• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.01a
• /
• pp.21-22
• /
• 2023

본 논문에서는 낙상과 비낙상 구별을 위한 분류 모델을 제안한다. 일상생활과 낙상을 구분해 내는 것은 낙상이 발생하기 이전에 감지하고 사고를 예방할 수 있다. 낙상은 일상생활 중 일어나기 쉬우며, 노인들에게는 골절 및 기관 파열 등과 같은 심각한 부상을 초래할 수 있기 때문에 낙상 방지를 위한 낙상과 비낙상 행동의 구분은 중요한 문제이다. 따라서 실시간으로 수집되는 다양한 활동에서의 센서 데이터를 활용하여 낙상과 비낙상의 행동을 구분하였다.

• Convergence Security Journal
• /
• v.15 no.7
• /
• pp.39-45
• /
• 2015

Industrial secrets that companies own recently protected by various act related industrial security such as Trade Secret Act, Act on Prevention of Divulgence and Protection of Industrial Technology, etc. However, despite such protection infringement and leakage accidents of industrial secrets is increasing every year. According to a survey conducted by KAITS(Korean Association for Industrial Technology Security) annual average of estimated damage by industrial secrets leakage is estimated to be "50 trillion won." This is equivalent to the amount of annual revenue of small businesses more than 4,700 units. Following this, industrial secrets leakage causes serious damages to competitiveness of nation and companies and economic. However investment and effort to the industrial secrets leakage crime is lack of level compared to the scale of damage. Actually, most companies except some major companies are lack of response action about industrial secrets leakage because of shortage of separate organization, workforce, budget for industrial secrets leakage security. This paper aims to understand the overall flow of the industrial secrets leakage crime through various taxonomy such as cause of occurrence and leakage pathway and grasp the condition of damage from industrial secrets leakage through analyzation of internal and external industrial secrets leakage crime. This is expected to be the basis for related research.

• Korean Journal of Psychosomatic Medicine
• /
• v.20 no.1
• /
• pp.40-49
• /
• 2012

Objectives : To examine emotional and psychological characteristics associated with suicide attempts in depressed patients. Methods : A sample of 37 inpatients diagnosed with major depressive disorder or depressive disorder NOS was divided into two groups : lifetime suicide attempters(N=15 ; 40.54%), non-attempters(N=22 ; 59.46%). Beck Depression Scale(BDI), Beck Anxiety Scale(BAI), Hamilton Depression Rating Scale(HDRS), Hamilton Anxiety Rating Scale(HARS), and MMPI-2 were used to evaluate symptoms severity and psychological characteristics. Results : Suicide attempters scored higher on the BDI though there were no group differences on the HDRS and on the both anxiety scales. Also they showed higher scores on the F, Fb, Pa, RC1, DEP, HEA, PK, AAS among MMPI-2 subscales. Our findings suggest that suicide attempters among depressed patients undergo more severe subjective distress and difficulties in adjustment than non-attempters. Also they were more hostile to others and showed lower trust. Lastly, they showed more somatic complaints and substance related problems. Conclusion : The present study showed that suicide attempters among depressed patients have distinct emotional and psychological characteristics. MMPI-2 would be helpful to assess suicidal risk of depressed patients.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.1
• /
• pp.105-122
• /
• 2022

According to the statistics about the fatal crashes that have occurred on the expressways for the last 5 years, those who died on the shoulders of the road has been as 3 times high as the others who died on the expressways. It suggests that the crashes on the shoulders of the road should be fatal, and that it would be important to prevent the traffic crashes by cracking down on the vehicles intruding the shoulders of the road. Therefore, this study proposed a method to detect a vehicle that violates the shoulder lane by using the Faster R-CNN. The vehicle was detected based on the Faster R-CNN, and an additional reading module was configured to determine whether there was a shoulder violation. For experiments and evaluations, GTAV, a simulation game that can reproduce situations similar to the real world, was used. 1,800 images of training data and 800 evaluation data were processed and generated, and the performance according to the change of the threshold value was measured in ZFNet and VGG16. As a result, the detection rate of ZFNet was 99.2% based on Threshold 0.8 and VGG16 93.9% based on Threshold 0.7, and the average detection speed for each model was 0.0468 seconds for ZFNet and 0.16 seconds for VGG16, so the detection rate of ZFNet was about 7% higher. The speed was also confirmed to be about 3.4 times faster. These results show that even in a relatively uncomplicated network, it is possible to detect a vehicle that violates the shoulder lane at a high speed without pre-processing the input image. It suggests that this algorithm can be used to detect violations of designated lanes if sufficient training datasets based on actual video data are obtained.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2020.11a
• /
• pp.161-162
• /
• 2020

Major advanced ports around the world are preparing for environmental regulations such as increased efficiency of ports and low emission of pollutants in ports by utilizing fourth industrial technologies and ICT technologies such as AI, big data, self-driving cars and connected cars. It is also investing in developing fully unmanned terminals to solve the problem of workforce reduction caused by avoidance of 3D industries. However, the introduction of advanced technology is being delayed in domestic ports, which has led to a drop in port efficiency. In addition, port safety accidents have also occurred frequently, seriously affecting port marketing. Thus, the characteristics and types of each container terminal in Korea were analyzed and the factors for introducing autonomous cooperative driving were classified into five section factors and 15 division factors. Hierarchically classified factors will be surveyed on workers working in shipping lines, port construction, container terminals and related ministries.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.24 no.1
• /
• pp.56-67
• /
• 2018

With the introduction of the maritime safety supervisor system in Korea following the passenger vessel Sewol accident, the safety control system for coastal vessels has been reinforced. A maritime safety supervisor performs marine accident prevention activities by offering periodical or occasional guidance and supervision. When a deficiency is found during guidance or supervision sessions, an order for improvement is issued to rectify the problem by such measures as supplementation or replacement of vessel facilities, improvement of work hours and working conditions for employees, educational and training programs for executives and employees, or the improvement of other affairs relating to maritime safety control. However the present order for navigation suspension by a maritime safety supervisor is limited solely to supplementation or replacement. For this reason, orders for navigation suspension against other facilities is impossible, even if a serious deficiency that could lead to a marine accident such as poor cargo loading conditions or unqualified crew is identified. Therefore, the order for vessel navigation suspension to secure seaworthiness should be expanded to include cargo loading/unloading operations, certificates and documentation, maritime safety management systems, and human elements including emergency drills and working conditions, in addition to the supplementation or replacement of vessel facilities that exists.

• Review of KIISC
• /
• v.30 no.2
• /
• pp.49-57
• /
• 2020

군사 등의 특수 목적으로만 사용되었던 무인비행체 드론이 최근 상용 수준의 간결한 구조와 저가화가 가능해지면서 여러 제조업체를 통하여 민간분야의 다양한 응용에 활용 가능함을 증명하고 있다. 그러나 제조업체들 간의 시장 우위 선점을 위한 과열 경쟁으로 인하여 보안 안전성 검증 단계를 거치지 않은 드론과 이에 수반되는 애플리케이션이 시장에 바로 출시되면서 이들이 우리 사회를 향한 공격도구로 활용될 수 있다는 새로운 잠재적 위협이 우려되고 있다, 이와 관련하여 현재 드론과 애플리케이션과의 연결 및 데이터 통신 과정에서 완성도가 낮은 접근제어 기술이나 암호화되지 않은 통신방식을 비롯하여 드론 내부 소프트웨어의 코딩 상의 문제점 등에 의하여 다양한 취약점이 노출되고 있는 상태이다. 이러한 취약점들로 인하여 드론의 인증 해제 및 하이재킹을 통한 불법 영상촬영이나 개인정보의 유출 등을 비롯하여 특정 목표물을 향한 드론의 고의적 추락 등이 발생할 경우 재산 피해뿐만 아니라 인명 피해까지 발생할 수 있다. 특히, 현재의 드론 응용은 초기단계여서 향후 다양한 응용과 유관 기술들이 폭넓게 전개되어야 하는 시점에서 이러한 사고 가능성은 매우 심각하게 인식되어야 할 것이다. 더구나 제4차 산업혁명 시대의 드론은 비상시를 위한 다이나믹 모바일 게이트웨이 역할까지도 수행하여야 하는 환경에서 악의적인 행위는 전체 사회로 확산될 우려도 있으므로 미래 사회의 드론을 위한 안전문제는 매우 시급하고 중대하다고 할 수 있다. 이에 본 고에서는 현재까지 발표된 드론에 대한 다양한 보안위협을 조사하고 이러한 보안 위협을 요소별로 분류하여 정리하였다. 본 기고가 간단하게나마 정리한 내용을 통하여 다양한 보안위협에 대한 대응기술을 준비하기 위한 시발점이 되었으면 한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.803-805
• /
• 2022

자율주행의 시대가 도래함에 따라, 딥러닝 모델에 대한 적대적 공격 위험이 함께 증가하고 있다. 카메라 기반 자율주행차량이 공격받을 경우 보행자나 표지판 등에 대한 오분류로 인해 심각한 사고로 이어질 수 있어, 자율주행 시스템에서의 적대적 공격에 대한 방어 및 보안 기술 연구가 필수적이다. 이에 본 논문에서는 GTSRB 표지판 데이터를 이용하여 각종 공격 및 방어 기법을 개발하고 제안한다. 시간 및 정확도 측면에서 성능을 비교함으로써, 자율주행에 최적인 모델을 탐구하고 더 나아가 해당 모델들의 완전자율주행을 위한 발전 방향을 제안한다.

• Information Systems Review
• /
• v.25 no.4
• /
• pp.113-130
• /
• 2023

Due to economic development and increasing gross national income, the number of automobiles continues to rise, leading to a serious issue of illegal parking due to limited road conditions and insufficient parking facilities. Illegal parking causes significant inconvenience and displeasure to people and can even result in accidents and loss of lives. The severity of accidents and their consequences, related to the growing number of vehicles and illegal parking, is escalating, particularly in the metropolitan areas. Consequently, efforts are being made to address this problem as a cause of social issues and come up with measures to reduce illegal parking. In particular, half of the public complaints in the metropolitan area are related to illegal parking, and the highest physical and human damage occurs in Gyeonggi. Thus, this study aims to use machine learning techniques based on data related to illegal parking in Suwon city, Gyeonggi, to categorize regional characteristics and propose effective measures to crack down on illegal parking. Additionally, practical, social, policy, and legal measures to decrease illegal parking in the metropolitan area are suggested. This study has academic significance in that it solved the problem of illegal parking, which is mentioned as one of the social problems that cause traffic congestion, by classifying regional characteristics using K-prototype, a machine learning algorithm. Furthermore, the results of this study contribute to practical and social aspects by providing measures to decrease illegal parking in the metropolitan area.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.12 no.5
• /
• pp.725-730
• /
• 2017

The use of general IT resources in the Instrumentation and Control system(I&C) for the safety of Nuclear Power Plants(NPPs) is increasing. As a result, potential security vulnerabilities of existing IT resources may cause cyber attack to NPPs, which may cause serious consequences not only to shutdown of NPPs but also to national disasters. In order to respond to this, domestic nuclear regulatory agencies are developing guidelines for regulating nuclear cyber security regulations and expanding the range of regulatory targets. However, it is necessary to take measures to cope with not only general security problems of NPPs but also attacks specific to NPPs. In this paper, we select 42 items related to the vulnerability inspection in the contents defined in R.G.5.71 and classify it into 5 types. If the vulnerability inspection tool is developed based on the proposed analysis, it will be possible to improve the inspection efficiency of the cyber security vulnerability of the NPPs.