• 한국컴퓨터정보학회논문지
• /
• 제23권9호
• /
• pp.81-86
• /
• 2018

Software defect severity is very important in projects with limited historical data or new projects. But general software defect prediction is very difficult to collect the label information of the training set and cross-project defect prediction must have a lot of data. In this paper, an unclassified data set with defect severity is clustered according to the distribution ratio. And defect severity-based prediction model is proposed by way of labeling. Proposed model is applied CLAMI in JM1, PC4 with the least ambiguity of defect severity-based NASA dataset. And it is evaluated the value of ACC compared to original data. In this study experiment result, proposed model is improved JM1 0.15 (15%), PC4 0.12(12%) than existing defect severity-based prediction models.

• 산업경영시스템학회지
• /
• 제27권2호
• /
• pp.10-16
• /
• 2004

Data mining technique is the exploration and analysis, by automatic or semiautomatic means, of large quantities of data in order to discover meaningful patterns and rules. This paper uses a data mining technique for the prediction of defect types in manufacturing Process. The Purpose of this Paper is to model the recognition of defect type Patterns and Prediction of each defect type before it occurs in manufacturing process. The proposed model consists of data handling, defect type analysis, and defect type prediction stages. The performance measurement shows that it is higher in prediction accuracy than logistic regression model.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권11호
• /
• pp.4028-4042
• /
• 2021

Aiming at the problem of software defect prediction difficulty caused by insufficient software defect marker samples and unbalanced classification, a semi-supervised software defect prediction model based on a tri-training algorithm was proposed by combining feature normalization, over-sampling technology, and a Tri-training algorithm. First, the feature normalization method is used to smooth the feature data to eliminate the influence of too large or too small feature values on the model's classification performance. Secondly, the oversampling method is used to expand and sample the data, which solves the unbalanced classification of labelled samples. Finally, the Tri-training algorithm performs machine learning on the training samples and establishes a defect prediction model. The novelty of this model is that it can effectively combine feature normalization, oversampling techniques, and the Tri-training algorithm to solve both the under-labelled sample and class imbalance problems. Simulation experiments using the NASA software defect prediction dataset show that the proposed method outperforms four existing supervised and semi-supervised learning in terms of Precision, Recall, and F-Measure values.

• 반도체디스플레이기술학회지
• /
• 제19권2호
• /
• pp.26-30
• /
• 2020

In this paper, we studied the problem if the experiment number occurring in order to identify defect in scaffold. We need to change each of the 5 print factor to predict defect when printing disk type scaffold using FDM 3d printer. So then the number of scaffold print will be more than 100,000 times. This experiment number is difficult to perform in the field. In order to solve this problem, we have produced a prediction model based on machine learning multiple linear regression using print conditions and defect scaffold data for print conditions. The prediction model produced was verified through experiments. The verification confirmed that the error was less than 0.5 %. We have confirmed that satisfied within the target margin of error 5 %.

• 반도체디스플레이기술학회지
• /
• 제19권4호
• /
• pp.59-64
• /
• 2020

In this paper, we found the solution using data based machine learning regression method to check the pore shape, to solve the problem of the experiment quantity occurring when producing scaffold with the 3d printer. Through experiments, we learned secured each print condition and pore shape. We have produced the scaffold from scaffold pore shape defect prediction model using multiple linear regression method. We predicted scaffold pore shapes of unsecured print condition using the manufactured scaffold pore shape defect prediction model. We randomly selected 20 print conditions from various predicted print conditions. We print scaffold five times under same print condition. We measured the pore shape of scaffold. We compared printed average pore shape with predicted pore shape. We have confirmed the prediction model precision is 99 %.

• 정보처리학회 논문지
• /
• 제13권5호
• /
• pp.236-242
• /
• 2024

소프트웨어 결함 예측(SDP)은 오류가 발생할 가능성이 있는 모듈을 사전에 식별하여 소프트웨어 개발의 효율을 높이고 있다. SDP에서의 주과제는 예측 성능을 향상시키는것에 있다. 최근 연구에서는 딥러닝 기법이 소프트웨어 결함 예측(SDP) 분야에 적용되어 있으며, 특히 구조화된 데이터를 분석하는 데 뛰어난 성능을 보이고 있는 SAINT 모델이 주목받고 있다. 본 연구는 SAINT 모델을 다른 주요 모델(XGBoost, Random Forest, CatBoost)과 비교하여 SDP에 적용 가능한 최신 딥러닝 기법을 조사하였다. SAINT는 일관되게 우수한 성능을 보여주며 결함 예측 정확도 향상에 효과적임을 입증하였다. 이 연구 결과는 실용적인 소프트웨어 개발 상황에서 결함 예측 방법론을 발전시킬 수 있는 SAINT의 잠재력을 강조하며, 교차 검증, 특성 스케일링, 비교 분석 등을 포함한 철저한 방법론을 통해 수행되었다.

• 한국정보과학회논문지:컴퓨팅의 실제 및 레터
• /
• 제15권12호
• /
• pp.943-947
• /
• 2009

소프트웨어의 결함을 예측하고 검증과 확인 활동을 통하여 효율적인 자원을 관리하기 위하여 많은 연구에서 결함 예측 모형을 제안하고 있다. 하지만 기존의 연구는 예측율이 최대 효과를 보이는 임계치에 결함 예측 모형의 예측율을 평가하고 있다. 이는 측정 시스템의 결함 정보를 알고 있는 가정하에서 평가가 이루어지는 것이기 때문에 실제 결함 정보를 알 수 없는 시스템에서는 최적의 임계치를 결정할 수 없다. 그러므로 임계치 선정의 중요성을 확인하기 위하여 본 연구에서는 결함 예측 모형으로 타 시스템의 결함을 예측하는 비교 실험을 하였다. 실험은 기존에 제안된 3개의 결함 예측 모형과 4개의 시스템을 대상으로 하였고 결함 예측 모형의 임계치별 예측의 정확성을 비교하였다. 실험결과에서 임계치는 모형의 예측율과 높은 관련이 있었지만 실제 결함 정보가 확인 안 되는 시스템에 대하여 결함을 예측하는 경우에는 임계치를 선정할 수 없음을 확인하였다. 따라서 결함 예측 모형을 타 시스템에 적용하기 위하석 임계치 선정에 관한 추후 연구가 필요함을 확인하였다.

• 대한산업공학회지
• /
• 제21권3호
• /
• pp.371-385
• /
• 1995

The yield of semiconductor chips is dependent not only on the average defect density but also on the distribution of defects over a wafer. The distribution of defects leads to consider a cluster index. This paper briefly reviews the existing yield prediction models ad proposes a new cluster index, which utilizes the information about the defect location on a wafer in terms of the coefficient of variation. An extensive simulation is performed under a variety of defect distributions and a yield prediction model is derived through the regression analysis to relate the yield with the proposed cluster index and the average number of defects per chip. The performance of the proposed simulation-based yield prediction model is compared with that of the well-known negative binomial model.

• 한국소성가공학회:학술대회논문집
• /
• 한국소성가공학회 2009년도 춘계학술대회 논문집
• /
• pp.94-97
• /
• 2009

Cast defect in large steel ingots are estimated in quality and compared each other cast conditions on simulation results by now. The cast defects, micro-crack, shrinkage, pin hole which are predictable in simulation with a reasonable accuracy. In this study, 15 ton steel ingot casting was simulated for solidification model and cast defect prediction. And the real cast was carried out in a foundry for the compeer to the simulation results, the cast defect prediction. Also, the quantity of predicted defect was tried to measuring with the defect mach counting for the various simulated cast conditions. The defect quantity work was used to find the optimized cast condition in DOE(design of experiment) procedure.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2022년도 가을 학술논문 발표대회
• /
• pp.223-224
• /
• 2022

The occurrence of defect, one of the major risk elements, gives rise to construction delays and additional costs. Although construction companies generally prefer to use a method of identifying and classifying the causes of defects, a system for predicting the rise of defects becomes important matter to reduce this harmful issue. However, the currently used methods are kinds of reactive systems that are focused on the defects which occurred already, and there are few studies on the occurrence of defects with prediction systems. This paper is about preliminary study on the development of judgemental algorithm that informs us whether additional works related to defect issue are needed or not. Among machine learning techniques, deep neural network was utilized as prediction model which is a major component of algorithm. It is the most suitable model to be applied to the algorithm when there are 8 hidden layers and the average number of nodes in each hidden layer is 70. Ultimately, the algorithm can identify and defects that may arise in later and contribute to minimize defect frequency.