• Journal of Information Processing Systems
• /
• 제19권1호
• /
• pp.46-54
• /
• 2023

To improve the railway transportation capacity and maximize the benefits of railway transportation, a method for layout optimization of railway transportation route based on deep convolution neural network is proposed in this study. Considering the transportation cost of railway transportation and other factors, the layout model of railway transportation route is constructed. Based on improved ant colony algorithm, the layout model of railway transportation route was optimized, and multiple candidate railway transportation routes were output. Taking into account external information such as regional information, weather conditions and actual information of railway transportation routes, optimization of the candidate railway transportation routes obtained by the improved ant colony algorithm was performed based on deep convolution neural network, and the optimal railway transportation routes were output, and finally layout optimization of railway transportation routes was realized. The experimental results show that the proposed method can obtain the optimal railway transportation route, the shortest transportation length, and the least transportation time, maximizing the interests of railway transportation enterprises.

• Journal of applied mathematics & informatics
• /
• 제16권1_2호
• /
• pp.337-354
• /
• 2004

SA, TS, GA and ACS are four of the main algorithms for solving challenging problems of intelligent systems. In this paper we consider Examination Timetabling Problem that is a common problem for all universities and institutions of higher education. There are many methods to solve this problem, In this paper we use Simulated Annealing, Tabu Search, Genetic Algorithm and Ant Colony System in their basic frameworks for solving this problem and compare results of them with each other.

• 정보처리학회논문지B
• /
• 제11B권1호
• /
• pp.77-82
• /
• 2004

강화학습에서 temporal-credit 할당 문제 즉, 에이전트가 현재 상태에서 어떤 행동을 선택하여 상태전이를 하였을 때 에이전트가 선택한 행동에 대해 어떻게 보상(reward)할 것인가는 강화학습에서 중요한 과제라 할 수 있다. 본 논문에서는 조합최적화(hard combinational optimization) 문제를 해결하기 위한 새로운 메타 휴리스틱(meta heuristic) 방법으로, greedy search뿐만 아니라 긍정적 반응의 탐색을 사용한 모집단에 근거한 접근법으로 Traveling Salesman Problem(TSP)를 풀기 위해 제안된 Ant Colony System(ACS) Algorithms에 Q-학습을 적용한 기존의 Ant-Q 학습방범을 살펴보고 이 학습 기법에 다양화 전략을 통한 상태전이와 TD-오류를 적용한 학습방법인 Ant-TD 강화학습 방법을 제안한다. 제안한 강화학습은 기존의 ACS, Ant-Q학습보다 최적해에 더 빠르게 수렴할 수 있음을 실험을 통해 알 수 있었다.

• Management Science and Financial Engineering
• /
• 제15권1호
• /
• pp.81-96
• /
• 2009

Data mining, specially clustering is one of exciting research areas for ant based algorithms. Ant clustering algorithm, however, has many difficulties for resolving practical situations in clustering. We propose a new grid-based ant colony algorithm for clustering of data. The previous ant based clustering algorithms usually tried to find the clusters during picking up or dropping down process of the items of ants using some stigmergy information. In our ant clustering algorithm we try to make the ants reflect neighborhood information within the storage nests. We use two ant classes, search ants and labor ants. In the initial step of the proposed algorithm, the search ants try to guide the characteristics of the storage nests. Then the labor ants try to classify the items using the guide in-formation that has set by the search ants and the stigmergy information that has set by other labor ants. In this procedure the clustering decision of ants is quickly guided and keeping out of from the stagnated process. We experimented and compared our algorithm with other known algorithms for the known and statistically-made data. From these experiments we prove that the suggested ant mining algorithm found the clusters quickly and effectively comparing with a known ant clustering algorithm.

• 한국경영과학회지
• /
• 제35권2호
• /
• pp.53-69
• /
• 2010

This paper proposes an ant-based routing algorithm, Ant System-Routing in wireless Senor Networks(AS-RSN), for wireless sensor networks. Using a transition rule in Ant System, sensors can spread data traffic over the whole network to achieve energy balance, and consequently, maximize the lifetime of sensor networks. The transition rule advances one of the original Ant System by re-defining link cost which is a metric devised to consider energy-sufficiency as well as energy-efficiency. This metric gives rise to the design of the AS-RSN algorithm devised to balance the data traffic of sensor networks in a decentralized manner and consequently prolong the lifetime of the networks. Therefore, AS-RSN is scalable in the number of sensors and also robust to the variations in the dynamics of event generation. We demonstrate the effectiveness of the proposed algorithm by comparing three existing routing algorithms: Direct Communication Approach, Minimum Transmission Energy, and Self-Organized Routing and find that energy balance should be considered to extend lifetime of sensor network and increase robustness of sensor network for diverse event generation patterns.

• ETRI Journal
• /
• 제35권3호
• /
• pp.414-424
• /
• 2013

We consider a new load balancing routing for delay-guaranteed services in the network in which the traffic is dynamic and network topologies frequently change. For such an ever-changing network, we propose a new online load balancing routing called AntLBR, which exploits the ant colony optimization method. Generally, to achieve load balancing, researchers have tried to calculate the traffic split ratio by solving a complicated linear programming (LP) problem under the static network environment. In contrast, the proposed AntLBR does not make any attempt to solve this complicated LP problem. So as to achieve load balancing, AntLBR simply forwards incoming flows by referring to the amount of pheromone trails. Simulation results indicate that the AntLBR algorithm achieves a more load-balanced network under the changing network environment than techniques used in previous research while guaranteeing the requirements of delay-guaranteed services.

• 정보처리학회논문지B
• /
• 제15B권3호
• /
• pp.245-252
• /
• 2008

본 연구에서는 개미 군락 시스템을 이용하여 디지털 영상의 영역을 분류하는 방법을 제안하였다. 개미 군락 시스템(Ant Colony System, ACS)은 조합 최적화 문제뿐 아니라 최근에는 영상처리 분야의 패턴 인식, 영상 추출, 에지 검색 등에 응용되고 있다. 디지털 영상처리에서 영역 분류는 영상 정보를 처리하는 분석 및 인식 분야에서 가장 중요한 단계중의 하나로 알려져 있으며, 잘 분류된 영역은 디지털 영상 부호화나 영상 분석 혹은 영상 인식과 같은 응용분야에서 더 좋은 결과를 얻을 수 있도록 해준다. 기존의 영상 처리에서의 영역 분류는 고정된 변수에 의하여 처리되어서 후처리 작업들이 필요하였으며 그 결과 또한 영상의 특성에 따라 변하였다. 그러나 본 연구에서는 개미의 무작위성을 이용함으로써 영상에 어느 정도의 변화가 발생하더라도 여전히 안정적인 결과를 얻을 수 있었다. 이러한 안정성과 유연성은 영상을 촬영하는 동안 발생할 수 있는 여러 종류의 잡음에 대하여 안정적인 상태를 유지할 수 있을 것이며 동영상내에서 급한 움직임에 의한 흐려짐에 대한 보상도 이루어 질 수 있을 것으로 기대한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권3호
• /
• pp.1111-1130
• /
• 2016

Cooperative communications can significantly improve the wireless transmission performance with the help of relay nodes. In cooperative communication networks, relay selection and power allocation are two key issues. In this paper, we propose a relay selection and power allocation scheme RS-PA-PSACO (Relay Selection-Power Allocation-Particle Swarm Ant Colony Optimization) based on PSACO (Particle Swarm Ant Colony Optimization) algorithm. This scheme can effectively reduce the computational complexity and select the optimal relay nodes. As one of the swarm intelligence algorithms, PSACO which combined both PSO (Particle Swarm Optimization) and ACO (Ant Colony Optimization) algorithms is effective to solve non-linear optimization problems through a fast global search at a low cost. The proposed RS-PA-PSACO algorithm can simultaneously obtain the optimal solutions of relay selection and power allocation to minimize the SER (Symbol Error Rate) with a fixed total power constraint both in AF (Amplify and Forward) and DF (Decode and Forward) modes. Simulation results show that the proposed scheme improves the system performance significantly both in reliability and power efficiency at a low complexity.

• 국제학술발표논문집
• /
• The 5th International Conference on Construction Engineering and Project Management
• /
• pp.243-251
• /
• 2013

Cash management is a major concern for all contractors in the construction industry. It is arguable that cash is the most critical resource of all. A contractor needs to secure sufficient funds to navigate the project to the end, while keeping an eye on maximizing profits along the way. Past research attempted to address such topic via developing models to tackle the time-cost tradeoff problem, cash flow forecasting, and cash flow management. Yet, little was done to integrate the three aspects of cash management together. This paper, as such, presents a comprehensive model that integrates the time-cost tradeoff problem, cash flow management, and cash flow forecasting. First, the model determines the project optimal completion time by considering the different alternative construction methods available for executing project activities. Second, it investigates different funding alternatives and proposes a project-level cash management plan. Two funding alternatives are considered; they are borrowing and company own financing. The model was built as a combinatorial optimization model that utilizes ant colony search capabilities. The model also utilizes Microsoft Project software and spreadsheets to maintain an environment that incorporates activities, their durations, and other project data, in order to estimate project completion time and cost. Ant Colony Optimization algorithm was coded as a Macro program using VBA. Finally, an example project was used to test the developed model, where it acted reliably in maximizing the contractor's profit in the test project.

• 정보처리학회논문지B
• /
• 제10B권7호
• /
• pp.751-756
• /
• 2003

개미 집단 최적화는 최근에 제안된 조합 최적화 문제를 해결하기 위한 메타 휴리스틱 탐색 방법으로, 그리디 탐색뿐만 아니라 긍정적 반응의 탐색을 사용한 모집단에 근거한 접근법으로 순회 판매원 문제를 풀기 위해 처음으로 제안되었다. 본 논문에서는 기존의 개미 집단 시스템의 성능을 향상시키기 위해 강화와 다양화를 통한 집단간 긍정적 상호작용과 부정적 상호작용을 수행하는 다중 집단 개미 모델을 제안한다. 이 알고리즘은 TSP 문제를 해결하기 위해 몇 개의 에이전트 집단으로 이루어진 ACS 집단간의 상호작용을 통해 문제를 해결하는 방법이다. 본 논문에서는 이 제안된 방법을 TSP 문제에 적용해 보고 그 성능에 대해 기존의 ACS 방법과 비교 평가해, 문제 해결의 질적 수준이 우수하다는 것을 실험을 통해 알아보고자 한다.