بهبود سیستمهای یادگیری تطبیقی: یک رویکرد احتمالی با استفاده از شبکههای بیزی و خوشهبندی کاربر
محورهای موضوعی : پردازش چند رسانه ای، سیستمهای ارتباطی، سیستمهای هوشمند
پروانه احمدی فرد
1
,
مجتبی صالحی
2
*
,
محمد یاراحمدی
3
,
مرتضی ذاکری
4
1 - کارشناسی ارشد، گروه کامپیوتر، واحد خرم آباد، دانشگاه آزاد اسلامی، خرم آباد، ایران
2 - مربی، گروه کامپیوتر، واحد خرم آباد، دانشگاه آزاد اسلامی، خرم آباد، ایران.
3 - مربی، گروه ریاضی، واحد خرم آباد، دانشگاه آزاد اسلامی، خرم آباد، ایران
4 - استادیار، دانشکده مهندسی کامپیوتر، دانشگاه صنعتی امیرکبیر، تهران، ایران
کلید واژه: سیستم آموزش هوشمند, انتخاب ویژگی, شبکه بیزین, الگوریتم .K-Means. ,
چکیده مقاله :
تحول سامانههای آموزش الکترونیکی دسترسی بیسابقهای به آموزش فراهم کرده و نیازهای متنوع کاربران را از طریق خدمات و روشهای مختلف برآورده میکند. با این حال، نبود تکنیکهای شخصیسازی و بهینهسازی مؤثر، مانع از بهرهبرداری کامل از پتانسیل این سامانهها شده است. این پژوهش یک چارچوب نوآورانه برای ارتقای کیفیت و انطباقپذیری سامانههای آموزشی مبتنی بر وب با استفاده از شبکههای بیزین ارائه میدهد. روش پیشنهادی شامل انتخاب ویژگی از طریق الگوریتم Relief، خوشهبندی کاربران با استفاده از الگوریتم k-means، و پیشنهاد خدمات بهصورت احتمالاتی بر اساس استنتاج بیزین است. انتخاب ویژگی با اولویتبندی ویژگیهای کلیدی کاربران، ابعاد دادهها را کاهش داده و کارایی پردازشی را افزایش میدهد. خوشهبندی، کاربران را بر اساس شباهتهایشان در گروههای همگن سازماندهی کرده و ارائه خدمات شخصیسازیشده را تسهیل میکند. این سامانه با استفاده از یک مجموعه داده شامل 2000 کاربر که هرکدام دارای 16 ویژگی و 24 خدمت بودند، ارزیابی شد. شبکههای بیزین روابط احتمالاتی و عدم قطعیتها را تحلیل کرده و خدمات مرتبط را به هر کاربر پیشنهاد میدهند. این روش مشکل آغاز سرد را برطرف کرده و انطباقپذیری و مقیاسپذیری را برای نیازهای متنوع کاربران بهبود میبخشد. نتایج آزمایشها دقتی معادل 88.15 درصد را نشان داد که مؤثر بودن مدل در مقایسه با روشهای سنتی را تأیید میکند. مزایای کلیدی شامل بهبود شخصیسازی، افزایش کارایی محاسباتی و ارتقای رضایت کاربران است. یافتههای این مطالعه، توانایی سامانههای آموزشی هوشمند را برای تطبیق پویا با نیازهای کاربران نشان داده و زمینهساز تجربههای آموزشی جذابتر و مؤثرتر میشود. پژوهشهای آتی بر ادغام الگوریتمهای فراابتکاری برای پیشبینی دقیقتر و دریافت بازخورد بلادرنگ کاربران به منظور بهبود فرآیند پیشنهاد متمرکز خواهند بود
Introduction: This study proposes an innovative framework to enhance the quality and adaptability of web-based educational systems using Bayesian networks. The proposed methodology aims to address issues like the cold-start problem and improve the scalability and personalization of educational services.
Method: The proposed methodology encompasses feature selection through the Relief algorithm, user clustering via k-means, and probabilistic service recommendation based on Bayesian inference. Feature selection prioritizes user-specific attributes, reducing data dimensionality and enhancing computational efficiency. Clustering organizes users into homogeneous groups based on similarities, facilitating tailored service provision. The system was validated using a dataset of 2000 users, each characterized by 16 features and linked to 24 services.
Results: The experimental results demonstrated an accuracy rate of 88.15%, underscoring the model's effectiveness compared to traditional techniques. Bayesian networks enabled the analysis of probabilistic relationships and uncertainties, ensuring that the most relevant services were recommended to each user.
Discussion: The proposed approach addressed the cold-start problem, improving scalability and adaptability to diverse user needs. Key advantages of this framework include enhanced personalization, computational efficiency, and significant improvements in user satisfaction. The study's findings highlight the potential of intelligent learning systems to adjust dynamically to user requirements, paving the way for more engaging and effective educational experiences. Future research will incorporate heuristic algorithms to improve prediction accuracy and integrate real-time user feedback to refine the recommendation process further.
[1] M.I. Burhan, A. Kumala Jaya, and L. Adira. "Bayesian Intelligent Tutoring System for Vocational High Schools." PENA TEKNIK: Jurnal Ilmiah Ilmu-Ilmu Teknik 9, no. 1, pp. 1-13, 2024.
[2] M. Tao, "Application of Bayesian Model in the Construction of Personalized Learning Platform for Internet Education," 2024 International Conference on Distributed Computing and Optimization Techniques (ICDCOT), Bengaluru, India, pp. 1-5, 2024.
[3] M. Chanthiran, A. B. Ibrahim, M. H. Abdul Rahman, and P. Mariappan, "Bayesian Network Approach in Educational Application Development: A Systematic Literature Review and Bibliometric Meta-Analysis", International Journal of Artificial Intelligence, vol. 9, no. 1, pp. 8-16, Jun. 2022.
[4] R. B. Kaliwal and S. L. Deshpande, "Assessment Study For E-Learning Using Bayesian Network," 2021 International Conference on Artificial Intelligence and Smart Systems (ICAIS), Coimbatore, India, pp. 79-84, 2021.
[5] I. Nekhaev, I. Zhuykov, S. Manukyants, Maslennikov, A. (2020). Applying Bayesian Network to Assess the Levels of Skills Mastering in Adaptive Dynamic OER-Systems. In: Silhavy, R., Silhavy, P., Prokopova, Z. (eds) Software Engineering Perspectives in Intelligent Systems. CoMeSySo 2020. Advances in Intelligent Systems and Computing, vol 1294, 2020.
[6] G. Li and Y. Wang, "Learner's emotion recognition for intelligent education systems," in 3rd Adv. Inf. Technol. Electron. Automat. Control Conf., IEEE, pp. 754–758, 2018.
[7] D. Qiu, "Development and implementation of an intelligent learning system for ideological and political education," in Int. Conf. on Virtual Reality and Intelligent Systems, IEEE, pp. 289–292, 2018.
[8] Y. Zhang, "Exploration on teaching reform of architectural design course in higher vocational colleges in the era of intelligent education," Advances in Higher Education, vol. 3, no. 3, pp. 33–35, 2019.
[9] M. Ally, "Foundations of educational theory for online learning," in Theory and Practice of Online Learning, T. Anderson, Ed., Edmonton: AU Press, pp. 15–44, 2008.
[10] F. Canales et al., "Adaptive and intelligent web-based education system: Towards an integral architecture and framework," Expert Systems with Applications, vol. 33, no. 4, pp. 1076–1089, 2007.
[11] H. T. Kahraman, S. Sagiroglu, and I. Colak, "Development of adaptive and intelligent web-based educational systems," in 4th Int. Conf. on Application of Information and Communication Technologies, IEEE, pp. 1–5, 2010.
[12] Z. Mousavi and M. Khan Babayi, "A data mining-based method for guiding students in educational systems," in 1st National Conference on Business Management, 2013.
[13] R.B. Kaliwal, S.L. Deshpande. Bayesian Network Model Based Classifiers Are Used in an Intelligent E-learning System. In: Garg, D., Rodrigues, J.J.P.C., Gupta, S.K., Cheng, X., Sarao, P., Patel, G.S. (eds) Advanced Computing. IACC 2023. Communications in Computer and Information Science, vol 2053, 2024.
[14] C. He, W. Liu and J. Ren, "Bayesian Network Structure Learning: A Review," 2022 6th Asian Conference on Artificial Intelligence Technology (ACAIT), Changzhou, China, pp. 1-7,2022.
[15] Li, G., & Wang, Y. Research on leamer's emotion recognition for intelligent education system. In 2018 IEEE 3rd Advanced Information Technology, Electronic and Automation Control Conference (IAEAC), pp. 754-758, October 2018.
[16] Qiu, D. Development and Implementation of Learning System of an Intelligent Learning System for Ideological and Political Education in Colleges under Mobile Platform. In 2018 International Conference on Virtual Reality and Intelligent Systems (ICVRIS), pp. 289-292, August 2018.
[17] H.T. Kahraman, S. Sagiroglu and I. Colak. Development of adaptive and intelligent web-based educational systems. In 2010 4th International Conference on Application of Information and Communication Technologies, pp. 1-5, 2010, October.
[18] Hu, H., Li, J., Lei, X., Qin, P., & Chen, Q. Design of health statistics intelligent education system based on Internet+. In Journal of Physics: Conference Series (Vol. 1168, No. 6, p. 062003, February 2019.
[19] Xu, Y. Physical Education Evaluation System Analysis and Intelligent Evaluation System Design. Caribbean Journal of Science, 52(4), pp. 1521-1524, 2019.
[20] R. O'Brien, M. Hartnett, and P. Rawlins, (2019). The centralization of elearning resource development within the New Zealand vocational tertiary education sector. Australasian Journal of Educational Technology, 2019.
[21] H. Bahador, S. Aliaei, and A. Bagheri, "Presenting a model for identifying factors affecting students' academic guidance using decision tree and neural network," in 2nd National Congress of New Technologies of Iran with the Aim of Achieving Sustainable Development, Tehran, Center for Achieving Sustainable Development Solutions, Mehr Arvand Higher Education Institute, 2015.
[22] B. Maghsoudi, S. Soleimani, A. Amiri, and M. Afsharchi, "Improving the quality of education in e-learning systems using educational data mining," Journal of Educational Technology, vol. 6, 2012.
[23] B. Minae, S. S. Mirfazel, and S. H. Hani, "Identifying factors affecting academic failure using association rules and cluster analysis," in 6th International Conference on Data Mining of Iran, 2013.
[24] Z. S. Mousavi and M. Khanbabaei, "Presenting a method based on a hybrid data mining technique for students' academic guidance," in 1st National Conference on Business Management, Hamedan, Tolou Farzin Science and Industry Company, Bu-Ali Sina University, 2013.
[25] F. Gharebaghi and A. Amiri, "A Novel Semi-Supervised Approach to Improve the Performance of E-learning," Intelligent Multimedia Processing and Communication Systems, vol. 3, no. 3, pp. 53-63, 2022.
[26] N. Farghzadeh and N. Modiri, "Developing a Performance-Aware Cloud Infrastructure in E-Learning and Virtual Systems," Intelligent Multimedia Processing and Communication Systems, vol. 2, no. 1, pp. 53-64, Mar. 2021
[27] M. Bazargani, S. H. Alizadeh, and B. Masoumi, "Group deep neural network approach in semantic recommendation system for movie recommendation in online networks," Electron. Commer. Res., 2024.