• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.9
• /
• pp.339-348
• /
• 2021

In recent software defect prediction research, defect prediction between cross projects and cross-version projects are actively studied. Cross-version defect prediction studies assume WP(Within-Project) so far. However, in the CV(Cross-Version) environment, the previous work does not consider the distribution difference between project versions is important. In this study, we propose an automated Bayesian optimization framework that considers distribution differences between different versions. Through this, it automatically selects whether to perform transfer learning according to the difference in distribution. This framework is a technique that optimizes the distribution difference between versions, transfer learning, and hyper-parameters of the classifier. We confirmed that the method of automatically selecting whether to perform transfer learning based on the distribution difference is effective through experiments. Moreover, we can see that using our optimization framework is effective in improving performance and, as a result, can reduce software inspection effort. This is expected to support practical quality assurance activities for new version projects in a cross-version project environment.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2016.05a
• /
• pp.42-43
• /
• 2016

해양분야에 e-Navigation 전략이 도입되면서 안전한 항행 지원을 위해 기존의 제품을 재설계 하거나 새로운 제품 설계가 이루어지고 있다. 항행 지원에 소프트웨어시스템의 영향이 커지고 있기 때문에 안전하고 견고한 시스템의 설계는 매우 중요하며, 이를 위해 높은 품질의 확보가 필요하다. IMO에서는 이러한 제품 설계를 위해 적절한 품질을 보장하고 목적에 맞는 제품 설계에 대한 내용을 담고 있는 소프트웨어 품질 보증 및 인간 중심 설계 가이드라인을 공식 승인하였다. 가이드라인에서 품질 보증은 제품 품질, 데이터 품질, 사용상 품질을 만족할 것을 포함한다. 다양한 품질 속성을 만족하기 위해서는 품질 속성간의 우선순위화가 필요하다. 본 논문에서는 안전하고 견고한 소프트웨어 시스템을 위해 AHP기법을 이용하여 제품에 따른 품질 속성을 우선순위화 하고, 전 개발 단계에 걸쳐 품질 속성이 반영되고 평가 될 수 있도록 한다.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2015.10a
• /
• pp.43-44
• /
• 2015

AIS-ASM is a one of the study to provide a variety of maritime safety information as well as ship's position and navigational information that is their own function since 2004. This study aims to reduce the marine officer's workload through automating marine officer's mandatory reporting items using the one of the next maritime digital communication technology (ASM2.0). For this purpose, we designed and experimented of the ASM2.0 protocol through analyzing a domestic regulation about passenger flight and AIS-ASM message.

• Progress in Medical Physics
• /
• v.26 no.3
• /
• pp.168-177
• /
• 2015

For evaluating the treatment planning accurately, the quality assurance for treatment planning is recommended when patients were treated with IMRT which is complex and delicate. To realize this purpose, treatment plan quality assurance software can be used to verify the delivered dose accurately before and after of treatment. The purpose of this study is to evaluate the accuracy of treatment plan quality assurance software for each IMRT plan according to MLC DLG (dosimetric leaf gap). Novalis Tx with a built-in HD120 MLC was used in this study to acquire the MLC dynalog file be imported in MobiusFx. To establish IMRT plan, Eclipse RTP system was used and target and organ structures (multi-target, mock prostate, mock head/neck, C-shape case) were contoured in I'mRT phantom. To verify the difference of dose distribution according to DLG, MLC dynalog files were imported to MobiusFx software and changed the DLG (0.5, 0.7, 1.0, 1.3, 1.6 mm) values in MobiusFx. For evaluation dose, dose distribution was evaluated by using 3D gamma index for the gamma criteria 3% and distance to agreement 3 mm, and the point dose was acquired by using the CC13 ionization chamber in isocenter of I'mRT phantom. In the result for point dose, the mock head/neck and multi-target had difference about 4% and 3% in DLG 0.5 and 0.7 mm respectively, and the other DLGs had difference less than 3%. The gamma index passing-rate of mock head/neck were below 81% for PTV and cord, and multi-target were below 30% for center and superior target in DLGs 0.5, 0.7 mm, however, inferior target of multi-target case and parotid of mock head/neck case had 100.0% passing rate in all DLGs. The point dose of mock prostate showed difference below 3.0% in all DLGs, however, the passing rate of PTV were below 95% in 0.5, 0.7 mm DLGs, and the other DLGs were above 98%. The rectum and bladder had 100.0% passing rate in all DLGs. As the difference of point dose in C-shape were 3~9% except for 1.3 mm DLG, the passing rate of PTV in 1.0 1.3 mm were 96.7, 93.0% respectively. However, passing rate of the other DLGs were below 86% and core was 100.0% passing rate in all DLGs. In this study, we verified that the accuracy of treatment planning QA system can be affected by DLG values. For precise quality assurance for treatment technique using the MLC motion like IMRT and VMAT, we should use appropriate DLG value in linear accelerator and RTP system.

• KIISE Transactions on Computing Practices
• /
• v.21 no.9
• /
• pp.616-621
• /
• 2015

Recently developed software systems have many components, and their complexity is thus increasing. Last year, about 375 bug reports in one day were reported to a software repository in Eclipse and Mozilla open source projects. With so many bug reports submitted, developers' time and efforts have increased unnecessarily. Since the bug severity is manually determined by quality assurance, project manager or other developers in the general bug fixing process, it is biased to them. They might also make a mistake on the manual decision because of the large number of bug reports. Therefore, in this study, we propose an approach of bug severity prediction to solve these problems. First, we find similar topics within a new bug report and reduce the candidate reports of the topic by using the meta field of the bug report. Next, we train the reduced reports by applying Naive Bayes Multinomial. Finally, we predict the severity of the new bug report. We compare our approach with other prediction algorithms by using bug reports in open source projects. The results show that our approach better predicts bug severity than other algorithms.

• The Journal of Korean Society for Radiation Therapy
• /
• v.26 no.2
• /
• pp.305-312
• /
• 2014

Purpose : The purpose of this study is to analyze the mechanical and leaf speed accuracy of the dynamic multileaf collimator (DMLC) and determine the appropriate period of quality assurance (QA). Materials and Methods : The quality assurance of the DMLC equipped with Millennium 120 leaves has been performed total 92 times from January 2012 to June 2014. The the accuracy of leaf position and isocenter coincidence for MLC were checked using the graph paper and Gafchromic EBT film, respectively. The stability of leaf speed was verified using a test file requiring the leaves to reach maximum leaf speed during the gantry rotation. At the end of every leaf speed QA, dynamic dynalog files created by MLC controller were analyzed using dynalog file viewer software. This file concludes the information about the planned versus actual position for all leaves and provides error RMS (root-mean square) for individual leaf deviations and error histogram for all leaf deviations. In this study, the data obtained from the leaf speed QA were used to screen the performance degradation of leaf speed and determine the need for motor replacement. Results : The leaf position accuracy and isocenteric coincidence of MLC was observed within a tolerance range recommanded from TG-142 reports. Total number of motor replacement were 56 motors over whole QA period. For all motors replaced from QA, gradually increased patterns of error RMS values were much more than suddenly increased patterns of error RMS values. Average error RMS values of gradually and suddenly increased patterns were 0.298 cm and 0.273 cm, respectively. However, The average error RMS values were within 0.35 cm recommended by the vendor, motors were replaced according to the criteria of no counts with misplacement > 1 cm. On average, motor replacement for gradually increased patterns of error RMS values 22 days. 28 motors were replaced regardless of the leaf speed QA. Conclusion : This study performed the periodic MLC QA for analyzing the mechanical and leaf speed accuracy of the dynamic multileaf collimator (DMLC). The leaf position accuracy and isocenteric coincidence showed whthin of MLC evaluation is observed within the tolerance value recommanded by TG-142 report. Based on the result obtained from leaf speed QA, we have concluded that QA protocol of leaf speed for DMLC was performed at least bimonthly in order to screen the performance of leaf speed. The periodic QA protocol can help to ensure for delivering accurate IMRT treatment to patients maintaining the performance of leaf speed.

• Progress in Medical Physics
• /
• v.21 no.4
• /
• pp.340-347
• /
• 2010

DQA, a patient specific quality assurance in tomotherapy, is usually performed using an ion chamber and a film. The result of DQA is analysed with the treatment planning system called Tomo Planning Station (TomoPS). The two-dimensional dose distribution of film measurement is compared with the dose distribution calculated by TomoPS using the ${\gamma}$-index analysis. In ${\gamma}$-index analysis, the criteria such as 3%/3 mm is used and we verify that whether the rate of number of points which pass the criteria (pass rate) is within tolerance. TomoPS does not provide any quantitative information regarding the pass rate. In this work, a method to get the pass rate of the ${\gamma}$-index analysis was suggested and a software PassRT which calculates the pass rate was developed. The results of patient specific QA of the intensity modulated radiation therapy measured with I'mRT MatriXX (IBA Dosimetry, Germany) and DQA of tomotherapy measured with film were used to verify the proposed method. The pass rate was calculated using PassRT and compared with the pass rate calculated by OmniPro I'mRT (IBA Dosimetry, Germany). The average difference between the two pass rates was 0.00% for the MatriXX measurement. The standard deviation and the maximum difference were 0.02% and 0.02%, respectively. For the film measurement, average difference, standard deviation and maximum difference were 0.00%, 0.02% and 0.02%, respectively. For regions of interest smaller than $24.3{\times}16.6cm^2$ the proposed method can be used to calculate the pass rate of the gamma index analysis to one decimal place and will be helpful for the more accurate DQA in tomotherapy.

• Journal of Information Technology Services
• /
• v.14 no.2
• /
• pp.129-142
• /
• 2015

The purpose of this study is to suggest an effective regression testing method in order to minimize the scope of test resulting from the modification of software and to prevent mismatch of test case and test objects. As a way to improve the efficiency of regression testing which uses a change-centric testing technique, the method flow is analyzed and grasped through a static analysis based on source code in order to identify modified parts. After the order of priority is set according to the results of user action log-based dynamic analysis on identified regression testing objects, test effect can be raised by adjusting the order of priority using code complexity. Quality assurance coverage can be checked using the user action log suggested in this study, and the progress of test and whether or not each function has been verified can be checked, too. In addition, by minimizing test parts and adjusting the order of test, costs and time can be saved, making it possible to conduct regression testing effectively.

• Journal of Biosystems Engineering
• /
• v.43 no.3
• /
• pp.229-236
• /
• 2018

Purpose: Makgeolli is a traditional alcoholic beverage made from rice with a fermentation starter called "nuruk." The concentration of alcohol in makgeolli depends on the temperature of the fermentation tank. It is important to monitor the alcohol concentration to manage the makgeolli production process. Methods: Data were collected from 84 makgeolli fermentation tanks over a year period. Independent variables included the temperatures of the tanks and the room where the tanks were located, as well as the quantity, acidity, and water concentration of the source. Software for the multilayer perceptron model (MLP) was written in Python using the Scikit-learn library. Results: Many models were created for which the optimization converged within 100 iterations, and their coefficients of determination $R^2$ were considerably high. The coefficient of determination $R^2$ of the best model with the training set and the test set were 0.94 and 0.93, respectively. The fact that the difference between them was very small indicated that the model was not overfitted. The maximum and minimum error was approximately 2% and the total MSE was 0.078%. Conclusions: The MLP model could help predict the alcohol concentration and to control the production process of makgeolli. In future research, the optimization of the production process will be studied based on the model.

• Proceedings of the Korea Database Society Conference
• /
• 1999.10a
• /
• pp.153-163
• /
• 1999

소프트웨어 프로젝트가 대규모화되고 복잡해짐에 따라 체계적인 품질보증이 더욱 필요해지고 있다. 고품질의 소프트웨어를 개발하기 위해서는 작업산출물(work product)에 대한 품질보증뿐 아니라 개발 프로세스(process)에 대한 품질보증 활동을 동시에 수행해야만 목표하는 품질에 접근할 수 있다. 그러나 소프트웨어 품질보증은 다양한 품질특성이나 개발 주체간의 시각 차이에 따라 달라지는 가변성을 지니고 있어 품질보증에 적지 않은 어려움이 내재되어있다. 이러한 품질보증의 어려움이 소프트웨어 품질을 저해하는 원인으로 작용하여 기업의 품질 경쟁력을 떨어뜨리고 있다. 본 연구는 이러한 품질보증 활동의 어려움을 해결하고 나아가 품질향상을 달성하기 위한 방법을 개발하고자 하였다. 품질향상을 위해서 품질보증 활동을 보다 계획적이고 체계적으로 수행하기 위한 SQA(Software Quality Assurance) 방법론을 개발하였다. 일반적으로 방법론이란 모든 프로젝트에 그대로 적용하기란 어렵다. SQA 방법론 또한 프로젝트의 특성이나 조직 특성에 따라 적절히 커스터마이징(Customizing)되어 사용하여야만 효과성을 제고할 수 있다. 그리하여 본 SQA 방법론에서도 품질보증활동을 체계적으로 지원하기 위해 수행되어야할 품질보증 태스크가 리파지토리로 구성되어 있다. 프로젝트 특성 둥에 따라 필요한 품질보증 태스크를 이 리파지토리로부터 선정하여 활용할 수 있게 된다. 마지막으로 프로젝트 특성 등에 따라 필요한 품질보증 활동을 커스터마이징하기 위한 전문가시스템 접근방법을 제시한다.