• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2005.06a
• /
• pp.143-146
• /
• 2005

Many data mining techniques have been proved useful in revealing important patterns from large data sets. Especially, data mining techniques play an important role in a customer data analysis in a financial industry and an electronic commerce. Also, there are many data mining related research papers in a semiconductor industry and an automotive industry. In addition, data mining techniques are applied to the bioinformatics area. To satisfy customers' various requirements, each industry should develop new processes with more accurate production criteria. Also, they spend more money to guarantee their products' quality. In this manner, we apply data mining techniques to the production-related data such as a test data, a field claim data, and POP (point of production) data in the automotive parts industry. Data collection and transformation techniques should be applied to enhance the analysis results. Also, we classify various types of manufacturing processes and proposed an analysis scheme according to the type of manufacturing process. As a result, we could find inter- or intra-process relationships and critical features to monitor the current status of the each process. Finally, it helps an industry to raise their profit and reduce their failure cost.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.31 no.1B
• /
• pp.21-27
• /
• 2011

When execute runoff forecasting, can not remove perfectly uncertainty of forecasting results. But, reduce uncertainty by various techniques analysis. This study applied various forecasting techniques for runoff prediction's accuracy elevation in Gongju basin. statics techniques is ESP, Period Average & Moving average, Exponential Smoothing, Winters, Auto regressive moving average process. Authoritativeness estimation with results of runoff forecasting by each techniques used MAE (Mean Absolute Error), RMSE (Root Mean Squared Error), RRMSE (Relative Root Mean Squared Error), Mean Absolute Percentage Error (MAPE), TIC (Theil Inequality Coefficient). Result that use MAE, RMSE, RRMSE, MAPE, TIC and confirm improvement effect of runoff forecasting, ESP techniques than the others displayed the best result.

• Nuclear Engineering and Technology
• /
• v.44 no.4
• /
• pp.421-428
• /
• 2012

Analog instrument and control systems in nuclear power plants have recently been replaced with digital systems for safer and more efficient operation. Digital instrument and control systems have adopted various fault-tolerant techniques that help the system correctly and safely perform the specific required functions regardless of the presence of faults. Each fault-tolerant technique has a different inspection period, from real-time monitoring to monthly testing. The range covered by each faulttolerant technique is also different. The digital instrument and control system, therefore, adopts multiple barriers consisting of various fault-tolerant techniques to increase the total fault detection coverage. Even though these fault-tolerant techniques are adopted to ensure and improve the safety of a system, their effects on the system safety have not yet been properly considered in most probabilistic safety analysis models. Therefore, it is necessary to develop an evaluation method that can describe these features of digital instrument and control systems. Several issues must be considered in the fault coverage estimation of a digital instrument and control system, and two of these are addressed in this work. The first is to quantify the fault coverage of each fault-tolerant technique implemented in the system, and the second is to exclude the duplicated effect of fault-tolerant techniques implemented simultaneously at each level of the system's hierarchy, as a fault occurring in a system might be detected by one or more fault-tolerant techniques. For this work, a fault injection experiment was used to obtain the exact relations between faults and multiple barriers of faulttolerant techniques. This experiment was applied to a bistable processor of a reactor protection system.

• Proceedings of the Korea Contents Association Conference
• /
• 2008.05a
• /
• pp.653-657
• /
• 2008

Industry related to digital contents is growing rapidly and is noticed as a higher value-added business. In digital reflex contents industry, computer graphics techniques are core techniques. Because they make production or scene that is difficult to photograph possible with real camera, expand a range of contents making. Lately, computer graphics techniques apply various fields such as blockbuster movie, game, educational contents, simulation etc, and there are many studies about movement of each object made up of contents or automation of object change. This paper shows the process of fishes growth, from spawn to a full-grown fish making use of 3D morphing techniques and want to plan fish growth process system that can know difference between fishes that are applied to 3D morphing techniques and normal full-grown fishes according to various environmental factors that affect growth.

• Journal of Information Processing Systems
• /
• v.16 no.4
• /
• pp.915-934
• /
• 2020

Software refactoring is a process to restructure an existing software code while keeping its external behavior the same. Currently, various refactoring techniques are being used to develop more readable and less complex codes by improving the non-functional attributes of software. Refactoring can further improve code maintainability by applying various techniques to the source code, which in turn preserves the behavior of code. Refactoring facilitates bug removal and extends the capabilities of the program. In this paper, an exhaustive review is conducted regarding bad smells present in source code, applications of specific refactoring methods to remove that bad smell and its effect on software quality. A total of 68 studies belonging to 32 journals, 31 conferences, and 5 other sources that were published between the years 2001 and 2019 were shortlisted. The studies were analyzed based on of bad smells identified, refactoring techniques used, and their effects on software metrics. We found that "long method", "feature envy", and "data class" bad smells were identified or corrected in the majority of studies. "Feature envy" smell was detected in 36.66% of the total shortlisted studies. Extract class refactoring approach was used in 38.77% of the total studies, followed by the move method and extract method techniques that were used in 34.69% and 30.61% of the total studies, respectively. The effects of refactoring on complexity and coupling metrics of software were also analyzed in the majority of studies, i.e., 29 studies each. Interestingly, the majority of selected studies (41%) used large open source datasets written in Java language instead of proprietary software. At the end, this study provides future guidelines for conducting research in the field of code refactoring.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.77-91
• /
• 2022

Various monitoring systems have been implemented in civil infrastructure to ensure structural safety and integrity. In long-term monitoring, these systems generate a large amount of data, where anomalies are not unusual and can pose unique challenges for structural health monitoring applications, such as system identification and damage detection. Therefore, developing efficient techniques is quite essential to recognize the anomalies in monitoring data. In this study, several machine learning techniques are explored and implemented to detect and classify various types of data anomalies. A field dataset, which consists of one month long acceleration data obtained from a long-span cable-stayed bridge in China, is employed to examine the machine learning techniques for automated data anomaly detection. These techniques include the statistic-based pattern recognition network, spectrogram-based convolutional neural network, image-based time history convolutional neural network, image-based time-frequency hybrid convolution neural network (GoogLeNet), and proposed ensemble neural network model. The ensemble model deliberately combines different machine learning models to enhance anomaly classification performance. The results show that all these techniques can successfully detect and classify six types of data anomalies (i.e., missing, minor, outlier, square, trend, drift). Moreover, both image-based time history convolutional neural network and GoogLeNet are further investigated for the capability of autonomous online anomaly classification and found to effectively classify anomalies with decent performance. As seen in comparison with accuracy, the proposed ensemble neural network model outperforms the other three machine learning techniques. This study also evaluates the proposed ensemble neural network model to a blind test dataset. As found in the results, this ensemble model is effective for data anomaly detection and applicable for the signal characteristics changing over time.

• Asia pacific journal of information systems
• /
• v.25 no.3
• /
• pp.579-596
• /
• 2015

Many studies have focused on the prediction of corporate credit rating using various data mining techniques. One of the most frequently used algorithms is support vector machines (SVM), and recently, novel techniques such as SVM+ and SVM+MTL have emerged. This paper intends to show the applicability of such new techniques to multi-classification and corporate credit rating and compare them with conventional SVM regarding prediction performance. We solve multi-class SVM+ and SVM+MTL problems by constructing several binary classifiers. Furthermore, to demonstrate the robustness and outstanding performance of SVM+MTL algorithm over other techniques, we utilized four typical multi-class processing methods in our experiments. The results show that SVM+MTL outperforms both conventional SVM and novel SVM+ in predicting corporate credit rating. This study contributes to the literature by showing the applicability of new techniques such as SVM+ and SVM+MTL and the outperformance of SVM+MTL over conventional techniques. Thus, this study enriches solving techniques for addressing multi-class problems such as corporate credit rating prediction.

• KIEAE Journal
• /
• v.2 no.1
• /
• pp.11-19
• /
• 2002

This Study aims to find out the planning aspects and detailed techniques in terms of concept of the Ecological Industrial Parks. It consists of the three parts : Firstly, according to theoretical review, this study gives a definition of the concept of ecological industrial parks. Secondly, it institutes planning aspects of ecological industrial parks based on the main concept. Thirdly, 8 case studies show us analysis of detailed techniques used each planning aspects. Ecological industrial parks mean industrial systems which make energy and substance circulated in order to reduce environmental pollutions inside and outside of park like natural ecosystem. To actualize ecological industrial parks, we have to adopt 3 planning aspects which are energy and substance recycling system, environmentally-friendly site planning based on ecology concept, constructing of ecological production and management. In case study, detailed techniques from each planning aspects are shown in table 8. As a result of case study, detailed techniques about planning of energy and substance recycling system is accommodated most. On the other hand, environmentally-friendly site planning techniques based on ecological concept is used passively. And detailed techniques about constructing of ecological production and management are very various as each cases. Finally, in terms of analysis, this study shows us appliable planning when we develop domestic Ecological industrial parks.

• Journal of Power Electronics
• /
• v.8 no.2
• /
• pp.171-180
• /
• 2008

One of the major problems in electric power quality is the harmonic contents. There are several methods of indicating the quantity of harmonic contents. The most widely used measure is the total harmonic distortion (THD). Various switching techniques have been used in static converters to reduce the output harmonic content. This paper presents and compares the two harmonic optimization techniques, known as optimal minimization of the total harmonic distortion (OMTHD) technique and optimized harmonic stepped-waveform (OHSW) technique used in multi-level inverters with unequal dc sources. Both techniques are very effective and efficient for improving the quality of the inverter output voltage. First, we describe briefly the cascaded H-bridge multi-level inverter structure. Then, we present the switching algorithm for the inverter based on OHSW and OMTHD techniques. Finally, the results obtained for the two techniques are analyzed and compared. The results verify the effectiveness of the both techniques in multi-level voltage-source inverter with non-equal dc sources, clarifying the advantages of each technique.

• The Journal of Korean Medical History
• /
• v.36 no.2
• /
• pp.61-76
• /
• 2023

Objectives: This study was designed to introduce distinctive Do-In techniques among the many found in the book 'Euibangyoochi'. Methods: 'Do-In section' of Euibangyoochi was translated, and distinctive Do-In techniques were extracted from it. These techniques were categorized as 'using specific actions', 'using vocal sounds'. Results: The Do-In methods in the 'Do-In section' of Euibangyoochi were categorized. The first category includes Do-In methods that involve specific actions, such as 'Myung Chun Go', 'Go-chi Beob', 'Ak-go Beob', 'Gun-yok Beob', and 'An-ma Beob'. The second category is the Do-In technique using vocal sounds, known as 'Yuk Ja Gyeol'. Conclusion: The 'Do-In section' of Euibangyoochi contains numerous Do-In techniques recorded in various texts. Among them, techniques with specified names were extracted and categorized. While there are currently no studies on the actual effects of these techniques, it is hoped that future research can validate their efficacy.