G
Geun-Sik Jo
Researcher at Inha University
Publications - 190
Citations - 2177
Geun-Sik Jo is an academic researcher from Inha University. The author has contributed to research in topics: Ontology (information science) & Recommender system. The author has an hindex of 22, co-authored 188 publications receiving 1916 citations.
Papers
More filters
Journal ArticleDOI
Collaborative filtering based on collaborative tagging for enhancing the quality of recommendation
TL;DR: Experimental results show that the proposed algorithm offers significant advantages both in terms of improving the recommendation quality for sparse data and in dealing with cold-start users as compared to existing work.
Journal ArticleDOI
Expert system for predicting stock market timing using a candlestick chart
Kyung-Ho Lee,Geun-Sik Jo +1 more
TL;DR: Wang et al. as mentioned in this paper developed a candlestick chart analysis expert system, or a chart interpreter, for predicting the best stock market timing, which has patterns and rules which can predict future stock price movements.
Journal ArticleDOI
Collaborative error-reflected models for cold-start recommender systems
TL;DR: This paper proposes a unique method of building models derived from explicit ratings and applies the models to CF recommender systems, and shows significant improvement in dealing with cold start problems, compared to existing work.
Journal ArticleDOI
Towards Aircraft Maintenance Metaverse Using Speech Interactions with Virtual Objects in Mixed Reality
Aziz Siyaev,Geun-Sik Jo +1 more
TL;DR: Mixed reality education and training of aircraft maintenance for Boeing 737 in smart glasses, enhanced with a deep learning speech interaction module for trainee engineers to control virtual assets and workflow using speech commands, enabling them to operate with both hands.
Journal ArticleDOI
Collaborative user modeling with user-generated tags for social recommender systems
TL;DR: By leveraging user-generated tags as preference indicators, a new collaborative approach to user modeling that can be exploited to recommender systems is proposed that provides a better representation in user interests and achieves better recommendation results in terms of accuracy and ranking.