• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.14 no.2
• /
• pp.119-127
• /
• 2004

Butterfly valves are popularly used in service in the industrial and water works pipeline systems with large diameter because of its lightweight, simple structure and the rapidity of its manipulation. Sometimes cavitation can occur. resulting in noise, vibration and rapid deterioration of the valve trim, and do not allow further operation. Thus, the monitoring of cavitation is of economic interest and is very importance in industry. This paper proposes a condition monitoring scheme using statistical feature evaluation and support vector machine (SVM) to detect the cavitation conditions of butterfly valve which used as a flow control valve at the pumping stations. The stationary features of vibration signals are extracted from statistical moments. The SVMs are trained, and then classify normal and cavitation conditions of control valves. The SVMs with the reorganized feature vectors can distinguish the class of the untrained and untested data. The classification validity of this method is examined by various signals that are acquired from butterfly valves in the pumping stations and compared the classification success rate with those of self-organizing feature map neural network.

• Journal of the Korea Computer Industry Society
• /
• v.7 no.1
• /
• pp.47-56
• /
• 2006

Proteome patterns reflect the underlying pathological state of a human organ. It is believed that the anomalies or diseases of human organs are identified by the analysis of the pattern. There are many ways to analysis these patterns. <중략> (colon cancer and leukemia dataset) indicates that the proposed method shows better classification performance and more stable results than other single kernel functions.

• Journal of the Korea Computer Industry Society
• /
• v.3 no.8
• /
• pp.1039-1048
• /
• 2002

It is difficult and laborious to distinguish between the original and the plagiarism about the electrical documents or on-line received documents, specially student homeworks because in many case, the homeworks are written on the same subject. Existing methods are not appropriate to solve this problem, which find the most appropriate category using the expression frequency of index term in documents to be classified. In this paper, a new classification method was proposed to distinguish between the original and the plagiarism about documents which were written similarly which is based on the syntagma vector - except the similar syntagma tree structure and non-index term.

• Journal of Korea Multimedia Society
• /
• v.13 no.10
• /
• pp.1506-1513
• /
• 2010

Game Software is the high-value industry that is based on fun elements. To develop Game Software successfully, the method for systematically classifying and searching about fun elements needs. However, fun elements of game are still made by game developers 'experience', and have ambiguities about what are considered at development phase because of difference between viewpoints and definitions about them. We structured 9 groups and 34 fun elements after that 50 fun elements elicited from existing literature are classifies and refines by statistical analysis. And we found a omitted area with the result that the classified elements are applied to Roger Callois's Theory. Finally, we elicited new elements of omitted areas from web site and searched 1 group and 4 fun elements.

• Journal of Korea Multimedia Society
• /
• v.20 no.11
• /
• pp.1759-1767
• /
• 2017

Although Open API has been invigorated by advancements in the software industry, diverse types of malicious code have also increased. Thus, many studies have been carried out to discriminate the behaviors of malicious code based on API data, and to determine whether malicious code is included in a specific executable file. Existing methods detect malicious code by analyzing signature data, which requires a long time to detect mutated malicious code and has a high false detection rate. Accordingly, in this paper, we propose a method that analyzes and detects malicious code using association rule mining and an Naive Bayes classification. The proposed method reduces the false detection rate by mining the rules of malicious and normal code APIs in the PE file and grouping patterns using the DHP(Direct Hashing and Pruning) algorithm, and classifies malicious and normal files using the Naive Bayes.

• Fashion & Textile Research Journal
• /
• v.4 no.1
• /
• pp.71-78
• /
• 2002

The purpose of this study was to classify body types of 800 female junior and high school students based on factor analysis, cluster analysis, and correspondence analysis of 15 photometric measurements of the subjects' lateral body lines. The results are as follows: The skeleton structure, which was represented the back bending by the photometric measurement, was already formed at age of 12 or 13, while the cervical skeleton, the size and inclination of the shoulder, and the degree of the lateral inclination of the upper body and the buttocks continued to grow by the age of 16. A factor analysis of the photometric measurement resulted in the sampling which determined the degree of the back bending, front-bust angle, and lateral view as well as the sampling whose factor represented the cervical inclination. A cluster analysis of the photometric measurement resulted in the four types of classification: Type 1, the straight type comprising 13.3% of the whole population; Type 2, the bent-forward type comprising 39.5%; Type 3, the lean-back type comprising 27.4%; and Type 4, the swayback type comprising 19.1%. Accordingly, the bent-forward type was found to be the dominant type among the four lateral body types.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.39 no.2
• /
• pp.217-232
• /
• 2015

Clothing design considers the concept of human body proportions. This paper proposes an anterior somatotype and body proportion modular by head ratio for 20s to 30s Korean males. Anterior somatotype is classified into 18-types with 13 ratios that consist of 7 heights and 6 widths divided by stature. A total of 18-types are expressed in numerical values that represent the percentage of the stature and geometrical figures represented on the grids one unit is 1% of the stature. The torso is divided by 6 modules that are side neck to shoulder, shoulder to axillary, axillary to waist, waist to navel, navel to hip, and hip to crotch. Head and leg can be estimated as numerical information of stature and torso. Morphological characteristics of anterior somatotype are analyzed by 4 factors based on results and 18-types named by simple signs. We develop a new classification of anterior somatotype that integrate vertical and horizontal characters of body proportions. The use of integrated classification in the clothing industry is expected to increase the clothing fit.

• Journal of Information Technology Services
• /
• v.12 no.2
• /
• pp.373-386
• /
• 2013

The purpose of this research is to develop a model for efficient service R&D investment in government budgeting process. It is necessary to develop an efficient and effective investment model to improve competitiveness of the service industry and national economy. Various existing types of service R&D classification have been reviewed. And object-oriented service R&D request classification types have been derived. A tentative model for evaluating service R&D requests have been developed through extensive discussions on effective methodologies. The model has been refined and revised by four service budgeting experts. The revised and refined checklists and guidelines have been used for 40 real service R&D requests evaluations. As a result, a full model for service R&D evaluation and budgeting has been proved to be useful. Also, a need for more efficient and concise evaluation model has been raised through this evaluation process. A brief model with only 10 checklists has been developed and its usefulness has been proven by pilot test with 10 real service R&D requests. The results of this study can be used for evaluation of service R&D proposals and effective budgeting of R&D requests for improving global competitiveness. Further research is needed for refining the developed evaluation models.

• Journal of Cadastre & Land InformatiX
• /
• v.45 no.1
• /
• pp.45-58
• /
• 2015

The Korean government strives to transform the society from one that stresses academic and qualification to one that stresses individual competencies. National Competency Standards(NCS) has been adopted to this end. However, NCS classifies cadastre into a group with survey and spatial information collection. Such classification limits cadastre to encompass cadastral administration, cadastral survey, geospatial survey, etc. This study reviews current status and implications of NCS, and proposes few solutions: improvement of classification system, introduction of cadastral industry cooperation model, curriculum development based on competency level, unification between NCS developer and learning module writing group, etc.

• Journal of the Korea Safety Management & Science
• /
• v.11 no.1
• /
• pp.27-33
• /
• 2009

A study of fracture to material is getting interest in nuclear and aerospace industry as a viewpoint of safety. Acoustic emission (AE) is a non-destructive testing and new technology to evaluate safety on structures. In previous research continuously, all tensile tests on the pre-defected coupons were performed using the universal testing machine, which machine crosshead was move at a constant speed of 5mm/min. This study is to evaluate an AE source characterization of SM45C steel by using k-nearest neighbor classifier, k-NNC. For this, we used K-means clustering as an unsupervised learning method for obtained multi -variate AE main data sets, and we applied k-NNC as a supervised learning pattern recognition algorithm for obtained multi-variate AE working data sets. As a result, the criteria of Wilk's $\lambda$, D&B(Rij) & Tou are discussed.