추천시스템을 위한 k-means 기법과 베이시안 네트워크를 이용한 가중치 선호도 군집 방법

박화범,조영성,고형화,Park, Wha-Beum,Cho, Young-Sung,Ko, Hyung-Hwa 한국데이터전략학회 2013 Journal of information technology applications & m Vol.20 No.3

Real time accessiblity and agility in Ubiquitous-commerce is required under ubiquitous computing environment. The Research has been actively processed in e-commerce so as to improve the accuracy of recommendation. Existing Collaborative filtering (CF) can not reflect contents of the items and has the problem of the process of selection in the neighborhood user group and the problems of sparsity and scalability as well. Although a system has been practically used to improve these defects, it still does not reflect attributes of the item. In this paper, to solve this problem, We can use a implicit method which is used by customer's data and purchase history data. We propose a new clustering method of weighted preference for customer using k-means clustering and Bayesian network in order to improve the accuracy of recommendation. To verify improved performance of the proposed system, we make experiments with dataset collected in a cosmetic internet shopping mall.

Camera Vision 기반 주행안전 시스템 구현에 관한 연구

박화범,김영길,Park, Hwa-Beom,Kim, Young-Kil 한국정보통신학회 2019 한국정보통신학회논문지 Vol.23 No.9

최근 발전되고 있는 정보통신 IT 기술은 자동차 시장에도 큰 영향을 미치며 발전하고 있다. 근래에는 운전자의 안전성과 편의성을 위해 IT 기술이 접목된 장치들이 장착되고 있다. 하지만 편의성이 증가된 장점과 함께 운전자의 주의 분산으로 인해 교통사고를 증가시키는 단점도 가져오게 되었다. 이러한 사고를 미연에 방지하기 위해 여러 방식과 종류의 안전시스템 개발이 필요하다. 본 논문에서는 두 개 이상의 센서를 이용한 레이더센서 와 카메라 융합 방식 및 Stereo Camera 방식을 이용하지 않고 하나의 단일 Camera를 이용하여 주/야간 차선이탈 경보 및 장애물 및 보행자 인식이 가능한 플랫폼을 구현 하고 차량에서 인식률 평가 및 유효성을 분석 하여 단일 카메라를 이용한 다기능 주행안전 플랫폼 연구를 제안 한다. The information and communication technology that is being developed recently has been greatly influencing the automobile market. In recent years, devices equipped with IT technology have been installed for the safety and convenience of the driver. However, it has the advantage of increased convenience as well as the disadvantage of increasing traffic accidents due to driver's distraction. In order to prevent such accidents, it is necessary to develop safety systems of various types and ways. In this paper implements a platform that can recognize LDWS and FCWS and PDWS by using a single camera without using radar sensor and camera fusion and stereo camera method using two or more sensors, and proposes to study multi-function driving safety platform using a single camera by analyzing recognition rate evaluation and validity on a vehicle.

와전류 코일 센서를 통한 차량용 코팅막 측정에 관한 연구

박화범,김영길,Park, Hwa-Beom,Kim, Young-Kil 한국정보통신학회 2019 한국정보통신학회논문지 Vol.23 No.9

부품 또는 제품들의 정전기 방지와 내마모성 및 내부식성 향상, 미각화 등 다양한 목적으로 코팅의 중요성이 증가되고 있다. 코팅막의 두께를 측정하는 방법으로 주로 프로브(probe)로 코팅면을 측정하는 접촉식 측정방식이 이용되는데, 코어의 투자율 변화에 의해 센서 출력 왜곡이나 부하 현상이 발생하여 정확도가 떨어지는 문제점이 있다. 본 논문에서는 비선형적인 특성에 의해 발생할 수 있는 문제점을 최적화된 회로설계와 두께측정 알고리즘을 적용하여 코팅막의 측정 오차를 줄이는 방법을 제안한다. 여러 코팅 샘플을 통한 실험 결과 ${\pm}2%$ 이내의 측정 정확도를 갖는 것을 확인할 수 있다. The importance of coatings has been increasing for different purposes such as prevention of static electricity of auto parts or products, improvement of abrasion and corrosion resistance, and enhancement of esthetics. As a method for measuring the thickness of a coating film, a contact method with probe is commonly used. However, it is problematic that accuracy of the sensor is degraded due to sensor output distortion or load phenomenon, which is caused by a change in magnetic permeability of the core. In this study, we propose a method to reduce the measurement error of the coating film by applying the optimized circuit design and the thickness measurement algorithm to the problems caused by the nonlinear characteristics. The tests result which have been taken with different thickness coating samples show that the measurement accuracy is within ${\pm}2%$.

추천시스템을 위한 k-means 기법과 베이시안 네트워크를 이용한 가중치 선호도 군집 방법

박화범(Wha-Beum Park),조영성(Young-Sung Cho),고형화(Hyung-Hwa Ko) 한국데이타베이스학회 2013 Journal of information technology applications & m Vol.20 No.S

Real time accessiblity and agility in Ubiquitous-commerce is required under ubiquitous computing environment. The Research has been actively processed in e-commerce so as to improve the accuracy of recommendation. Existing Collaborative filtering (CF) can not reflect contents of the items and has the problem of the process of selection in the neighborhood user group and the problems of sparsity and scalability as well. Although a system has been practically used to improve these defects, it still does not reflect attributes of the item. In this paper, to solve this problem, We can use a implicit method which is used by customer’s data and purchase history data. We propose a new clustering method of weighted preference for customer using k-means clustering and Bayesian network in order to improve the accuracy of recommendation. To verify improved performance of the proposed system, we make experiments with dataset collected in a cosmetic internet shopping mall.

마이닝과 FRAT기반 가중치 선호도 군집을 이용한 추천 기법에 관한 연구

박화범(Wha-Beum Park),조영성(Young-Sung Cho),고형화(Hyung-Hwa Ko) 한국디지털콘텐츠학회 2013 한국디지털콘텐츠학회논문지 Vol.14 No.4

Real-time accessibility and agility are required in u-commerce under ubiquitous computing environment. Most of the existing recommendation techniques adopt the method of evaluation based on personal profile, which has been identified with difficulties in accurately analyzing the customers level of interest and tendencies, as well as the problems of cost, consequently leaving customers unsatisfied. Researches have been conducted to improve the accuracy of information such as the level of interest and tendencies of the customers. However, the problem lies not in the preconstructed database, but in generating new and diverse profiles that are used for the evaluation of the existing data. Also it is difficult to use the unique recommendation method with hierarchy of each customer who has various characteristics in the existing recommendation techniques. Accordingly, this dissertation used the implicit method without onerous question and answer to the users based on the data from purchasing, unlike the other evaluation techniques. We applied FRAT technique which can analyze the tendency of the various personalization and the exact customer.

영상압축에 강인한 변질검증 워터마킹에 관한 연구

안성철,이경학,박화범,고형화,Ahn, Sung-Cheol,Lee, Kyoung-Hak,Park, Hwa-Bum,Ko, Hyung-Hwa 한국통신학회 2006 韓國通信學會論文誌 Vol.31 No.12C

소프트웨어의 발전으로 인해 디지털 컨텐츠에 대한 복사, 변경이 손쉽게 일반인들에 의해서도 가능하게 되어 컨텐츠의 제작자는 소유권 수장이나 내용의 변질에 대한 인증과 검증을 필요로 하게 되었다. 변질검증(Fragile) 워터마킹 기법은 워터마크가 삽입된 영상의 변질 및 훼손 여부를 판별할 수 있지만, 고의적이지 않은 표준화된 영상압축 등에서도 워터마크가 사라지는 문제점이 있다. 본 논문에서 JPEG 압축과 같은 영상처리에서는 강인하지만 변질에는 약한 Semi-Fragile 워터마킹 방법을 제안하였다. 제안한 방법은 블록간의 상관관계를 이용하여 워터마크를 생성하고, DCT(Discrete Cosine Transform)수행 후에 계수 값들의 양자화를 이용하여 HVS(Human Visual System)에 둔감한 부분의 계수 값에 삽입하는 방법을 제안하였다. 실험결과 공간영역 상에서 미세한 변화에도 변질여부의 검출 정도가 뛰어났으며, 변질된 부분을 블록별로 검출할 수 있어 공간상의 어떤 위치의 픽셀들이 변화하였는지를 시각적으로 확인할 수 있었다. The rapid progress of the software has enabled individuals to copy and remark digital contents, which was only done by professionals. As a solution for the problems, contents producer needs to have certification and inspection of its contents and hold the proprietary right. A fragile watermarking method is able to detect the distortion and damage of watermarked image, but the watermark is also fragile on standardized image compression. That is the problem of fragile watermarking technique. We propose semi-fragile watermarking technique that is robust in the image processing such as JPEG compression used on computer, but it is fragile on the addition of noise and other attacks. In the proposed method, we can generate the watermarks of an image from the relationship between two block coefficients, also the generated watermark is inserted into insensible part of HVS(Human Visual System) after processing DCT(Discrete Cosine Transform) and using quantization. As a result, on the spatial domain, high detection of distortion has been possible even in slight changes, and could detect the corrupted blocks on image. Therefore, it is simple to judge the pixels at which some location has been changed in the space.

영상 압축에 강인한 변질검증 워터마킹에 관한 연구

안성철(Sung Cheol Ahn),박화범(Wha Beum Park),고형화(Hyung Hwa Ko) 한국통신학회 2005 한국통신학회 학술대회논문집 Vol.2005 No.6