• 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.

• Journal of Information Technology Applications and Management
• /
• v.28 no.6
• /
• pp.133-143
• /
• 2021

Unity's Cinemachine, one of the game production technologies, can produce 3D images. However, since Cinemachine is a game production tool, video creators may find it difficult because the work process of Cinemachine is unfamiliar and complicated. However, it is necessary to learn new technologies for the future of video contents that will be advanced in the future. In order to understand Chinemachine as a video producer, I would like to embody the scene of the movie. We are going to produce a storyboard scene for storytelling in Cinemachine. We defined the workflow of Unity Cinemachine while directing the scene by creating a story, and also checked the advantages and cautions. I hope it will be an opportunity to enjoy using Unity Cinemachine, which is constantly evolving.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2000.10a
• /
• pp.763-766
• /
• 2000

본 논문에서는 최근 활성화되고 있는 인터넷방송의 스트리밍 영상물 제공 방법을 개선하여, 자동으로 사용자의 연결속도에 적합한 스트리밍 영상물을 선택 제공하는 방법을 구현하고자 한다. 대부분의 스트리밍 영상물을 제공하는 방법은 각 속도에 적합한 영상물을 각각 모두 나열하여 사용자가 선택, 제공받는 방법을 택하고 있지만 이는 사용자의 선택이 잘못된 경우 연결속도에 따른 최적의 영상물을 제공받을 수 없는 단점을 지니고 있다. 따라서, 본 논문에서는 사용자의 연결속도에 따라서 자동적으로 최적의 스트리밍 영상물을 제공할 수 있는 방법을 제시하고자 한다.

• The Journal of the Korea Contents Association
• /
• v.11 no.11
• /
• pp.102-110
• /
• 2011

This study is to reveal the meaning of the interaction between a player and a game with the approach of an operational interaction such as joystick and keyboard, and also a representational interaction that the player takes during the game. It has been usually recognized that cut-scene in existing games is just limited to the role of opening scene that delivers mainly a background story of the game, and has the only passive function that serves additionally the expression of the state of the player or the replay of the results of the player's action. But in the aspect of game-direction, the study of the player's action about the interaction movie of 'Uncharted2', for example, one of the most representative video games, shows the possible classification of interaction movie along with three functions(situation direction, induced selective-action, information transfer). As a result, it is judged that interaction movie is not an additional element for the game-play, but rather takes the function of as an interface. The effective application of interaction movie could help a smooth connection between the recognizability from the view point of the player and the playing from the main character's viewpoint, ultimately leading to a direct means to maximize the delivery of the story.

• Journal of Digital Convergence
• /
• v.18 no.12
• /
• pp.525-531
• /
• 2020

In today's IT environment where various pieces of information are distributed in large volumes, recommendation systems are in the spotlight capable of figuring out users' needs fast and helping them with their decisions. The current recommendation systems, however, have a couple of problems including that user preference may not be reflected on the systems right away according to their changing tastes or interests and that items with no relations to users' preference may be recommended, being induced by advertising. In an effort to solve these problems, this study set out to propose a Fuzzy-AHP-based movie recommendation system by applying the BRNN(Bidirectional Recurrent Neural Network) language model. Applied to this system was Fuzzy-AHP to reflect users' tastes or interests in clear and objective ways. In addition, the BRNN language model was adopted to analyze movie-related data collected in real time and predict movies preferred by users. The system was assessed for its performance with grid searches to examine the fitness of the learning model for the entire size of word sets. The results show that the learning model of the system recorded a mean cross-validation index of 97.9% according to the entire size of word sets, thus proving its fitness. The model recorded a RMSE of 0.66 and 0.805 against the movie ratings on Naver and LSTM model language model, respectively, demonstrating the system's superior performance in predicting movie ratings.

• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.1126-1129
• /
• 2006

최근 멀티플렉스 극장들이 많이 생기면서 영화 관객들이 한 장소에서 다양한 영화를 선택하여 감상할 수 있게 되었다. 그러나 극장에서 제공하는 영화정보는 비치된 팜플렛과 공중파 광고홍보가 유일하며 더 자세한 정보를 얻기 위해서는 인터넷이나 다른 매체를 통해 사전에 정보를 입수해야 하는 불편함이 존재하고 있다. 본 논문에서는 증강현실 기술을 이용하여 관객이 특정 마커가 부착된 영화팜플렛을 카메라에 비추면 마커에 해당되는 동영상을 찾아 재생하고 이때 스크린에 출력되는 동영상을 통해 영화의 예고편 및 등장인물에 대한 소개 등을 실시간으로 관객에게 제공하는 시스템을 구현한다. 본 시스템을 통해 관객에게 별도의 매체나 시간의 소비 없이 해당 극장에서 다양한 영화에 대한 정보를 쉽게 얻을 수 있고 이는 영화를 선택하는데 있어서 많은 편리함을 제공할 뿐만 아니라 영화를 선택하는 과정에 있어 시각적인 재미를 함께 제공한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.2
• /
• pp.538-561
• /
• 2020

Recommender Systems (RecSys) have a major role in e-commerce for recommending products, which they may like for every user and thus improve their business aspects. Although many types of RecSyss are there in the research field, the state of the art RecSys has focused on finding the user similarity based on sequence (e.g. purchase history, movie-watching history) analyzing and prediction techniques like Recurrent Neural Network in Deep learning. That is RecSys has considered as a sequence prediction problem. However, evaluation of similarities among the customers is challenging while considering temporal aspects, context and multi-component ratings of the item-records in the customer sequences. For addressing this issue, we are proposing a Deep Learning based model which learns customer similarity directly from the sequence to sequence similarity as well as item to item similarity by considering all features of the item, contexts, and rating components using Dynamic Temporal Warping(DTW) distance measure for dynamic temporal matching and 2D-GRU (Two Dimensional-Gated Recurrent Unit) architecture. This will overcome the limitation of non-linearity in the time dimension while measuring the similarity, and the find patterns more accurately and speedily from temporal and spatial contexts. Experiment on the real world movie data set LDOS-CoMoDa demonstrates the efficacy and promising utility of the proposed personalized RecSys architecture.

• Korean System Dynamics Review
• /
• v.10 no.2
• /
• pp.5-27
• /
• 2009

Multiplex is a representative culture facility of citizens. Therefore, a lot of researches and investment on multiplex are carried out to improve benefits of service suppliers and users. Especially, focused on main services of a theatre such as ticket booking and issuing within multiplex, examination of tickets, admission information of movie screens and screening information inquiry, improvement activities are carried out. However, it is not enough to evaluate on what efficiency the above efforts have in the viewpoint of customer benefits and business. Therefore, this study analyzed value and limit of the newest service of multiplex applying the existing ubiquitous concept(u-multiplex service), and proposed a model and a plan for improving the existing services. The study interviewed with specialists in the related field and applied workshop-shape group interview to 110 university students and simulated service models. The contribution of the study is to analyze the value and limit of the existing multiplex service objectively, and to propose a new service model and plan to improve its limitation. In the future, the study plans to research on service models by extending space and functional roles of multiplex to the whole subsidiary facilities including movie screens.

• The Journal of the Korea Contents Association
• /
• v.14 no.10
• /
• pp.429-437
• /
• 2014

Product promotion App is developed using an interactive video in order to overcome the existing ATL marketing limitations and to respond to target age groups and lifestyle changes. The product promotion App which is positioned as a smart care center by analyzing customer needs with the Customer Journey Map, is comprised of 3 categories such as interest, information and management reflecting media characteristics of smart mobile contents. It intends to induce viral promotions with comical and interactive alopecia simulator directly described by a specialist doctor which ensures reliability of products. In addition, it is made for customers to continuously manage the alopecia through management tools, and company can expect an effect of being used as a core tool for marketing activities by offering promotional information along with product feedbacks.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.9 no.1
• /
• pp.195-206
• /
• 1998

The purpose of this study is (a)to identify reading effect on the imagination, and (b)to compare reading effect with audio-visual materials. For these purposes, 25 elementary school students and 11 university students participated in the reading project. The participants of this project painted a car and a beast after reading a book and watching a movie, Main findings and conclusions made in this study are summarised as follows : (1)Reading is better than a movie for the people's imagination. (2)Children can imagine much more freely than the adults. It is expected that these results can be used for the children's reading education and programs.