Browse > Article

Developing Sensibility Fashion Design System Using Collaborative Filtering Personalization Technique Based on Server-Client Interaction  

Jung, Kyongyong (Department of Computer Science & Information Engineering, Inha University)
Na, Youngjoo (Department of Clothing and Textiles, Inha University)
Publication Information
Textile Science and Engineering / v.42, no.2, 2005 , pp. 118-128 More about this Journal
Abstract
In order to develop fashion products of sensibility and high quality, we propose the fashion design recommendation system (FDRAS), a design expert system. We programed the co-operative filter personal techniques, using collaborative filtering to search the textile and fashion design database, and this was an effective tool providing a fashion design fitted to customer's need. A user-interface tool is developed to recommend fashion designs according to the user's need, and enhance the efficiency in user interface. We selected 41 fashion design drawings from a picture dictionary to prepare the questionnaire: 15 collar types, 8 sleeve types, 10 skirt types and 3 lengths, and 5 color tones, and performed a survey for establishing the database. 889 subjects participated in this survey. Developing this recommendation system, database of the designs and the related sensibility, and transformation algorithm was established. The visualization of the results of recommended designs to a consumer is presented in 2D and 2.5D graphics. The performance of FDRAS is tested according to three algorithms in terms of mean absolute error (MAE).
Keywords
Citations & Related Records
연도 인용수 순위
  • Reference
1 K. Y. Jung and Y. J. Na, 'Design Supporting System for Textile Product Development Based in Human Sensibility Ergonomics', J Korean Fiber Soc, 2003, 40(3), 312-320
2 J. S. Breese, D. Heckerman, and C. Kadie, 'Empirical Analysis of Predictive Algorithms for Collaborative Filtering', In Proc. of 14th Conf. on Uncertainty in Artificial Intelligence, pp.43-52, 1998
3 K. Y. Jung, J. H. Kim, and J. H. Lee, 'User Preference Prediction Method Using Associative User Clustering and Bayesian Classification', Proc. of Korea Information Science Society, pp.109-111, 2001
4 K. Y. Jung and J. H. Lee, 'Prediction of User Preference in Recommendation System Using Association User Clustering and Bayesian Estimated Value', Lecture Notes in Artificial Intelligence 2557, Springer-Verlag, 2002, pp.284-296
5 I.R.I Color Institute, 'What Color Is Proper? Color Combination', Young Jin Pub., Seoul, 2003
6 J. Herlocker, J. Konstan, A. Borchers, and J. Riedl, 'An Algorithm Framework for Performing Collaborative Filtering', Proc. of ACM SIGIR'99, pp.230-237, 1999
7 K. Y. Jung, J. H. Kim, H. M. Jung, and J. H. Lee, 'An ItemBased Collaborative Filtering Technique by Associative Relation Clustering in Personalized Recommender Systems', Journal of Korea Information Science Society: Software and Applications, 2004, 31(4), 467-477
8 K. Y. Jung, Y. J. Na, D. H. Park, and J. H. Lee, 'Discovery Knowledge of User Preferences: Ontologies in Fashion Design Recommender Agent System', Lecture Notes in Computer Science 3044, Springer-Verlag, 2004, pp.863-872
9 G. Karypis, 'Evaluation of Item-Based Top-N Recommendation Algorithms', Technical Report CS-TR-00-46, Computer Science Dept., University of Minnesota, 2000
10 S. O. Shin, K. H. Oh, S. H. Lee, and Y. J. Na, 'Fashion & Clothing', Kyomunsa, Seoul, 1999, pp.264-266
11 M. O. Connor and J. Herlocker, 'Clustering Items for Collaborative Filtering', In Proc. of ACM SIGIR Workshop on Recommender Systems, Berkeley, CA, 1999
12 O. K. Kwon, Y. J. Na, and H. E. Kim, 'Fashion & Sensibility Science', Kyomunsa, Seoul, 2000, pp.25-30
13 C. Basu, H. Hirsh, and W. W. Cohen, 'Recommendation as Classification: Using Social and Content-based Information in Recommendation', Proc. of 15th National Conference on Artificial Intelligence, pp.714-720, 1998
14 N. Good, B. Schafer, J. Konstan, A. Borchers, B. Sarwar, and J. Riedl, 'Combining Collaborative Filtering with Personal Agents for Better Recommendation', AAAI/IAAI, pp.439-446, 1999