Earticle

본 연구는 사고위험이 상존하는 교차로와 횡단보도에서의 사고 예방을 위한 솔루션으로 기 존의 일반적인 센서로는 보행자와 차량의 이동방향을 예측하여 신호를 변경하거나 경고를 하는데 어려움이 있었지만, 카메라를 이용한 객체인식을 통한 감지 솔루션의 경우 다양한 피사체에 대한 능 동적 대처로 사고 발생율을 감소 시켜 줄 수 있는 효과적인 대안이 될 수 있다. 본 연구를 통해 독 자적으로 확보한 기술로는 농기계/전동카트에 대한 인식률 부분에 있어서 타 기업이 보유하지 못한 데이터와 판독 능력을 확보하였으며, 객체인식 부분의 인식률 향상을 위하여 인식 영역 최적화에 대 한 S/W 기술을 확보 하였다.

This study is a solution to prevent accidents at intersections and crosswalks where the risk of accidents always exists. Although it was difficult to predict the direction of movement of pedestrians and vehicles and change signals or issue warnings with existing general sensors, object detection using cameras was difficult. In the case of a detection solution through recognition, it can be an effective alternative that can reduce the accident rate by actively responding to various subjects. The technology independently secured through this study secured data and reading capabilities that other companies did not possess in terms of recognition rates for agricultural machinery/electric carts, and S/O for recognition area optimization to improve the recognition rate in object recognition. W technology was secured.

본 논문에서는 ITS 분야의 한국의 표준화 역량을 점검하였으며, 아시안 국가들의 ITS 표준 화 참여 및 서비스 현황과 한국과의 협력 희망정도를 조사 분석하였다. 그 결과 한국은 ITS 표준화 분야에서 국제적인 역량을 인정받고 있으며, 싱가포르를 제외한 아세안 대부분의 국가 들은 ITS 표준화 참여도와 서비스 도입이 미진한 것으로 파악되었다. 또한 아세안 대부분의 나라들이 한국과 ITS 표준화 협력을 희망하고 있으며, 우선적으로 ITS 표준화의 기반인 ITS 시스템 아키텍처 구축을 선호하는 것으로 파악되었다. 또한 표준화 도입 서비스분야로는 아세 안 국가 간 물류운송 효율성 제고 등을 고려하여 화물 운송 분야가 우선 적용 서비스 분야로 제시되었다.

In this paper, Korea's standardization capacity in the ITS field was examined, and the status of participation in ITS standardization and services of ASEAN countries, and the degree of hope for cooperation with Korea was investigated and analyzed. Korea is recognized for its international competency in the field of ITS standardization, and most ASEAN countries, excluding Singapore, are found to have insufficient participation in ITS standardization and service introduction. In addition, most ASEAN countries are strongly hoping for ITS standardization cooperation with Korea, and the preliminary establishment of the ITS system architecture as the basis for ITS standardization was derived as a project of hope for cooperation. In addition, as a service field for introducing standardization, Freight transport was suggested as a priority application service field in order to improve the efficiency of logistics transportation between ASEAN countries

Vehicular ad hoc network (VANETs) has gained wide popularity such that it is necessary to incorporate trust among each node in the network. However, trust management among vehicles is a challenging task as malicious nodes are prone to disturb data transmission among different vehicles. The aim of this work is to establish the truth of consensus, to identify the malicious nodes with no further delay, by considering the decision of each vehicle on finding the trust values. The experimental analysis for the proposed approach done using the NS3 with CAIDA data set, the proposed scheme shows superior results compared to the other existing schemes for the detection rate of malicious nodes. It enhances the attack Detection Rate (DR) as 96.5% for the projected dual weighted trust evaluation technique. But, DR for the triumphing technique firecol is 74.9% and AODV is 60%. Thus, it is experimentally proved that dual weighted trust mechanism has high attack detection rate, comparatively. Also, proposed method outperforms very well with respect to the data transmission parameters like packet delivery ratio, energy Consumption and average latency comparatively over the existing mechanisms.

본 연구에서는 자율 주행을 위한 지능형 교통 시스템(ITS)을 최적화하는 데 있어 엣지 컴퓨팅의 혁신적인 잠재력 을 연구하였다. 방대한 양의 데이터를 로컬에서 실시간으로 처리하는 엣지 컴퓨팅의 능력은 신속한 의사 결정 및 향상된 안전 조치를 포함하여 자율주행차의 중요한 요구 사항을 해결하는 데 필수 요소이다. 엣지 컴퓨팅과 기존 ITS 인프라의 통합을 탐구하고, 현지화된 데이터 처리가 대기 시간을 크게 줄여 자율주행차의 반응성을 향상시키는 방법을 강조한다. 실시간 교통 관리, 충돌 방지 시스템 및 동적 경로 최적화를 지원하는 강력한 프레임워크를 집합적으로 형성하는 엣지 서버, 센서 및 V2X(Vehicle-to-Everything) 통신 기술의 배포를 검토한다. 또한 본 연구는 보안, 데이터 통합, 시스템 확장성 등 ITS에서 엣지 컴퓨팅을 구현하는 데 있어 가장 중요한 과제를 다루며 잠재적인 솔루션과 향후 연구 방향에 대한 통찰력을 제공한다. 이 논문은 완전 자율 주행이라는 비전을 실현하는 데 있어 엣지 컴퓨팅의 중추적인 역할을 강조 하고, 보다 안전하고 효율적이며 지속 가능한 교통 시스템을 달성하는 데 기여하는 논문이다.

In this scholarly investigation, the focus is placed on the transformative potential of edge computing in enhancing Intelligent Transportation Systems (ITS) for the facilitation of autonomous driving. The intrinsic capability of edge computing to process voluminous datasets locally and in a real-time manner is identified as paramount in meeting the exigent requirements of autonomous vehicles, encompassing expedited decision-making processes and the bolstering of safety protocols. This inquiry delves into the synergy between edge computing and extant ITS infrastructures, elucidating the manner in which localized data processing can substantially diminish latency, thereby augmenting the responsiveness of autonomous vehicles. Further, the study scrutinizes the deployment of edge servers, an array of sensors, and Vehicle-to-Everything (V2X) communication technologies, positing these elements as constituents of a robust framework designed to support instantaneous traffic management, collision avoidance mechanisms, and the dynamic optimization of vehicular routes. Moreover, this research addresses the principal challenges encountered in the incorporation of edge computing within ITS, including issues related to security, the integration of data, and the scalability of systems. It proffers insights into viable solutions and delineates directions for future scholarly inquiry.

본 연구에서는 사물인터넷에 인공지능 기술을 융합하여 사물인 자율주행 자동차와 커넥티드 자동차들이 스스로 정보를 수집하고 분석하여 의사결정을 하도록 돕는 연구이다. 이에 CIoT를 이용한 지능형교통시스템을 연구하여 교통 효율성과 안전성을 향상하고, 교통 상황을 실시간 수집‧분석하며, 차량 흐름을 최적화하여 교통사고 예방과 사용자의 편의성을 증대할 수 있다. 제안한 연구결과를 통하여 교통 체증을 완화하고 탄소 중립과 에너지 효율을 높일 수 있는 친환경 연구이다. 본 연구는 지능형교통시스템(ITS)에 최적화된 인지사물인터넷 연구를 통하 여 도로 안전을 강화하고, 효율성을 높이는데 기여할 수 있으며, 교통 복잡도를 개선하여, 자원을 절약하고 환경 오염을 줄일 수 있는 지속 가능한 도시 모빌리티 지원이 가능하다. 또한, ITS을 적용한 교통 인프라에 최적화된 자율주행 및 커넥티드 차량 맞춤형 교통 시스템 개발에 기여하는 연구이다.

This study aims to enhance the efficiency and safety of transportation by developing an intelligent transportation system (ITS) using the Internet of Things (IoT) and artificial intelligence (AI) technologies. The proposed system will enable self-driving and connected vehicles to autonomously collect and analyze information, make decisions, and optimize traffic flow. This will lead to reduced traffic congestion, improved traffic safety, and enhanced user convenience. Additionally, the system will contribute to achieving carbon neutrality and energy efficiency by reducing fuel consumption and emissions. Key contributions of this research include: Development of an optimized cognitive IoT for ITS to enhance road safety and efficiency. Improvement of traffic complexity, resource conservation, and environmental pollution reduction through sustainable urban mobility support. Development of a customized transportation system for self-driving and connected vehicles optimized for ITS-based traffic infrastructure. The proposed research has the potential to revolutionize transportation by making it safer, more efficient, and more sustainable.

최근 활발히 연구되는 딥러닝 방법론은 인공지능의 성능을 급속도로 향상시켰고, 이에 따라 다양한 산업 분야에서 딥러닝을 활용한 시스템이 제시되고 있다. 교통 시스템에서는 GNN을 활용한 공간-시간 그래프 모델링이 교통 속도 예측에 효과적인 것으로 밝혀졌지만, 이는 메모 리 병목 현상을 유발하기 때문에 모델이 비효율적으로 학습된다는 단점이 있다. 따라서 본 연 구에서는 그래프 분할 방법을 통해 도로 네트워크를 분할하여 메모리 병목 현상을 완화함과 동시에 우수한 성능을 달성하고자 한다. 제안 방법론을 검증하기 위해 인천시 UTIC 데이터 분석 결과를 바탕으로 Jensen-Shannon divergence를 사용하여 도로 속도 분포의 유사도를 측정 하였다. 그리고 측정된 유사도를 바탕으로 스펙트럴 클러스터링을 수행하여 도로 네트워크를 군집화하였다. 성능 측정 결과, 도로 네트워크가 7개의 네트워크로 분할되었을 때 MAE 기준 5.52km/h의 오차로 비교 모델 대비 가장 우수한 정확도를 보임과 동시에 메모리 병목 현상 또 한 완화되는 것을 확인할 수 있었다.

Deep learning methodology, which has been actively studied in recent years, has improved the performance of artificial intelligence. Accordingly, systems utilizing deep learning have been proposed in various industries. In traffic systems, spatio-temporal graph modeling using GNN was found to be effective in predicting traffic speed. Still, it has a disadvantage that the model is trained inefficiently due to the memory bottleneck. Therefore, in this study, the road network is clustered through the graph clustering algorithm to reduce memory bottlenecks and simultaneously achieve superior performance. In order to verify the proposed method, the similarity of road speed distribution was measured using Jensen-Shannon divergence based on the analysis result of Incheon UTIC data. Then, the road network was clustered by spectrum clustering based on the measured similarity. As a result of the experiments, it was found that when the road network was divided into seven networks, the memory bottleneck was alleviated while recording the best performance compared to the baselines with MAE of 5.52km/h.

It is an important to quickly and accurately forecasting road network traffic flow in intelligent transportation systems, Aiming at the forecasting problem of short-term traffic flow, this paper proposed a traffic flow prediction algorithm, which based on traffic flow sequence partition and neural network model. Firstly, the algorithm divided the traffic flow into different patterns and time sequence by clustering, secondly, described and predicted traffic flow model according to BP neural network. Finally, the experiment shows that based on combined model is much accurate.

Vehicle Ad hoc Network are composed of the vehicle with wireless communication equipment, road construction collecting base station transmission network, background processing server and related acquisition and processing software system. Based on Internet of things simulation console, this paper designs vehicle to vehicle scenarios of Intelligent Transportation System, simulates its communication process , analyzes the simulation data of sending and receiving, evaluates the entire performance of the network, which can offer reference to designing and optimizing the Vehicle Ad hoc Network. In this paper we try to prove: In the low speed motion in vehicle to vehicle scenario of Vehicle Ad hoc Network, as the routing protocol in the network layer, AODV protocol is much better than DSR protocol.

Traditional approaches for some applications of Intelligent Transportation System(ITS), such as license plate tilt correction and vehicle speed estimation generally require feature extraction, however, feature extraction is a difficult task in complex traffic environment, and it is prone to be affected by the moving status of object and dynamic environment. In this paper, we tried a new analysis method without feature extraction for these two applications. The approach is based on enumeration. All the possible results of image analysis are tested by the testing function. Then, the extreme value of the testing function is selected and the corresponding result is just the concerning result. In the experiment, our method is applied to vehicle license plate tilt correction and vehicle speed estimation. The results demonstrate the proposed method has certain degree of robustness and validity.

In this paper, a two-step approach for vehicles detection is proposed. The first step of approach is to approximate vehicles’ potential locations through searching for shadow area of vehicle low-part. In order to find these shadows, Haar-like feature with Adaboost was used to train a Haar detector offline and the relearning process with hard training samples is applied to increase detection rate. Based on the previous processing, ROI (Region of interest) + HOG + SVM algorithm is used for vehicle verification. At last, K-means approach is used to combine the similar detection results. The experimental results proved that our system could be used for real-time preceding vehicle detection robustly and accurately.

In this paper, we propose new method which can provide user the path to the target place efficiently. It stores the state of roads to target place as the form of Q-table and finds the proper path using Q-table.0-table is updated by the information about real traffic which is reported by users. This method can provides the proper path, using less storage and less computation time than the conventional method which stores entire road traffic information and finds the path by graph search algorithm.