• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.10
• /
• pp.431-436
• /
• 2023

Recently the incorporation of artificial intelligence approaches in the field of software engineering has been one of the big topics. In the world, there are actively studying in two directions: 1) software engineering for artificial intelligence and 2) artificial intelligence for software engineering. We attempt to apply artificial intelligence to software engineering to identify and refactor bad code module areas. To learn the patterns of bad code elements well, we must have many datasets with bad code elements labeled correctly for artificial intelligence in this task. The current problems have insufficient datasets for learning and can not guarantee the accuracy of the datasets that we collected. To solve this problem, when collecting code data, bad code data is collected only for code module areas with high-complexity, not the entire code. We propose a method for exploring common weakness enumeration by learning the collected dataset based on transfer learning of the CodeBERT model. The CodeBERT model learns the corresponding dataset more about common weakness patterns in code. With this approach, we expect to identify common weakness patterns more accurately better than one in traditional software engineering.

• Journal of The Korean Association For Science Education
• /
• v.38 no.4
• /
• pp.541-553
• /
• 2018

The purpose of this study is to explore the relationship between epistemic goals, epistemic considerations and complexity of reasoning of science high school students in an open inquiry and to explore the context on how open inquiry compares with the characteristics of an authentic scientific inquiry. Two teams were selected as focus groups and a case study was conducted. The findings are as follows: First, the contexts, such as 'sharing the value for the phenomenon understanding, reflection on the value of the research, task characteristics that require collaboration and consensus, and sufficient communication opportunities,' promote epistemic goals and considerations. On the other hand, contexts such as 'lack of opportunity for critical review of related literature and environmental constraints' lowered epistemic sides. Second, epistemic goals and considerations influenced the reasoning complexity. The goal of 'scientific sense making' led to reasoning that pose testable hypotheses based on students' own questions. The high justification considerations led to purposely focusing attention to the control designs and developing creative experimental know-how. The high audience considerations led to defending their findings through argumentation and suggesting future research. On the other hand, the goal of 'doing the lesson' and the low justification considerations led to reasoning that did not interpret the meaning of the data and did not control the limit of experiment. The low audience considerations led to reasoning that did not actively defend their findings and not suggest future research. The results of this study suggest that guidance should provide communication and critical review opportunities.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.37 no.2
• /
• pp.419-425
• /
• 2017

Managing mega construction project is a very challenging task due to its large scale and complexity. To deal with the challenge, progress measurement must be estimated reliably and effectively. Many researchers have presented progress measurement methods, but previous studies are limited to single or several types of facilities. Thus, they have difficulties to being applied to mega construction projects that covers multiple facilities. To overcome the limitations, this paper proposes a progress measurement framework considering characteristics of mega construction projects. The framework consists of four phases : development of Work Breakdown Structure, determination of weights of main facilities and sub facilities, and calculation of the integrated progress rate. To validate the proposed approach, a case study of Sejong city in Korea was performed. The results of the case study showed the applicability of the proposed framework and confirmed that it enables to reliably measure progress rate of mega construction projects.

• Journal of Korea Multimedia Society
• /
• v.10 no.10
• /
• pp.1260-1270
• /
• 2007

Testing and diagnosis of analog circuits(or mixed-signal circuits) continue to be a hard task for test engineers and efficient test methodologies to solve these problems are needed. This paper proposes a novel analog circuits test technique using time slot specification (TSS) based built-in current sensors (BICS). A technique for location of a fault site and separation of fault type based on TSS is also presented. The proposed built-in current sensors and TSS technique has high testability, fault coverage and a capability to diagnose catastrophic faults and parametric faults in analog circuits. In order to reduce time complexity of test point insertion procedure, external output and power nodes are used for test points and the current sensors are implemented in the automatic test equipment(ATE). The digital output of BICS can be easily combined with built-in digital test modules for analog IC test.

• The Korean Society of Law and Medicine
• /
• v.11 no.2
• /
• pp.181-208
• /
• 2010

Maternity services is often perceived as a troublesome business and obstetric litigation is on the increase in Western countries. Overall, the number of claim and cost of litigation to the NHS Litigation Authority (NHSLA) from maternity services in the UK is increasing every year. Maternity services account for 60-70% of the total sum paid. This has widespread implications for both the individual practitioners and the institutions where they work, due to increasing malpractice insurance premiums. Fear of litigation is also attracting fewer medical graduates into the specialty, leading to a recruitment crisis in obstetrics and gynaecology. The litigation process can cause pain, suffering and distress to clinicians as well as to the patients and their families. Litigation in maternity services is the result of a complex of events when malpractice (presumed or real) impacts on the attitude of pregnant women and their environment. In such complexity, information is mandatory but may often be misinterpreted. If messages are not tailored to the receiver's capacity, communicating well with the pregnant patient becomes crucial. Therefore, to reduce medicallegal issues in obstetrics, increasing attention and an applicable standard of obstetric care to avoid negligence and medical errors should go along with other measures. Considering UK's experiences, NHS redress scheme make it easier to pursue small claims and birth related claims, without necessarily reducing the number of claims processed through the conventional legal system and perhaps encouraging even more of them. The task of dealing with the greater number of inquiries into their practice would inevitably create an added burden for clinicians and hospital managers. Thus further proposals are required to limit the cost of processing inflated claims and to consider whether clinicians should be given some protection from litigation alleging a failure to prevent birth related impairment.

• Journal of Korea Multimedia Society
• /
• v.12 no.11
• /
• pp.1652-1660
• /
• 2009

The main objective of this research is to build a behavior prediction model of gameplay for MMO (Massively Multiplayer Online) game using the GOMS analysis method. GOMS analysis is an observational approach to HCI(Human Computer Interaction) to model and predict behaviors of a human operator in a highly interactive task. In this research, a pilot experiment was previously conducted with three skilled gamers. The gamers were provided with the goals and operators through the user's guide book, and they found methods and selection rules while being observed. Based on the results obtained from the pilot study, this research was expanded and the model was further tested with 30 subjects (game experts). The new outcomes revealed that the relevance of GOMS analysis for predicting selection rules is 96.25% according to the degree of abstraction and 77.35% based on the degree of complexity. This research will provide game designers with a new testing mechanism in the early development stages, in order to improve the quality of the game product.

• Korean Journal of Remote Sensing
• /
• v.33 no.4
• /
• pp.423-436
• /
• 2017

This paper presents a deep learning-based road segmentation framework from very high-resolution orthophotos. The proposed method uses Deep Convolutional Autoencoders for end-to-end mapping of orthophotos to road segmentations. In addition, a set of post-processing steps were applied to make the model outputs GIS-ready data that could be useful for various applications. The optimization of the model's parameters is explained which was conducted via grid search method. The model was trained and implemented in Keras, a high-level deep learning framework run on top of Tensorflow. The results show that the proposed model with the best-obtained hyperparameters could segment road objects from orthophotos at an average accuracy of 88.5%. The results of optimization revealed that the best optimization algorithm and activation function for the studied task are Stochastic Gradient Descent (SGD) and Exponential Linear Unit (ELU), respectively. In addition, the best numbers of convolutional filters were found to be 8 for the first and second layers and 128 for the third and fourth layers of the proposed network architecture. Moreover, the analysis on the time complexity of the model showed that the model could be trained in 4 hours and 50 minutes on 1024 high-resolution images of size $106{\times}106pixels$, and segment road objects from similar size and resolution images in around 14 minutes. The results show that the deep learning models such as Convolutional Autoencoders could be a best alternative to traditional machine learning models for road segmentation from aerial photographs.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.2
• /
• pp.517-524
• /
• 2010

Recently, the size of online texts and textual information is increasing explosively, and the automated classification has a great potential for handling data such as news materials and images. Text classification system is based on supervised learning which needs laborous work by human expert. The main goal of this paper is to reduce the manual intervention, required for the task. The other goal is to increase accuracy to be high. Most of the documents have high complexity in contents and the high similarities in their described style. So, the classification results are not satisfactory. This paper shows the implementation of classification system based on ETOM+RPost algorithm and classification progress using SPAM data. In experiments, we verified our system with right-training documents and wrong-training documents. The experimental results show that our system has high accuracy and stability in all situation as 16% improvement in accuracy.

• Journal of KIISE:Computer Systems and Theory
• /
• v.36 no.2
• /
• pp.60-67
• /
• 2009

Analyzing protein-protein interactions(PPI) is an important task in bioinformatics as it can help in new drugs' discovery process. However, due to vast amount of PPI data and their complexity, efficient visualization of the data is still remained as a challenging problem. We have developed efficient and effective visualization system that integrates Gene Ontology(GO) and PPI network to provide better insights to scientists. To provide efficient data visualization, we have employed dynamic interactive graph drawing methods and context-based browsing strategy. In addition, quick and flexible cross-reference system between GO and PPI; LCA(Least Common Ancestor) finding for GO; and etc are supported as special features. In terms of interface, our visualization system provides two separate graphical windows side-by-side for GO graphs and PPI network, and also provides cross-reference functions between them.

• The Journal of the Korea Contents Association
• /
• v.18 no.5
• /
• pp.1-10
• /
• 2018

The purpose of this study is to provide a cost effective usability test model for business web site development. In this study, we present a usability test model that combines Concurrent Think Aloud, performance measurement, coaching method, and remote test method. Testing target was the consortium website of electronic information joint licensing. Test participants were actual users selected by their task roles and proficiency in different levels. We improved the system by reflecting the results of user test analysis and re-tested usability test again. The result showed that usability of all participants was improved in the aspect of the time required and the complexity of mouse trajectory. It is expected that the usability test model presented in this study can be used to cost-effectively evaluate and analyze business web sites. We suggest that research various usability test model considering the characteristics of websites.