• Journal of Korean Society of Disaster and Security
• /
• v.16 no.3
• /
• pp.27-34
• /
• 2023

In Korea, safety inspections of bridges are conducted periodically in accordance with law. Bridges are classified according to type, length, etdc., and the content and frequency of safety inspections are different. Bridges safety evaluation is performed on relatively large bridges, and safety evaluation of small bridges, which account for the majority of all bridges, is not mandatory. Therefore, in this study, in order to confirm the safety of small-scale bridges, a correlation analysis study was conducted with the common load carrying rate for each safety evaluation indicator. For this purpose, inspection reports of bridges from local goverments were collected, and the values for each bridges for about 50 indicators in the report were converted into data. By performing cleaning on the collected data and analyzing the correlation with the common load carrying rate, the top indicators related to safety for each bridges type were derived.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.9
• /
• pp.1-7
• /
• 2024

In this paper, we proposes a Convolutional Neural Networks(CNN) equipped with Batch Normalization(BN) for handwritten digit recognition training the MNIST dataset. Aiming to surpass the performance of LeNet-5 by LeCun et al., a 6-layer neural network was designed. The proposed model processes 28×28 pixel images through convolution, Max Pooling, and Fully connected layers, with the batch normalization to improve learning stability and performance. The experiment utilized 60,000 training images and 10,000 test images, applying the Momentum optimization algorithm. The model configuration used 30 filters with a 5×5 filter size, padding 0, stride 1, and ReLU as activation function. The training process was set with a mini-batch size of 100, 20 epochs in total, and a learning rate of 0.1. As a result, the proposed model achieved a test accuracy of 99.22%, surpassing LeNet-5's 99.05%, and recorded an F1-score of 0.9919, demonstrating the model's performance. Moreover, the 6-layer model proposed in this paper emphasizes model efficiency with a simpler structure compared to LeCun et al.'s LeNet-5 (7-layer model) and the model proposed by Ji, Chun and Kim (10-layer model). The results of this study show potential for application in real industrial applications such as AI vision inspection systems. It is expected to be effectively applied in smart factories, particularly in determining the defective status of parts.

• Journal of Korean Society of Transportation
• /
• v.26 no.3
• /
• pp.7-16
• /
• 2008

The immigration procedure at airports is vital to making passenger and cargo transport faster. The rapid procedure of immigration could be an important determining factor when passengers select an air transport company, one that should have high satisfactory in terms of their service level and efficiency. Therefore, the advanced airport makes it easy for customers and their cargo to proceed. The coordination between authorities related to the Korean international airport is not satisfactory for customers. This paper analyzes the factors necessary to enhance the airport immigration procedure with the movement of aircrafts, passengers, cargo, and post, using the CK(Cook and Kress) model of DEA(Data Envelopment Analysis). From this study, the author found that research and development will be needed to improve the immigration procedure, especially on facilities and their operating systems. There are needed, also, performance indicators and a continuous monitoring system.

• Journal of the Korea Convergence Society
• /
• v.9 no.4
• /
• pp.31-45
• /
• 2018

Recent dramatical development of computer technology related to internet technology intensifies the dispute over software of computer or smart device. Research on software has been flourished with political issuing of fierce competition among nations for software development. Particularly industrial growth in ethernet based big data and IoT (Internet of Things) has promoted to build and develop open source programs based on java, xcode and C. On these circumstances, issue on software piracy has been confronted despite the basic security policy protecting intellectual property rights of software and thus it is of substantial importance to protect the rights of originality of source program license. However, the other issue on source technology protection of developer is the possibility of hindrance to advancement in industry and culture by developing programs. This study discuss the way of enhancing legal stability of IoT application program development and reinforcing precision in inspection of program plagiarism by analyzing the source programs with newly introducing text mining technique, thus suggests an alternative protective way of infringement of personal information due to duplicating program.

• Journal of Korean Society of Rural Planning
• /
• v.13 no.2
• /
• pp.121-132
• /
• 2007

In this study, We developed an evaluation system for the interim check of Integrated Rural Village Development Project and analyzed its applicability to an actual evaluation process through a pilot evaluation on regions selected. The evaluation system consists of documentary assessments(30%) and field inspections(70%). The documentary assessments are quantitative assessments on check-lists reports by self-evaluation prepared by local governments. The field inspections are qualitative assessments by evaluation teams. Sixteen evaluation indices were developed for documentary assessments and seven criteria were designed for field inspections. For a pilot evaluation, one region in each province excluding Jeju Do, eight regions was selected and the field inspections due to circumstances was proceeded in two regions. The results of documentary assessments indicate that most of regions are evaluated low in project performance attributable to the delay in security for sites. In the field inspections, it appears that most of the regions evaluated high at the documentary assessments got a high point from them. They also show that coordination of action plans, rather than quantitative achievements, is a base determining success of the projects.

• Journal of the Korean Society for information Management
• /
• v.21 no.4 s.54
• /
• pp.329-352
• /
• 2004

In this knowledge-based society of this age, librarianship takes a professional position and requires essential principles of ethics that has to be observed. Therefore, library associations and professional communities all over the world have released criteria and code of ethics to make their professional positions to keep. This research investigated and analyzed the codes of ethics for librarians in United States, Great Britain, Japan, and South Korea which are based on the mission of each library of each country. Based on these analysis and comparison, this research proposed more advanced codes of ethics for South Korea. The proposed model of codes of ethics consists of two parts: ethics for information and ethics for professional positions. The ethics for information contains six essential elements: equal access and services for information, denial of inspection, protection of privacy, neutralization of librarian, and security of intellectual freedom. The ethics for professional positions consists of 8 essential aspects: exclusion of personal benefit, continuous efforts for developing knowledge, keep the professional position, conflicts between professional task and organization, relationship with co-workers, ensure the conditions of rights and welfare for employees, cooperations among libraries, and contribution for creation of new culture.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.1
• /
• pp.137-143
• /
• 2017

X-ray image is a widely used to medical examination, airport security and cargo inspection. However, X-ray images contain many visual noise, which interrupt image analysis. Consequently, it is primary importance to reduce noises of X-ray image. In this paper, we present a improved denoise technique for x-ray image using pixel value and range weights. First, we denoise a x-ray image using bilateral filter. Next, we detect a edge region of the original x-ray image. If a denoised pixel belongs to the edge region, we calculate weighting values of original x-ray image and denoised x-ray image in $3{\times}3$ neighboring pixels and compute the cost value to determine the boundary pixel value. Finally, the pixel value having minimum cost is determined as the pixel value of the denoised x-ray image. Simulation results show that the proposed algorithm achieves good performance in terns of PSNR comparison and subjective visual quality.

• Ocean and Polar Research
• /
• v.39 no.2
• /
• pp.159-168
• /
• 2017

To evaluate the accuracy of UAV photogrammetry for Hyangho coast, eastern coast of Korea, we conducted a field experiment wherein UAV photogrammetry test was repeated three times. Since the Haygho coast is located within a military reservation zone, it was necessary to obtain permission to gain access to the beach and to have sensitive aerial photographs showing military facilities inspected and cropped. The standard deviation of the UAV shooting position between the three tests was less than 1 m, but repeatability of footprint on the ground was low due to wind-driven variability of the UAV pose. Self-calibrating bundle adjustment(SCBA) of implementing non-metric camera calibration was failed in one test. In two tests, the vertical error was twice as large as the pixel size except for those areas that were subject to security inspection and cropping. Given the problems that can arise with regard to the repeatability of the shooting area as well as the possibility of failure with regard to SCBA, we strongly recommend that UAV photogrammetry in coastal areas needs to be repeated at least twice.

• Journal of Digital Convergence
• /
• v.15 no.1
• /
• pp.381-391
• /
• 2017

Biometric technology is a technology for authenticating a user using the physical or behavioral features of the inherent characteristics of the individual. With the necessity and efficiency of the technology in the fields of finance, security, access control, medical welfare, inspection, and entertainment, the service range has been expanding. Biometrics using biometric information such as fingerprints and faces have been exposed to counterfeit and disguised threats and become a social problem. Recent studies using a bio-signal from the inside of the body other than the bio-information of the external body are being developed. This paper analyzes the recent research and technology of biometric systems using bio-signals, ECG, heart sounds, EEG, and EMG to present the skills needed for the development direction. In the future, utilizing the deep learning to build and analyze database to manage bio-signal based big data for the complex condition of individuals, biometrics technologies suitable for real time environment are expected to be researched.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.15 no.6
• /
• pp.37-42
• /
• 2015

Although online search engine service provide a convenient means to search for information on the World Wide Web, it also poses a risk of disclosing privacy. Regardless of such risk, most of users are neither aware of their personal information being exposed on search results nor how to redress the issue by requesting removal of information. According to the 2015 parliamentary inspection of government offices, many government agencies were criticized for mishandling of personal information and its leakage on online search engine such as Google. Considering the fact that the personal information leakage via online search engine has drawn the attention at the government level, the online search engine and privacy issue needs to be rectified. This paper, by examining current online search engines, studies the degree of personal information exposure on online search results and its underlying issues. Lastly, based on research result, the paper provides a sound policy and direction to the removal of exposed personal information with respect to search engine service provider and user respectively.