• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.5
• /
• pp.835-846
• /
• 2020

BEC (Business Email Compromise) attacks are frequently occurring by impersonating accounts or management through e-mail and stealing money or sensitive information. This type of attack accounts for the largest portion of the recent trade fraud, and the FBI estimates that the estimated amount of damage in 2019 is about $17 billion. However, if you look at the response status of the companies compared to this, it relies on the traditional SPAM blocking system, so it is virtually defenseless against the BEC attacks that social engineering predominates. To this end, we will analyze the types and methods of BEC accidents and propose ways to effectively counter BEC attacks by companies through AI(Artificial Intelligence).

• Journal of Information Processing Systems
• /
• v.16 no.1
• /
• pp.224-237
• /
• 2020

Recognition of banknote serial number is one of the important functions for intelligent banknote counter implementation and can be used for various purposes. However, the previous character recognition method is limited to use due to the font type of the banknote serial number, the variation problem by the solid status, and the recognition speed issue. In this paper, we propose an aspect ratio based character region segmentation and a convolutional neural network (CNN) based banknote serial number recognition method. In order to detect the character region, the character area is determined based on the aspect ratio of each character in the serial number candidate area after the banknote area detection and de-skewing process is performed. Then, we designed and compared four types of CNN models and determined the best model for serial number recognition. Experimental results showed that the recognition accuracy of each character was 99.85%. In addition, it was confirmed that the recognition performance is improved as a result of performing data augmentation. The banknote used in the experiment is Indian rupee, which is badly soiled and the font of characters is unusual, therefore it can be regarded to have good performance. Recognition speed was also enough to run in real time on a device that counts 800 banknotes per minute.

• Nuclear Engineering and Technology
• /
• v.52 no.5
• /
• pp.984-994
• /
• 2020

It is reported that about 20% of accidents at nuclear power plants in Korea and abroad are caused by human error. One of the main factors contributing to human error is fatigue, so it is necessary to prevent human errors that may occur when the task is performed in an improper state by grasping the status of the operator in advance. In this study, we propose a method of evaluating operator's fitness-for-duty (FFD) using various parameters including eye movement data, subjective fatigue ratings, and operator's performance. Parameters for evaluating FFD were selected through a literature survey. We performed experiments that test subjects who felt various levels of fatigue monitor information of indicators and diagnose a system malfunction. In order to find meaningful characteristics in measured data consisting of various parameters, hierarchical clustering analysis, an unsupervised machine-learning technique, is used. The characteristics of each cluster were analyzed; fitness-for-duty of each cluster was evaluated. The appropriateness of the number of clusters obtained through clustering analysis was evaluated using both the Elbow and Silhouette methods. Finally, it was statistically shown that the suggested methodology for evaluating FFD does not generate additional fatigue in subjects. Relevance to industry: The methodology for evaluating an operator's fitness for duty in advance is proposed, and it can prevent human errors that might be caused by inappropriate condition in nuclear industries.

• Journal of KIBIM
• /
• v.10 no.4
• /
• pp.70-80
• /
• 2020

In the MEP(Mechanical Electrical and Plumbing) field, the utilization of BIM-based drawings is lower than in the architectural and structural sectors, and the limited BIM collaboration problem caused by different levels of BIM utilization in each field is becoming a serious problem in adoption and utilizing BIM. Therefore, this study analyzed the current status of BIM application in the field of mechanical equipment in the construction industry and analyzed the practical problems and limitations of adoption and utilizing BIM from a corporate perspective based on Delphi analysis techniques. Based on the results of the analysis, the limitations of the current MEP BIM application were classified into economic, technical, institutional, and social factors to derive detailed items, and, accordingly, the improvement measures were classified as institutional, policy, and technical measures. As a result, the company intends to maximize the value of BIM utilization in the MEP field by presenting improvement plans to activate BIM in the field of mechanical equipment based on the opinions of the company, thereby laying the foundation for BIM in the construction industry by creating a collaborative BIM environment for each sector in the domestic construction industry.

• Journal of Practical Engineering Education
• /
• v.13 no.3
• /
• pp.491-496
• /
• 2021

In this thesis, we intend to use CCTVs installed in existing parking lots to understand the current status of parking lots and provide real-time information to users through Android applications. It describes how to set the ROI in the parking area using YOLO V3 and how to provide the number of vacancies that change in real time through the set ROI, and describes how to link CCTV-server-user using IMAGE ZMQ and FIREBASE. The user can know the real-time situation of the parking lot near the destination before arriving through the application and can come up with various measures accordingly.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.6
• /
• pp.1075-1080
• /
• 2022

Recently, the effort is continuously applied in machine learning and deep learning algorithm which is represented as artificial intelligence algorithm in the varies field such as prediction, classification and clustering. In this paper, we propose detection algorithm for un-peeling status of PCB protection film by using Dectron2. We use 42 images of data as training and 19 images of data as testing based on 61 images which was taken under the condition of a critical reflection angel of 42.8°. As a result, we get 16 images that was detected and 3 images that was not detected among 19 images of testing data.

• Progress in Superconductivity and Cryogenics
• /
• v.11 no.3
• /
• pp.26-30
• /
• 2009

Korea Superconducting Tokamak Advanced Research(KSTAR) device is composed of 30 superconducting magnets, magnet structure, vacuum vessel, cryostat, current feeder system, and etc. KSTAR device is operated in the cryogenic temperature and high magnetic field. We install about 800 sensors - temperature sensors, stain gages, displacement gages, hall sensors - to monitor the thermal, mechanical, electrical status of KSTAR during operation. As a tremendous numbers of sensors should be installed for monitoring the KSTAR device, the method of effective installation was developed. The sensor test was successfully carried out to check its reliability and its reproduction in the cryogenic temperature. The sensor signal is processed by PXI-based DAQ system and communicated with central control system via machine network and is shown by Operator Interface(OPI) display in the main control room. In order to safely operate the device, any violations of mechanical & superconductive characteristic of the device components were informed to its operation system & operator. If the monitored values exceed the pre-set values, the protective action should be taken against the possible damage. In this paper, the system composition, operation criteria, operation result were presented.

• Journal of Korean Society for Quality Management
• /
• v.51 no.1
• /
• pp.119-129
• /
• 2023

Purpose: This study proposes a classification model for implementing condition-based maintenance (CBM) by monitoring the real-time status of a machine using acceleration sensor data collected from a vehicle. Methods: The classification model's performance was improved by applying Fourier transform to convert the acceleration sensor data from the time domain to the frequency domain. Additionally, the Generative Adversarial Network (GAN) algorithm was used to augment images and further enhance the classification model's performance. Results: Experimental results demonstrate that the GAN algorithm can effectively serve as an image augmentation technique to enhance the performance of the classification model. Consequently, the proposed approach yielded a significant improvement in the classification model's accuracy. Conclusion: While this study focused on the effectiveness of the GAN algorithm as an image augmentation method, further research is necessary to compare its performance with other image augmentation techniques. Additionally, it is essential to consider the potential for performance degradation due to class imbalance and conduct follow-up studies to address this issue.

• Journal of the Korean Society for information Management
• /
• v.39 no.1
• /
• pp.119-143
• /
• 2022

This preliminary study examined the status of data science-related course syllabi in the American Library Association (ALA) accredited Library and Information Science (LIS) programs. The purpose of this study was to explore LIS course syllabi related to data science, such as course title, course description, learning outcomes, and weekly topics. LIS programs offer various topics in data science such as the introduction to data science, data mining, database, data analysis, data visualization, data curation and management, machine learning, metadata, and computer programming. This study contributes to helping instructors develop or revise course materials to improve course competencies related to data science in the ALA-accredited LIS programs.

• Journal of the Korean Society of Radiology
• /
• v.83 no.6
• /
• pp.1208-1218
• /
• 2022

In the medical field, artificial intelligence has been used in various ways with many developments. However, most artificial intelligence technologies are developed so that one model can perform only one task, which is a limitation in designing the complex reading process of doctors with artificial intelligence. Multi-task learning is an optimal way to overcome the limitations of single-task learning methods. Multi-task learning can create a model that is efficient and advantageous for generalization by simultaneously integrating various tasks into one model. This study investigated the concepts, types, and similar concepts as multi-task learning, and examined the status and future possibilities of multi-task learning in the medical research.