بهینه سازی و پیش بینی برنامه های موردعلاقه کاربران با استفاده از رویکرد فیلترینگ مشارکتی و الگوریتم فاخته
محورهای موضوعی : مهندسی برق و کامپیوتررضا مولایی فرد 1 * , جواد محمدزاده 2 , پیام یاراحمدی 3
1 - گروه مهندسی کامپیوتر، دانشکده کامپیوتر و فناوری اطلاعات، واحد علوم و تحقیقات، دانشگاه آزاد اسلامی، تهران
2 - گروه مهندسی کامپیوتر، دانشکده هوش مصنوعی، واحد کرج، دانشگاه آزاد اسلامی، کرج، ایران
3 - گروه مهندسی کامپیوتر، دانشگاه ملی تاراس شوچنکو کیف، کیف، اوکراین
کلید واژه: سیستم توصیه گر, برنامه موبایل, فیلترینگ مشارکتی, الگوریتم فاخته, داده کاوی.,
چکیده مقاله :
در این تحقیق به ارائه روشی به منظور بهبود سیستمهای توصیهگر برنامه موبایل با استفاده از فیلترینگ مشارکتی و الگوریتم فراابتکاری فاخته پرداخته میشود که برای خوشهبندی دادهها از الگوریتم SW-DBSCAN استفاده شده که این الگوریتم توانست میزان کارایی ۹۹% را در بخش خوشهبندی به دست آورد که از سایر الگوریتمهای مشابه توانست عملکرد بهتری را به دست آورد. همچنین برای بهینهسازی دادهها از الگوریتم فاخته استفاده شده که این الگوریتم توانست عملکرد ۹۸% را به دست آورد و نسبت به الگوریتمهای کرم شبتاب، گرگ خاکستری و بهینهسازی ذرات عملکرد بهتری را به دست آورد. برای قسمت پیشبینی نیز از الگوریتم شبکههای عصبی استفاده شده که در این بخش نیز توانست عملکرد قابل قبولی نسبت به سایر الگوریتمهای مشابه به دست آورد که در نهایت با استفاده از سیستم توصیهگر مبتنی بر فیلترینگ مشارکتی این اطلاعات در اختیار کاربر قرار میگیرد. یکی از مشکلاتی که سیستمهای توصیهگر با آن مواجه هستند، مشکل داشتن معنای یکسان است. مشکل داشتن معنای یکسان وقتی رخ میدهد که یک آیتم با دو یا چند نام نشان داده شود؛ نامهایی که معنای مشابهی دارند. در چنین مواردی، سیستم توصیهگر نمیتواند تشخیص دهد که این نامها نشاندهنده اقلام متفاوتی هستند یا همگی به یک آیتم یکسان اشاره دارند که در این روش سعی به برطرفکردن آن شد. همچنین طبق تحقیقات صورتگرفته، استفاده از این روش پیشنهادی تا ۹۴% میتواند نیازهای کاربر را بهدرستی تشخیص داده و پیشنهادهای مناسبی را به کاربر پیشنهاد دهد.
This research presents a method to improve mobile application recommendation systems using collaborative filtering and the cuckoo meta-heuristic algorithm. The SW-DBSCAN algorithm was used for data clustering. This algorithm was able to achieve an efficiency of 99% in the clustering section, which was better than other similar algorithms. Also, the cuckoo algorithm was used to optimize the data, which achieved a performance of 98% and achieved better performance than the firefly, gray wolf, and particle optimization algorithms. For the prediction part, a neural network algorithm was used, which was also able to achieve acceptable performance compared to other similar algorithms. Ultimately, this information is provided to the user using a recommender system based on collaborative filtering. One of the problems that recommender systems face is the problem of having the same meaning. The problem of having the same meaning occurs when an item is represented by two or more names, names that have the same meaning. In such cases, the recommender system cannot distinguish whether these names represent different items or all refer to the same item, which is what this method attempts to solve. Also, according to research, using this recommended method can correctly identify user needs up to 94% of the time and offer appropriate suggestions to the user.
[1] S. Kim, et al., "PubChem in 2021: new data content and improved web interfaces," Nucleic Acids Research, vol. 49, no. D1, pp. D1388-D1395, 2021.
[2] Adiyanto and Nurasiah, "Customer relationship management (CRM) based on web to improve the performance of the company," IAIC Trans. on Sustainable Digital Innovation, vol. 1, no. 1, pp. 32-41, Oct. 2019.
[3] A. Lau, E. Tsui, and W. Lee, "An ontology-based similarity measurement for problem-based case reasoning," Expert Systems with Applications, vol. 36, no. 3, pt. 2, pp. 6574-6579, Apr. 2009.
[4] F. Beierle and T. Eichinger, "Collaborating with users in proximity for decentralized mobile recommender systems," in Proc. IEEE Smart World, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation, pp. 1192-1197, Leicester, UK, 19-23 Aug. 2019.
[5] M. Montaner, B. López, J. L. De La Rosa, "A taxonomy of recommender agents on the Internet," Artificial Intelligence Review, vol. 19, pp. 285-330, 2003.
[6] B. Abu-Salih, et al., "Toward a knowledge-based personalised recommender system for mobile app development," JUCS-J. of Universal Computer Science, vol. 27, no. 2, pp. 208-229, 2021.
[7] C. Yang, et al., "Enhancing mobile app recommendations through adaptive fusion of long-term stability and short-term interests," Information Sciences, vol. 699, Article ID: 121817, May 2025.
[8] D. Yu, X. Zhou, A. Noorian, and M. Hazratifard, "An AI-driven social media recommender system leveraging smartphone and IoT data," The J. of Supercomputing, vol. 81, no. 1, pp. 1-32, Jan. 2025.
[9] F. Nadeem and M. Suleman, Developing a Personalized Recommender System for Enhanced User Experience in Mobile Applications, Oct. 2024. DOI:10.13140/RG.2.2.19331.31528 [10] Y. Gong, et al., "EdgeRec: recommender system on edge in mobile Taobao," in Proc. of the 29th ACM Int. Conf. on Information & Knowledge Management, pp. 2477-2484, Virtual Event Ireland, 19-23 Oct. 2020.
[11] E. Pimenidis, N. Polatidis, and H. Mouratidis, "Mobile recommender systems: identifying the major concepts," J. of Information Science, vol. 45, no. 3, pp. 387-397, Jun. 2019.
[12] H. Yin, et al., "Mobi-SAGE-RS: a sparse additive generative model-based mobile application recommender system," Knowledge-Based Systems, vol. 157, pp. 68-80, Oct. 2018.
[13] H. Ranaivoson, A. Smets, and P. Ballon, "15 Challenges and opportunities for recommender systems in media markets," In U. Rohn, M. B. von Rimscha, and T, Raats (Eds.) De Gruyter Handbook of Media Economics, pp. 215-228, Boston: De Gruyter, 2024.
[14] E. Hasan, M. Rahman, C. Ding, J. X. Huang, and S. Raza, Review-Based Recommender Systems: A Survey of Approaches, Challenges and Future Perspectives, arXiv preprint arXiv:2405.05562, 2024.
[15] X. Chen, S. Wang, J. McAuley, D. Jannach, and L. Yao, "On the opportunities and challenges of offline reinforcement learning for recommender systems," ACM Trans. on Information Systems, vol. 42, no. 6, Article ID: 150, 26 pp., Nov. 2023.
[16] N. Alharbe, M. A. Rakrouki, and A. Aljohani, "A collaborative filtering recommendation algorithm based on embedding representation," Expert Systems with Applications, vol. 215, Article ID: 119380, Apr. 2023.
[17] S. A. N. Alexandropoulos, S. B. Kotsiantis, and M. N. Vrahatis, "Data preprocessing in predictive data mining," The Knowledge Engineering Review, vol. 34, 2019. doi:10.1017/S026988891800036X
[18] N. Ohadi, et al., "SW-DBSCAN: a grid-based DBSCAN algorithm for large datasets," in Proc. 6th Int. Conf. on Web Research, pp. 139-145, Tehran, Iran, 22-23 Apr. 2020.
[19] Y. Jiang, C. Kang, Y. Shen, T. Huang, and G. Zhai, "Research on Argo data anomaly detection based on improved DBSCAN algorithm," in Proc. China Conference on Wireless Sensor Networks, pp. 44-54, Guangzhou, China, 10-12 Nov. 2022.
[20] R. Molaee Fard and P. Yarahmadi, "A recommendation system in the medical industry using SW-DBSCAN algorithm," International J. of Web Research, vol. 5, no. 1, pp. 82-87, Winter-Spring 2022.
[21] M. A. Sorkhi, E. Akbari, M. Rabbani, and H. Motameni, "A dynamic density-based clustering method based on K-nearest neighbor," Knowledge and Information Systems, vol. 66, pp. 3005-3031, 2024.
[22] I. De Moura Ventorim, D. Luchi, A. L. Rodrigues, and F. M. Varejão, "BIRCHSCAN: a sampling method for applying DBSCAN to large datasets," Expert Systems with Applications, vol. 184, Article ID: 115518, Dec. 2021.
[23] O. Bourkoukou and O. Achbarou, "Weighting based approach for learning resources recommendations," JOIV: International J. on Informatics Visualization, vol. 2, no. 3, pp. 104-109, 2018.
[24] B. Zhao, Y. Zheng, X. Yu, W. Song, "A study on product recommendation based on dynamically adjusted multimodal weights," in Proc. IEEE 5th Int. Conf. on Software Engineering and Artificial Intelligence, pp. 235-239, Fuzhou, China, 20-22 Jun. 2025.
[25] H. R. Boveiri, "An enhanced cuckoo optimization algorithm for task graph scheduling in cluster-computing systems," Soft Computing, vol. 24, no. 13, pp. 10075-10093, 2020.
[26] X. Cai, et al. "An under‐sampled software defect prediction method based on hybrid multi‐objective cuckoo search," Concurrency and Computation: Practice and Experience, vol. 32, no. 5, Article ID: e5478, Mar. 2020.
[27] F. Rezaimehr and C. Dadkhah, "T&TRS: robust collaborative filtering recommender systems against attacks," Multimedia Tools and Applications, vol. 83, pp. 31701-31731, 2024.
[28] C. Yuan, Y. Yang, and Y. Liu, "Sports decision-making model based on data mining and neural network," Neural Computing and Applications, vol. 33, pp. 3911-3924, 2021.
[29] N. Zhou, "Database design of regional music characteristic culture resources based on improved neural network in data mining," Personal and Ubiquitous Computing, vol. 24, no. 1, pp. 103-114, Feb. 2020.
[30] A. Sahu, G. M. Harshvardhan, and M. K. Gourisaria, "A dual approach for credit card fraud detection using neural network and data mining techniques," in Proc. IEEE 17th India Council Int. Conf., 7 pp., New Delhi, India, 10-13 Dec. 2020.
[31] H. Zhou, G. Sun, S. Fu, J. Liu, X. Zhou, and J. Zhou, "A big data mining approach of PSO-based BP neural network for financial risk management with IoT," IEEE Access, vol. 7, pp. 154035-154043, 2019.
[32] S. Wang, J. Cao, and P. Yu, "Deep learning for spatio-temporal data mining: a survey," IEEE Trans. on Knowledge and Data Engineering, vol. 34, no. 8, pp. 3681-3700, Aug. 2020.
[33] R. Molaee Fard, "Provide a video recommendation system using collaborative filtering and data mining methods," J. of Advances in Computer Research, vol. 12, no. 1, pp. 13-25, 2021.
[34] S. M. Z. Kashani and J. Hamidzadeh, "Feature selection by using privacy-preserving of recommendation systems based on collaborative filtering and mutual trust in social networks," Soft Computing, vol. 24, no. 15, pp. 11425-11440, Aug. 2020.