RFM 기법과 연관성 규칙을 이용한 개인화된 전자상거래 추천시스템

진병운(Byeong-Woon Jin),조영성(Young-Sung Cho),류근호(Keun-Ho Ryu) 한국컴퓨터정보학회 2010 韓國컴퓨터情報學會論文誌 Vol.15 No.12

이 논문은 RFM 기법과 연관성 분석을 이용한 개인화된 전자상거래 추천 시스템을 제안한다. 제안된 전자상거래 추천시스템은 사용자의 평가 자료에 의존하지 않고 묵시적인(Implicity)방법을 이용하여 고객정보와 구매이력 정보를 기반으로 RFM(Recency, Frequency, Monetary) 기법을 이용한 고객 세분화와 교차판매(cross-sell)관계를 찾는 연관성 분석을 이용한 개선된 시스템이다. 또한 고객군별 구매특성 분석을 통하여 효율적인 마케팅 전략과 고객관계관리(CRM: Customer Relationship Management)방법을 제시한다. 현업에서 사용하는 데이터 셋을 구성하여 실험 및 평가를 통해서 효용성을 입증 및 평가하여 일대일 웹 마케팅을 실현하였다. This paper proposes the recommendation system which is advanced using RFM method and Association Rules in e-Commerce. Using a implicit method which is not used user's profile for rating, it is necessary for user to keep the RFM score and Association Rules about users and items based on the whole purchased data in order to recommend the items. This proposing system is possible to advance recommendation system using RFM method and Association Rules for cross-selling, and also this system can avoid the duplicated recommendation by the cross comparison with having recommended items before. And also, it's efficient for them to build the strategy for marketing and crm(customer relationship management). It can be improved and evaluated according to the criteria of logicality through the experiment with dataset collected in a cosmetic cyber shopping mall. Finally, it is able to realize the personalized recommendation system for one to one web marketing in e-Commerce.

공장지역에서 주거지역으로의 대지용도 변경시 소음현황 및 관련법규

조영운(Cho Young-Woon),주문기(Ju Mun-Ki),오양기(Oh Yang-ki) 한국건축친환경설비학회 2009 한국건축친환경설비학회 학술발표대회 논문집 Vol.2009 No.10

열저항과 K-factor를 이용한 LED 조명광원의 정션온도 예측기법에 관한 연구

이호운(Ho-Woon Lee),조영진(Young-Jin cho),곽계달(Kae-Dal Kwack) 대한기계학회 2009 대한기계학회 춘추학술대회 Vol.2009 No.11

It is difficult to determine the maximum and partial junction temperature simultaneously because LED lightings are manufactured using several chips with low power rather than single chip with high power. In this study, in case of the lighting source module of the MR16 assembled lots of the LED, the method determining the maximum and partial junction temperature simultaneously with LED and simply applying to the industrial site was deduced. At this end, by using the transient measuring technique, the thermal resistance of an one-chip was analyzed in detail and the thermal resistance of the whole module was calculated by applying to the K-factor calculation method. Comparing to these techniques, thermal network techniques, by using conduction and convection thermal resistance, which can estimate the maximum and partial junction temperature of the LED chip simultaneously in which it is adhered to a module by applying the MR16 optical source module to the thermal resistance was propose.

건설 현장 CCTV 영상을 이용한 작업자와 중장비 추출 및 다중 객체 추적

조영운 ( Cho¸ Young-woon ),강경수 ( Kang¸ Kyung-su ),손보식 ( Son¸ Bo-sik ),류한국 ( Ryu¸ Han-guk ) 한국건축시공학회 2021 한국건축시공학회지 Vol.21 No.5

건설업은 업무상 재해 발생빈도와 사망자 수가 다른 산업군에 비해 높아 가장 위험한 산업군으로 불린다. 정부는 건설 현장에서 발생하는 산업 재해를 줄이고 예방하기 위해 CCTV 설치 의무화를 발표했다. 건설 현장의 안전 관리자는 CCTV 관제를 통해 현장의 잠재된 위험성을 찾아 제거하고 재해를 예방한다. 하지만 장시간 관제 업무는 피로도가 매우 높아 중요한 상황을 놓치는 경우가 많다. 따라서 본 연구는 딥러닝 기반 컴퓨터 비전 모형 중 개체 분할인 YOLACT와 다중 객체 추적 기법인 SORT을 적용하여 다중 클래스 다중 객체 추적 시스템을 개발하였다. 건설 현장에서 촬영한 영상으로 제안한 방법론의 성능을 MS COCO와 MOT 평가지표로 평가하였다. SORT는 YOLACT의 의존성이 높아서 작은 객체가 적은 데이터셋을 학습한 모형의 성능으로 먼 거리의 물체를 추적하는 성능이 떨어지지만, 크기가 큰 객체에서 뛰어난 성능을 나타냈다. 본 연구로 인해 딥러닝 기반 컴퓨터 비전 기법들의 안전 관제 업무에 보조 역할로 업무상 재해를 예방할 수 있을 것으로 판단된다. The construction industry has the highest occupational accidents/injuries and has experienced the most fatalities among entire industries. Korean government installed surveillance camera systems at construction sites to reduce occupational accident rates. Construction safety managers are monitoring potential hazards at the sites through surveillance system; however, the human capability of monitoring surveillance system with their own eyes has critical issues. A long-time monitoring surveillance system causes high physical fatigue and has limitations in grasping all accidents in real-time. Therefore, this study aims to build a deep learning-based safety monitoring system that can obtain information on the recognition, location, identification of workers and heavy equipment in the construction sites by applying multiple object tracking with instance segmentation. To evaluate the system's performance, we utilized the Microsoft common objects in context and the multiple object tracking challenge metrics. These results prove that it is optimal for efficiently automating monitoring surveillance system task at construction sites.

건설 현장 CCTV 영상에서 딥러닝을 이용한 사물 인식 기초 연구

강경수 ( Kang Kyung-su ),조영운 ( Cho Young-woon ),류한국 ( Ryu Han-guk ) 한국건축시공학회 2020 한국건축시공학회 학술발표대회 논문집 Vol.20 No.2

The construction industry has the highest occupational fatality and injury rates related to accidents of any industry. Accordingly, safety managers closely monitor to prevent accidents in real-time by installing surveillance cameras at construction sites. However, due to human cognitive ability limitations, it is impossible to monitor many videos simultaneously, and the fatigue of the person monitoring surveillance cameras is also very high. Thus, to help safety managers monitor work and reduce the occupational accident rate, a study on object recognition in construction sites was conducted through surveillance cameras. In this study, we applied to the instance segmentation to identify the classification and location of objects and extract the size and shape of objects in construction sites. This research considers ways in which deep learning-based computer vision technology can be applied to safety management on a construction site.

주거지역의 외부소음현황 및 규제기준에 관한 연구

오양기(Oh Yang-Ki),조영운(Cho Young-Woon),주문기(Chu Mun-Ki) 한국건축친환경설비학회 2010 한국건축친환경설비학회 논문집 Vol.4 No.1

Due to the expansion of residential area and redevelopment of the city, the industrial area tends to be changed into residential area. It is often the case that only a part of the industrial area is changed to residential area while the other part remains as industrial area. There are complaints and even violent activities from the residents of changed residential area against the noise sources in the remained part of industrial area. while the noise emission level of the factories in the industrial area are keeping the emission standard of noise and vibration(Article No. 8) noticed from Ministry of Environment , it sometimes still exceed the regulation scheme of residential noise environment noticed by Ministry of Land, Transport and Maritime Affairs. In these basis, this study aims to check the changed residential area has a proper noise environment and to confirm the related regulations on noise performance have appropriate standards.

아파트 건설 현장 작업자 특징 추출 및 다중 객체 추적 방법 제안

강경수 ( Kang Kyung-su ),조영운 ( Cho Young-woon ),류한국 ( Ryu Han-guk ) 한국건축시공학회 2021 한국건축시공학회 학술발표대회 논문집 Vol.21 No.1

The construction industry has the highest occupational accidents/injuries among all industries. Korean government installed surveillance camera systems at construction sites to reduce occupational accident rates. Construction safety managers are monitoring potential hazards at the sites through surveillance system; however, the human capability of monitoring surveillance system with their own eyes has critical issues. Therefore, this study proposed to build a deep learning-based safety monitoring system that can obtain information on the recognition, location, identification of workers and heavy equipment in the construction sites by applying multiple-object tracking with instance segmentation. To evaluate the system's performance, we utilized the MS COCO and MOT challenge metrics. These results present that it is optimal for efficiently automating monitoring surveillance system task at construction sites.

냉각수로 하천수를 이용하는 열교환 시스템내 Fouling 형성에 관한 연구

성순경(Sun-Kyung Sung),서상호(Sang-Ho Suh),노형운(Hyung-Woon Roh),조영일(Young-Il Cho) 대한기계학회 2003 대한기계학회 춘추학술대회 Vol.2003 No.4

Scale is formed when hard water is heated or cooled in heat transfer equipments such as heat<br/> exchangers, condensers, evaporators, cooling towers, boilers, and pipe walls. When scale deposits in a<br/> heat exchanger surface, it is traditionally called fouling. The objective of the present study is to<br/> investigate the formation of fouling in a heat exchanging system. A lab-scale heat exchanging system is<br/> built-up to observe and measure the formation of fouling experimentally. Water analyses are conducted<br/> to obtain the properties of HAN river water. In the present study a microscopic observation is<br/> conducted to visualize the process of scale formation. Hardness of HAN-river water is higher than that<br/> of tap water in Seoul.

Lab - Scale 판형열교환 시스템에서 가시화를 이용한 Fouling Mechanism 해석

성순경(Sun Kyung Sung),서상호(Sang Ho Suh),노형운(Hyung Woon Roh),조영일(Young Il Cho) 대한설비공학회 2003 대한설비공학회 학술발표대회논문집 Vol.2003 No.-

The Prelude에 나오는 물, 바람, 섬, 동굴의 이미지 연구

조영운 안양대학교 1997 논문집 Vol.17 No.-

Prelude is a long poem like an epic and autobiographical. In the 20th century time began to play an important role in novels of James Joyce and Proust. Prelude began to attract the attentions of literary men. Wordsworth's recollection is a kind of stream of consciousness. Nature is very important in his poems, especially in Prelude. To understand this epic-like long poem, we must know the relationship between the poet and nature. Wordsworth loves nature itself literally and he obtains the power to live in the noisy world from nature. And he thinks also that nature is a kind of revelation of life's deep meaning and God's intention. He uses many natural things to understand what is hidden in life and the depth of it. They are wind and water, islands, cavern and mountains. They are used as setting to provoke the mood in which he is prepared to thke part. The images of wind and water are used to manifest power and vitality in the universe. Often when the situation is not fit for wind and water to apper as part of the surrounding scene, their symbolic value is made use of on the figurative level. The image of island is isolation as it is really surrounded by water geographically. It the poet wants to concentrate on deeper meaning or thought, he cut himself off from the outer world using the image of island. This traditional use of insolation by using the image of island goes back to Rousseau. And Rousseau borrows this method from Robinson Crusoe by defoe. There is another image. Though it is less articulated, the poet records intimations of the inner world by means of it. When we encounter such words as Under-thirst, Under-presence, Under-soul, the kind of image appear. We might call it the image of cavern. This image has two functions. One is inevitable and fearful isolation from any external medium without which the mind cannot kept healthy. The other has the opposite function. It is suggestive of fertility and creation. Like all of Wordsworth's central images, the cavern can stand potentially for several things, even apparent opposites.