Digital Library[ Search Result ]
Analysis of the Cost-effectiveness of Regression Testing Techniques in Continuous Integration Environments based on Failure to Pay Attention
http://doi.org/10.5626/JOK.2018.45.10.1029
In continuous integration (CI) environments, it is possible to provide fast feedback on test failures by applying cost-effective regression-testing techniques. In this study, we analyze the cost-effectiveness of two test-case prioritization techniques based on the test history of three industrial projects. In addition, because test failures may have different degrees of attention paid to them by different developers in CI environments, we consider this characteristic in the experiment. As a result, we discovered that the cost-effectiveness of applying the TCP techniques can be similar to that of not applying any of the TCP techniques when failure of the developers to pay attention is considered. The experiment shows that it is necessary to improve the state-of-the-art test-case prioritization techniques for CI environments by considering such characteristics.
User-Weighted Viewpoint/Lighting Control for Multi-Object Scene
http://doi.org/10.5626/JOK.2018.45.9.888
In computer graphics, viewpoint selection for objects in a scene has been performed by evaluating the goodness of sampled viewpoints. Since the definition of a good viewpoint varies according to the user’s purpose, various measurements such as entropy and mesh saliency have been used. In this paper, we propose a method of selecting the best viewpoint and lighting for a multi-object scene, based on the user-assigned importance of each object. After sampling a viewpoint and lighting from the surrounding sphere of the scene, we render the images by combining the sampled viewpoint and lighting. We then select the best result that coincides with user-assigned importance by quantifying the saliency of each object in the rendered image. While this technique has the disadvantage of high computation cost due to the need to render combinations of viewpoints and lighting, it obtains the viewpoint and lighting most suitable for the user`s needs. In order to minimize the computation cost, an object-by-object pixel classification technique on GPU is also proposed in this paper.
Korean Machine Reading Comprehension using Reinforcement Learning and Dual Co-Attention Mechanism
http://doi.org/10.5626/JOK.2018.45.9.932
Machine Reading Comprehension is a question-answering model for the purposes of understanding a given document and then finding the correct answer within the document. Previous studies on the Machine Reading Comprehension model have been based on end-to-end neural network models with various attention mechanisms. However, in the previous models, difficulties arose when attempting to find answers with long dependencies between lexical clues because these models did not use grammatical and syntactic information. To resolve this problem, we propose a Machine Reading Comprehension model with a dual co-attention mechanism reflecting part-of-speech information and shortest dependency path information. In addition, to increase the performances, we propose a reinforce learning method using F1-scores of answer extraction as rewards. In the experiments with 18,863 question-answering pairs, the proposed model showed higher performances (exact match: 0.4566, F1-score: 0.7290) than the representative previous model.
Resolution of Answer-Repetition Problems in a Generative Question-Answering Chat System
http://doi.org/10.5626/JOK.2018.45.9.925
A question-answering (QA) chat system is a chatbot that responds to simple factoid questions by retrieving information from knowledge bases. Recently, many chat systems based on sequence-to-sequence neural networks have been implemented and have shown new possibilities for generative models. However, the generative chat systems have word repetition problems, in that the same words in a response are repeatedly generated. A QA chat system also has similar problems, in that the same answer expressions frequently appear for a given question and are repeatedly generated. To resolve this answer-repetition problem, we propose a new sequence-to-sequence model reflecting a coverage mechanism and an adaptive control of attention (ACA) mechanism in a decoder. In addition, we propose a repetition loss function reflecting the number of unique words in a response. In the experiments, the proposed model performed better than various baseline models on all metrics, such as accuracy, BLEU, ROUGE-1, ROUGE-2, ROUGE-L, and Distinct-1.
Title Generation Model for which Sequence-to-Sequence RNNs with Attention and Copying Mechanisms are used
http://doi.org/10.5626/JOK.2017.44.7.674
In big-data environments wherein large amounts of text documents are produced daily, titles are very important clues that enable a prompt catching of the key ideas in documents; however, titles are absent for numerous document types such as blog articles and social-media messages. In this paper, a title-generation model for which sequence-to-sequence RNNs with attention and copying mechanisms are employed is proposed. For the proposed model, input sentences are encoded based on bi-directional GRU (gated recurrent unit) networks, and the title words are generated through a decoding of the encoded sentences with keywords that are automatically selected from the input sentences. Regarding the experiments with 93631 training-data documents and 500 test-data documents, the attention-mechanism performances are more effective (ROUGE-1: 0.1935, ROUGE-2: 0.0364, ROUGE-L: 0.1555) than those of the copying mechanism; in addition, the qualitative-evaluation radiative performance of the former is higher.
Active Vision from Image-Text Multimodal System Learning
In image classification, recent CNNs compete with human performance. However, there are limitations in more general recognition. Herein we deal with indoor images that contain too much information to be directly processed and require information reduction before recognition. To reduce the amount of data processing, typically variational inference or variational Bayesian methods are suggested for object detection. However, these methods suffer from the difficulty of marginalizing over the given space. In this study, we propose an image-text integrated recognition system using active vision based on Spatial Transformer Networks. The system attempts to efficiently sample a partial region of a given image for a given language information. Our experimental results demonstrate a significant improvement over traditional approaches. We also discuss the results of qualitative analysis of sampled images, model characteristics, and its limitations.
Comparing Initiating and Responding Joint Attention as a Social Learning Mechanism : A Study Using Human-Avatar Head/Hand Interaction
Mingyu Kim, So-Yeon Kim, Kwanguk Kim
Joint Attention (JA) has been known to play a key role in human social learning. However, relative impact of different interaction types has yet to be rigorously examined because of limitation of existing methodologies to simulate human-to-human interaction. In the present study, we designed a new JA paradigm with emulating human-avatar interaction and virtual reality technologies, and tested the paradigm in two experiments with healthy adults. Our results indicated that initiating JA (IJA) condition was more effective than responding JA (RJA) condition for social learning in both head and hand interactions. Moreover, the hand interaction involved better information processing than the head interaction. The implication of the results, the validity of the new paradigm, and limitations of this study were discussed.
Modeling of Visual Attention Probability for Stereoscopic Videos and 3D Effect Estimation Based on Visual Attention
Boeun Kim, Wonseok Song, Taejeong Kim
Viewers of videos are likely to absorb more information from the part of the screen that attracts visual attention. This fact has led to the visual attention models that are being used in producing and evaluating videos. In this paper, we investigate the factors that are significant to visual attention and the mathematical form of the visual attention model. We then estimated the visual attention probability using the statistical design of experiments. The analysis of variance (ANOVA) verifies that the motion velocity, distance from the screen, and amount of defocus blur affect human visual attention significantly. Using the response surface modeling (RSM), we created a visual attention score model that concerns the three factors, from which we calculate the visual attention probabilities (VAPs) of image pixels. The VAPs are directly applied to existing gradient based 3D effect perception measurement. By giving weights according to our VAPs, our algorithm achieves more accurate measurement than the existing method. The performance of the proposed measurement is assessed by comparing them with subjective evaluation as well as with existing methods. The comparison verifies that the proposed measurement outperforms the existing ones.
A Graph Neural Network Approach for Predicting the Lung Carcinogenicity of Single Molecular Compounds
http://doi.org/10.5626/JOK.2025.52.6.482
Cancer is one of the major diseases causing millions of deaths worldwide every year, and lung cancer has been recorded as the leading cause of cancer-related deaths in Korea in 2022. Therefore, research on lung cancer-causing compounds is essential, and this study proposes and evaluates a novel approach to predict lung cancer-causing potential using graph neural networks to overcome the limitations of existing machine learning and deep learning methods. Based on SMILES(Simplified Molecular Input Line Entry System) information from the compound carcinogenicity databases CPDB, CCRIS, IRIS and T3DB, the structure and chemical properties of molecules were converted into graph data for training, and the proposed model showed superior prediction performance compared to other models. This demonstrates the potential of graph neural networks as an effective tool for lung cancer prediction and suggests that they can make important contributions to future cancer research and treatment development.
Drug Toxicity Prediction Using Integrated Graph Neural Networks and Attention-Based Random Walk Algorithm
Jong-Hoon Park, Jae-Woo Chu, Young-Rae Cho
http://doi.org/10.5626/JOK.2025.52.3.234
The traditional drug development process is often burdened by high costs and lengthy timelines, leading to increasing interest in AI-based drug development. In particular, the importance of AI models for preemptively evaluating drug toxicity is being emphasized. In this study, we propose a novel drug toxicity prediction model, named Integrated GNNs and Attention Randon Walk (IG-ARW). The proposed method integrates various Graph Neural Network (GNN) models and uses attention mechanisms to compute random walk transition probabilities, extracting graph features precisely. The model then conducts random walks to extract node features and graph features, ultimately predicting drug toxicity. IG-ARW was evaluated on three different datasets, demonstrating strong performances with AUC scores of 0.8315, 0.8894, and 0.7476, respectively. Notably, the model was proven to be highly effective not only in toxicity prediction, but also in predicting other drug characteristics.
Search
Journal of KIISE
- ISSN : 2383-630X(Print)
- ISSN : 2383-6296(Electronic)
- KCI Accredited Journal
Editorial Office
- Tel. +82-2-588-9240
- Fax. +82-2-521-1352
- E-mail. chwoo@kiise.or.kr