• Title/Summary/Keyword: Recognize-into

Search Result 1,121, Processing Time 0.026 seconds

Customer Behavior Prediction of Binary Classification Model Using Unstructured Information and Convolution Neural Network: The Case of Online Storefront (비정형 정보와 CNN 기법을 활용한 이진 분류 모델의 고객 행태 예측: 전자상거래 사례를 중심으로)

  • Kim, Seungsoo;Kim, Jongwoo
    • Journal of Intelligence and Information Systems
    • /
    • v.24 no.2
    • /
    • pp.221-241
    • /
    • 2018
  • Deep learning is getting attention recently. The deep learning technique which had been applied in competitions of the International Conference on Image Recognition Technology(ILSVR) and AlphaGo is Convolution Neural Network(CNN). CNN is characterized in that the input image is divided into small sections to recognize the partial features and combine them to recognize as a whole. Deep learning technologies are expected to bring a lot of changes in our lives, but until now, its applications have been limited to image recognition and natural language processing. The use of deep learning techniques for business problems is still an early research stage. If their performance is proved, they can be applied to traditional business problems such as future marketing response prediction, fraud transaction detection, bankruptcy prediction, and so on. So, it is a very meaningful experiment to diagnose the possibility of solving business problems using deep learning technologies based on the case of online shopping companies which have big data, are relatively easy to identify customer behavior and has high utilization values. Especially, in online shopping companies, the competition environment is rapidly changing and becoming more intense. Therefore, analysis of customer behavior for maximizing profit is becoming more and more important for online shopping companies. In this study, we propose 'CNN model of Heterogeneous Information Integration' using CNN as a way to improve the predictive power of customer behavior in online shopping enterprises. In order to propose a model that optimizes the performance, which is a model that learns from the convolution neural network of the multi-layer perceptron structure by combining structured and unstructured information, this model uses 'heterogeneous information integration', 'unstructured information vector conversion', 'multi-layer perceptron design', and evaluate the performance of each architecture, and confirm the proposed model based on the results. In addition, the target variables for predicting customer behavior are defined as six binary classification problems: re-purchaser, churn, frequent shopper, frequent refund shopper, high amount shopper, high discount shopper. In order to verify the usefulness of the proposed model, we conducted experiments using actual data of domestic specific online shopping company. This experiment uses actual transactions, customers, and VOC data of specific online shopping company in Korea. Data extraction criteria are defined for 47,947 customers who registered at least one VOC in January 2011 (1 month). The customer profiles of these customers, as well as a total of 19 months of trading data from September 2010 to March 2012, and VOCs posted for a month are used. The experiment of this study is divided into two stages. In the first step, we evaluate three architectures that affect the performance of the proposed model and select optimal parameters. We evaluate the performance with the proposed model. Experimental results show that the proposed model, which combines both structured and unstructured information, is superior compared to NBC(Naïve Bayes classification), SVM(Support vector machine), and ANN(Artificial neural network). Therefore, it is significant that the use of unstructured information contributes to predict customer behavior, and that CNN can be applied to solve business problems as well as image recognition and natural language processing problems. It can be confirmed through experiments that CNN is more effective in understanding and interpreting the meaning of context in text VOC data. And it is significant that the empirical research based on the actual data of the e-commerce company can extract very meaningful information from the VOC data written in the text format directly by the customer in the prediction of the customer behavior. Finally, through various experiments, it is possible to say that the proposed model provides useful information for the future research related to the parameter selection and its performance.

A Study on the Indexing System Using a Controlled Vocabulary and Natural Language in the Secondary Legal Information Full-Text Databases : an Evaluation and Comparison of Retrieval Effectiveness (2차 법률정보 전문데이터베이스에 있어서 통제어 색인시스템과 자연어 색인시스템의 검색효율 평가에 관한 연구)

  • Roh Jeong-Ran
    • Journal of the Korean Society for Library and Information Science
    • /
    • v.32 no.4
    • /
    • pp.69-86
    • /
    • 1998
  • The purpose of velop the indexing algorithm of secondary legal information by the study of characteristics of legal information, to compare the indexing system using controlled vocabulary to the indexing system using natural language in the secondary legal information full-text databases, and to prove propriety and superiority of the indexing system using controlled vocabulary. The results are as follows; 1)The indexing system using controlled vocabulary in the secondary legal information full-text databases has more effectiveness than the indexing system using natural language, in the recall rate, the precision rate, the distribution of propriety, and the faculty of searching for the unique proper-records which the indexing system using natural language fans to find 2)The indexing system which adds more words to the controlled vocabulary in the secondary legal information full-text databases does not better effectiveness in the retail rate, the precision rate, comparing to the indexing system using controlled vocabulary. 3)The indexing system using word-added controlled vocabulary with an extra weight in the secondary legal information full-text databases does not better effectiveness in the recall rate, the precision rate, comparing to the indexing system using word-added controlled vocabulary without an extra weight. This study indicates that it is necessary to have characteristic information the information experts recognize - that is to say, experimental and inherent knowledge only human being can have built-in into the system rather than to approach the information system by the linguistic, statistic or structuralistic way, and it can be more essential and intelligent information system.

  • PDF

Characteristics of Velocity and Electrical Resistivity in Gassy Sediments Results of Mudbelt Sediments in the Southeastern Inner Shelf of Korea (가스함유퇴적물에서의 음파전달속도 및 전기비저항 특성: 한국남동해역 이토대 퇴적물의 분석결과)

  • Kim, Dae-Choul;Park, Soo-Chul;Seo, Young-Kyo
    • The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
    • /
    • v.6 no.4
    • /
    • pp.249-258
    • /
    • 2001
  • Compressional wave velocity and electrical resistivity of muddy sediments in the southeastern inner shelf of Korea were studied using nine piston core samples. The acoustic and physical properties were measured with 10 cm depth interval. Sediment structures were examined by x-radiographs of the cored sediments. Subbottom profiles were obtained by a high-resolution acoustic subbottom profiler. Acoustic turbid layers are clearly seen on the profiles, and x-radiographs of the sediments showed degassying structures formed by gas escaping. On the basis of x-radiographic images, velocities, electrical resistivities and physical properties, the sediments are divided into gassy and non-gassy sediments. The presence of gas and degassying structures result in a marked variation in velocity and electrical resistivity. It can be concluded that velocity and electrical resistivity arep arameter to recognize gassy sediment. The velocity is important parameter to indicate gassy sediment.

  • PDF

A Study on the Types and Effective Management Schemes of the Cooperative Farmers' Organizations in Korea (작목별 협동조직의 유형과 효율적 운영방안에 관한 연구)

  • Choi, Min-Ho;Cheong, Ji-Woong;Kim, Sung-Soo
    • Journal of Agricultural Extension & Community Development
    • /
    • v.2 no.2
    • /
    • pp.205-227
    • /
    • 1995
  • The objectives of this study were to 1) classify the cooperative farmers' organizations in Korea according to the development level and institutional aspects through the exploration of its' conceptual and institutional basis, 2) analyze the farmers' needs for organization, 3) identify the problems and situation of organizations, and 4) formulate an effective management model for each cooperative farmers' organization. The study was carried out through a review of literature and using available statistical data collected from various sources and empirical survey. Major findings of the study were: 1) the cooperative farmers' organizations could be classified into four types : crop units, farming cooperative corporation, trust farming companies and joint-stock agri-business. 2) a lot of members of the organization feel that the information is insufficient, the opportunity to suggest their own ideas is hardly given, and the members are not satisfied with the cooperation among the members, 3) the members who have higher level of schooling education showed a higher participation level in the organization, 4) most of members did not recognize the organization they participated in, 5) participation of the organization's members and concerned institutions is an important factor to promote problem solving and better communication within the organization, 6) any type of continuing education for the members is needed to facilitate the transfer of a new agricultural and organizational technology, 7) research and development(R & D) is one of the most important factors of the development of organizations, 8) most organizations are deficient in professional management skills(financial, personal, accounts, etc.), 9) the trust farming companies have difficulties in managing the firm on account of the characteristics of agriculture(especially seasonal), the dispersed trust lands, and the need for more alternative work in the winter season, and 10) in the case of agri-businesses, their organizations are more specialized in marketing and have more structured systems of management. Based on the results of the study the following recommendations were made for further improvement and development of agricultural cooperative organizations : (1) More governmental support should be given to education for improvement of the organizational structure. And more deliberate and differentiated governmental support should be provided for the organizations to be viably managed. (2) For more efficient communication between the members and the organization, more opportunities for discussion are needed. (3) The more research should be committed to this kind of work in order to get more analytic data and strategic plans of cooperative organizations.

  • PDF

Reduction of the Useless Radiation Exposure to Patients and Improvement of the Skill to Manage the Test according to Minimizing Changes of Posture in Bone Mineral Density (골밀도 검사에서 환자 자세 변경 최소화에 따른 수검자의 불필요한 피폭선량 감소 및 생산성 향상)

  • Kim, Ho-Sung;Dong, Kyung-Rae;Kim, Chang-Bok
    • The Journal of the Korea Contents Association
    • /
    • v.9 no.4
    • /
    • pp.228-235
    • /
    • 2009
  • As we recognize the health care, test of BMD is increased. There are various methods in BMD, Dual Energy X-ray absorptiometry (DEXA) which has high precision and accuracy, and low medical exposure dose has been widely used. To measure the changes of BMD, the test must be done as same posture at first and follow up study performed a year. we analyze the difference in the hour taken before and after the examination by radiologic technologist, frequency of scout scan, and the amount of the radiation exposure. The hour of the examination and frequency of the scout scan were shorten and the dose of the radiation exposure is reduced. As the numerical value of total subjects is converted into that of one person, the duration for the test was 52 seconds, the frequency for the scout scan 0.79 time, and the dose for the radiation exposure $13{\mu}Sv$. When the health care provider perform the precise and easy methods to minimize changes of posture and the skillful ability to manage the test, useless radiation is decreased.

A Study on the Change of Identity and Agency of International Marriage Migrant Women Changing with the Social Positionality : A Case Study of Gumi (국제결혼이주여성의 정체성 및 주체성의 사회적 위치성에 따른 변화 -구미 지역의 국제결혼이주여성의 생애사 분석을 중심으로-)

  • Park, Shin-Kyu
    • Journal of the Korean association of regional geographers
    • /
    • v.14 no.1
    • /
    • pp.40-53
    • /
    • 2008
  • A case study has been conducted on the changes in the identity and agency of international marriage migrant women who experienced a shift from a immigrant worker to a foreign spouse and a Korean citizen. The life histories of the eight female migrants living in Gumi area, a representative inland industrial complex in Korea, have been investigated by in-depth interview. The aim is to examine how the female migrants reconstruct and interpret their lives. The results reveal that the identy of a female migrant is flexible depending on her social positionality. The identities established from the past experiences in their native countries have been changed by their situations and conditions in Korea. The female immigrants recognize that their problems have been an important issue both in government policy and mass media. However, the female migrants express a strong revolt against the fact that they are considered as underclass victims or innocent people from underdeveloped countries. This implies their ambivalence toward international marriage that they selected subjectively. There is a finding to show a new possibility; the Transnational Marriage & Family Support Center supported by Government may provide a good ground for the female migrants to be a active group agent. The results illustrate that the international marriage migrant women could not be classified into a single group as wives. Called for are diverse researches reflecting the complex situations of migrant women.

  • PDF

Characteristics of Sign Distribution in Underground Space (지하공간에 있어서 사인류의 분포특성)

  • Choi Ji-Sook;Yoo Hyun-Bae
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.10 no.7
    • /
    • pp.1180-1187
    • /
    • 2006
  • We Studied the method of structuring the sign system for pedestrians in the underground space by investigating and analyzing the sign system at Tae-jon Underground Commercial Area in Korea by 1) classifying the signs by types and comparing their numder for each type in sections, 2) classiflying the signs by the points of installation, types, functions and contents of information and comparing their numbers, 3) classifying the signs by their height and comparing by the points of installation, and 4) classifying the signs by their points of installation finding patterns. As a result, we found out that the current pedestrian signs in Tae-jon Underground Commercial Area could by classified into those installted with a certain regularity and those concentrated in at certain points. We also found out that there were many problems with the current signs system. The big gap of the type and numble of the signs, concentration of the signs at the gate (entrance), and the big gap of the function of the signs by their points of installation. And the gap of the signs by the number of installation is big between the North side and the South side. Most of signs concentrated in the South side show the problems of installation attached by the types and quantity of information. We suggest that type of information has consistency by posting of signs, at the same time, the necessary information should be offered in order for the pedestrians to easily recognize as they more in the Underground space.

A Study on Placeness of Gwangju Art Street Looked through Experience of Life Subjects (생활주체의 경험을 통해 본 광주 예술의 거리 장소성 연구)

  • Kim, Yeon-Gyeong;Lee, Mu-Yong
    • Journal of the Korean association of regional geographers
    • /
    • v.21 no.3
    • /
    • pp.529-552
    • /
    • 2015
  • This study aims to analyze the placeness of Gwangju Art Street and the changing process of the street, looked through the experiences of life subjects living in this street. For this purpose, at first, history before art street was designated was traced by reviewing geographical characteristics and spatial transformation of the Art Street with the trend of Gwangju art scene and economic political situation. And then, in order to analyze the placeness of Gwangju Art Street, formation factors of placeness are extracted into physical element, behavior element and semantic element. Physical element and behavior element were analyzed through in-depth interview and data analysis for individual and microscopic historical process of life subjects being experienced in the street that is contrary to policy and plan. Finally, a semantic element was identified through questionnaire as to how people recognize current art street through a history being experienced as a venue of conflict of meaning. It is implied that bottom up place making policies that may connect context of the formation of placeness with the viewpoint of life subject in the Art Street is required to be presented now.

  • PDF

A Study on Geographical Category Classification of Road Names of New Address System : in the Case of Cheongju City (새주소 체계 도로명의 지리적 유형 분류에 관한 연구 - 청주시를 사례로 -)

  • Hong, Seon-il;Kim, Young-Hoon
    • Journal of the Korean association of regional geographers
    • /
    • v.21 no.3
    • /
    • pp.553-568
    • /
    • 2015
  • This paper focuses on the geographical characteristics and the spatial distributions and patterns of the road names in the new address system for which all the 183 road names of Cheongju City has been used. All 183 road names in Cheongju City and their textural information are analyzed and classified into four main categories and six divisions as sub-category. Each type is mapped and its spatial patterns are discussed in order to identify the interaction between the road name and the geographical characteristics of each type. From the discussion stated in the paper, it can be inferred that the road name is not only a representative place name in an area, but also presents an important geographical feature reflecting the toponymy of the cultural and historical backgrounds of an area. Therefore, it is necessary to recognize that for road naming, various aspects such as geographical backgrounds and characteristics should be considered. These are directly related to the publicity and utilization of the road names to the public who is still unfamiliar with the new address system to be used. Finally, various geographical topics and approaches such as toponymy and spatial analysis are proposed for further geographical research, which will contribute to the extent of geographical research scopes.

  • PDF

A Study on the Subjectivity about Nursing Student's Attitude after Hand Washing Education (간호학과 학생들의 손씻기 교육 후 태도 유형에 관한 주관성 연구)

  • Kim, Yun-Jeong
    • Journal of Digital Convergence
    • /
    • v.11 no.12
    • /
    • pp.621-630
    • /
    • 2013
  • This study, after education for nursing students through texts on hand washing, PPT materials and practices, will investigated the types of the subjects' attitude toward hand washing and attempt to provide basic data needed for nursing education and nursing practice program. As the methods of this research, Q methodology was applied, and 20 sophomores in the Department of Nursing Science as P-sample from October 8, 2012 to October 15, 2012 were asked to distribute Q-sample of 9-point Q-sample distribution, and the collected data were processed with principal factor analysis method by the PC QUANL program. As a result of the research, their attitude toward hand washing was classified into 3 types. The three factors extracted all had eigenvalues greater than 1.0 and explained approximately 56.67% of the variation in responses 40.41%, 10.14% and 6.11% respectively. Type 1 was the ones with the increased number of hand washing; Type 2 was the ones who recognize the need of hand washing education; and Type 3 was the ones who dry hands after washing. In conclusion, the significance of the classification of the types of the attitude after the hand washing education is that with the development of programmes of nursing education and nursing practice, individualized intervention strategies should be differently provided.