• Journal of Information Technology Applications and Management
• /
• v.15 no.2
• /
• pp.1-14
• /
• 2008

The distinguished prosperity of information technologies from great progress of e-business during the last decade has unavoidably made software development for active data mining to discovery hidden predictive information regarding business trends and behavior from vary large databases. Therefore this paper develops an active mining object(ADMO) component, which provides real-time predictive information from web databases. The ADMO component is to extended ADO(ActiveX Data Object) component to active data mining component based on COM(Component Object Model) for application program interface(API). ADMO component development made use of window script component(WSC) based on XML(eXtensible Markup Language). For the purpose of investigating the application environments and the practical schemes of the ADMO component, experiments for diverse practical applications were performed in this paper. As a result, ADMO component confirmed that it could effectively extract the analytic information of classification and aggregation from vary large databases for Web services.

• Journal of KIISE:Software and Applications
• /
• v.31 no.8
• /
• pp.1113-1120
• /
• 2004

This paper proposes a novel hybrid genetic algorithm for the feature selection. Local search operations are devised and embedded in hybrid GAs to fine-tune the search. The operations are parameterized in terms of the fine-tuning power, and their effectiveness and timing requirement are analyzed and compared. Experimentations performed with various standard datasets revealed that the proposed hybrid GA is superior to a simple GA and sequential search algorithms.

• Journal of KIISE:Software and Applications
• /
• v.28 no.1
• /
• pp.64-72
• /
• 2001

결정트리 생성은 일련의 특징값으로 기술된 사례들로부터 분류 지식을 추출하는 학습 방법중의 하나이다. 현장에서 수집되는 사례들은 관측 오류, 주관적인 판단, 불확실성 등으로 인해서 애매하게 주어지는 경우가 많다. 퍼지숫자나 구간값을 사용함으로써 이러한 애매한 데이타의 수치 속성은 쉽게 표현될 수 있다. 이 논문에서는 수치 속성은 보통값 뿐마아니라 퍼지숫자나 구간값을 갖을 수 있고, 비수치 속서은 보통값을 가지며, 데이터의 클래스는 확신도를 기자는 학습 데이터들로 부터, 분류 규칙을 마이닝하기 위한 퍼지 결정트리 생성 방법을 제안한다. 또한 제안한 방법에 의해 생성된 퍼지 결정트리를 사용하여, 새로운 데이터에 대한 클래스를 결정하는 추론 방법을 소개한다. 한편, 제안된 방법의 유용성을 보이기 위해 수행한 실험의 결과를 보인다.

• Journal of KIISE:Software and Applications
• /
• v.30 no.1_2
• /
• pp.51-57
• /
• 2003

For QA systems to return correct answer phrases, it is very important that they correctly and stably analyze users' intention. To satisfy this need, we propose a question type classifier (i.e. asking point identifier) for practical QA systems. The classifier uses a hybrid method that combines a statistical method with a rule-based method according to some heuristic rules. Owing to the hybrid method, the classifier can reduce the time to manually construct rules, yield high precision rate and guarantee robustness. In the experiment, we accomplished 80% accuracy of the question type classification.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.11 no.3
• /
• pp.192-197
• /
• 2003

The ‘AEIPR’(Accelerometer Established Inertial Profiling Reference) method has been applied to measure the road profile. The dynamic road profiling method using AEIPR has the advantages of cost effectiveness, measuring speed and relatively high reliability. However, it is required to improve the double integration algorithm to get the measurement results with the accuracy of hither level. In the first part of this paper, the effective double integration algorithm is suggested and the ‘Road Profiler’ software is developed on the basis of the algorithm. Road profiling tests are performed using the developed ‘Road Profiler’ system on the specially designed tracks for the durability tests and the various types of pubic roads. Test results are shown and evaluated by the international road evaluation indicies and classification.

• Journal of KIISE:Software and Applications
• /
• v.29 no.3
• /
• pp.180-191
• /
• 2002

We present a new text localization method in images using a multi-layer perceptron(MLP) and a multiple continuously adaptive mean shift (MultiCAMShift) algorithm. An automatically constructed MLP-based texture classifier generates a text probability image for various types of images without an explicit feature extraction. The MultiCAMShift algorithm, which operates on the text probability Image produced by an MLP, can place bounding boxes efficiently without analyzing the texture properties of an entire image.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.8
• /
• pp.361-368
• /
• 2016

While dimension reduction methods on high dimensional data have been widely studied, research on dimension reduction methods for high dimensional streaming data with concept drift is limited. In this paper, we review incremental dimension reduction methods and propose a method to apply dimension reduction efficiently in order to improve classification performance on high dimensional streaming data with concept drift.

• Journal of the Korean Society for Precision Engineering
• /
• v.30 no.12
• /
• pp.1295-1301
• /
• 2013

The cause of flow mark defect is known as non-uniform temperature of mold surface when the flow front meets the cold cavity. The exact definition and classification of Flow mark is not clear because the mechanism of flow mark is not figured out till now. Any injection molding analysis software can not predict the flow mark phenomena. To solve weldline and flow mark defects, the gate thickness is reduced to increase the melt front velocity and the melt front velocity of the flow mark area is increased from 82.3mm/s to 104.7mm/s. In addition, the bulk temperature of the flow mark area is increased from $178.3^{\circ}C$to $215.2^{\circ}C$ by adding a cold slug well. The flow mark phenomena can be greatly reduced by increasing the flow front velocity and elevating the bulk temperature.

• Journal of the Korean Society for Precision Engineering
• /
• v.6 no.3
• /
• pp.109-119
• /
• 1989

This paper discusses the system layout of flexible manufacturing system. A definition of flexible manufacturing system has not been necessarily classified yet. An understanding, and an objective of its application are different in a variety of industries. It could be treated as the system adopting flexble-Automation and FMS has been improving as a form of parts maching system. It was thought that the problems of machining function and transfer function were important. This paper introduces parts family and machine groups to increase machining function and transfer function. Parts family and machine tool groups were made up by means of multidimensional dizitizing analysis. A new software algorithm for forming parts family and machine groups has been proposed. Flexible manufacturing system was layout according to the FMS transfer function classification.

• Proceedings of the KSME Conference
• /
• 2000.11a
• /
• pp.590-595
• /
• 2000

On the contrary to the increasing needs of shape qualities, most of quality inspections are carried out by manual or operator's insight. To find the causes of shape inferiority, it is required to gather and analyze the shape measurement data. As a result the winding profile measurement system ($TELE-SCANNER^{(R)}$) is developed to analyze the coiling process and automate the manual measuring process for winding profile of hot-rolled coils. The winding profile measurement system measures and analyzes winding profile shapes of hot-rolled coils, and classifies them into several dominant patterns that are related to normal or abnormal mechanical conditions of down-coiler. The system also contains analysis software to quantify the winding profile shapes and patterns, and to produce statistics to help search the causes of profile shape inferiority.