• Journal of KIISE:Software and Applications
• /
• v.31 no.12
• /
• pp.1672-1683
• /
• 2004

Recommender system is a kind of web intelligence techniques to make a daily information filtering for people. Researchers have developed collaborative recommenders (social recommenders), content-based recommenders, and some hybrid systems. In this paper, we introduce a new hybrid recommender method - ICHM where clustering techniques have been applied to the item-based collaborative filtering framework. It provides a way to integrate the content information into the collaborative filtering, which contributes to not only reducing the sparsity of data set but also solving the cold start problem. Extensive experiments have been conducted on MovieLense data to analyze the characteristics of our technique. The results show that our approach contributes to the improvement of prediction quality of the item-based collaborative filtering, especially for the cold start problem.

• Journal of KIISE:Software and Applications
• /
• v.31 no.4
• /
• pp.457-466
• /
• 2004

Recommendation is to offer information which fits user's interests and tastes to provide better services and to reduce information overload. It recently draws attention upon Internet users and information providers. The collaborative filtering is one of the widely used methods for recommendation. It recommends an item to a user based on the reference users' preferences for the target item or the target user's preferences for the reference items. In this paper, we propose a neural network based collaborative filtering method. Our method builds a model by learning correlation between users or items using a multi-layer perceptron. We also investigate integration of diverse information to solve the sparsity problem and selecting the reference users or items based on similarity to improve performance. We finally demonstrate that our method outperforms the existing methods through experiments using the EachMovie data.

• Journal of Fashion Business
• /
• v.12 no.5
• /
• pp.77-93
• /
• 2008

The purpose of the study was to examine make-up expression elements of horror characters as an evil spirit, a vampire, a zombie, a monster and a psycho murderer through make-up, focused on horror movies of the United States after1960s. First, an evil spirit was expressed that the pupil grew dim without a focus and the skin was torn by going bad and rot completely. Also, it was expressed that its teeth was changed to pointed canine teeth as a wild beast and its pale and bloodless face showed blood vessels clearly. To express its bloodless and pale skin, air brush was swept into the skin over several times. Its canine tooth was made acryl powder into its shape and was harden to make its shape smooth. Also, it was colored to show people like the real thing. Second, a vampire was expressed by make-up elements as long nails, a sharp canine tooth, a pale skin with a blood vessel and dead eyes. Its rough skin and long nails were manufactured with latex foam, which was colored like the skin. Third, a monster image as a werewolf was expressed by make-up elements as fur, sharp teeth, changed nails and toenails, a rough skin and a face changed to a wolf. Rubber mask and rubber body suit were manufactured as a make-up of special character and so all its body was changed. Fourth, a psycho murderer and body-deformed man were expressed by make-up elements as a distorted mask, swelled-up and deformed skull and face form, terribly deformed body, discolored and hang down skin and teeth with an indeterminate form. Its body and face were manufactured by the foam latex technology according to make-up design as a make-up of special character.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.10a
• /
• pp.625-628
• /
• 2009

Busan was wasteland of visual industry, But It has been undergo a complete change visual industry city since It was started 1st Busan International Film Festival(PIFF) in 1996. It promoted Cineport Busan, 1st step. promotion age 'good city film' 2004, 2nd step. settlement age 'good city produce movie' from 2005 to 2007, now 3rd step. development age settle down visual industry and progressing project for make importance place produce movie. so, employment problem of region visual human resources. It is indispensable element for become real region industry in visual industry. So that, this study analyzes what is problem of visual industry and human resources in Busan city. Then inquired what will happen supply region visual human resources through visual importance city Busan development plan.

• Journal of Broadcast Engineering
• /
• v.26 no.5
• /
• pp.543-552
• /
• 2021

The story is formed by the flow of the development and resolution of the conflict between the characters. Namely, the story consists of conflict setting, development, and resolution. Character region is an important expression technique to describe the emotions or states of characters and the relationship between characters and the environment. The purpose of this paper is to propose a method for detecting the transition of conflict from the graph of character region's change. To this end, we present a method of generating a change graph of a character region in a movie by calculating the character region and a method of detecting a conflict transition scene from a graph of character region's change. To verify the performance of the proposed method, an experiment was conducted to extract conflict transition scenes for 7 movies, and performance evaluation results of 73.57% accuracy and 77.26% recall were obtained. This proves that it is possible to extract conflict transition scenes based on the character region.

• Journal of Digital Convergence
• /
• v.19 no.3
• /
• pp.279-285
• /
• 2021

This paper criticized that online classes during the Covid-19 period were centered on knowledge and information education, and sought ways to improve empathy as a way to improve students' sociality. The teaching-learning process was designed around the movie <(500) Days of Summer> which has the theme and story of parting and growth. On this paper the stage of empathy was divided into three stages, recognize-into, feeling-into, emotional-transaction stage. In particular, considering the process of transitioning from emotional empathy to behavioral empathy as the key to communication education, the class was designed in five stages, with an expression stage between the feeling-into stage and the emotional-transaction stage. This course is possible when learners sympathize with the work itself and reflect on their own narrative, so literary therapeutic was used, and students's response statements were collected to prove that this process is meaningful for improving empathy. In this article, the class was designed for the movie <(500) Days of Summer>, but this teaching-learning model can be applied to other contemporary film texts.

• Journal of Broadcast Engineering
• /
• v.27 no.5
• /
• pp.665-675
• /
• 2022

After the COVID-19 pandemic, there has been growing interests in metaverse technology and social use of virtual reality platforms in non-face-to-face environments, but social issues and ethical concerns raised by metaverse have not been sufficiently discussed. In this paper, we discuss the social functions of the metaverse by examining the movie 'Ready Player One', and investigate the ethical problems that may arise in various implementation of metaverse. We identify the potential ethical problems that could occur in the context of metaverse including identity fragmentation, metaverse violence and crime, and mismanagement of personal information. We also propose some promising approaches to tackle these ethical problems ranging over descriptive ethics, normative ethics, and analytical (meta) ethics.

• Korean Journal of Communication Studies
• /
• v.18 no.1
• /
• pp.165-193
• /
• 2010

The current study has significance in that it increases our understanding of BPL effectiveness by adding long-term memory dependent variables to widely used short-term memory variables. Furthermore, two unit of analysis of the current study, subject and BPL, made richer analysis possible as compared to previous studies. The result showed that BPL was effective in short-term recognition(52.8% of BPLs), long-term recognition(44.4% of BPLs), and long-term recall(30.6% of BPLs). The further result showed that audiovisual BPL, closeup BPL, long-exposed brand, leading actor using brand were more effective than other kinds of BPL. On the other hand, preference for the movie and preference for the actor were not significant factors in increasing people's memory of the brand name. Future researchers should settle the confusion existed in this field by inventing a more elaborate research design and exploring mediating and moderating variables in the subject of BPL effectiveness.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.5
• /
• pp.1413-1432
• /
• 2023

Recommender systems aim to recommend items to users by taking into account their probable interests. This study focuses on creating a model that utilizes multiple sources of information about users and items by employing a multimodality approach. The study addresses the task of how to gather information from different sources (modalities) and transform them into a uniform format, resulting in a multi-modal feature description for users and items. This work also aims to transform and represent the features extracted from different modalities so that the information is in a compatible format for integration and contains important, useful information for the prediction model. To achieve this goal, we propose a novel multi-modal recommendation model, which involves extracting latent features of users and items from a utility matrix using matrix factorization techniques. Various transformation techniques are utilized to extract features from other sources of information such as user reviews, item descriptions, and item categories. We also proposed the use of Principal Component Analysis (PCA) and Feature Selection techniques to reduce the data dimension and extract important features as well as remove noisy features to increase the accuracy of the model. We conducted several different experimental models based on different subsets of modalities on the MovieLens and Amazon sub-category datasets. According to the experimental results, the proposed model significantly enhances the accuracy of recommendations when compared to SVD, which is acknowledged as one of the most effective models for recommender systems. Specifically, the proposed model reduces the RMSE by a range of 4.8% to 21.43% and increases the Precision by a range of 2.07% to 26.49% for the Amazon datasets. Similarly, for the MovieLens dataset, the proposed model reduces the RMSE by 45.61% and increases the Precision by 14.06%. Additionally, the experimental results on both datasets demonstrate that combining information from multiple modalities in the proposed model leads to superior outcomes compared to relying on a single type of information.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.277-280
• /
• 2021

Recently as various contents are mass produced based on high accessibility, the media contents market is more active. Users want to find content that suits their taste, and each platform is competing for personalized recommendations for content. For an efficient recommendation system, high-quality metadata is required. Existing platforms take a method in which the user directly inputs the metadata of an image. This will waste time and money processing large amounts of data. In this paper, for media hyperpersonalization recommendation, keyframes are extracted based on the YCrCb color model of the video based on movie trailers, movie genres are distinguished through supervised learning of artificial intelligence and In the future, we would like to propose a utilization plan for generating metadata.