• Journal of the Society of Disaster Information
• /
• 제20권1호
• /
• pp.138-146
• /
• 2024

Purpose: The purpose of this study is to find cases of using information and communication technology and smart mobility technology in snow removal vehicles and equipment for rapid and efficient road snow removal in the event of a snowstorm, and to find ways to utilize them. Method: Cases of domestic and overseas snow removal methods are investigated, and snow removal operation methods incorporating new technologies are presented. Result: Most of the operation of snow removal equipment in Korea uses GPS, CCTV, and road traffic information systems, and in the case of overseas, road weather information systems and road snow removal monitoring systems are used. It is expected that snow removal technology using autonomous snow removal vehicles, which are smart mobility, will be developed in the future. Conclusion: The results of this study can contribute to the policy of using snow removal equipment and snow removal vehicles of local governments and related organizations.

• Journal of Positioning, Navigation, and Timing
• /
• 제12권3호
• /
• pp.323-332
• /
• 2023

Today, services using Positioning, Navigation, and Timing (PNT) technology are provided in various fields, such as smartphone Location-Based Service (LBS) and autonomous driving. Generally, outdoor positioning techniques depend on the Global Navigation Satellite System (GNSS), and the need for positioning techniques that guarantee positioning accuracy, availability, and continuity is emerging with advances in service. In particular, continuity is not guaranteed in urban canyons where it is challenging to secure visible satellites with standalone GNSS, and even if more than four satellites are visible, the positioning accuracy and stability are reduced due to multipath channels. Research using Low Earth Orbit (LEO) satellites is already underway to overcome these limitations. In this study, we conducted a trend analysis of LEO-PNT research, an LEO satellite-based navigation and augmentation system. Through comparison with GNSS, the differentiation of LEO-PNT was confirmed, and the system design and receiver processing were analyzed according to LEO-PNT classification. Lastly, the current status of LEO-PNT development by country and institution was confirmed.

• Journal of the Korea Institute of Military Science and Technology
• /
• 제27권2호
• /
• pp.256-264
• /
• 2024

In the last 10 years, AI has made rapid progress, and image classification, in particular, are showing excellent performance based on deep learning. Nevertheless, due to the nature of deep learning represented by a black box, it is difficult to actually use it in critical decision-making situations such as national defense, autonomous driving, medical care, and finance due to the lack of explainability of judgement results. In order to overcome these limitations, in this study, a model description algorithm capable of local interpretation was applied to the inception network-derived AI to analyze what grounds they made when classifying national defense data. Specifically, we conduct a comparative analysis of explainability based on confidence values by performing LIME analysis from the Inception v2_resnet model and verify the similarity between human interpretations and LIME explanations. Furthermore, by comparing the LIME explanation results through the Top1 output results for Inception v3, Inception v2_resnet, and Xception models, we confirm the feasibility of comparing the efficiency and availability of deep learning networks using XAI.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 한국방송∙미디어공학회 2019년도 추계학술대회
• /
• pp.87-88
• /
• 2019

최근 기계학습 기술의 급속한 발전에 힘입어 자율주행을 위한 객체 인식 및 처리 기술 역시 비약적으로 발전하고 있다. 그러나 이러한 기계학습의 성능은 모델의 구조와 학습용 데이터의 품질에 영향을 받는다. 특히 주행환경을 잘 표현하는 학습데이터가 중요한데 전혀 새로운 도로, 주행환경, 장애물, 정적 혹은 동적 객체 등을 마주하면 정확도와 안정성에서 부정적인 영향을 받을 수 있는 것이다. 해외의 주행 데이터들에 크게 의존하고 있는 우리나라의 현실에 비춰 볼 때 국내 환경에 맞는 학습데이터를 쉽고 효율적으로 확보/관리/분석할 수 있게 하는 환경의 구축이 시급하다. 따라서 본 논문에서는 자율주행을 위한 기계학습 데이터를 효과적으로 관리하고 분석하기 위한 소프트웨어를 설계하고 개발하였다. 구체적으로는 수집된 영상들을 관리하는 기능, 영상에 존재하는 노이즈 제거 및 화질 개선 처리 기능, 학습 및 검증을 위한 메타 정보 태깅 기능, 태깅 정보의 통계적 분석 기능들을 포함한다. 개발한 소프트웨어는 우리나라에서 자체 촬영한 자율주행 학습 영상들에 대해 딥러닝 모델들을 학습하고 검증하는데 활용할 예정이다.

• Journal of Information Technology Applications and Management
• /
• 제28권3호
• /
• pp.59-75
• /
• 2021

This study aims to establish a foundation for autonomous driving on campus and communication of abundant university information in the HCI environment in a VR environment where college freshmen can freely travel around campus facilities. The purpose of this study is to develop a three-dimensional VR-style campus tour system to establish a media environment to provide abundant university information guidance services to freshmen in non-face-to-face situations. This study designed a three-dimensional virtual reality campus tour system to solve the problem of discontinuity in which VR360 filming space does not lead to space like reality, and to solve many problems of expertise in VR technology by constructing an integrated production environment of tour system. We aim to solve the problem of inefficiency, which requires a large amount of momentum in virtual space, by constructing a GUI that utilizes the motion of the field of view focus. The campus environment was designed as a three-dimensional virtual reality using a three-dimensional graphic design. In non-face-to-face situations, college freshmen freely transformed the HMD VR device, smartphone, FPS operation mode of the gyroscope sensor. The design elements of the three-dimensional virtual reality campus tour system were classified as ①Visualization of factual experiences, ②Continuity of space movement, ③Operation, automatic operation mode, ④Natural landscape animation, ⑤Animation according to wind direction, ⑥Actual space movement mode, ⑦Informatization of spatial understanding, ⑧GUI by experience environment, ⑨Text GUI by building, ⑩VR360, 3D360 Studio Environment, ⑪Three-dimensional virtual space coupling block module, ⑫3D360-3D Virtual Space Transmedia Zone, ⑬Transformable GUI(VR Device Dual Viewer-Gyro Sensor Full Viewer-FPS Operation Viewer) and an integrated production environment was established with each element. It is launched online (http://vautu.com/u1) by constructing a GUI for free driving mode and college information screens to adapt to college life for freshmen, and designing an environment that can be used simultaneously by current media such as PCs, Android, and iPads. Therefore, it conducted user research, held a development presentation, a forum on excellence in university innovation support projects, and applied it as a system on the website of a particular university. College freshmen will be able to experience university information directly from the web and app to the virtual reality campus environment.

• Journal of Engineering Education Research
• /
• 제24권3호
• /
• pp.50-57
• /
• 2021

Although the mathematics education process in AI education is a very important issue, little cases are reported in developing effective methods on AI and mathematics education at the university level. The universities cover all fields of mathematics in their curriculums, but they lack in connecting and applying the math knowledge to AI in an efficient manner. Students are hardly interested in taking many math courses and it gets worse for the students in humanities, social sciences and arts. But university education is very slow in adapting to rapidly changing new technologies in the real world. AI is a technology that is changing the paradigm of the century, so every one should be familiar with this technology but it requires fundamental math knowledge. It is not fair for the students to study all math subjects and ride on the AI train. We recognize that three key elements, SW knowledge, mathematical knowledge, and domain knowledge, are required in applying AI technology to the real world problems. This study proposes a modular approach of studying mathematics knowledge while connecting the math to different domain problems using AI techniques. We also show a modular curriculum that is developed for using math for AI-driven autonomous driving.

• Journal of Korea Society of Industrial Information Systems
• /
• 제29권1호
• /
• pp.31-48
• /
• 2024

The domestic automotive industry must consider a strategic shift from traditional automotive component manufacturing to align with future trends such as connectivity, autonomous driving, sharing, and electrification. This research conducted topic modeling on R&D projects in the future automotive sector funded by the Ministry of Trade, Industry, and Energy from 2013 to 2021. We found that topics such as sensors, communication, driver assistance technology, and battery and power technology remained consistently prominent throughout the entire period. Conversely, topics like high-strength lightweight chassis were observed only in the first period, while topics like AI, big data, and hydrogen fuel cells gained increasing importance in the second and third periods. Furthermore, this research analyzed the areas of concentrated investment for each period based on topic-specific government investment amounts and investment growth rates.

• Journal of Forest and Environmental Science
• /
• 제39권4호
• /
• pp.254-260
• /
• 2023

A sensor system has been developed that uses an ultrasonic sensor to detect the downhill slope on the side of a forest road and prevents a vehicle-type forest machine from rolling down a mountainside. A specular reflection of ultrasonic wave might cause severe issues in measuring distances to targets. By investigating the installation angle of the sensor to minimize the negative effects of specular reflection, the installation angle of lateral monitoring ultrasonic sensor could be determined based on the width of road shoulder. Obstacles such as small rocks or piece of log in a forest road may cause the forest machine to be overturned while the machine riding over due to excessive its posture change. It was determined that the laser sensor could be a part of a sensor system capable of specifying the location and size of small obstacles. Not only this sensor system including ultrasonic and laser sensors can issue a warning of dangerous sections to drivers in forest forwarders currently in use, but also it can be used as a driving safety sensor in autonomous forest machine or remote-control forest machine in the future.

• Journal of Positioning, Navigation, and Timing
• /
• 제7권1호
• /
• pp.43-52
• /
• 2018

In recent years, the need of high accuracy navigation for vehicles has increased due to the development of autonomous driving vehicles and increase in land transportation convenience. This study is performed for vehicle users to achieve a performance of centimeter-level positioning accuracy by utilizing Compact Network Real-time Kinematic (RTK) that is applicable as a national-level infrastructure. To this end, medium-baseline RTK was implemented in real time to estimate accurate integer ambiguities between reference stations for reliable generation of Network RTK correction using the linear combination of carrier-phase observations and L1/L2 pseudo-range measurements. The residual tropospheric error was estimated in real time to improve the accuracy of double-differenced integer ambiguity resolution between network configuration reference stations that have at least 30 km or longer baseline distance. In addition, C++ based software was developed to enable real-time generation and broadcasting of Compact Network RTK correction information by utilizing an accurately estimated double-differenced integer ambiguity values. As a result, the horizontal and vertical 95% accuracy was 2.5cm and 5.2cm, respectively, without performance degradation due to user's position change within the network.