• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.01a
• /
• pp.35-38
• /
• 2023

포트홀은 주행하는 자동차와 접촉이 이뤄지면 차체나 운전자에게 충격을 주고 제어를 잃게 하여 도로 위 안전을 위협할 수 있다. 포트홀의 검출을 위한 국내 동향으로는 진동을 이용한 방식과 신고시스템 이용한 방식과 영상 인식을 기반한 방식이 있다. 이 중 영상 인식 기반 방식은 보급이 쉽고 비용이 저렴하나, 컴퓨터 비전 알고리즘은 영상의 품질에 따라 정확도가 달라지는 문제가 있었다. 이를 보완하기 위해 영상 인식 기반의 딥러닝 모델을 사용한다. 따라서, 본 논문에서는 사전 학습된 딥러닝 모델의 정확도 향상을 위한 Feature Level Ensemble 기법을 제안한다. 제안된 기법은 사전 학습된 CNN 모델 중 Test 데이터의 정확도 기준 Top-3 모델을 선정하여 각 딥러닝 모델의 Feature Map을 Concatenate하고 이를 Fully-Connected(FC) Layer로 입력하여 구현한다. Feature Level Ensemble 기법이 적용된 딥러닝 모델은 평균 대비 3.76%의 정확도 향상을 보였으며, Top-1 모델인 ShuffleNet보다 0.94%의 정확도 향상을 보였다. 결론적으로 본 논문에서 제안된 기법은 사전 학습된 모델들을 이용하여 각 모델의 다양한 특징을 통해 기존 모델 대비 정확도의 향상을 이룰 수 있었다.

• Journal of Hydrogen and New Energy
• /
• v.34 no.6
• /
• pp.555-561
• /
• 2023

In this study, we proposed a standard model for the design, construction and demonstration of the technology development and substantiation of small hydrogen powered vessel in order to respond to the alternative fuel-using vessel market that requires the use of low-carbon/carbon-free fuel as a greenhouse gas reduction measure. The hydrogen fuel cell-based electric propulsion system developed through this is optimized through performance and durability tests on the land-based test site (LBTS), and the electric propulsion system applied to this result is mounted on a small hydrogen propulsion vessel and operated. Simultaneously, through the digital twin technology between the LBTS and the hydrogen-propelled vessel on the sea, the technology that can predict and diagnose the problems that can occur in the electric propulsion system of the vessel is applied to carry out the empirical study of the hydrogen-propelled vessel. In addition, we propose a commercialization model by analyzing the economic feasibility of the demonstration vessel.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.5
• /
• pp.92-107
• /
• 2023

Recently, along with the continuous increase in the supply of electric vehicles, electric vehicle fire accidents are also showing a rapidly increasing trend. Electric vehicle fires last for a long time compared to fires in internal combustion engine vehicles and have problems with the risk of secondary explosions and the generation of large amounts of smoke. In particular, electric vehicle fires in underground roads, which are semi-enclosed spaces, may amplify the problems of existing electric vehicle fires. On the other hand, there are no domestic response guidelines for electric vehicle fires occurring inside underground roads. Therefore, an awareness of fire accidents was confirmed through a survey of the general public, and electric vehicle fire characteristics and primary considerations were derived from stakeholders related to electric vehicle fires in underpasses. Through this, the guidelines for responding to electric vehicle fires on underground roads were established.

• Journal of Sensor Science and Technology
• /
• v.32 no.5
• /
• pp.320-327
• /
• 2023

In this study, an FPGA-based sealer inspection system was developed to inspect the sealer applied to install vehicle glass on a car body. The sealer is a liquid or paste-like material that promotes adhesion such as sealing and waterproofing for mounting and assembling vehicle parts to a car body. The system installed in the existing vehicle design parts line does not detect the sealer in the glass rotation section and takes a long time to process. This study developed a line laser camera sensor and an FPGA vision signal processing module to solve this problem. The line laser camera sensor was developed such that the resolution and speed of the camera for data acquisition could be modified according to the irradiation angle of the laser. Furthermore, it was developed considering the mountability of the entire system to prevent interference with the sealer ejection machine. In addition, a vision signal processing module was developed using the Zynq-7020 FPGA chip to improve the processing speed of the algorithm that converted the profile to the sealer shape image acquired from a 2D camera and calculated the width and height of the sealer using the converted profile. The performance of the developed sealer application inspection system was verified by establishing an experimental environment identical to that of an actual automobile production line. The experimental results confirmed the performance of the sealer application inspection at a level that satisfied the requirements of automotive field standards.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.34 no.2
• /
• pp.217-228
• /
• 2024

LiDAR(Light Detection And Ranging) sensors, which play a pivotal role among cameras, RADAR(RAdio Detection And Ranging), and ultrasonic sensors for the safe operation of autonomous vehicles, can recognize and detect objects in 360 degrees. However, since LiDAR sensors use lasers to measure distance, they are vulnerable to attackers and face various security threats. In this paper, we examine several security threats against LiDAR sensors: relay, spoofing, and replay attacks, analyze the possibility and impact of physical jamming attacks, and analyze the risk these attacks pose to the reliability of autonomous driving systems. Through experiments, we show that jamming attacks can cause errors in the ranging ability of LiDAR sensors. With vehicle-to-vehicle (V2V) communication, multi-sensor fusion under development and LiDAR anomaly data detection, this work aims to provide a basic direction for countermeasures against these threats enhancing the security of autonomous vehicles, and verify the practical applicability and effectiveness of the proposed countermeasures in future research.

• KOREAN JOURNAL OF PACKAGING SCIENCE & TECHNOLOGY
• /
• v.29 no.3
• /
• pp.203-209
• /
• 2023

The increasing saturation challenges in storage facilities for Low- and Intermediate-Level Radioactive Waste call for a more efficient storage approach. Consequently, we have developed a square-structured container that features a storage capacity approximately 20% greater than that of conventional drum-type containers. Considering the need to contain various radioactive wastes from nuclear power usage securely until they no longer pose a threat to human health or the environment, this study focuses on evaluating the sealing efficacy of the newly designed rectangular container using finite element analysis. Since radioactive waste containers typically do not experience external forces except under special circumstances, our analysis simulated the impact of an external force, assuming a fall scenario. After fastening the bolts, we examined the vertical stress distribution on the container by applying the calculated external force. The analysis confirms the container's stable seal.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.1
• /
• pp.197-205
• /
• 2024

Development of AI and big data-based algorithms to advance and optimize the recognition and detection performance of various static/dynamic vehicles in front and around the vehicle at a time when securing driving safety is the most important point in the development and commercialization of autonomous vehicles. etc. are being studied. However, there are many research cases for recognizing the same vehicle by using the unique advantages of radar and camera, but deep learning image processing technology is not used, or only a short distance is detected as the same target due to radar performance problems. Therefore, there is a need for a convergence-based vehicle recognition method that configures a dataset that can be collected from radar equipment and camera equipment, calculates the error of the dataset, and recognizes it as the same target. In this paper, we aim to develop a technology that can link location information according to the installation location because data errors occur because it is judged as the same object depending on the installation location of the radar and CCTV (video).

• Journal of IKEEE
• /
• v.28 no.1
• /
• pp.116-122
• /
• 2024

AMBA AHB-Lite bus is widely used in on-chip bus protocol for low-power and cost-effective SoC. However, it lacks built-in error detection and correction for end-to-end data integrity. This can lead to data corruption and system instability, particularly in harsh environments like automotive applications. To mitigate this problem, this paper proposes the application of SEC-DED (Single Error Correction-Double Error Detection) to AMBA AHB-Lite bus. It aims not only to detect errors in real-time but also to correct them, thereby enhancing end-to-end data integrity. Simulation results demonstrate real-time error detection and correction when errors occur, which bolsters end-to-end data integrity of automotive on-chip bus.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.2
• /
• pp.127-132
• /
• 2024

Recently, secondary batteries, commonly known as rechargeable batteries, find widespread applications across various industries. Particularly valued for their compact and lightweight characteristics, they play a crucial role in diverse portable electronic devices such as smartphones, laptops, and tablets, offering high energy density and efficient charge-discharge capabilities. Moreover, they serve as vital components in electric vehicles and contribute significantly to the field of renewable energy as part of Energy Storage Systems(ESS). However, despite advancements in this technology, issues such as reduced lifespan, cracking, damage, and even the risk of fire can arise due to excessive charging and discharging of secondary batteries. To address these challenges, Battery Management System(BMS) are employed to protect against overcharging and improve overall performance. Nevertheless, understanding the protective range settings of BMS using lithium-ion batteries, the most commonly used secondary batteries, and lead-acid batteries can be challenging. Therefore, this paper aims to utilize a battery charge-discharge tester and simulator to investigate the charging and discharging characteristics of lithium-ion batteries and lead-acid batteries, addressing the associated challenges of reduced lifespan, cracking, damage, and fire hazards in secondary batteries.

• Korean Journal of Materials Research
• /
• v.34 no.10
• /
• pp.506-514
• /
• 2024

High-frequency soft magnetic Ni, Fe, and Co-based thin films have been developed, typically as nanocrystals and amorphous alloys. These Ni, Fe, and Co-based thin films exhibit remarkably good frequency dependence up to high frequencies of several tens of MHz. These properties arise from the moderate magnetic anisotropy and fairly high electrical resistivity that result from the microstructural characteristics of the nanocrystalline and amorphous states. In this paper, Al-Co/AlN-Co and Al-N/AlN-Co multilayer films were deposited using two-facing-target type sputtering (TFTS). Their microstructures, magnetic and electrical properties were studied with the expectation that inserting Al-Co or Al-N as an interlayer could effectively reduce the coercive force and produce films with relatively high resistivity. A new approach is presented for the fabrication of Al-Co (Al-N)/AlN-Co multilayer films, prepared with the TFTS system. The deposited films were isothermally annealed at different temperatures and investigated for microstructure, magnetic properties and resistivity. The TFTS method used in this experiment is suitable for fabricating Al-Co(Al-N)/AlN-Co multilayer films with different layer thickness ratio (LTR). The annealing conditions, thickness of the multilayer film, and LTR can control the physical properties as well as the microstructure of the manufactured film. Magnetization and resistance increased and coercivity decreased as LTR decreased. The thin film with LTR = 0.175 exhibited high resistivity values of 2,500 µΩ-cm, magnetization of 360 emu/cm³, and coercivity of 5 Oe. Results suggests that thin films with such good resistivity and magnetization would be useful as high-density recording materials.