• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.236-238
• /
• 2022

According to the current Road Traffic Act, the 2020 amendment bill is currently in effect as a system that designates vehicle types for each lane for the purpose of securing road use efficiency and traffic safety. When comparing the number of traffic accident fatalities per 10,000 vehicles in Germany and Korea, the number of traffic accident deaths in Germany is significantly lower than in Korea. The representative case of the German autobahn, which did not impose a speed limit, suggests that Korea's speeding laws are not the only answer to reducing the accident rate. The designated lane system, which is observed in accordance with the keep right principle of the Autobahn Expressway, plays a major role in reducing traffic accidents. Based on this fact, we propose a traffic enforcement system to crack down on vehicles violating the designated lane system and improve the compliance rate. We develop a designated lane enforcement system that recognizes vehicle types using Yolo5, a deep learning object recognition model, recognizes license plates and lanes using OpenCV, and stores the extracted data in the server to determine whether or not laws are violated.Accordingly, it is expected that there will be an effect of reducing the traffic accident rate through the improvement of driver's awareness and compliance rate.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.2 s.308
• /
• pp.19-29
• /
• 2006

As the security of personal information is becoming more important in mobile phones, we are starting to apply iris recognition technology to these devices. In conventional iris recognition, magnified iris images are required. For that, it has been necessary to use large magnified zoom & focus lens camera to capture images, but due to the requirement about low size and cost of mobile phones, the zoom & focus lens are difficult to be used. However, with rapid developments and multimedia convergence trends in mobile phones, more and more companies have built mega-pixel cameras into their mobile phones. These devices make it possible to capture a magnified iris image without zoom & focus lens. Although facial images are captured far away from the user using a mega-pixel camera, the captured iris region possesses sufficient pixel information for iris recognition. However, in this case, the eye region should be detected for accurate iris recognition in facial images. So, we propose a new fast iris detection method, which is appropriate for mobile phones based on corneal specular reflection. To detect specular reflection robustly, we propose the theoretical background of estimating the size and brightness of specular reflection based on eye, camera and illuminator models. In addition, we use the successive On/Off scheme of the illuminator to detect the optical/motion blurring and sunlight effect on input image. Experimental results show that total processing time(detecting iris region) is on average 65ms on a Samsung SCH-S2300 (with 150MHz ARM 9 CPU) mobile phone. The rate of correct iris detection is 99% (about indoor images) and 98.5% (about outdoor images).

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.22 no.5
• /
• pp.515-528
• /
• 2020

Underground concrete structures are usually designed to be used for decades, but in recent years, many of them are nearing their original life expectancy. As a result, it is necessary to promptly inspect and repair the structure, since it can cause lost of fundamental functions and bring unexpected problems. Therefore, personnel-based inspections and repairs have been underway for maintenance of underground structures, but nowadays, objective inspection technologies have been actively developed through the fusion of deep learning and image process. In particular, various researches have been conducted on developing a concrete crack detection algorithm based on supervised learning. Most of these studies requires a large amount of image data, especially, label images. In order to secure those images, it takes a lot of time and labor in reality. To resolve this problem, we introduce a method to increase the accuracy of crack area detection, improved by 0.25% on average by applying adversarial learning in this paper. The adversarial learning consists of a segmentation neural network and a discriminator neural network, and it is an algorithm that improves recognition performance by generating a virtual label image in a competitive structure. In this study, an efficient deep neural network learning method was proposed using this method, and it is expected to be used for accurate crack detection in the future.

• Proceedings of the Korean Society for the Gifted Conference
• /
• 2003.11a
• /
• pp.167-169
• /
• 2003

과학영재 교육의 목적과 효과를 달성하기 위해서는 과학영재들의 특성, 과학영재의 판별이나 교육 프로그램의 개발, 과학영재들의 과학, 과학자, 과학관련 직업에 대한 인식 등 여러 요소들에 초점을 맞추어 연구해야 하며 이를 바탕으로 교육해야 한다. 과학영재교육의 중요한 점 중 하나는 우리가 교육하는 과학영재들이 성장해서 그들의 영재성을 발휘하도록 하는 것에 있다. 이는 국가적으로도 매우 중요한 일이다. 과학기술의 발달과 국가의 발전은 뛰어난 영재들이 기여를 하였으며 그 업적을 통해 국제경쟁 사회를 선도해 나갈 수 있기 때문이다. 과학영재 교육의 성공 기준 중 하나로 노벨상 수상을 기대하는 것이라고 생각할 수 있다. 물론 노벨상만을 목표로 하는 것은 과학영재교육이 왜곡될 수 있으나, 과학영재교육을 통해서 과학 분야에 뛰어난 인재를 양성하고 이들로부터 과학의 수준이 높아지면서 자연스럽게 노벨상을 수상할 수 있을 것이다. 2002년 노벨 과학상에서 일본은 물리학과 화학 두 분야에서 수상자를 배출하였다. 특히 노벨 화학상을 받은 다나카 고이치는 박사학위도 없는 40대의 평범한 회사원이었다. 그는 일본 과학계를 장악하고 있는 유명 국립대학의 교수도 아니고, 수상 발표 뒤 대부분의 일본 화학자들이 누군지 몰라 당황했을 정도로 잘 알려지지 않은 인물이었다. 이러한 사건은 일본인들에게 희망을 안겨주었으며 과학 및 과학자에 대한 관심과 투자에 대한 인식에 있어 많은 변화를 초래하였다. 노벨상 자체가 국가정책의 목표가 될 수는 없지만, 과학자나 국민 개개인들에게 희망이 되는 것은 사실이다. 해마다 노벨상 수상자가 발표되는 시점에서 우리들은 아주 오랫동안 방관자가 되어 왔다. 이제 여러 과학영재교육기관 등을 통해서 과학영재 교육을 효율적으로 실시한다면 조만간 상황이 바뀔 것으로 기대할 수 있다.택한 이유는 첫 번째가 사회 봉사와 국가 발전에 기여하기 위한 것이었으며, 다음으로는 생활의 안정을 꼽고 있었다. 이외에도 과학적 업적 달성을 위해, 자신의 꿈(이상) 실현을 위해 등의 이유를 들고 있었다. 이러한 경향은 남자 영재와 여자 영재들간에 다소 차이는 있었으나 거의 유사한 것으로 조사되었다(Pearson $X^2$=2.186, p>0.05). 우수한 능력을 소유한 영재들이 과학관련 분야를 선호하지 않는다면 우리나라의 과학 발전은 그리 낙관할 수 없을 것이다. 그러므로, 영재들을 과학 관련 분야로 이끌어 그들이 소유한 영재성을 발휘하도록 하는 것은 매우 중요한 일일 것이다. 이룰 위해서는 과학 영재들이 자신의 능력에 대한 자신감을 더욱 높여야 하며 그 능력을 과학관련 분야에 발휘하도록 하기 위한 국가적, 사회적, 교육적 노력이 필요하다. 노력이 필요하다.~42.1mg$CO_2$/kg.hr였으며 12$^{\circ}C$에서 2.5~8.2mg$CO_2$/kg.hr로 일반적으로 보고되고 있는 토마토 호흡속도와 일치하는 결과를 나타내었다.다.환원당인 sucrose 함량은 계속 증가하였고 fructose, glucose, sorbitol의 함량(추황의 sorbitol을 제외)은 생장이 촉진됨에 따라 증가하다가 다시 점차적으로 감소하였다. 이러한 결과는 총당과 환원당의 측정결과와 일치한 것으로 나타났다. 결론적으로 배의 성장에 따라 산 함량은 감소하였고 당 함량은 증가하였다.luco-pyranoside, quercetin 7-O- -glucopyranoside, acacetin 7-O-$\beta$-D-glucuronide and apigenin-6-C-$\beta$

• Korean journal of communication and information
• /
• v.59
• /
• pp.31-49
• /
• 2012

This study investigates normative role model of the journalists under the changing environment. Firstly, this article explores what pressure the new media environment gives to the journalists in their routine of news production and distribution. These are stated from the angle of epistemological, professional and interactive pressure. Next, as a reference for the standard journalism in the age of mass media, the idea of Rhee Young-hee, a late journalist who won respects from many Korean journalists, is studied. His firm belief in the pursuit of hard facts, rigorous investigative writing and expertism are spelt out. Then, this study explores how, in real term, this pressure changes the journalistic value, norm and practices in the newsroom. Ten of Koran journalists are interviewed in order to get their idea about the emerging journalistic standards under the digital environment. From this in-depth interviews, it is conclued that the pursuit of hard fact, investigative writing, expertism of Rhee Young-hee are, nonetheless the change of the media technology, still effective and provide good reference points for the enhancement of the standard of journalism in Korea. However, it is also suggested that the methods to fulfil desirable journalism in the digital age should be different from that of the mass communication age. The interviewees make propose that the journalist, as a network node, news curator or coordinator, should actively interact with the audiences facilitating their enhanced potential as a news 'prosumer'(producer and consumer).

• Management & Information Systems Review
• /
• v.33 no.4
• /
• pp.99-118
• /
• 2014

Using the theory of attribution, this study investigates the determinants if controllability and explores underlying dimensions of online information credibility, and then investigates if the credibility of online information influences the users' intention to use the online information for evaluating or judging the involved products. Moreover, as a research attempt to investigate the impacts of online information credibility, this study examines whether the main effect of perceived online information credibility on the intention of using online information to make a decision of purchase is mediated by both perceived risk and perceived usefulness. A total of 287 survey forms were collected from online consumers. We examined reliability by exploring internal consistency of the multiple item scales in the overall sample. Convergent and discriminant validity were also examined for evidence of construct validity. Then, PLS technique was employed to test the research model. As a result of analyzing data from a dataset of 287 responses via PLS technique, it is found that (1) both sources (controllability and stability) of perceived credibility are significantly associated with both perceived risk and perceived usefulness, and (2) perceived risk as well as perceived usefulness partially mediate the link between the two sources of credibility and intention to use. The findings of this study also suggest that the two dimensions of online information credibility influence information recipient's intention to use. Moreover, the online information including descriptions about controllability and stability can trigger potential consumers to perceive risk about consumption of the informed products and services. Therefore, providing online information with highly described controllability and stability can increase not only the credibility of the online information itself, but also the intention to use the online information through perceived risk and usefulness.

• Science of Emotion and Sensibility
• /
• v.22 no.1
• /
• pp.45-54
• /
• 2019

Empathy has been observed to be pivotal in enhancing both social relations and the efficiency of task performance. Empathetic interaction has been shown to begin with individuals mirroring each other's facial expressions, vocal tone, actions, and so on. The internal responses of the cardiovascular activity of people engaged in empathetic interaction are also known to be synchronized. This study attempted to objectively and quantitatively define the rules of empathy with regard to the synchronization of cardiac rhythm between persons. Seventy-four subjects participated in the investigation and were paired to imitate the facial expressions of their partner. An electrocardiogram (ECG) measurement was taken as the participants conducted the task. Quantitative indicators were extracted from the heart rhythm pattern (HRP) and the heart rhythm coherence (HRC) to determine the difference of synchronization of heart rhythms between two individuals as they pertained to empathy. Statistical significance was confirmed by an independent sample t-test. The HRP and HRC correlation(r) between persons increased significantly with empathy in comparison to an interaction that was not empathetic. A difference of the standard deviation of NN intervals (SDNN) and the dominant peak frequency decreased. Therefore, significant parameters to evaluate empathy have been proposed through a step-wise discrimination analysis. Empathic interactions may thus be managed and monitored for high quality social interaction and communication.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.12
• /
• pp.25-34
• /
• 2020

In this paper, we empirically compare the effectiveness of training models to recognize beauty-related skin disease using supervised deep learning algorithms. Recently, deep learning algorithms are being actively applied for various fields such as industry, education, and medical. For instance, in the medical field, the ability to diagnose cutaneous cancer using deep learning based artificial intelligence has improved to the experts level. However, there are still insufficient cases applied to disease related to skin beauty. This study experimentally compares the effectiveness of identifying beauty-related skin disease by applying deep learning algorithms, considering CNN, ResNet, and SE-ResNet. The experimental results using these training models show that the accuracy of CNN is 71.5% on average, ResNet is 90.6% on average, and SE-ResNet is 95.3% on average. In particular, the SE-ResNet-50 model, which is a SE-ResNet algorithm with 50 hierarchical structures, showed the most effective result for identifying beauty-related skin diseases with an average accuracy of 96.2%. The purpose of this paper is to study effective training and methods of deep learning algorithms in consideration of the identification for beauty-related skin disease. Thus, it will be able to contribute to the development of services used to treat and easy the skin disease.

• Progress in Medical Physics
• /
• v.26 no.1
• /
• pp.52-58
• /
• 2015

The automated dental cavity detection program for a new concept intra-oral dental x-ray imaging device, an auxiliary diagnosis system, which is able to assist a dentist to identify dental caries in an early stage and to make an accurate diagnosis, was to be developed. The primary theory of the automatic dental cavity detection program is divided into two algorithms; one is an image segmentation skill to discriminate between a dental cavity and a normal tooth and the other is a computational method to analyze feature of an tooth image and take an advantage of it for detection of dental cavities. In the present study, it is, first, evaluated how accurately the DRLSE (Direct Regularized Level Set Evolution) method extracts demarcation surrounding the dental cavity. In order to evaluate the ability of the developed algorithm to automatically detect dental cavities, 7 tooth phantoms from incisor to molar were fabricated which contained a various form of cavities. Then, dental cavities in the tooth phantom images were analyzed with the developed algorithm. Except for two cavities whose contours were identified partially, the contours of 12 cavities were correctly discriminated by the automated dental caries detection program, which, consequently, proved the practical feasibility of the automatic dental lesion detection algorithm. However, an efficient and enhanced algorithm is required for its application to the actual dental diagnosis since shapes or conditions of the dental caries are different between individuals and complicated. In the future, the automatic dental cavity detection system will be improved adding pattern recognition or machine learning based algorithm which can deal with information of tooth status.

• Journal of the Society of Disaster Information
• /
• v.19 no.3
• /
• pp.498-509
• /
• 2023

Purpose: This paper proposes a method detecting the falling of a maintenance worker in the underground utility tunnel, by applying deep learning techniques using CCTV video, and evaluates the applicability of the proposed method to the worker monitoring of the utility tunnel. Method: Each rule was designed to detect the falling of a maintenance worker by using the inference results from pre-trained YOLOv5 and OpenPose models, respectively. The rules were then integrally applied to detect worker falls within the utility tunnel. Result: Although the worker presence and falling were detected by the proposed model, the inference results were dependent on both the distance between the worker and CCTV and the falling direction of the worker. Additionally, the falling detection system using YOLOv5 shows superior performance, due to its lower dependence on distance and fall direction, compared to the OpenPose-based. Consequently, results from the fall detection using the integrated dual deep learning model were dependent on the YOLOv5 detection performance. Conclusion: The proposed hybrid model shows detecting an abnormal worker in the utility tunnel but the improvement of the model was meaningless compared to the single model based YOLOv5 due to severe differences in detection performance between each deep learning model