• Proceedings of the Korea Information Processing Society Conference
• /
• 2011.04a
• /
• pp.1285-1286
• /
• 2011

MovieLens를 대상으로 하는 추천 시스템에 대한 연구 중 k-NN 추천 방법은 정확도가 비교적 높지만 평점을 예측할 수 없는 상황이 발생할 수 있다. 본 논문에서는 기존 방법의 문제점을 해결한 장르기반 추천 방법 제안하고, 실험을 통하여 제안하는 방법이 모든 영화에 대한 평점의 예측이 가능함을 검증한다.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.12 no.1
• /
• pp.119-129
• /
• 2016

Rapid changes to the paradigm of smart media have created a communication environment through merging with various media such as IoT technology, which is internet of things. Among them, user' need for a start home, which is one of people living conditions, has been growing and values of the communication environment in a living space using a smart mirror have been growing. However, studies on figuring out behavior and analyzing needs of family members who actually use the living space are insufficient. This study is to draw the service system of the home smart mirror by analysis of behavior and needs of users of the living space. For a research method for analysis of behavior of family members, I wrote two kinds of user's experience maps, which are frequency of use of a quantitative space of a living space and space's important value scales by persona study and depth interview. Through this, applied spaces of the home smart mirror (living room, bathroom, powder room, dress room, porch, kitchen, room) and the types of user needs (type of providing information, entertainment type, control type, service type) have been drawn and statistical analysis methodology has been utilized for a research of user preferences in regard to correlation between living spaces and types of user needs based on a survey. As a result of analysis of ages and gender, types of user needs by space have been drawn and the service system of the home smart mirror has been drawn. It would be utilized as a basic material for various contents development and design using the smart mirror in the future.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.2
• /
• pp.709-730
• /
• 2017

To address the challenge of unprecedented growth in mobile data traffic, ultra-dense network deployment is a cost efficient solution to offload the traffic over some small cells. The overlapped coverage areas of small cells create more than one candidate access points for one mobile user. Signal strength based user association in IEEE 802.11 results in a significantly unbalanced load distribution among access points. However, the effective bandwidth demand of each user actually differs vastly due to their different preferences for mobile applications. In this paper, we formulate a set of non-linear integer programming models for joint user association control and user demand guarantee problem. In this model, we are trying to maximize the system capacity and guarantee the effective bandwidth demand for each user by soft-association control with a software defined network controller. With the fact of NP-hard complexity of non-linear integer programming solver, we propose a Kernighan Lin Algorithm based graph-partitioning method for a large-scale network. Finally, we evaluated the performance of the proposed algorithm for the edge users with heterogeneous bandwidth demands and mobility scenarios. Simulation results show that the proposed adaptive soft-association control can achieve a better performance than the other two and improves the individual quality of user experience with a little price on system throughput.

• Journal of KIISE:Computing Practices and Letters
• /
• v.7 no.6
• /
• pp.684-695
• /
• 2001

Recent recommender system uses a method of combining collaborative filtering system and content based filtering system in order to solve sparsity and first rater problem in collaborative filtering system. Collaborative filtering systems use a database about user preferences to predict additional topics. Content based filtering systems provide recommendations by matching user interests with topic attributes. In this paper, we describe a method for discovery of user preference through combining two techniques for recommendation that allows the application of machine learning algorithm. The proposed collaborative filtering method clusters user using genetic algorithm based on items categorized by Naive Bayes classifier and the content based filtering method builds user profile through extracting user interest using relevance feedback. We evaluate our method on a large database of user ratings for web document and it significantly outperforms previously proposed methods.

• The KIPS Transactions:PartB
• /
• v.16B no.1
• /
• pp.55-62
• /
• 2009

Collaborative filtering is a popular technique that recommends items based on the opinions of other people in recommender systems. Memory-based collaborative filtering which uses user database can be divided in user-based approaches and item-based approaches. User-based collaborative filtering predicts a user's preference of an item using the preferences of similar neighborhood, while item-based collaborative filtering predicts the preference of an item based on the similarity of items. This paper proposes a combined forecast scheme that predicts the preference of a user to an item by combining user-based prediction and item-based prediction using the ratio of the number of similar users and the number of similar items. Experimental results using MovieLens data set and the BookCrossing data set show that the proposed scheme improves the accuracy of prediction for movies and books compared with the user-based scheme and item-based scheme.

• Journal of the Korean Institute of Rural Architecture
• /
• v.16 no.3
• /
• pp.19-26
• /
• 2014

This study aims to examine residents' satisfaction and behavioral condition at the commercial street of Historic and Cultural Environmental Districts in Gyeongju. To achieve this, the study relied on empirical study method and additionally, present condition survey was performed with a user interview. residents' satisfaction and preferences analysis was conducted to figure out present conditions and improvements. This work has completed a total analysis of the architectural characteristics and street factors among various factors which influence residents' satisfaction level including physical street equipments and street view factors which are main contents of previous studies and street improvement project. Using statistical analysis, each factor's significance was verified quantitatively. Accordingly, this study presents prior consideration points before planning the commercial street improvement project and the region development project.

• Proceedings of the IEEK Conference
• /
• 2004.08c
• /
• pp.576-580
• /
• 2004

In this paper, we present a design and implementation of a TV-Anytime compliant STB to provide personalized content consumption according to user preferences and various terminal/network conditions. This paper mainly details with a metadata engine which consists of meta data de-multiplexing, metadata decoding, and metadata-based content browsing. For personalized content consumption, the proposed metadata engine provides the following key functionalities: advanced EPG, non-linear segment navigation wirh Tables-of-Content and/or event-based summary, automatic recommendation of user-preferred programs, and etc. The implemented STB employing the metadata engine is successfully tested with a set of service scenarios in an end-to-end broadcasting test-bed.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2004.10a
• /
• pp.1048-1052
• /
• 2004

The ubiquitous environment is to support people in their everyday life in an inconspicuous and unobtrusive way. This requires that information of the person and her preferences, liking, and habits are available in the ubiquitous system. In this paper, we propose the context aware system that can provide the tailored information service for user in ubiquitous computing environment. The system architecture is composed of 4 domain models that can perform some pre-defined tasks independently. And we suggest the hybrid algorithm combined with fuzzy and Bayesian network to reason what information is suitable for user environment. Finally, we apply to agent based RGA(Research Guide Assistant).

• Journal of Korea Multimedia Society
• /
• v.13 no.6
• /
• pp.841-848
• /
• 2010

Conventional filters using email header and body information equally judge whether an incoming email is spam or not. However this is unrealistic in everyday life because each person has different criteria to judge what is spam or not. To resolve this problem, we consider user preference information as well as email category information derived from the email content. In this paper, we have developed a personalized anti-spam system using ontologies constructed from rules derived in a data mining process. The reason why traditional content-based filters are not applicable to the proposed experimental situation is described. In also, several experiments constructing classifiers to decide email category and comparing classification rule learners are performed. Especially, an ID3 decision tree algorithm improved the overall accuracy around 17% compared to a conventional SVM text miner on the decision of email category. Some discussions about the axioms generated from the experimental dataset are given too.

• Korean Institute of Interior Design Journal
• /
• no.19
• /
• pp.121-127
• /
• 1999

The objective of this study was to criticize the model house of apartment and suggest a evaluation model which could be used as an effective tool. The evaluation model had been developed based on the theoretical framework suggested by previous results of research related on housing design, which comprised the following four components : 1) the paradigm of future home and life-style, 2) marketing effects of housing developer, 3) goals and principles of housing design and 4) results of user-preferences study, an evaluation model was suggested as a preliminary form which would be modified in detail after series of tests in the field. The evaluation model will be used to provide standardized criteria for the quality of model houses, and eventually help to improve the quality of apartment housing design by balanced information from theorist, user and developer.