• Journal of Creative Information Culture
• /
• v.5 no.2
• /
• pp.145-156
• /
• 2019

In this study, we have developed and evaluated an information extracting module based on the named entity recognition technique. For the given purpose in this paper, the module was designed to apply to the problem dealing with extraction of postal address information from arbitrary documents without any prior knowledge on the document layout. From the perspective of information technique practice, our approach can be said as a probabilistic n-gram (bi- or tri-gram) method which is a generalized technique compared with a uni-gram based keyword matching. It is the main difference between our approach and the conventional methods adopted in natural language processing that applying sentence detection, tokenization, and POS tagging recursively rather than applying the models sequentially. The test results with approximately two thousands documents are presented at this paper.

• Journal of Creative Information Culture
• /
• v.5 no.1
• /
• pp.15-24
• /
• 2019

Tools and methods for interacting with the virtual environment are essential in order for a student to perform the virtual reality education contents. However, since the developed controller has generally been constructed for adults, it is necessary to study interaction tools considering the purpose of education and the level of students. Therefore, this study analyzed elementary and middle school students' perceptions of HMD and interactive tools, which are currently widely used as an initial research for developing interactive tools. Results show that students' perceptions has increased in post-questionnaire compared to pre-questionnaire, indicating that the universal controller can be used in the education. Implications for the development of interaction tools are discussed based on interviews with students.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.222-224
• /
• 2022

Deep learning-based computer vision applications in the field of object segmentation take a transfer learning method using hyperparameters and models pretrained and distributed by STOA techniques to improve performance. Custom datasets used in this process require a lot of resources, such as time and labeling, in labeling tasks to generate Ground Truth information. In this paper, we present an automatic labeling construction method using object segmentation techniques so that resources such as time and labeling can be used less to build custom datasets used in deep learning neural networks.

• Journal of the Korean Society of Safety
• /
• v.38 no.5
• /
• pp.51-57
• /
• 2023

Numerous studies have been conducted to analyze the causal relationships of maritime accidents using natural language processing techniques. However, when multiple causes and effects are associated with a single accident, the effectiveness of extracting these causal relations diminishes. To address this challenge, we compiled a dataset using verdicts from maritime accident cases in this study, analyzed their causal relations, and applied labeling considering the association information of various causes and effects. In addition, to validate the efficacy of our proposed methodology, we fine-tuned the KoELECTRA Korean language model. The results of our validation process demonstrated the ability of our approach to successfully extract multiple causal relationships from maritime accident cases.

• Journal of Intelligence and Information Systems
• /
• v.20 no.1
• /
• pp.133-148
• /
• 2014

Recently, with the advent of various information channels, the number of has continued to grow. The main cause of this phenomenon can be found in the significant increase of unstructured data, as the use of smart devices enables users to create data in the form of text, audio, images, and video. In various types of unstructured data, the user's opinion and a variety of information is clearly expressed in text data such as news, reports, papers, and various articles. Thus, active attempts have been made to create new value by analyzing these texts. The representative techniques used in text analysis are text mining and opinion mining. These share certain important characteristics; for example, they not only use text documents as input data, but also use many natural language processing techniques such as filtering and parsing. Therefore, opinion mining is usually recognized as a sub-concept of text mining, or, in many cases, the two terms are used interchangeably in the literature. Suppose that the purpose of a certain classification analysis is to predict a positive or negative opinion contained in some documents. If we focus on the classification process, the analysis can be regarded as a traditional text mining case. However, if we observe that the target of the analysis is a positive or negative opinion, the analysis can be regarded as a typical example of opinion mining. In other words, two methods (i.e., text mining and opinion mining) are available for opinion classification. Thus, in order to distinguish between the two, a precise definition of each method is needed. In this paper, we found that it is very difficult to distinguish between the two methods clearly with respect to the purpose of analysis and the type of results. We conclude that the most definitive criterion to distinguish text mining from opinion mining is whether an analysis utilizes any kind of sentiment lexicon. We first established two prediction models, one based on opinion mining and the other on text mining. Next, we compared the main processes used by the two prediction models. Finally, we compared their prediction accuracy. We then analyzed 2,000 movie reviews. The results revealed that the prediction model based on opinion mining showed higher average prediction accuracy compared to the text mining model. Moreover, in the lift chart generated by the opinion mining based model, the prediction accuracy for the documents with strong certainty was higher than that for the documents with weak certainty. Most of all, opinion mining has a meaningful advantage in that it can reduce learning time dramatically, because a sentiment lexicon generated once can be reused in a similar application domain. Additionally, the classification results can be clearly explained by using a sentiment lexicon. This study has two limitations. First, the results of the experiments cannot be generalized, mainly because the experiment is limited to a small number of movie reviews. Additionally, various parameters in the parsing and filtering steps of the text mining may have affected the accuracy of the prediction models. However, this research contributes a performance and comparison of text mining analysis and opinion mining analysis for opinion classification. In future research, a more precise evaluation of the two methods should be made through intensive experiments.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.15 no.5
• /
• pp.360-366
• /
• 2022

This paper presents a AI model structure for restoring Korean traditional palace photographs, which remain only black-and-white photographs, to color photographs using Pix2Pix, one of the adversarial generative neural network techniques. Pix2Pix consists of a combination of a synthetic image generator model and a discriminator model that determines whether a synthetic image is real or fake. This paper deals with an artificial intelligence model by adjusting a receptive field of the discriminator, and analyzes the results by considering the characteristics of the ancient palace photograph. The receptive field of Pix2Pix, which is used to restore black-and-white photographs, was commonly used in a fixed size, but a fixed size of receptive field is not suitable for a photograph which consisting with various change in an image. This paper observed the result of changing the size of the existing fixed a receptive field to identify the proper size of the discriminator that could reflect the characteristics of ancient palaces. In this experiment, the receptive field of the discriminator was adjusted based on the prepared ancient palace photos. This paper measure a loss of the model according to the change in a receptive field of the discriminator and check the results of restored photos using a well trained AI model from experiments.

• Journal of the Korea Concrete Institute
• /
• v.23 no.3
• /
• pp.281-287
• /
• 2011

Recently, bridge construction technology has made great progress from development of high performance materials and new bridge types. However, most technology are based on methods of cast-in-place and material cost saving. The method of cast-in-place concrete causes environmental damages and costumer complaints. Especially, under bad weather conditions, the construction can not proceed. To overcome these disadvantages, new construction methods were developed to reduce construction time. These methods are called precast method. Most prefabricated methods have been applied to superstructure constructions of bridges, but very minutely applied to substructure constructions. The most important agendas on precast method are light weight and transportability of the precasted members, because very strict transporting specifications exist for road transportation of the precasted members. For example, the weight and length of coping members may be larger than the available transporting vehicles. Although column is constructed by precast method to save construction time, if coping member is constructed by cast-in-place method, then the column construction time reduction becomes meaningless. Therefore, in this study, a new precast coping member and a connecting system of column-coping member are proposed. The proposed method is verified by analyzing their ultimate performance through analysis and experimental study.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.28 no.6
• /
• pp.1475-1487
• /
• 2018

To verify remitter's identity when the remitter transfers money to a recipient using an electronic financial service provided by the financial institution, the remitter inputs the information; such as the withdrawal account number, the withdrawal amount, the password pre-registered with the financial company, or the information from authenticating medium that is previously distributed by the financial institution. However, the 1-Way transaction between the financial institution and the remitter is exposed to a great risk of accidents such as an anomaly remittance or a voice phishing fraud. Therefore, in this study, we propose a 2-WAY trade verification model for electronic financial transaction that can be mutually agreed by allowing the recipient to share the transaction information with the remitter and the financial company. We have improved the traditional electronic financial transaction's method by replacing it to 2-WAY trade method, and it is used for various purposes; such as preventing an error within the remittance or voice phishing fraud, enhancing loan transaction and contract transaction, etc. Through these variety of applications, we are expecting to reduce the inconveniences while improving the convenience of financial transaction and vitalizing the P2P transaction of financial institution.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.2
• /
• pp.651-658
• /
• 2021

Because bolts with anti-loosening coatings are used mainly for joining safety-related components in automobiles, accurate automatic screening of these coatings is essential to detect defects efficiently. The performance of the convolutional neural network (CNN) used in a previous study [Identification of bolt coating defects using CNN and Grad-CAM] increased with increasing number of data for the analysis of image patterns and characteristics. On the other hand, obtaining the necessary amount of data for coated bolts is difficult, making training time-consuming. In this paper, resorting to the same VGG16 model as in a previous study, transfer learning was applied to decrease the training time and achieve the same or better accuracy with fewer data. The classifier was trained, considering the number of training data for this study and its similarity with ImageNet data. In conjunction with the fully connected layer, the highest accuracy was achieved (95%). To enhance the performance further, the last convolution layer and the classifier were fine-tuned, which resulted in a 2% increase in accuracy (97%). This shows that the learning time can be reduced by transfer learning and fine-tuning while maintaining a high screening accuracy.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.26 no.6
• /
• pp.431-438
• /
• 2013

The systemization of construction information is required over whole life cycle of facilities to improve productivity of construction industry. BIM(Building Information Modeling) is a technology to manage information based on 3D information model. It has been actively suggested as one of the alternatives. However, it may be currently concentrated on the large project while the small and medium project based on BIM are slightly treated in indifference. In the case of small and medium project, the loss of information has been occurred more seriously than large project. However, it is hard to introduce BIM to the small and medium companies due to the lack of investment resources. This study has been performed to set up information management system based on BIM considering characteristics of small and medium project without excessive investment. In this study, pseudo BIM is defined as BIM for small and medium project. The concept of pseudo BIM has been suggested. The PLIB of ISO and construction information classification system of MOLIT in Korea are used to construct data dictionary for pseudo BIM. A pilot test is performed to verify the effectiveness of pseudo BIM.