• 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.

• The Journal of the Korea Contents Association
• /
• v.10 no.4
• /
• pp.123-132
• /
• 2010

Beginning in 1990's, 3D filmmaking reappeared. As almost every job in filmmaking is digitalized, 3D takes advantage of its new software and hardware, and digital friendly customers as well. One reason why Korean cinema should take 3D seriously is that it can resolve the old and tough problem of unemployed human resources in film production. Another reason is the cooperation programs in which universities and 3D companies can join. 3D cinema can create new cinema goers who don't belong the regular viewer. The totally new experience of 3D can bring people to the movie theaters, and this will add up the total movie customers that expand the whole film industry. The newly designed 3D also could take care of piracy of movie file uploading and downloading through internet. 3D cinema would be precious alternative for film industries of Korea.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.284-286
• /
• 2021

With the continuous development of the Internet and digital, platforms are emerging to store large amounts of media data and provide customized services to individuals through online. Companies that provide these services recommend movies that suit their personal tastes to promote media consumption. Each company is doing a lot of research on various algorithms to recommend media that users prefer. Movies are divided into genres such as action, melodrama, horror, and drama, and the film's audio (music, sound effect, voice) is an important production element that makes up the film. In this research, based on movie trailers, we extract audio for each genre, check the commonalities of audio for each genre, distinguish movie genres through supervised learning of artificial intelligence, and propose a utilization method for generating metadata in the future.

• International journal of advanced smart convergence
• /
• v.4 no.2
• /
• pp.131-137
• /
• 2015

Home Entertainment system is recently being offered by Home Theater & Smart TV with contents service. Also, console game is being played in the media like in TV. The usage of 4D as the main technology in entertainment industry has mostly been limited in Theme Park, Amuse Park, Theater, and contents for Movie and Animation. Some simulation systems for game has been developed but they were made mostly by using electric or hydraulic motion system which cause high power consumption and have a restriction of place for install. The paper is attempted to build Home Entertainment system which makes users feel realistic contents by developing 4D systems for Home Entertainment rather than before. 4D control S/W in which user can insert and edit 4D effects on contents of all areas such as game, movie, and broadcasting is developed. Also, built-in pneumatic cylinder in 4D system which can be easily controlled and managed in home is developed.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.10
• /
• pp.185-198
• /
• 2021

With the development of Internet technology, because traditional recommendation algorithms cannot learn the in-depth characteristics of users or items, this paper proposed a recommendation algorithm based on the AMITI(attention mechanism and improved TF-IDF) to solve this problem. By introducing the two-layer attention mechanism into the CNN, the feature extraction ability of the CNN is improved, and different preference weights are assigned to item features, recommendations that are more in line with user preferences are achieved. When recommending items to target users, the scoring data and item type data are combined with TF-IDF to complete the grouping of the recommendation results. In this paper, the experimental results on the MovieLens-1M data set show that the AMITI algorithm improves the accuracy of recommendation to a certain extent and enhances the orderliness and selectivity of presentation methods.

• Journal of the Korean Society for Library and Information Science
• /
• v.48 no.1
• /
• pp.257-276
• /
• 2014

The purpose of this study is to investigate the patterns and barriers of the Internet for the elderly adults in Korea. Data was collected through the face to face interview using a questionnaire for the residence of Daegu and Kyungsang Buk-Do areas targeted over the 60-years-olds elder adults. A total of 119 valid response data were analyzed with the descriptive statistics and the group differences by age and gender using SPSS 18.00. It found that the most of the elder adults access the Internet to seek the entertainment contents, the knowledge-related contents, and the cultural and art contents. They spend most of the Internet online session to do searching information and enjoying movie and music. However, there were age differences and gender differences within the subjects. The complexity of computer and the Internet usage is one of the barriers for the Internet access, and they suggest that a customized education and training courses of computer literacy for the elderly adults would be the ways of resolve those obstructions.

• Korean Institute of Interior Design Journal
• /
• v.14 no.1
• /
• pp.81-90
• /
• 2005

This study was intended to suggest the design guidelines of digital home on the basis of digital-related human behavior. In order to achieve this, what and how often internet was used in the home, how living pattern and space usage was changing according to digitalization were examined and lastly, the design guidelines of digital home based on these findings were suggested. The subjects were 400 housewives who lived In 85m'-sized housing unit of the new apartment complex in Busan. They were average age of 38 and their eldest children were in the stage of elementary schooling or preschooling. Many of them had relatively high educational level and middle income level. The results of the study were as follows; 1) The respondents used internet more frequently for information searching, children's education, and Internet shopping. Therefore, it would be desirable to divide zoning of housing unit into space for routine activities, space for working, and for cultural activities. 2) Digitalization changed human living pattern like follows; it reduced time of shopping, information searching, banking, and going out. Also, it increased time of spending alone, watching movie, and playing game. Therefore, digital home should be designed to facilitate social Interaction between family members, cultural and recreational activities, and indoor or outdoor exercise within each housing unit or in apartment complex.

• Journal of Korea Multimedia Society
• /
• v.8 no.6
• /
• pp.807-813
• /
• 2005

The production and authoring of digital multimedia contents are most important fields in multimedia technology. Nowadays web-based technology and related multimedia software technology are growing in the IT industry and these technologies are evolving most rapidly in our life. The technology of digital audio and video processing is utilizing rapidly to improve quality of our life, Also we are more interested in high sense and artistic feeling in the music and entertainment areas by use of three dimensional (3D) digital sound technology continuously as well as 3D digital video technology. The service field of digital audio contents is increasing rapidly through the Internet. And the society of Internet users wants the audio contents service with better quality. Recently Internet users are not satisfying the sound quality with 2 channels stereo but seeking the high quality of sound with 5,] channels such as 3D audio of the movie films. But it might be needed proper hardware equipments for the service of 3D sound to satisfy this demand. In this paper, we expand the simple 3D audio generator developed and propose a web-based music bank by the software development of 3D audio generation player in 3D sound environment with two speakers minimizing hardware equipments, Also we believe that this study would contribute greatly to digital 3D sound service of high quality for music and entertainment mania.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.14 no.6
• /
• pp.303-308
• /
• 2014

This paper deals with interface design of a university webzines that to search through an internet portal site Naver. It was obtained the following conclusions. First, university webzines are using a hypertext link to such images, text, movie. Second, it could be seen that mainly been using block grid, the module grid, and a transformed layout of 2 tier grid. Third, Seoul woman's University, Kyungpook National University, and Korea Maritime University's webzines found that layout, color, user-friendly access the structure. Fourth, webzine was used the text or image a link, search function, site map, icon, favorites, quick menus, navigation bars, and rollover menu. Last, university webzines were shown to contribute mere to the enhancement of its value as a promotional medium.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.16 no.1
• /
• pp.33-42
• /
• 2016

Recently, an environment in which public opinions are expressed about various areas is expanded around SNSs or internet potals, thus, opinion documents get bigger rapidly. Under these circumstances, it is essential to utilize automatic summarization techniques for understanding whole contents of large opinion documents. However, it is hard to summarize efficiently those documents with traditional text summarization technologies since the documents include subject expressions as well as features of targets objects. Proposed method in this paper defines features of opinion documents, and designed to retrieve representative sentences expressing opinions of those features. In addition, through experiments, we prove the usefulness of proposed method.