• Soft Computing and Machine Intelligence
• /
• 제1권1호
• /
• pp.11-23
• /
• 2021

House price prediction is a significant financial decision for individuals working in the housing market as well as for potential buyers. From investment to buying a house for residence, a person investing in the housing market is interested in the potential gain. This paper presents machine learning algorithms to develop intelligent regressions models for House price prediction. The proposed research methodology consists of four stages, namely Data Collection, Pre Processing the data collected and transforming it to the best format, developing intelligent models using machine learning algorithms, training, testing, and validating the model on house prices of the housing market in the Capital, Islamabad. The data used for model validation and testing is the asking price from online property stores, which provide a reasonable estimate of the city housing market. The prediction model can significantly assist in the prediction of future housing prices in Pakistan. The regression results are encouraging and give promising directions for future prediction work on the collected dataset.

• 유통과학연구
• /
• 제5권2호
• /
• pp.101-117
• /
• 2007

최근 유통산업의 성장과정에서 신유통업태의 등장과 대형할인점의 다점포화 전략으로 유통환경이 급변하고 있다. 경쟁이 격화됨에 따라 대형할인점들은 저가격 전략 및 상품차별화 등을 위해 유통업체브랜드(Private Brand: PB) 개발을 확대하고 있다. 그러나 장기적 경기불황으로 인해 실용적이고 합리적 사고를 가지고 있는 신세대 주부 및 직장인이 주요 고객층으로 자리 잡으면서 과거 지향해 오던 저가전략은 더 이상 새로운 것이 될 수 없게 되었다. 한편, 최근 대형할인점들은 신규고객 확보를 위해 지방 출점을 강화하고 있다. 그러나 지역간 소비자 태도, 소득 및 소비패턴 등의 격차로 인하여 지방출점의 어려움을 겪고 있다. 이에 대형할인점들은 출점지역의 고객 특성에 대한 체계적인 이해와 유통업체브랜드(PB)의 소비자 선호의 지역간 특성 차이를 확인하는 것이 필수적인 과제가 되었다. 즉, 이러한 유통업체의 경쟁적 지방 점포확장과 소비자의 가치관의 변화는 지역간 출점을 앞두고 있는 대형할인점에 대한 PB상품 선호와 구매행동에 대한 연구를 요구하고 있다. 이에 본 연구는 소비자의 관점에서 선행연구를 토대로 PB상품 선호도와 선택된 변수들을 중심으로 유통업체 브랜드 제품의 구매의도와 관련하여 경기지역 도시의 지역간 차이가 존재하는지를 분석하는데 그 목적을 두고 있다.

• 농촌계획
• /
• 제19권3호
• /
• pp.13-24
• /
• 2013

With the increase of visitors to rural tourism villages, the direct selling at sites is getting vitalized. Accordingly, their display stores is getting more important. Therefore, this study has selected 30 domestic rural tourism villages as study objects for the attitude survey of 200 farming suppliers and the site examination for the designs of those display stores in order to analyze their status and classify the types of necessity. Such operation status as sale item, sale method, method of supply and demand, major customer, sales scale, manager, opening hour, and operation cost were examined, to identity and for design factors the pattern, material quality and color were investigated. For the attitude of farming suppliers, the tactics of sales, the reason for being positive or negative, the functionality and the features of display stores were examined through brainstorming. IBM SPSS Statistics 20 Program was employed for Frequency, which indicated that village chiefs and store managers with the sales scale of 1 to 20 million won are dealing with female customers in their 40's and 50's and that those stores are open at the time of experience or year round without any operation expense. Permanent type and Fixed type were found to be the design factors of the display-case type with the material and the color of wood and orange respectively. The result of investigation analysis of farming suppliers' attitude showed the followings: the need of display stores is quite high, structure type and permanent type have high fitness and from the viewpoint of display-on-table type as a standard moving type was very convenient. The analysis of significant items at the characteristics of those display stores revealed that their locations, quality conservation, sanitation, users' convenience, designs and promotion are very important. The result of status analysis revealed that though there is a correlation among the types of display stores depending on the visiting season of tourists their installing is not desirable. Three types have been analyzed: Type 1 is a structure type only in the villages with continuous visitors, Type 2 a moving-table type only in the villages with temporary visitors and Type 3 is a fixed display-case type.

• 한국화재소방학회논문지
• /
• 제12권1호
• /
• pp.15-21
• /
• 1998

본 연구에서는 국내의 30년간 발생한 백화점 화재 사고사례를 토대로 그 심각성 예측을 위해 확률적 인 접근을 하였다. 백화점 화재의 년간 발생 건수와 그 피해액 정도를 고려하여 위험 수준을 산정해 보 았다 또한 본 연구에서는 백화점 화재발생 시나리오를 작성해 미국 NIST에서 개발한 FPETOOL 프로그 램을 이용하여 백화점에서의 화재에 대한 심각성을 예측하였다 . FPETOOL 프로그햄 실행 결과로 화재 발생시 인체가 위험해지는 용도, 연기충, 가스 농도의 수준에 도탈하는 시간올 알 수 있었다. 백화점에서 화재가 발생했을 경우 그에 따른 재산피해, 인명피해가 매우 크며, 잠재하는 위험성이 매 우 크므로 미연에 방지해야 한다.

• 한국산업융합학회 논문집
• /
• 제26권1호
• /
• pp.113-119
• /
• 2023

In this paper, we propose an optimization of a pose estimation deep learning model for recognition of abnormal behavior in unmanned stores using radio frequencies. The radio frequency use millimeter wave in the 30 GHz to 300 GHz band. Due to the short wavelength and strong straightness, it is a frequency with less grayness and less interference due to radio absorption on the object. A millimeter wave radar is used to solve the problem of personal information infringement that may occur in conventional CCTV image-based pose estimation. Deep learning-based pose estimation models generally use convolution neural networks. The convolution neural network is a combination of convolution layers and pooling layers of different types, and there are many cases of convolution filter size, number, and convolution operations, and more cases of combining components. Therefore, it is difficult to find the structure and components of the optimal posture estimation model for input data. Compared with conventional millimeter wave-based posture estimation studies, it is possible to explore the structure and components of the optimal posture estimation model for input data using genetic algorithms, and the performance of optimizing the proposed posture estimation model is excellent. Data are collected for actual unmanned stores, and point cloud data and three-dimensional keypoint information of Kinect Azure are collected using millimeter wave radar for collapse and property damage occurring in unmanned stores. As a result of the experiment, it was confirmed that the error was moored compared to the conventional posture estimation model.

• 대한한의학원전학회지
• /
• 제12권2호
• /
• pp.176-183
• /
• 1999

Each life has its own properties that distinguish one another. With this property, Oriental medicine suggests original diagnosis and treament. Our process of aging shows typical outline of cycle, i. e. from one's birth to death. Understanding the life cycle of men gives us very good hint to predict one's state of health, possible diseases, characteristics of disease in each term of his/her life cycle. It's because body and mode of diseases change according to age. Aging starts when $\breve{U}$m Essence(陰精)-the essence one receive from parents-dries up or when Deficient Fire(虛火) soars. Parts that compose our body-bones, muscles, flesh, etc.-gradually weaken and worn out as they no longer get support from Yang-Ki(陽氣), In "Yellow Emperor's Classic", aging starts around one's forties when $\breve{U}$m Essence(陰精) is reduced to less than half. However, what is usually accepted is that women start aging from 49 and men 64, regarding significant geriatric disease. As it is mentioned, aging starts with exhaustion of $\breve{U}$m Essence(陰精) which results in soaring Deficient Fire. Main symptoms are weak mental state due to Sin(神) disorder, and weak physical state due to Spleen and Stomacn(脾胃) disorder. Main principle in treating and preventing diseases related to aging is preserving $\breve{U}$m Essence(陰精), as well as fortifying Ki and Blood(氣血). To do this, Lung(肺)-which collects $\breve{U}$m Essence(陰精), and Kidney(腎) stores-which stores $\breve{U}$m Essence(陰精).

• 패션비즈니스
• /
• 제18권3호
• /
• pp.1-13
• /
• 2014

This study investigated the store switching behavior of fashion stores targeting college students. A random sample of college students completed a questionnaire that contained measurements of store property, relationship quality, switching intent of store, preference of on/offline store, purchase of brand/non-brand product and monthly clothing expenses. The factors extracted as switching behavior of on/offline fashion store are store property, relationship quality and switching intent of store. Dimensions of store switching behavior in online shopping mall is revealed to be composed of diversity/ easy to search, store reliability, home page layout, sales promotion, reliability, commitment and switching intent of store. Also those of offline store is revealed to be composed of store comfort/salespeople service, product diversity, store location, product price, reliability, commitment and switching intent of store. The significant differences were found between store switching behavior of college students by preference of on/offline store and purchase of national brand/non brand. It is expected that this results can be used as a basic material for further study and setting up the fashion retailing strategies in fashion store for selling non brand products.

• 소성∙가공
• /
• 제12권2호
• /
• pp.110-115
• /
• 2003

This paper is concerned with the compression test and forming process of flange by using virtual reality and analysis(simulation) program. This virtual manufacturing can be carried out one personal computer without any expensive devices for experiment. The virtual manufacturing composed of three modules such as the imput, calculation and the output modules on internet. Internet user can give the material's property and process parameters to the sever computer at the input module. On the calculation module, a simulator computes the virtual manufacturing process by analysis program and stores the data as a file. The output module is the program in which internet user can confirm virtual manufacturing results by showing tables, graphs, and 3D animation. This programs is designed by an internet language such as HTML, CGI, VRML and JAVA ,while analysis programs use the finite increasing, the virtual manufacturing technique will substitute many real experiments in the future.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 ITC-CSCC -3
• /
• pp.1764-1767
• /
• 2002

Recent explosive increases in information 'volume have led to a rapid development or a change of information technology which stores, searches, and manages a vast amount of information. It is considered that an effective share and utilization of a large amount of digital information produced by work performances is a pivotal element which can make decisive contributions to a great success of business management. This common property of information reflects a changing social paradigm including a change of business processes. This paper is aimed at designing and embodying the construction of knowledge base in an efficient project management system using unsupervised data mining techniques in order to extract information and utilize it as knowledge about standard data (statistical data, template etc.,), size prediction and a danger precaution notice which are needed for a plan and a scheduling of a new project from data coming from already-established projects.

• 경영과정보연구
• /
• 제33권5호
• /
• pp.97-115
• /
• 2014

최근 한국과 중국의 대형마트시장의 경쟁이 치열해지면서 고객만족을 충족시키기 위해 점포속성, 제품속성, 서비스속성, 물리적 환경요인에 관한 연구가 이루어지고 있다. 이에 본 연구에서 한국과 중국 대형마트 구매자의 점포선택요인을 알아보고, 점포에 대한 고객만족과 재방문의도와의 영향관계를 분석하는 것을 목적으로 연구모형을 설계하였다. 또한 점포에 대한 중국과 한국의 고객만족과 재방문의도에 영향을 미치는 관계차이에 대해서도 알아보았다. 이에 따른 개념적 이해와 기존연구의 검토를 통해 가설을 설정하고 관련성 검증을 실시하였다. 실증분석을 위한 자료의 수집은 한국내 대형마트를 이용한 한국 소비자들과 중국내 대형마트를 이용한 중국인 소비자들 대상으로 자료를 수집하였으며 설정된 연구가설에 대해 구조방정식모형 분석을 통해 검증하였다.