• International Journal of Computer Science & Network Security
• /
• v.22 no.10
• /
• pp.1-10
• /
• 2022

Nowadays software defect prediction (SDP) is most active research going on in software engineering. Early detection of defects lowers the cost of the software and also improves reliability. Machine learning techniques are widely used to create SDP models based on programming measures. The majority of defect prediction models in the literature have problems with class imbalance and high dimensionality. In this paper, we proposed Centroid and Nearest Neighbor based Class Imbalance Reduction (CNNCIR) technique that considers dataset distribution characteristics to generate symmetry between defective and non-defective records in imbalanced datasets. The proposed approach is compared with SMOTE (Synthetic Minority Oversampling Technique). The high-dimensionality problem is addressed using Ant Colony Optimization (ACO) technique by choosing relevant features. We used nine different classifiers to analyze six open-source software defect datasets from the PROMISE repository and seven performance measures are used to evaluate them. The results of the proposed CNNCIR method with ACO based feature selection reveals that it outperforms SMOTE in the majority of cases.

• International conference on construction engineering and project management
• /
• 2015.10a
• /
• pp.627-628
• /
• 2015

Construction defect which can causes economic damage such as schedule delay, cost overrun is a considerably important factor in construction industry. In general, a construction defect features a difficulty to find out causes precisely because it occurs when several interrelated causes combine. Yet, studies have tried to understand the interrelationships between factors are limited. In addition, despite of a tremendous amount of construction data, it's not still enough to analyze them, but tends to depend on experience or know-how of practitioners. Thus, it is necessary to identify underlying causes in influential factors by utilizing related data. This paper analyses Interrelationships between causal factors using Association Rule Mining to discover root causes of construction defects. Confidence and Lift that can be used for presenting the interrelationships of the causes were extracted from 1241 cases in 30 projects in Korea. It is expected that this paper allows the construction managers to discover key factors and make right decisions to reduce occurrence of construction defects. Furthermore, analysis of interrelationships can improve understanding of structural patterns of construction defects.

• Korean Journal of Construction Engineering and Management
• /
• v.20 no.6
• /
• pp.3-10
• /
• 2019

The entire duration of the long-term continuous construction contract project cannot be expected when calculating the initial budget as the construction of the contract is carried out annually according to the budget composition. In addition, the statutes related to the defect liability and execution of contracts have not been established systematically in relation to the contract. Therefore, there are many problems at the actual construction site with regard to the defect liability or the performance of the contract in relation to the contract. In this study, the following improvement directions were presented for the efficient operation of the contracts: First, the defect liability is legal and should be specified in an Act rather than an enforcement decree. Second, if the parties to the contract vary in the following order in the contract, the special agreement should be specified in the enforcement decree. Third, in the event of an indirect cost due to the extension of the period of the long-term continuous work, the contingency items of the total project cost management policy should be utilized. Fourth, in the case of general construction contract conditions, clauses related to the purchase of the premium of the CAR, inspection, taking over, defect repair, and defect inspection shall be supplemented.

• Journal of KIISE:Software and Applications
• /
• v.33 no.7
• /
• pp.605-614
• /
• 2006

The success of a software development project can be determined by the use of QCD. And as a software's size and complexity increase, the importance of early quality assurance rises. Therefore, more effort should be given to prevention, as opposed to correction. In order to provide a framework for the prevention of defects, defect detection activities such as peer review and testing, along with analysis of previous defects, is required. This entails a systematization and use of quality data from previous development efforts. FMEA, which is utilized for system safety assurance, can be applied as a means of software defect prevention. SW-FMEA (Software Failure Mode Effect Analysis) attempts to prevent defects by predicting likely defects. Presently, it has been applied to requirement analysis and design. SW-FMEA utilizes measured data from development activities, and can be used for defect prevention on both the development and management sides, for example, in planning, analysis, design, peer reviews, testing, risk management, and so forth. This research discusses about related methodology and proposes defect prevention model based on SW-FMEA. Proposed model is extended SW-FMEA that focuses on system analysis and design. The model not only supports verification and validation effectively, but is useful for reducing defect detection.

• Current Photovoltaic Research
• /
• v.4 no.3
• /
• pp.124-129
• /
• 2016

Recently industry has voiced a need for optimally designing the production process of low-cost, high-quality ingots by improving productivity and reducing production costs with the Czochralski process. Crystalline defect control is important for the production of high-quality ingots. Also oxygen is one of the most important impurities that influence crystalline defects in single crystals. Oxygen is dissolved into the silicon melt from the silica crucible and incorporated into the crystalline a far larger amount than other additives or impurities. Then it is eluted during the cooling process, there by causing various defect. Excessive quantities of oxygen degrade the quality of silicone. However an appropriate amount of oxygen can be beneficial. because it eliminates metallic impurities within the silicone. Therefore, when growing crystals, an attempt should be made not to eliminate oxygen, but to uniformly maintain its concentration. Thus, the control of oxygen concentration is essential for crystalline growth. At present, the control of oxygen concentration is actively being studied based on the interdependence of various factors such as crystal rotation, crucible rotation, argon flow, pressure, magnet position and magnetic strength. However for methods using a magnetic field, the initial investment and operating costs of the equipment affect the wafer pricing. Hence in this study simulations were performed with the purpose of producing low-cost, high-quality ingots through the development of a process to optimize oxygen concentration without the use of magnets and through the following. a process appropriate to the defect-free range was determined by regulating the pulling rate of the crystals.

• Journal of the Korea Institute of Building Construction
• /
• v.15 no.2
• /
• pp.209-215
• /
• 2015

This study was conducted to analyze the actual utilization rate of the deposit for defect repair of apartment complexes and its influential factors. We analyzed the data on enforced defect deposit cases by using one-sample t-test, Pearson's correlation analysis, and simple linear regression analysis. The difference between the deposit amount specified and the enforcement amount actually disbursed was found to about 0.51%. The change rates for short-term costs amounted approximately to $839KRW/m^2$ and 130,000 KRW/household per year, and those for long-term costs were $647KRW/m^2$ and 123,207 KRW/household per year. The results warrant the need for further research on establishing a deposit amount based on actual statistical data.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.3
• /
• pp.209-220
• /
• 2023

Recently, defects that occurred during the construction of apartment houses have become a social issue. Defects in apartment houses lead to waste of resources and economic loss, causing psychological and physical damage to customers, and a decrease in reliability and financial loss to construction companies. The purpose of this study was to analyze the impact of defect occurrence according to the difference in project management level in the apartment housing construction stage, and to investigate the extent to which the project manager's experience affects the defect occurrence rate. For the empirical analysis of the study, statistical analysis was conducted using data collected from 130 actual projects. The results of the analysis showed that schedule management, cost management, and quality management had a positive effect on reducing the defect occurrence rate in the execution stage of apartment housing construction, while human resource management productivity had a negative effect. This study theoretically demonstrated the importance of project management, and in practice, showed that schedule management, cost management, and quality management should be faithfully performed in the execution stage to reduce the rate of defects after project completion. It was also suggested that hiring an experienced project manager would help reduce project defects.

• The KIPS Transactions:PartD
• /
• v.15D no.3
• /
• pp.321-326
• /
• 2008

The software defects that are not found in the course of a project frequently appear during the conduct of the maintenance procedure after the complete development of the software. As the frequency of surfacing of defects during the maintenance procedure increases, the cost likewise increases, and the quality and customer reliability decreases. The defect rate will go down only if cause analysis and process improvement are constantly performed. This study embodies the defect tracking system (DTS) by considering the Pareto principle: that most defects are repetitions of defects that have previously occurred. Based on the records of previously occurring defects found during the conduct of a maintenance procedure, DTS tracks the causes of the software defects and provides the developer, operator, and maintenance engineer with the basic data for the improvement of the software concerned so that the defect will no longer be manifested or repeated. The basic function of DTS is to analyze the defect type, provide the measurement index for it, and aggregate the program defect type. Doing these will pave the way for the full correction of all the defects of a software as it will enable the defect correction team to check the measured defect type. When DTS was applied in the software configuration management system of the W company, around 65% of all its software defects were corrected.

• Journal of Navigation and Port Research
• /
• v.28 no.1
• /
• pp.43-49
• /
• 2004

Defects inspection of commodities are very important with those design and manufacturing process and essential to strengthen the competitiveness of those. If on-line automatic defects detection is performed without damaging to products, the production cost shall be curtailed through the reducing man-power, economical management of Q.C(Quality Control). In this paper, it is suggested three spatial filtering methods which can extract the necessary information in case of defects being on the surface of object like iron plate. In addition, the dependence of filtering characteristics on parameters such as the pitch and width of slits is analyzed and the surface defect detection system is constructed. Several experiments were carried out for determining the adequate spatial filtering method through comparing and analyzing effects of parameters like defect's size and shape, intensity of light, noise of coherent source and slit number.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.35 no.6
• /
• pp.594-602
• /
• 2022

Cast-resin transformers are widely installed in various electrical power systems because of their low operating cost and low influence on external environmental factors. However, when they have an internal defect during the manufacturing process or operation, a partial discharge (PD) occurs, and eventually destroys the insulation. In this paper, a Rogowski-type PD sensor was studied to replace commercial PD sensors used for the insulation diagnosis of power apparatus. The proposed PD sensor was manufactured with four different types of PCB-based winding structures, and it was analyzed in terms of the detection characteristics for standard calibration pulses and the changes of the output voltage according to the distance. The output increased linearly in accordance with the applied discharge amount. It was confirmed that the hexagon structure sensor had the highest sensitivity, because the winding cross-sectional area of the sensor was larger than others. In addition, as the distance from the defect increased, the output voltage of the sensors decreased by 7.32% on average. It was also confirmed that the attenuation rate according to the distance decreased as the input discharge amount increased. For the application of this new type sensor, PD electrode system was designed to simulate the void defect. Waveforms and PRPD patterns measured by the proposed PD sensors at DIV and 120% of DIV were the same as the results measured by MPD 600 based on IEC 60270. The proposed PD sensors can be installed on the inner wall of the transformer tank by coating its surfaces with a non-conductive material; therefore, it is possible to detect internal defects more effectively at a closer distance from the defect than the conventional sensors.