• Information Systems Review
• /
• v.4 no.1
• /
• pp.47-67
• /
• 2002

Since mid 90's, most of firms utilizing web as a communication vehicle with customers are keenly interested in web log file which contains a lot of trails customers left on the web, such as IP address, reference address, cookie file, duration time, etc. Therefore, an appropriate analysis of the web log file leads to understanding customer's behaviors on the web. Its analysis results can be used as an effective marketing information for locating potential target customers. In this study, we introduced a web mining technique using Clementine of SPSS, and analyzed a set of real web log data file on a certain Internet hub site. We also suggested a process of various strategies build-up based on the web mining results.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1999.10a
• /
• pp.194-195
• /
• 1999

• Journal of Engineering Education Research
• /
• v.9 no.4
• /
• pp.71-82
• /
• 2006

To accomplish the educational objectives of a department, a system for CQI(Continuous Quality Improvement) is necessary. Improving the educational system by survey analysis is one of the most important factors for accomplishing the educational objectives. In general, survey analysis is carried out by using statistical distribution on an attribute or correlation analysis between two attributes. However, these analysis schemes have a limitation that they cannot find relations among various attributes. In this paper, an in-depth survey analysis method applying data mining techniques is presented. Data mining is a technique for extracting interesting knowledges from a large set of data. Survey from undergraduate students in the School of Computing of Soongsil University is analyzed in this paper by using a data mining tool, called Clementine. Results of Clementine analysis show the relationship between 'grade', and other attributes hierarchically, and provide useful information that can be applied in student consulting and program improvement.

• The Bulletin of The Korean Astronomical Society
• /
• v.39 no.2
• /
• pp.99.1-99.1
• /
• 2014

달은 global magnetic fields가 존재하지 않으나, 달 표면에 국지적으로 자기장이 존재하며 이러한 현상의 원인은 계속 연구중이다. 달의 자기이상 현상이 나타나는 지역 중 광학적으로 밝고 어두운 패턴이 관측되는 지역을 Swirl이라한다. Mare Crisium ($17.18^{\circ}N$, $59.1^{\circ}E$)은 표면에 2개의 자기이상 지역과 광학적으로 밝은 지역들이 존재하지만, Swirl로 잘 알려진 Reiner Gamma와 같은 지역의 광학적 밝기와 패턴의 차이가 있다. 이를 위해 본 연구에서는 Lunar Prospector (LP) 위성의 magnetometer (MAG) 자료를 이용하여 자기장 분포에 관한 연구 및 Clementine 위성의 UV/VIS 영상자료를 이용하여 광학적 특성 연구를 진행하였다. LP의 MAG 자료는 Mare Cirisium지역의 22.3 km 고도에서 관측된 744개의 자료를 활용하였으며, Clementine의 영상자료는 750 nm, 950 nm의 반사도에 따른 Optical Maturity (OMAT)를 활용하였다. Mare Crisium의 북쪽지역은 자기이상 현상과 OMAT의 고유특성이 동시에 나타나며 이는 swirl과 유사하다. 특히, Mare Cirisum서쪽에 있는 Proclus crater 잔해 일부가 Mare Crisium의 북쪽지역까지 퍼져있어 이와 관련하여 자기장 존재여부에 따른 광학적 특성의 차이점을 조사하였다. 본 논문에서는 Mare Crisium 지역의 Swirl 진위여부를 추론하며, 본 논문에서 이용한 방법의 유용성에 대하여 검증하고자 한다.

• The Korean Journal of Applied Statistics
• /
• v.14 no.2
• /
• pp.475-486
• /
• 2001

데이터마이닝 패키지에 구현된 분류나무 알고리즘 가운데 CART, CHAID, QUEST, C4.5에서 변수 선택법을 비교하였다. CART의 전체탐색법이 편의를 갖는다는 사실은 잘알려졌으며, 여기서는 상품화된 패키지들에서 이들 알고리즘의 편의와 선택력을 모의실험 연구를 통하여 비교하였다. 상용 패키지로는 CART, Enterprise Miner, AnswerTree, Clementine을 사용하였다. 본 논문의 제한된 모의실험 연구 결과에 의하면 C4.5와 CART는 모두 변수선택에서 심각한 편의를 갖고 있으며, CHAID와 QUEST는 비교적 안정된 결과를 보여주고 있었다.

• Communications for Statistical Applications and Methods
• /
• v.8 no.2
• /
• pp.531-541
• /
• 2001

In this study, we compare the capabilities of the data mining tools of the most updated version objectively and provide the useful information in which enterprises and universities chose them. In particular, we compare the SAS/Enterprise Miner 3.0, SPSS/Clementine 5.2 and IBM/Intelligent Miner 6.1 which are well known and easily gotten.

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.2 no.1
• /
• pp.51-56
• /
• 2009

This study was tried to analyze the diagnosis of patients with cerebral infarction by sequence modeling that was one of data mining analysis method and find out previous disease or complication of patients with cerebral infarction. Mass data that the diagnosis code of cerebral infarction was 163 in 2000 to 2007 were extracted from A hospital's database and then the data mart was constructed for analysis. Total 2,267 patients illnesses were diagnosed as cerebral infarction and 32,692 cases related diagnosis were extracted. Sequence modeling in Clementine 12.0 program was used to analyze diagnosis of patients with cerebral infarction and 8 meaningful rules were found in this paper. This result could be used as a basic data to make secondary cerebral infarction prevention program and to prevent complication of cerebral infarction.

• Journal of the Korean Data and Information Science Society
• /
• v.20 no.2
• /
• pp.425-433
• /
• 2009

Data mining is the method to find useful information for large amounts of data in database. It is used to find hidden knowledge by massive data, unexpectedly pattern, relation to new rule. We need a data mining tool to explore a lot of information. There are many data mining tools or solutions; E-Miner, Clementine, WEKA, and R. Almost of them are were focused on diversity and general purpose, and they are not useful for laymen. In this paper we design and implement a web-based data mining tool using PHP and WEKA. This system is easy to interpret results and so general users are able to handle. We implement Apriori algorithm of association rule, K-means algorithm of cluster analysis, and J48 algorithm of decision tree.

• Journal of Life Science
• /
• v.22 no.7
• /
• pp.871-879
• /
• 2012

Polyploids are a potentially important germplasm source in seedless citrus breeding program. Seedlessness is one of the most promising traits of commercial mandarin breeds that mandarin triploid hybrids possess permanently. The formation of new constant triploid hybrids can be recovered through diploid species hybridization from the fusion of divalent gametes at low frequencyor intra-and inter-ploidy crosses. However, extensive breeding work based on small $F_1$ hybrid seeds developed is impossible without a very effective aseptic methodology and ploidy event. In this study, in vitro embryo culture was employed to recover natural hybrids from monoembryonic diploid, open-pollinated mandarin. Flow cytometry was used to determine ploidy level. A total of 10,289 seeds were extracted from 792 fruits having approximately 13 seeds per fruit. Average frequency of small seeds developed was 7.1%, while the average frequency of small seeds per fruit were: 8.9% for 'Clementine' 10.2% for 'Harehime' 2.6% for 'Kamja' 3.1% for 'Pyunkyool' 2.8% for 'Sadookam' and 7.0% for 'Wilking' mandarin. Average size of a perfect seed was $49.52{\pm}0.07mm^2$ ('Clementine') while the small seed measured $7.95{\pm}0.04mm^2$ ('Clementine'), which was about 1/6 smaller than the perfect seed. In total, 731 small seeds were obtained and all of them contained only one embryo per seed. The efficiency of 'Clementine' was 14 times higher than 'Wilking' and more than 109 times higher than 'Pyunkyool'. The basic information on spontaneous polyploidy provides for the hybridization of constant triploids and increases the efficiency of conventional cross.

• Journal of the Korea Society of Computer and Information
• /
• v.9 no.3
• /
• pp.109-113
• /
• 2004

This paper is to investigate the efficiency of the process of data preparation for existing data mining tools, and present a design principle for a new efficient data preparation system . We compare the often used data mining tools based on the access method to local and remote databases, and on the exchange of information resources between different computers. The compared data mining tools are Answer Tree, Clementine, Enterprise Miner, and Weka. We propose a design principle for an efficient system for data preparation for data mining on the distributed networks.