• 한국측량학회:학술대회논문집
• /
• 한국측량학회 2010년 춘계학술발표회 논문집
• /
• pp.27-28
• /
• 2010

Finding shortest path technique running time differs depending on applying of the algorithm and data, and also used a lot of difference in effectiveness depending on the environment occurs. Therefore, the algorithm and environment based on this study, the relationship between optimal solutions and compare running time.

• 대한임베디드공학회논문지
• /
• 제12권2호
• /
• pp.113-120
• /
• 2017

In this paper, we present a night-time vehicle detection method using CNN (Convolutional Neural Network) classification. The camera based night-time vehicle detection plays an important role on various advanced driver assistance systems (ADAS) such as automatic head-lamp control system. The method consists mainly of thresholding, labeling and classification steps. The classification step is implemented by existing CIFAR-10 model CNN. Through the simulations tested on real road video, we show that CNN classification is a good alternative for night-time vehicle detection.

• 산업공학
• /
• 제11권1호
• /
• pp.75-84
• /
• 1998

The important issue for intra-city vehicle scheduling is to measure and store actual vehicle travel speeds between customer locations. Travel speeds(and times) in nearly all metropolitan areas change drastically during the day because of congestion in certain parts of the city road network. We propose three models for estimating departure time-dependent travel speeds between locations that relieve much burden for the data collection and computer storage requirements. Two of the three models use a least squares method and the rest one employs a neural network trained with the back-propagation rule. On a real-world study using the travel speed data collected in Seoul, we found out that the neural network model is more accurate than the other two models.

• 한국시뮬레이션학회:학술대회논문집
• /
• 한국시뮬레이션학회 2002년도 추계학술대회 논문집
• /
• pp.163-170
• /
• 2002

Terrain surfaces have to be modeled in very detail and wheel-surface contacting geometry must be well defined in order to obtain proper ground-reaction and friction forces for realistic simulation of off-road vehicles. Delaunay triangulation is one of the most widely used methods in modeling 3-dimensional terrain surfaces, and T-search is a relevant algorithm for searching resulting triangular polygons. The T-search method searches polygons in successive order and may not allow real-time computation of off-road vehicle dynamics if the terrain is modeled with many polygons, depending on the computer performance used in the simulation. In order to accelerate the searching speed of T-search, a terrain database of triangular polygons is modeled in multi-levels by adopting the LOD (Level of Detail) method used in realtime computer graphics. Simulation results show that the new LOD search is effective in shortening the required computing time. The LOD search can be even further accelerated by introducing an NN (Neural Network) algorithm, in the cases where a appropriate range of moving paths can be predicted by cultual information of the simulated terrain, such as lakes, houses, etc.. Numerical tests show that LOD-NN search almost double the speed of the original T-search.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2021년도 제64차 하계학술대회논문집 29권2호
• /
• pp.223-224
• /
• 2021

Recently, k-farthest neighbor (kFN) queries have not as much attention as k-nearest neighbor (kNN) queries. Therefore, this study considers moving k-farthest neighbor (MkFN) queries for spatial network databases. Given a positive integer k, a moving query point q, and a set of data points P, MkFN queries can constantly retrieve k data points that are farthest from the query point q. The challenge with processing MkFN queries in spatial networks is to avoid unnecessary or superfluous distance calculations between the query and associated data points. This study proposes a batch processing algorithm, called MOFA, to enable efficient processing of MkFN queries in spatial networks. MOFA aims to avoid dispensable distance computations based on the clustering of both query and data points. Moreover, a time complexity analysis is presented to clarify the effect of the clustering method on the query processing time. Extensive experiments using real-world roadmaps demonstrated the efficiency and scalability of the MOFA when compared with a conventional solution.

• 한국재난정보학회 논문집
• /
• 제13권1호
• /
• pp.96-105
• /
• 2017

지구 온난화는 인류의 재앙이며, 그 주된 원인은 이산화탄소이다. 따라서 온실가스 저감을 위한 범국가적 정책이 수행되고 있으며, 정책의 수립/집행에 있어 정확한 온실가스 배출량 산정은 매우 주요하다. 도로이동오염원에 의한 온실가스 배출량 산정을 위해서는 도로구간별 CO2 배출 원단위가 필요하며, 이는 차량의 속도자료를 이용하여 산정된다. 그러나 전국 도로망에 대한 속도자료의 수집 및 분석에는 한계가 있다. 따라서 본 연구에서는 방대한 양의 차량 내비게이션 자료를 이용한 비집계방식의 도로구간 CO2 배출량 원단위 산정방법을 제시한다. 제시된 방법론은 기존 집계방식에 의한 CO2 배출 원단위보다 정확하며, 전국 도로망에 직접적으로 적용이 가능하다.

• 한국GIS학회:학술대회논문집
• /
• 한국GIS학회 2008년도 공동추계학술대회
• /
• pp.182-187
• /
• 2008

실제 도로 교통망에서 경로를 탐색할 때 방향전환에 대해 고려해야 한다. 왜냐하면 똑같은 출발지와 목적지를 가지는 각각 다른 경로 즉, 직진이 많은 경로와 방향전환이 많은 경로를 비교하면 직진이 많은 경로가 더 빨리 도착할 수 있다. 이 논문에서는 기존에 방향전환에 대해 연구된 $TA^*$ 알고리즘 보다 방향전환횟수는 늘어나지만 탐색비용을 줄일 수 있는 $VTA^*$ 알고리즘을 제안한다. 방향전환을 고려하지 않은 $A^*$ 알고리즘, 방향전환을 고려한 $TA^*$ 알고리즘과 이 논문에서 제안하는 $VTA^*(n)$ 알고리즘을 비교하였다. 그 결과 $TA^*$ 알고리즘보다 탐색비용이 평균 7.31%가량 줄어들고, $A^*$ 알고리즘보다 방향전환 횟수는 27.95% 가량 감소되는 결과를 보였다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2009년도 정보 및 제어 심포지움 논문집
• /
• pp.347-349
• /
• 2009

Air quality of indoor space environment is affected by various pollutants like as particles and chemical stuffs. The indoor air pollution affects directly the human respiration organs to cause consequently unpleasant mental status. The $CO_2$ concentration level is one of the harmful components of air pollutants. Major factor to increase the $CO_2$ concentration level is the people's breath amount in indoor. The car exhaust gas diffused from the around road also has strong affect on $CO_2$ concentration. There are some other reasons to affect the $CO_2$ concentration change, such as, real-time change of the population movement, closeness to the indoor air flow inlet window and changes in road car traffic amount. A remote monitoring system to measure environmental indoor air pollution concerning on the $CO_2$ concentration was studied and installed realized set-up model. Zigbee network configuration was applied for this system and the $CO_2$ concentration data were collected through USN network. A software program was developed to assure systematic analysis and to display real-time data on web pages. For the experimental test various condition was set up, like as, window opening, stopping air condition operation and adjusting fan heater work, etc. The analysis result showed the relation of various environmental conditions to $CO_2$ concentration changes. The causes to increase $CO_2$ concentration were experimentally defined as windows closing, the stopping air condition system, fan heater operation. To keep the $CO_2$ concentration under the legally required ppm level in public access indoor space, the developed remote measurement system will be usefully applied.

• 대한교통학회지
• /
• 제29권5호
• /
• pp.79-89
• /
• 2011

최근에 들어 우리나라에서는 회전교차로에 대한 연구가 많이 진행되고 있으나, 대부분 회전교차로의 교통운영측면에서의 효과에 대한 연구가 주를 이루고 있고, 국외에 비해 교통안전측면 혹은 연속적인 회전교차로 설치를 포함한 다양한 회전교차로 도입방안 등에 대한 연구는 미흡한 실정이다. 더욱이 대부분의 회전교차로 건설이 개별교차로 별 개선을 위해 적용되고 있어 회전교차로의 축간 혹은 네트워크 차원에서의 운영효과는 간과되고 있다. 따라서 본 연구에서는 회전교차로 도입 시 교차로 운영상의 효과를 극대화시킬 수 있는 인접 교차로사이의 적정거리를 도출하고, 그 결과를 바탕으로 실제 도로네트워크에서 연속적인 회전교차로 도입 시의 네트워크 차원의 운영 효과를 분석하였다. 분석결과, 150m이내에 신호교차로가 있을 경우 회전교차로의 교통소통효과는 급격히 감소함이 분석되어 회전교차로 도입 시의 인접교차로와의 거리는 약 150m가 확보되어야 인접신호교차로의 영향을 감소시킬 수 있는 것으로 나타났다. 또한 인천시 논현지구를 대상으로 수행된 현장조사결과를 토대로 시뮬레이션 분석한 결과, 하나의 교차로만을 회전교차로로 전환할 경우보다 연속적으로 다수의 교차로를 회전교차로로 전환할 경우에 운영효과는 매우 높게 나타남을 확인할 수 있었다.

• 정보통신설비학회논문지
• /
• 제8권3호
• /
• pp.122-131
• /
• 2009

Ubiquitous-Transportation sensor network is able to realize a vehicle ad-hoc network. Since there are some problems in an existing ITS system, the new technology and traffic information strategies are requirements in this advanced system, u-TSN. The purposes of this paper is to introduce the components on u-TSN system, establish new traffic strategies for this system, and then evaluate these strategies by making a comparative study of ITS and using micro traffic simulator, AIMSUN. The strategy evaluated by AIMSUN is position-based multicast strategy which provides traffic information to vehicles using V2I (vehicle to Infrastructure) communication. This paper focuses on the providing real-time route guidance information when congestion is occurred by the incidents. This study estimates total travel time on each route by API modules. Result from simulation experiments suggests that position-based multicast strategy can achieve more optimal network performance and increased driver satisfaction since the total accumulated travel times of both the major road and the total system on position-based multicast strategy are less than those on VMS.