• Journal of the Institute of Convergence Signal Processing
• /
• v.12 no.2
• /
• pp.150-156
• /
• 2011

Smart Highway is a next generation highway that significantly improves a traffic safety, reduces incidence of traffic accidents, and supports intelligent and convenient driving environments so that drivers can drive at high speeds in safety. In order to implement smart highway, it is required to gather a large amount of data including conditions of a road and the status of vehicles, and other useful data. To provide situation information of highway, it has been gathered traffic information using optical sensors(CCTV, etc.). However, this technique has problems such as the problem of information gathering, lack of accuracy depending on weather conditions and limitation of maintenance. It needs radar system which has not effect on environmental change and algorithm processing technique in order to provide information for a safety driving to driver and car. In this paper, it is used radar with 9.4GHz to test performance of a road surface and developed radar system for detecting test. And we compared and analyzed a performance of data acquired from each radar through computer simulation.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.2
• /
• pp.104-113
• /
• 2019

The road management institute needs lots of cost to repair road surface damage. These damages are inevitable due to natural factors and aging, but maintenance technologies for efficient repair of the broken road are needed. Various technologies have been developed and applied to cope with such a demand. Recently, maintenance technology for road surface damage repair is being developed using image information collected in the form of a black box installed in a vehicle. There are various methods to extract the damaged region, however, we will discuss the image recognition technology of the deep neural network structure that is actively studied recently. In this paper, we introduce a new neural network which can estimate the road damage and its location in the image by region-based convolution neural network algorithm. In order to develop the algorithm, about 600 images were collected through actual driving. Then, learning was carried out and compared with the existing model, we developed a neural network with 10.67% accuracy.

• Convergence Security Journal
• /
• v.18 no.2
• /
• pp.133-139
• /
• 2018

The 5 Game changer means the concepts of the army's operation against the enemy's asymmetric threats so that minimize damage to the public and leads to victory in war in the shortest time. A study of network architecture of Dronebot operation is a key study to carry out integrated operation with integrated C4I system by organically linking several drones battle groups through ICT. The NBC reconnaissance drones can be used instead of vehicles and humans to detect NBC materials and share situations quickly. However, there is still a lack of research on the swarm flight of the NBC reconnaissance drones and the weaknesses of cyber electronic warfare. In this study, we present weaknesses and countermeasures of CBRNs in swarm flight operations and provide a basis for future research.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.2
• /
• pp.72-81
• /
• 2023

This research proposes a novel approach to tackle the challenge of categorizing unstructured customer complaints in the automotive industry. The goal is to identify potential vehicle defects based on the findings of our algorithm, which can assist automakers in mitigating significant losses and reputational damage caused by mass claims. To achieve this goal, our model uses the Word2Vec method to analyze large volumes of unstructured customer complaint data from the National Highway Traffic Safety Administration (NHTSA). By developing a score dictionary for eight pre-selected criteria, our algorithm can efficiently categorize complaints and detect potential vehicle defects. By calculating the score of each complaint, our algorithm can identify patterns and correlations that can indicate potential defects in the vehicle. One of the key benefits of this approach is its ability to handle a large volume of unstructured data, which can be challenging for traditional methods. By using machine learning techniques, we can extract meaningful insights from customer complaints, which can help automakers prioritize and address potential defects before they become widespread issues. In conclusion, this research provides a promising approach to categorize unstructured customer complaints in the automotive industry and identify potential vehicle defects. By leveraging the power of machine learning, we can help automakers improve the quality of their products and enhance customer satisfaction. Further studies can build upon this approach to explore other potential applications and expand its scope to other industries.

• The Journal of Bigdata
• /
• v.9 no.1
• /
• pp.89-100
• /
• 2024

In the field of computer vision, models such as You Look Only Once (YOLO) and ResNet are widely used due to their real-time performance and high accuracy. However, to apply these models in real-world environments, factors such as runtime compatibility, memory usage, computing resources, and real-time conditions must be considered. This study compares the characteristics of three deep model runtimes: ONNX Runtime, TensorRT, and OpenCV DNN, and analyzes their performance on two models. The aim of this paper is to provide criteria for runtime selection for practical applications. The experiments compare runtimes based on the evaluation metrics of time, memory usage, and accuracy for vehicle license plate recognition and classification tasks. The experimental results show that ONNX Runtime excels in complex object detection performance, OpenCV DNN is suitable for environments with limited memory, and TensorRT offers superior execution speed for complex models.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.25 no.6
• /
• pp.245-253
• /
• 2021

RC slab bridges account for the largest portion of deteriorated bridges in Korea. However, most RC slabs are not included in the first and second classes of bridges, which are subject to bridge safety management and maintenance. The highest damaged components in highway bridges are the subsidiary facilities including expansion joints and bearings. In particular, leakage through expansion joints causes deterioration and cracks of concrete and exposure of reinforced bars. Therefore, this study analyzed the effect of adhesion damage at expansion joints on the response of the deck in RC slab bridges. When the spacing between the expansion joints at both ends was closely adhered, cracks occurred in the concrete at both ends of the deck due to the resistance rigidity at the expansion joints. Based on the response results, the correlation analysis between displacements in the longitudinal direction of the expansion joint and concrete stress at both ends of the deck for each damage scenario was performed to investigate the effect of the occurrence of damage on the bridge behavior. When expansion joint devices at both sides were damaged, the correlation between displacement and stress showed a low correlation of 0.18 when the vehicles proceeded along all the lanes. Compared with those in the intact state, the deflections of the deck in the damaged case at both sides showed a low correlation of 0.34 to 0.53 while the vehicle passed and 0.17 to 0.43 after the vehicle passed. This means that the occurrence of cracks in the ends of concrete changed the behavior of the deck. Therefore, data-deriven damage detection could be developed to manage the damage to expansion joints that cause damage and deterioration of the deck.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.33 no.6
• /
• pp.2359-2368
• /
• 2013

Cone penetration tests (CPTs) have been increasingly used for site characterizations. However, the site investigations using CPTs are often limited due to soil conditions depending on the cone size and capacity of the CPT system. The small sectional area of a miniature cone improves the applicability of the CPT system due to the increased capacity of the CPT system. A continuous intrusion system using a coiled rod allows fast and cost effective site investigation. In this study, the performance of the continuous intrusion miniature cone penetration test (CIMCPT) system has been evaluated by comparison tests with the standard CPT system at several construction sites in Korea. The results show that the CIMCPT system has a same performance with the CPT system and has advantages on the mobility and applicability. According to field verification tests for scale effect evaluation, the cone tip resistance evaluated by CIMCPT overestimates by 10% comparing to standard CPTs. A crawler mounted with the CIMCPT system has been implemented to improve accessibility to soft ground, and has shown improvement over the truck type CIMCPT system. Therefore, the improved CIMCPT system can be utilized as a cost effective and highly reliable soil investigation methodology to detect the depth of soft ground and to evaluate soil classification.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2009.06a
• /
• pp.208-208
• /
• 2009

최근 광섬유 센서기술의 수요는 전 산업분야에 걸쳐 높아지고 있으며, 이에 비례하여 기업 간, 국가 간 경쟁이 첨예화되고 있다. 또한 소형화, 경량화, 고성능화 센서에 대한 요구도 높아지고 있어 종래의 각종 센서들의 형태와 개선을 위한 연구개발이 매우 활발하게 전개되고 있으므로 이를 대체할 수 있는 광섬유 센서의 수요가 급격히 늘어날 전망이다. 기존 침입자 감지 시스템은 태풍, 낙뢰, 폭설, 폭우 등의 기상변화나 지반 흔들림, 통행차량 진동 및 전자기 간섭 등에 영향을 받아 오작동, 오경보가 빈번히 발생된다. 이러한 문제의 해결책으로 광섬유 센서 케이블을 이용한 시스템이 대안으로 부각되고 있다. 현재 국내에서 군부대, 공항을 중심으로 펜스와 휴전선 철책에 힘입자 감지를 위하여 도입되고 있다. 광섬유 센서 케이블을 사용하는 광망경비시스템은 광섬유 센서 케이블을 그물망 형태(광망)로 만들어 경계 지역에 설치된다. 광망경비시스템의 원리는 광섬유에 광펄스를 입사시켜 순환시키는데 침입자가 광망을 절단하거나 외력을 가할 경우 발생되는 레일리 산란에 기인하는 후방산란과 접속점과 파단점에서 생기는 반사광을 OTDR(Optical Time Domain Reflectometer)로 검출하여 침입상황 및 침입위치를 탐지한다. 그러나 이러한 침입자 감지를 위한 광망경비시스템의 핵심부품인 광섬유 센서 케이블은 기존에 전량 해외수입에 의존하고 있는 실정이며, 지금까지 국내에서 생산하기 위한 제작 기술과 노하우가 초보단계에 머물러 있다. 이러한 광섬유 센서 케이블 제작에 있어서 중요한 부분이 패키징 기술이라 할 수 있다. 이는 광섬유 센서를 일반적인 피복 구조로 패키징하게 되면, 센서 고유의 특성이 패키징 과정과 운반과정, 포설과정에서 변하게 되고 센서로써의 신뢰성이 크게 저하된다. 본 연구에서는 힘입자 감지용 광섬유 센서 케이블의 설계와 제작을 위한 제조공법을 확립하고, 이를 이용해 제작된 광섬유 센서 케이블의 신뢰성 특성을 평가하였다. 설계 제작된 광섬유 센서 케이블의 구조는 멀티모드광섬유(MMF) 에 0.9 mm Tight buffer를 코팅하고, 광심선 주위에 아라미드 얀을 삽입시킨 후 고문자 수지를 적용하여 외부 피복 (jacket)을 하였다. 제작된 광섬유 센서 케이블의 외경 측정결과 기준치 ($2.95\;{\pm}\;0.03$ mm)를 모두 만족하였고, 850 nm 파장에서의 광 손실 측정 결과 4.0 dB/km 이하였다. 또한 주요 항목의 신뢰성 특성 시험결과, 인장강도는 8~10 kg의 인장력을 갖으며 온도순환시험 ($-30^{\circ}C\;{\sim}\;+75^{\circ}C$)에서의 광 손실은 0.6 dB 이하로 나타나 침입자 감지용 광섬유 센서 케이블로 적합함을 확인할 수 있었다.

• Journal of Korean Society of Environmental Engineers
• /
• v.34 no.12
• /
• pp.863-870
• /
• 2012

The market trends of automatic meter reading associated with smart water meters were investigated. Also, recent developments and field applications of key technology for automatic meter reading associated with smart water meters were analyzed. Smart water meters have been manufactured mostly in United States and Europe and have been expanded their business to Asia. Integrated water management system combining with the additional functions such as real-time consumption metering, cost notification, water conservation, leak detection, water quality monitoring, and flow control have been operated in automatic meter reading. Both water quality and quantity data measured from smart water meters and sensors were transferred to data concentration units through neighborhood area network, and then were transferred to integrated server through wide area network. The data transfer methods were determined by comprehensively considering urban scale, density of smart water meters, power supply and network topologies. Common data collection methods such as fixed network to data concentation units, vehicles drive by, people walk by, and drone fly by have been applied. The automatic meter reading associated with smart water meters are spread throughout the world, and both water and energy savings result in saving the money and reducing the greenhouse gases emission.

• Korean Journal of Construction Engineering and Management
• /
• v.1 no.1 s.1
• /
• pp.87-94
• /
• 2000

Crack sealing, a routine and necessary part of pavement maintenance, is a dangerous, costly, and labor-intensive operation. Within the North America, about ${\$}200$ million is spent annually on crack sealing, with the Texas Department of Transportation (TxDOT) spending about ${\$}7$ million annually (labor alone accounts for over 50 percent of these costs). Prompted by concerns of safety and cost, the University of Texas at Austin, in cooperation with TxDOT and the Federal Highway Administration (FHWA) has developed a unique computer-guided Automated Road Maintenance Machine (ARMM) for pavement crack sealing. In 1999, successful field tests have been undertaken in 8 States around the U.S. This paper first describes significance of the automated crack sealing and technical advances in automated crack sealers including the ARMM, developed in the U.S. It then discusses the ARMM's field implementation and performance evaluation results, and improvements and modifications suggested through the technology evaluation during the field trials. Current research efforts and future work plans in its further development are also presented in this paper.