• Journal of KIISE
• /
• v.44 no.8
• /
• pp.832-841
• /
• 2017

Bug reports are essential documents for developers to localize and fix bugs. These reports contain information regarding software bugs or failures that occur during software operation and maintenance phase. Information Retrieval-based Bug Localization (IR-BL) techniques have been proposed to reduce the time and cost it takes for developers to resolve bug reports. However, if a low-quality bug report is submitted, the performance of such techniques can be significantly degraded. To address this problem, we propose a quality prediction method that selects low-quality bug reports. This process; defines a Quality property of a Bug report as a Query (Q4BaQ) and predicts the quality of the bug reports using machine learning. We evaluated the proposed method with 3 open source projects. The results of the experiment show that the proposed method achieved an average F-measure of 87.31% and outperformed previous prediction techniques by up to 6.62% in the F-measure. Finally, a combination of the proposed method and traditional automatic query reformulation method improved the MRR and MAP by 0.9% and 1.3%, respectively.

• Journal of Broadcast Engineering
• /
• v.27 no.2
• /
• pp.240-243
• /
• 2022

Tracking the location of program defects is an essential task for software maintenance and repair. When a bug report is submitted, bug localization is a costly task because of the developer's manual effort. Many researchers have tried to automate the task, but according to the reported results, the performance is still insufficient in practice. Therefore, in this study, we analyzed a large amount of bug report data and the latest research and found that the existing studies used only one preprocessing without considering the characteristics of the bug report. In this paper, to solve the problems mentioned earlier, we propose a pre/post-processing operator selection approach for bug localization.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.5
• /
• pp.235-241
• /
• 2015

Nowadays, research and industry on the internet of things is rapidly developing. Bug fixed field of the Software development related internet of things is a very important things. In this study, we analyze the properties that can affect what the bug fix-time by analyzing the time required to fix a bug associated with the Internet of Things. Using the k-NN classification method based on the attribute information to be classified as bug reports. Extracts a bug report based on the results of a similar property. Bug fixed by calculating the time of a similar bug report predicts the fix-time for new bugs. Depending on the prediction of the properties that affect the bug correction time, the properties of os, component, reporter, and assignee showed the best prediction accuracy.

• Journal of the Korean Institute of Telematics and Electronics T
• /
• v.36T no.4
• /
• pp.115-122
• /
• 1999

The Y2K bug, what is called "millennium bug" or "2000 year bug", take place because the year after 2000 year is not recognize as the year marking method of the computer designed for take up two-digit number. This takes place because the RTC chip architecture of PC can not change the century information to the operating together with date. In this paper, we make an analysis about Y2K hardware bug of RTC in the IBM compatible PC, and make a Y2K compensation board in order to solve Y2K hardware bug. And the test results by various Y2K diagnosis program is bug before put in Y2K compensation board, but is not bug after put in Y2K compensation board. Therefore, we suggest a solution method for Y2K hardware bug of RTC in the IBM compatible PC.

• Journal of KIISE
• /
• v.44 no.11
• /
• pp.1156-1164
• /
• 2017

Existing studies on automatic bug triage were mostly used the method of designing the prediction system based on the machine learning algorithm. Therefore, it can be said that applying a high-performance machine learning model is the core of the performance of the automatic bug triage system. In the related research, machine learning models that have high performance are mainly used, such as SVM and Naïve Bayes. In this paper, we apply Deep Learning, which has recently shown good performance in the field of machine learning, to automatic bug triage and evaluate its performance. Experimental results show that the Deep Learning based Bug Triage system achieves 48% accuracy in active developer experiments, un improvement of up to 69% over than conventional machine learning techniques.

• Korean journal of applied entomology
• /
• v.44 no.4 s.141
• /
• pp.287-292
• /
• 2005

The soybean varieties the bean bug preferred the least were Kwangankong, Namhaekong, Sunamkong, Sorogkong, and Anpyeongkong, and next to them was Pungsannamulkong, among 25 varieties examined. Myongjunamulkong and Eunhakong supported a good growth of the bug as the daily gains of weight of 3rd instar nymphs were 14,9 and 13.9 mg, respectively. On the other hand the bug on Punsannamulkong gained weight daily as little as 10.1 mg. On Pungsannamulkong the nymphal development of the bean bug took $24.5{\pm}2.1$ days, about three days longer than those on Myunjunamulkong and Eunhakong. The survival of the bean bug on Punsannamulkong was 83%, slightly lower than those on Myunjunarnulkong and Eunhakong. It seemed evident that Pungsannamulkong have a non-preference type resistance to the bean bug.

• Soft Computing and Machine Intelligence
• /
• v.1 no.1
• /
• pp.1-10
• /
• 2021

Analysis and Tracking of bug reports is a challenging field in software repositories mining. It is one of the fundamental ways to explores a large amount of data acquired from defect tracking systems to discover patterns and valuable knowledge about the process of bug triaging. Furthermore, bug data is publically accessible and available of the following systems, such as Bugzilla and JIRA. Moreover, with robust machine learning (ML) techniques, it is quite possible to process and analyze a massive amount of data for extracting underlying patterns, knowledge, and insights. Therefore, it is an interesting area to propose innovative and robust solutions to analyze and track bug reports originating from different open source projects, including Mozilla and Eclipse. This research study presents an ML-based classification model to analyze and track bug defects for enhancing software engineering management (SEM) processes. In this work, Artificial Neural Network (ANN) and Naive Bayesian (NB) classifiers are implemented using open-source bug datasets, such as Mozilla and Eclipse. Furthermore, different evaluation measures are employed to analyze and evaluate the experimental results. Moreover, a comparative analysis is given to compare the experimental results of ANN with NB. The experimental results indicate that the ANN achieved high accuracy compared to the NB. The proposed research study will enhance SEM processes and contribute to the body of knowledge of the data mining field.

• The Korean Journal of Pesticide Science
• /
• v.20 no.2
• /
• pp.159-164
• /
• 2016

The winter cherry bug (Acanthocoris sordidus Thunberg, Coreidae, Hemiptera) is a insect pest that have a piercing sucking type mouthpart, and it is injured to solanaceous plants including pepper plant. For the control of the winter cherry bug, 20 organic synthetic insecticides and 7 environmental friendly agricultural materials (EFAMs) were selected with single formulation. Fenitrothion, fenthion and phenthoate were significantly higher mortality to adults and 3rd instar nymphs of winter cherry bug as over 95 and 100 % after 72 hours with treatment. Otherwise, in case of EFAMs, there is no significantly higher effective materials to adults and 3rd instar nymphs of winter cherry bug. Eighty percentage of Sophora flavescens was showed only around 50% mortality with the high variation after 72 hours with treatment against adult of the winter cherry bug.

• Korean journal of applied entomology
• /
• v.30 no.1
• /
• pp.58-64
• /
• 1991

This study was carried out to investigate the occurrence of bug species around bank and paddy field and its peckey rice in four different districts of Kyonggi Area, and then to observe the distribution of bug species causing pee key rice. The results obtained were as follows; Thirty one bug species were collected around bank and its dominant species were Eyarcoris parvus, Nabis stenoferus, Stictopleurus crassicornis and each constituted 35.9, 20.2, 6.5 %, respectively. On the other hand, 11 bug species in paddy field were identified and the dominant species among them were Nabis stenoferus, Adelphocoris triannulatus, Eyarcoris parvus. Pee key rice induced by the infestation of bug species was 34.7% in Eyarcoris parvus and 2.7% in Aeschynteles maculatus. The occurrence of pecked rice injured by bugs was severe on milk ripe stage through heading stage to yellow ripe stage of rice growth period. Peckey rice among rice varieties was higher in Sobaekbyeo, extremely early mature variety, and Taebaegbyeo, early mature variety. The occurrence of peckey rice was higher in mountainous area such as Pocheon culturing early mature rice varieties.

• Korean journal of applied entomology
• /
• v.46 no.2
• /
• pp.221-227
• /
• 2007

Stink bug species and host plants occurred in fallow lands for rice product regulation were studied in Honam area from 2004 to 2005. A total of 26 bug species in 8 families were surveyed in the fallow lands. Population density of Cletus punctiger adult reached its peak in July and was higher in fallow lands close to mountain area in Muan. Population density of stink bug species occurred in plain area of Wanju were significantly low in 2004 and population density of C. punctiger adult reached its peak in July and August in fallow lands in 2005. Five species of stink bug including C. punctiger immigrated from fallow lands to rice fields in August, and three other species including Cletus schmidti in September. Eight stink bug species which were observed to feed on weeds in fallow lands were C. punctiger, C. schmidti, Eurydema gebleri, Pachygrontha antennata, Trigonotylus caelestialium, Aelia fieberi, Eysarcoris aeneus, and Nezara antennata.