• Proceedings of the Korean Information Science Society Conference
• /
• 2010.06c
• /
• pp.43-48
• /
• 2010

정보의 수가 급격하게 증가하면서 일반적인 정보 검색은 사용자의 생활 패턴이나 선호도를 전혀 반영하지 않은 결과를 보여준다. 이로 인하여 자신에게 적합한 정보를 제공받는 개인화 서비스에 대한 연구가 활발히 연구되고 있다. 본 논문에서는 개인화 서비스를 위한 선호도 조사의 방법으로 GPS로그 파일을 이용한다. GPS로그는 사용자의 모든 이동에 대한 객관적인 기록이므로 이를 분석하면 개인의 선호도와 숨어 있는 패턴을 발견할 수 있다. GPS로그를 관리하기 위한 방법으로 대용량 이동 객체 분산 컴퓨팅 시스템을 기반인 GALIS를 응용한 GPS로 그 관리 시스템을 제안하며, 프로토타입 구현을 통해 시스템의 효율성을 보인다.

• Journal of the Korean Society for Precision Engineering
• /
• v.22 no.11 s.176
• /
• pp.64-71
• /
• 2005

In order to measure surface roughness profile, stylus type equipments are commonly used, but the stylus keeps contact with surface and damages specimens by its tip pressure. Therefore, optics based measurement systems are developed, and light phase interferometer, which is based on light interference phenomenon, is the most noticeable research. However, light interference based measurements require translation mechanisms of nano-meter order in order to generate phase differences or multiple focusing, thus the systems cannot satisfy the industrial need of on-the-machine and in-process measurement to achieve factory automation and productive enhancement. In this research, we focused light reflectance phenomenon rather than the light interference, because reflectance based method do not need translation mechanisms. However, the method cannot direct]y measure surface roughness profile, because reflected light consists of several components and thus it cannot supply surface height information with its original form. In order to overcome the demerit, we newly proposed an image processing based algorithm, which can separate reflected light components and conduct parameterization and reconstruction process with respect to surface height information, and then confirmed the reliability of proposed algorithm by experiment.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.4
• /
• pp.9-19
• /
• 2010

In this paper, a new program recommendation system is proposed to recommend user preferred VOD program in IPTV environment. A proposed system is implemented with hybrid filtering method that can cooperatively complements the shortcomings of the content-based filtering and collaborative filtering. For a user program preference, a single-scaled measure is designed so that the recommendation performance between content-based filtering and collaborative filtering is easily compared and reflected to final hybrid filtering procedure. In order to provide more accurate program recommendation, we use not only the user watching history, but also the user program preference and sub-genre program preference updated every week as a user preference profile. System performance is evaluated with modified IPTV data from real 24-weeks cable TV watching data provided by Nilson Research Corp. and it shows quite comparative quality of recommendation.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.49 no.3
• /
• pp.46-55
• /
• 2012

Recently, the concept of PES(Personal Environment Service) is being widely discussed on various standardization organizations such as ITU-R, ETSI, 3GPP, TTA and etc. The purpose of PES is to introduce the services which can dynamically, automatically and intelligently reconfigures the electronic, electrical, and mechanical equipment surrounding the user according to the user preferences included in a user's profile by using a smartphone embedding WPAN radio technologies such as bluetooth and WiFi. This research introduces an Android Platform-based PES system which consists of a PES app, PES devices and a PES server. A smartphone platform is Android 2.2(Froyo) version and 4 simulated PES devices were implemented by using Galaxy Tab. It has shown that the PES would be a killer application of M2M(Machine-to-Machine) or D2D(Device-to-Device) in the future and it would need to study how to update a user's profile based on analyzing user's behaviour for enhancing the PES user's satisfaction.

• Proceedings of the Korean Association of Geographic Inforamtion Studies Conference
• /
• 2008.10a
• /
• pp.106-112
• /
• 2008

Personalization is user oriented dynamic method based on user preferences for easy access to what users want to view or get. It has become more important in mobile domain with rapid growth of wireless Internet and mobile phone market after success of web based market and therefore, it can be applied to service of spatial analysis result. In this paper, spatial analysis using user profile and notification service methods are proposed as one of personalized spatial data service methods for mobile users. A service system for spatial analysis with user profile is designed to prove possibility of spatial analysis based on user preferences and notification service is also designedto show generated output can be sent to user's mobile devices efficiently to make users informed of preferred information. Prototype system is implemented and it is applied to real estate data that has many selectable conditions by users. Information service based on user preferences can be applied to spatial data by using proposed system and it is efficient when cache module is used to shorten response time. Various user models for application domains and performance evaluation methods need to be developed in the future.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04a
• /
• pp.532-534
• /
• 2004

무선 단말기 보급의 증가로 PDA 또는 휴대폰 등을 통한 인터넷 접속이 증가하고 있다. 하지만 현재 대부분의 웹사이트는 페이지 크기나 용량이 데스크톱에 최적화되어 있기 때문에, 무선 단말기를 이용한 원활한 인터넷 서핑이 어렵다. 본 논문에서는 이러한 문제점을 해결하기 위해서 개인화된 북마크를 통해 원하는 서비스에 바로 접근할 수 있는 방법을 제안한다. 제안한 기법은 기존 페이지 중심의 북마크를 개선하여 웹사이트 별로 일련의 페이지들을 북마크하여 무선 단말기를 통해 제공함으로써, 웹사이트의 구조를 한눈에 쉽게 파악하고 원하는 페이지에 더욱 빠르게 접근할 수 있는 방안을 제시한다. 또한 모바일 에이전트환경에서 사용자의 선호도 프로파일과 유사한 사용자들이 해놓은 사이트 단위의 북마크를 추출한 후, 사용자에게 제공해주는 기법을 제안한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.10c
• /
• pp.652-654
• /
• 2003

무선 단말기 보급의 증가로 PDA 또는 휴대폰 등을 통한 인터넷 접속이 증가하고 있다. 하지만 현재 대부분의 웹 사이트는 페이지 크기나 용량이 데스크톱을 위해 최적화 되어 있기 때문에. 무선 단말기를 이용한 원활한 인터넷 서핑이 어렵다. 이런 문제에 대한 해결책으로 개인화된 북마크를 통해 원하는 서비스에 바로 접근할 수 있는 방법을 제안한다. 본 논문에서 제안한 기법은 기존 페이지 중심의 북마크를 개선하여 웹 사이트 별로 일련의 페이지들을 북마크하여 무선 단말기를 통해 제공함으로써, 웹 사이트의 구조를 한눈에 쉽게 파악하고 원하는 페이지에 더욱 빠르게 접근할 수 있는 방안을 제시한다. 또한 사용자들의 선호도 프로파일을 이용하여 유사한 관심분야를 갖는 사용자들을 그룹화한 후 같은 그룹내의 사람들이 생성한 북마크를 웹 사이트 접근시 추천해주는 기법을 제안한다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.9 no.6
• /
• pp.1625-1631
• /
• 2008

This paper is going to research about RFID real time position finder technology and the offline shopping mall's client shop list managed by the RF fused Tag USB memory to analyze out the output of the data for providing real time interactive customer intelligence commodity system.

• Journal of Korean Society for Geospatial Information Science
• /
• v.20 no.4
• /
• pp.67-75
• /
• 2012

For the last few years, LBS has attracted considerable attention from many industries and societies as a result of propagated smart devices. LBS has a high utilization of mobile users as it uses user positions as a significant factor. Current LBS has only taken user position into account and it makes some limits. So, it is necessarily suggested that support for personalized services which consider user's motion, traffic condition, weather condition, time, personal information and preferences that have a huge impact on the accuracy. The purpose of this study is to design the inference systems with user's motion, preferences and schedules and provide users with the personalized information. To achieve this, Movement Ontology, User Profile Ontology, Schedule Ontology and Work Ontology should be constructed and based on this, smart applications were developed. Developed applications induced appropriately recommended results according to user's preference, motion and directions.

• Information Systems Review
• /
• v.23 no.3
• /
• pp.51-75
• /
• 2021

Global e-commerce websites offer personalized recommendation services to gain sustainable competitiveness. Existing studies have offered personalized recommendation services using quantitative preferences such as ratings. However, offering personalized recommendation services using only quantitative data has raised the problem of decreasing recommendation performance. For example, a user gave a five-star rating but wrote a review that the user was unsatisfied with hotel service and cleanliness. In such cases, has problems where quantitative and qualitative preferences are inconsistent. Recently, a growing number of studies have considered review data simultaneously to improve the limitations of existing personalized recommendation service studies. Therefore, in this study, we identify review and rating mismatches and build a new user profile to offer personalized recommendation services. To this end, we use deep learning algorithms such as CNN, LSTM, CNN + LSTM, which have been widely used in sentiment analysis studies. And extract sentiment features from reviews and compare with quantitative preferences. To evaluate the performance of the proposed methodology in this study, we collect user preference information using real-world hotel data from the world's largest travel platform TripAdvisor. Experiments show that the proposed methodology in this study outperforms the existing other methodologies, using only existing quantitative preferences.