory," Neural computation, pp. 1735-1780, 1997.
  • [29] A. Graves "Generating Sequences With Recurrent Neural Networks," arXiv:1308.0850v5, 2014.
  • [30] A. Graves, "Generating Sequences With Recurrent Neural Networks," arXiv:1308.0850v5, 2014.
  • [31] Y. Liu, C. Sun, L. Lin, and X. Wang, "Learning Natural Language Inference using Bidirectional LSTM model and Inner-Attention," preprint: arxiv.org/abs/1605.09090v1, pp. 1-5, 2016.
  • [32] L. Cronbach, "Coefficient alpha and the internal structure of tests," Psychometrika, vol. 16, pp. 297-334, 1951.
  • [33] I. Sutskever, O. Vinyals, and Q. V. Le, "Sequence to Sequence Learning with Neural Networks," arXiv preprint arXiv:1511.08308, 2014.
  • [34] W. Zaremba and I. Sutskeve, "Learning to Execute," arXiv preprint arXiv:1410.4615, 2014.
  • [35] J. Pennington, R. Socher, and M. C. D, "Glove: Global vectors for word representation," EMNLP, vol. 14, pp. 1532-1543, 2014.
  • [36] L. Mou, M. Rui, G. Li, Y. Xu, L. Zhang, R. Yan, et al., "Recognizing entailment and contradiction by tree-based convolution," arXiv preprint arXiv:1512.08422., 2015.
علوم رایانش و فناوری اطلاعات
دوره 17، شماره 2
پاییز و زمستان
آذر 1398