• Journal of Korea Multimedia Society
• /
• v.5 no.6
• /
• pp.745-752
• /
• 2002

A* algorithm is widely used in optimal car route search which is a kind of informed search, since the locations of starting and ending points are known a priori. Unidirectional A* algorithm requires considerable search time but guarantees a optimal path, bidirectional A* algorithm does not guarantee a optimal path and takes even longer search time than unidirectional search to guarantee a optimal path. In this paper, a new bidirectional A* algorithm which requites less search time and guarantees a optimal path is proposed. To evaluate the efficiency of the proposed algorithm, several experiments are conducted in real road map and the results show that the algorithm is very effective in terms of finding a optimal path and search time.

• Journal of KIISE:Information Networking
• /
• v.37 no.1
• /
• pp.35-41
• /
• 2010

Since the ad-hoc network allow nodes to communicate each other without infrastructure system and predefined configuration, it comes into the spotlight that is suitable to ubiquitous society. In ad-hoc network, route recovery mechanism is considered important. Normally route recovery is needed to solve the link failure problem because there is no route maintaining system like a router in ad-hoc networks. In this paper we propose BS-AODV(Bidirectional Searching-AODV) route recovery method. The proposed method is a local repair method that can be applied in all of the network area. Unlike a limited local repair method in AODV. the proposed method adopts the bidirectional searching method where the upstream/downstream nodes can send the route maintenance messages. Restricting the flooding of route request messages, the proposed scheme attempts to minimize the costs of local repair, the performance of the proposed scheme is evaluated through the simulations. In two scenarios which variate the node numbers and node speed, the comparison among the proposed scheme, AODV and AOMDV is shown in terms of the control traffic and data delivery ratio.

• Journal of The Korean Association of Information Education
• /
• v.2 no.2
• /
• pp.252-259
• /
• 1998

Vehicle navigation systems employ a certain route planning algorithm that provides the shortest path between the starting point and the destination point. The performance of a given route planning algorithm is measured through the degree of optimal route selection and the time cost to complete searching an optimal path. In this paper, various route planning algorithms are evaluated through computer simulation based on a real digital map database. Among those algorithms evaluated in this paper, the Modified Bi-directional A${\ast}$ algorithm is found to be the best algorithm for use in vehicle navigation systems.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.7
• /
• pp.103-111
• /
• 2014

This paper proposes a modified algorithm that improves on Dijkstra's algorithm by applying it to purely two-way traffic paths, given that a road where bi-directional traffic is made possible shall be considered as an undirected graph. Dijkstra's algorithm is the most generally utilized form of shortest-path search mechanism in GPS navigation system. However, it requires a large amount of memory for execution for it selects the shortest path by calculating distance between the starting node and every other node in a given directed graph. Dijkstra's algorithm, therefore, may occasionally fail to provide real-time information on the shortest path. To rectify the aforementioned shortcomings of Dijkstra's algorithm, the proposed algorithm creates conditions favorable to the undirected graph. It firstly selects the shortest path from all path vertices except for the starting and destination vertices. It later chooses all vertex-outgoing edges that coincide with the shortest path setting edges so as to simultaneously explore various vertices. When tested on 9 different undirected graphs, the proposed algorithm has not only successfully found the shortest path in all, but did so by reducing the time by 60% and requiring less memory.

• Journal of Korean Society of Transportation
• /
• v.23 no.7 s.85
• /
• pp.99-110
• /
• 2005

Total travel cost of route which connects origin with destination (O-D) is consist of the total sum of link travel cost and route perception cost. If the link perception cost is different according to the origin and destination, optimal route search has limitation to reflect the actual condition by route enumeration problem. The purpose of this study is to propose optimal route searching formulation and algorithm which is enable to reflect different link perception cost by each route, not only avoid the enumeration problem between origin and destination. This method defines minimum unit of route as a link and finally compares routes using link unit costs. The proposed method considers the perception travel cost at both origin and destination in optimal route searching process, while conventional models refect the perception cost only at origin. However this two-way searching algorithm is still not able to guarantee optimum solution. To overcome this problem, this study proposed an orign based optimal route searching method which was developed based on destination based optimal perception route tree. This study investigates whether proposed numerical formulas and algorithms are able to reflect route perception behavior reflected the feature of origin and destination in a real traffic network by the example research including the diversity of route information for the surrounding area and the perception cost for the road hierarchy.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2004.05a
• /
• pp.1557-1560
• /
• 2004

무선 Ad-Hoc 네트워크를 위한 대부분의 라우팅 프로토콜들은 모든 링크가 양방향임을 가정하고 설계되었다. 그러나 현실적으로 Ad-Hoc 네트워크에 참여하는 노드들은 서로 다른 전송 파워를 가질 수 있고, 잡음 또는 간섭 등으로 인하여 지역적이고 일시적인 단 방향 링크를 야기시킬 수 있다. 기존 Ad-Hoc 라우팅 프로토콜 중의 하나인 AODV 프로토콜은 단 방향 링크 존재 시에 이를 경로에서 제거함으로써 양방향 링크만으로 구성된 경로를 다시 탐색하게 된다. 본 논문에서는 단방향 링크 존재 시에 야기될 수 있는 AODV 프로토콜의 문제점과 이를 해결하기 위한 기존 연구들을 소개하고, 나아가서 단?향 링크 존재 시에 적용할 수 있는 AODV 프로토콜을 변형한 라우팅 알고리즘을 제안한다.

• Proceedings of the Korean Association of Geographic Inforamtion Studies Conference
• /
• 2004.03a
• /
• pp.51-56
• /
• 2004

인터넷 통신과 무선 이동 통신의 발달은 최적 경로 탐색이 인터넷 웹 페이지를 통하여 서비스될 수 있도록 하였으며, CNS(Car Navigation System)를 이용한 서비스도 가능하도록 하였다. 나아가 개인용 휴대통신 장비인 PDA나 핸드폰을 이용하여서도 그 서비스가 제공되고 있다. 기존의 양방향 A＊ 알고리즘에서는 현재 노드에서 목적지까지의 예상 비용을 직선 거리를 사용하였지만 본 논문에서는 현재 노드까지 지나온 경로에 대한 정보를 이용하였다. 지금까지 지나온 경로의 평균 경로 비용을 계산하여 이용함으로써, 직선 길이가 아닌 지금까지 지나온 경로의 정보를 이용할 수 있었고, 지나온 경로의 정보와 앞으로 탐색할 경로에 대한 애매한 정보들(도로의 속도, 날씨, 주행시간대)을 퍼지를 이용하여 계산하였다. 퍼지를 이용하여 도로의 애매한 정보들을 실시간으로 활용할 수 있는 알고리즘을 제안하고 제안한 알고리즘의 타당성을 실험을 통하여 검증하였다.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.2
• /
• pp.147-154
• /
• 2010

This paper suggests new route plan cost calculation and cost-effective route plan algorithm and architecture for the new city traffic information system when it is operated nationwide. New algorithm and architecture estimates cost with traffic speeds which is supported for all different lanes, stratifies logical layer which process different levels' traffic information with diverse traffic patterns and provides different traffic information in the few levels. Also suggested new algorithm supports drivers' customized traffic information through both-way communications and plans routes effectively based on the distance between drivers' start position and destination and different levels which start and end position located. It proposes additional research items and requirement for integration between different cities' traffic information system which the national police agency invested and led.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.05a
• /
• pp.421-424
• /
• 2013

차량 애드 혹 네트워크는 도심 교차로에서 도로의 특성과 차량의 높은 이동성으로 인해 네트워크의 단절이 자주 일어난다. 향상된 지리기반 라우팅 프로토콜인 GBSR(Greedy Border Superiority Routing)은 V2V(Vehicle-to-Vehicle)에 적합하다. 그러나 탐욕모드에서 stale노드가 로컬최대에 직면하는 문제를 가지고 있다. EGBSR(Enhanced GBSR)은 반대 방향의 차량과 같은 방향의 차량에게 보내는 비콘 메시지와 도로 정보를 관리하는 테이블을 이용하여 경로를 탐색하고 설정된 경로를 통해 패킷을 보낸다. 이를 통해 소스노드가 목적지노드에 빠르고 안전하게 패킷을 전달할 수 있는 양방향 라우팅 기법 제안한다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.11a
• /
• pp.41-43
• /
• 2019

Image-to-image 변환에서 인상적인 성능을 보이는 StarGAN 은 모델의 성능에 중요한 영향을 끼치는 adversarial weight, classification weight, reconstruction weight 라는 세가지 하이퍼파라미터의 결정을 전제로 하고 있다. 본 연구에서는 이 중 conditional GAN loss 인 adversarial loss 와 classification loss 를 대치할 수 있는 attribute loss를 제안함으로써, adversarial weight와 classification weight 를 최적화하는 데 걸리는 시간을 attribute weight 의 최적화에 걸리는 시간으로 대체하여 하이퍼파라미터 탐색에 걸리는 시간을 획기적으로 줄일 수 있게 하였다. 제안하는 attribute loss 는 각 특징당 GAN 을 만들 때 각 GAN 의 loss 의 합으로, 이 GAN 들은 hidden layer 를 공유하기 때문에 연산량의 증가를 거의 가져오지 않는다. 또한 reconstruction loss 를 단순화시켜 연산량을 줄인 simplified content loss 를 제안한다. StarGAN 의 reconstruction loss 는 generator 를 2 번 통과하지만 simplified content loss 는 1 번만 통과하기 때문에 연산량이 줄어든다. 또한 이미지 Framing 을 통해 배경의 왜곡을 방지하고, 양방향 성장을 통해 학습 속도를 향상시킨 아키텍쳐를 제안한다.