Personalized Nutrition Recommendation For Diabetic Patients Using Improved K-Means And Krill-Herd Optimization
[Full Text]
AUTHOR(S)
K.Renuka Devi, J.Bhavithra, Dr.A.Saradha
KEYWORDS
Recommender systems, collaborative filtering, Improved K-means clustering, Improved Krill-Herd Optimization, Diabetes.
ABSTRACT
In the growing world of rapid technology, Recommender system (RS) plays one of the significant roles in making decisions to the appropriate users. To maintain blood glucose in balanced level, there is a need of recommender system to recommend appropriate nutrition to those diabetic patients. An optimization technique plays a significant role in refining the attributes of appropriate algorithm to produce more optimized results to the user. The usage of recommender systems is to analyze the individual patient profiles to recommend the specific nutrition by means of collaborative filtering. The Patient’s profile will get generated by analyzing thirty features for each of them. The Improved Krill Herd based optimization with Improved K-Means (IKH-IKC) system clusters those profiles using improved k-means clustering algorithm. To enhance the accuracy of recommendations, Improved Krill-Herd optimization algorithm has been applied. To validate the IKH-IKC idea, the experiment was carried out with 150 patient profiles. The efficiency of IKH-IKC system was analyzed with different metrics like Precision, Recall, F-measure, Accuracy, Matthews correlation, Fallout rate, Miss rate, Root Mean Squared Error (RMSE). The Experimental evaluation conveys that the IKH-IKC idea generates better clustering and optimized results to the user with low error rate.
REFERENCES
[1] Y. Koren, R.M. Bell, “Advances in Collaborative Filtering in Recommender Systems Handbookâ€, Springer, vol. 1, issue. 3, pp. 45–186, 2011.
[2] Bharti KK, Singh PK, “Hybrid Dimension Reduction by Integrating Feature Selection with Feature Extraction Method for Text Clusteringâ€, Springer: Expert System Applications, vol. 42, issue. 6, pp. 3105–3114, 2015.
[3] Xiaofeng Li et al., “Improved Hybrid Collaborative Filtering Algorithm Based on K-Meansâ€, Elsevier: Expert Systems with Applications, vol. 842, pp. 928–934, 2019.
[4] Kunal Shah et al., “Unsupervised Recommender Systems: An Overview of Different Approaches to Recommendationsâ€, In the Proceedings of the 2017 IEEE International Conference on Innovations in Information, Embedded and Communication Systems (ICIIECS), pp. 1-4, 2017.
[5] Shani G., Gunawardana A., “Evaluating Recommendation Systemsâ€, Recommender Systems Handbook. Springer, vol. 6, issue. 10, pp. 257-297, 2009.
[6] Portugal, I., Alencar, P.S., & Cowan, D.D, “The use of machine learning algorithms in recommender systems: A systematic reviewâ€, Expert Systems Applications, vol. 97, pp. 205-227, 2015.
[7] Feng Zhang et al., “Unsupervised Feature Selection Based on Feature Relevanceâ€, In the Proceedings of IEEE Eighth International Conference on Machine Learning and Cybernetics, Baoding, pp.487-492, 2009.
[8] Semeh Ben Salema et al., “A Fast and Effective Partitional Clustering Algorithm for Large Categorical Datasets using a K-means Based Approachâ€, Elsevier-Computers & Electrical Engineering, vol. 37, issue. 9, pp. 463-483, 2018.
[9] Ayon Dey, “Machine Learning Algorithms: A Reviewâ€, International Journal of Computer Science and Information Technologies, vol. 7, issue. 3, pp. 174-1179, 2016.
[10] Deepak Rai, Kirti Tyagi, “Bio-inspired optimization techniques: a critical comparative study.†ACM SIGSOFT Software Engineering Notes, vol. 38, pp. 1-7, 2013.
[11] Jinlong Hu et al., “A User Similarity - Based Top-N Recommendation Approach for Mobile In-Application Advertisingâ€, Elsevier-Expert Systems with Applications, vol. 111, pp. 51-60, 2018.
[12] Anand Khandare and A.S. Alvi, “Clustering Algorithms: Experiment and Improvementsâ€, Springer-Computing and Network Sustainability, vol. 25, issue.12, pp. 263-271, 2017.
[13] Abualigah, Laith Mohammad, Ahamad Tajudin Khader, Essam Said Hanandeh, and Amir H. Gandomi, “A Novel Hybridization Strategy for Krill-Herd Algorithm Applied to Clustering Techniquesâ€, Elsevier-Applied Soft Computing, vol. 60, pp. 423-435, 2017.
[14] Laith Mohammad Abualigah, Ahamad Tajudin Khader, Essam Said Hanandeh, “Hybrid Clustering Analysis using Improved Krill-Herd Algorithmâ€, Springer-Applied Intelligence, vol. 48, issue. 11, pp. 4047–4071, 2018.
[15] M.V.B.T.Santhi et al., “Enhancing K-Means Clustering Algorithmâ€, International Journal on Computer Science and Technology (IJCST), vol. 2, issue. 4, pp. 235-246, 2011.
[16] Huanjing Wang et al., “A Comparative Study of Threshold-based Feature Selection Techniquesâ€, In the Proceedings of 2010 IEEE International Conference on Granular Computing, vol 10, pp. 499-504, 2010.
[17] Dataset 1: Dua, D. and Karra Taniskidou, E. (2017). UCI Machine Learning Repository [http://archive.ics.uci.edu/ml]. Irvine, CA: University of California, School of Information and Computer Science.
[18] Dataset2:http://www.ars.usda.gov/Services/docs.htm?docid=8964.
[19] Rao RV, Rai DP, Balic J, “A multi-objective algorithm for optimization of modern machining processesâ€, Engineering Applications of Artificial Intelligence, vol.61, pp.103–125, 2017.
[20] X. Chen et al., “K means: Automated two – level variable weigting Clustering Algorithm for Multiview Dataâ€, IEEE transactions on knowledge and Data Engineering, vol. 25, pp. 932-944, 2013.
[21] G.Y. Zhang et al., “K-means: Two Level Weighted Collaborative K-means for Multiview Clusteringâ€, IEEE: Knowledge Based Systems, vol. 150, pp. 127-138, 2018.
[22] Divya Pandove et al., “A Comprehensive Study on Clustering Approaches for Big Data Miningâ€, In the proceedings of IEEE Sponsored 2nd International Conference on Electronics and Communication System, vol.6, pp. 1333-1338, 2015.
[23] Jonathan Jeffrey et al., “Optimizing Web Structures Using Web Mining Techniquesâ€, Springer: Intelligent Data Engineering and Automated Learning, vol. 4881, pp. 653–662, 2007.
[24] Daniel Kluver et al., “Rating-Based Collaborative Filtering: Algorithms and Evaluationâ€, Springer - Social Information Access, vol. 42, issue. 8, pp. 344-390, 2018.
[25] Gunnar Schröder, Maik Thiele, and Wolfgang Lehner, “Setting Goals and Choosing Metrics for Recommender System Evaluationsâ€, In UCERSTI2 Workshop at the 5th ACM conference on recommender systems, Chicago, USA, vol. 23, pp. 53-61, 2011.
[26] X.T. Zhang et al., “Multi-Task Multi-View Clusteringâ€, In the proceedings of IEEE Transactions on Knowledge & Data Engineering, vol. 28, issue. 4, pp. 3324-3338, 2016.
[27] Abualigah LM et al., “A Novel Hybridization Strategy for Krill-Herd Algorithm Applied to Clustering Techniquesâ€, Springer: Applications of Soft Computing, vol. 60, pp. 423–435, 2017.
[28] J. Bhavithra, A. Saradha, “Personalized web page recommendation using case-based clustering and weighted association rule miningâ€, Springer, vol. 22, issue. 3, pp. 6991–7002, 2018
|