Earticle

In this paper, we developed a heuristic algorithm to assign job to workers in parallel line inspection process without sequence. Objective of assigning job in inspection process is only to assign job to workers evenly. But this objective needs much time and effort since there are many cases in assigning job and cases increase geometrically if the number of job and worker increases. In order to solve this problem, we proposed heuristic algorithm to assign job to workers evenly. Experiments of assigning job are performed to evaluate performance of this heuristic algorithm. The result shows that heuristic algorithm can find the optimal solution to assign job to workers evenly in many type of cases. Especially, in case there are more than two optimal solutions, this heuristic algorithm can find the optimal solution with 98% accuracy.

In this paper, we raised the performance of heuristic algorithm to assign job to workers in parallel line inspection process without sequence. In previous research, we developed the heuristic algorithm. But the heuristic algorithm can't find optimal solution perfectly. In order to solve this problem, we proposed new method to make initial solution called FN(First Next) method and combined the new FN method and old FE method using previous heuristic algorithm. Experiments of assigning job are performed to evaluate performance of this FE+FN heuristic algorithm. The result shows that the FE+FN heuristic algorithm can find the optimal solution to assign job to workers evenly in many type of cases. Especially, in case there are optimal solutions, this heuristic algorithm can find the optimal solution perfectly.

k -club은 소셜 네트워크 분석에서 다양한 형태의 소셜 그룹을 설명하기 위해 제안된 그래프 모델 중 하나로, 단순 그래프에서 부분 정점 집합 S 에 의한 유도 부분그래프(Induced subgraph)의 지름이 k보다 작거나 같은 경우 S 를 k -club이라 한다. 본 논문에서는 유전알고리즘을 이용하여 그래프에서 크기가 최대인 k -club을 찾는 문제인 Mk CP(Maximum k -Club Problem)을 계산하는 HGA+DROP 알고리즘을 제안한다. 본 알고리즘은 k -club을 위한 휴리스틱 알고리즘 k -CLIQUE & DROP을 변형하고 휴리스틱 유전 알고리즘(HGA)을 사용해 한 번의 수행으로 복수 개의 k -club을 구하였다. 기존 알고리즘의 결과와 비교하기 위해 DIMACS 그래프들에 대하여 k 가 2, 3, 4 그리고 5일 때 MkCP를 계산하였다.

Given an undirected simple graph, k -club is one of the proposed structures to model social groups that exist in various types in Social Network Analysis (SNA). Maximum k -Club Problem (Mk CP) is to find a k -club of maximum cardinality in a graph. This paper introduces a Genetic Algorithm called HGA+DROP which can be used to approximate maximum k -club in graphs. Our algorithm modifies the existing k -CLIQUE & DROP algorithm and utilizes Heuristic Genetic Algorithms (HGA) to obtain multiple k-clubs. We experiment on DIMACS graphs for k = 2, 3, 4 and 5 to compare the performance of the proposed algorithm with existing algorithms.

In this study, we developed a heuristic algorithm to get better efficiency of clustering than conventional algorithms. Conventional clustering algorithm had lower efficiency of clustering as there were no solid method for selecting initial center of cluster and as they had difficulty in search solution for clustering. EMC(Expanded Moving Center) heuristic algorithm was suggested to clear the problem of low efficiency in clustering. We developed algorithm to select initial center of cluster and search solution systematically in clustering. Experiments of clustering are performed to evaluate performance of EMC heuristic algorithm. Squared-error of EMC heuristic algorithm showed better performance for real case study and improved greatly with increase of cluster number than the other ones.

글로벌 경제 침체 속에서 기업은 날로 높아져 가는 소비자들의 수요를 만족하기 위하여 납기 대응 그리고 LB(Line Balance, 라인편성효율) 향상과 제조원가의 절감을 위한 생산성 향상은 중요한 개선 항목이다. 따라서 본 연구에서는 자동차 물류 중 조달물류를 대상으로 하여 불출자의 로드밸런스율을 증대할 수 있는 휴리스틱 알고리즘 개발에 대하여 연구를 진행함으로써 1차 목표 값을 적용하 였을 load balancing율은 45.6%에서 91.7%로 개선 된 것을 확인할 수 있었다.

공급자와 소비자간의 정보공유는 기능 중심에서 프로세스 중심이 되면서, 유연성과 고객 서비스를 극대화하기 위한 새로운 물류 개념을 요구하게 되었다. 다시 말하면 원부자재의 조달에서부터 생산을 거쳐 고객에게 판매되기까지의 전 과정에 걸친 개체간의 수요와 공급의 사슬관계를 의미하는 공급망 내에서 정보, 자금 그리고 물의 흐름을 관리 통제하는 공급사슬경영(SCM)이 사업의 핵심역량으로 인식되고 있다. 또한 국내 기업들의 수․배송 업무의 합리화는 국내 기업 물류관리의 가장 중요한 과제중의 하나로 부각되고 있다. 물류센터로부터 각 거래처로 물품을 배달하는 배송업무의 경우에는 기업의 물류정보시스템이 상류 중심의 데이터 체계로 구축되어왔기 때문에 물류관리 업무의 합리화에 활용할 수 있는 기초 데이터 부재와 현실적인 제약조건들을 고려한 효율적인 자동배차 알고리듬을 적용하지 못했기 때문에 배차담당자들의 수작업 조정시간이 장시간 소요되었다. 따라서 본 논문에서는 현실적인 다양한 제약조건을 만족하고, 수작업 조정시간이 대폭 줄이면서, 우편중심 좌표를 이용한 차량별 근거리 그룹핑으로 자동배차 지원시스템의 휴리스틱 알고리듬을 설계하도록 한다.

Moreover a new logistics concept is needed through the sharing information between suppliers and consumers, which maximizes the level of customers service and its flexibility by changing functional-oriented to process-oriented. In other words, Supply Chain Management(SCM) is now considered as a key aspect of business, which controls the flows of information, funds, and goods in the supply chain. Rationalization of transport-delivery system will be one of the most important issues on logistics management to the domestic companies. The companies need the effective delivery system. Especially in the case of delivery system from distribution centers to customers or vendors, it might take a long time to control the delivery system manually because it would be hard to apply the automatic vehicle routing algorithm effectively considering all the practical constraints. Thus this study develops a heuristic algorithm of automatic vehicle delivery support system in terms of grouping by short ranges of vehicle movement utilizing postal coordinates, which satisfies a variety of realistic constraints and reduces controlling time of manual operations.

Companies are pursuing the management of small quantity batch production or JIT(Just-in-time) system for improving the delivery response and LOB(Line Balancing) in order to satisfy consumers’ increasing demands in the current global economic recession. And in order to improve the growth of production for reducing manufacturing cost, improvements of the Load Balancing have become an important reformation factor. Thus this paper is aimed at warehouse which procures materials on the assembly line in procurement logistics of automotive logistics and proceed with research on heuristic algorithm development which can increase the Load Balancing of workers. As a result of this study, when applied the primary target value, it was verified that the whole workers decreased from 28 to 24. Furthermore, when specified the secondary target value and applied algorithm once more, it was verified that the Load Balance Ratio was improved from 44.96% to 91.7%.

교통 네트워크에서 하나의 노드로부터 다른 노드로 가는 최단 경로 탐색은 탐색속도와 함께 정확성도 매우 중요시 되고 있다. 기존 A* 알고리즘은 빠른 탐색속도가 큰 장점이기는 하지만, 분석네트워크가 다소 복잡하고, 링크수가 많은 대규모 네트워크에서는 최단 통행경로를 가까운 노드의 순서대로 단계적으로 찾아내는 데 정확도가 다소 낮은 약점을 갖고 있다. 따라서 본 연구에서는 A* 알고리즘의 평가함수와 알고리즘을 수정하여 정확성을 높일 수 있도록 하였다. 구 체적으로는 평가함수를 선적인 개념에서 면적인 개념으로 전환하였고, 계산단계의 진행과정에서 실제 부하량이 적을수 록 무조건 좋은 것이 아니라, 부하량이 커도 목표노드에 가까운 것이라면 더욱 최단경로에 유리하다는 개념을 도입한 것이다. 마지막으로 평가함수 값은 반복계산을 수행할수록 적어야 하는데, 이렇지 못할 경우, 피드백 기능을 부가하여 탐색 정확도를 높이도록 알고리즘을 수정하였다. 이렇게 개선된 알고리즘을 실제 네트워크상에서 적용해 본 결과, 유용 성이 있는 것으로 밝혀졌다.

In transportation networks, searching speed and result accuracy are becoming more critical on searching minimum path algorithm. Current A* algorithm has a big advantage of high searching speed. However, it has disadvantage of complicated searching network and low accuracy rate of finding the minimum path algorithm. Therefore, this study developed A* algorithm’s heuristic function and focused on improving it’s disadvantages. Newly developed function in this study contains the area concept, not the line concept. During the progress, this study adopts the idea of a heavier node that remains lighter to the target node is better that the lighter node that becomes heavier when it is connected to the other. Lastly, newly developed algorithm has the feedback function, which allows the larger accuracy value of heuristic than before. This developed algorithm tested on real network, and proved that developed algorithm is useful.

In the real life learning process, the teacher communicates with the students for a better learning outcome. The teaching-learning-based optimization (TLBO) algorithm simulates this procedure and shows its great performance in solving the constrained and unconstrained nonlinear optimization problem. This paper presents an adaptive direction strategy（ADS ）t o improve the searching ability for the TLBO algorithm. The improved algorithm is tested through searching the optimal points for a few typical testing functions. The testing result shows that the improved TLBO algorithm could obtain better optimal solutions in shorter time. Compared to the normal TLBO algorithm, the stability and effectiveness of the improved algorithm are increased greatly.

경제급전 최적화 문제를 해결하는 결정론적인 알고리즘에 존재하지 않아 지금까지는 비결정론적인 휴리스틱 알고리즘들이 제안되고 있다. 본 논문은 균형과 교환 방법을 도입하여 경제급전의 최적화 문제를 풀 수 있는 알고리즘을 제안하였다. 제안된 알고리즘은 초기치에 대해 성인걸음수와 아기걸음 수별로 발전량을 감소시켜 SIGMA P _{i} =P _{d}로 균형을 맞추고, 이 때 최소 발전비용을 가진 방법을 선택한다. 다음으로 선택된 방법에 대해 성인걸음-아기걸음 교환과 거인걸음 교환 방법으로 최적화한 값을 구하여 최소값 방법을 선택한다. 마지막으로 선택된 방법에 대해 P _{i} ± beta ,`( beta =0.1,`0.01,`0.001.`0.0001)의 교환을 수행하였다. 경제급전 문제의 시험사례로 빈번히 활용되고 있는 3개 데이터에 대해 제안된 알고리즘을 적용한 결과 2개 데이터에서는 성능을 향상시켰으며, 1개 데이터는 기존의 최적해와 동일한 결과를 얻었다. 제안된 알고리즘은 항상 동일한 결과를 얻을 수 있고, 모든 데이터에 적합하므로 경제급전 최적화 알고리즘으로 실제 적용이 가능하다.

In the absence of a deterministic algorithm for economic load dispatch optimization problem (ELDOP), existing algorithms proposed as solutions are inevitably non-deterministic heuristic algorithms. This paper, therefore, proposes a balance-and-swap algorithm to solve an ELDOP. Firstly, it balances the initial value to SIGMA P _{i} =P _{d} by subsequently reducing power generation for each adult-step and baby-step and selects the minimum cost-generating method. Subsequently, it selects afresh the minimum cost-generating method after an optimization of the previously selected value with adult-step baby-step swap and giant-step swap methods. Finally, we perform the P _{i} ± beta ,`( beta =0.1,`0.01,`0.001.`0.0001) swap. When applied to the 3 most prevalently used economic load dispatch problem data, the proposed algorithm has obtained improved results for two and a result identical to the existing one for the rest. This algorithm thus could be applied to ELDOP for it has proven to consistently yield identical results and to be applicable to all types of data.

Traditionally, the assignment problem between tasks and processors is worked out by scheduling methods. In this paper, we have an innovative idea to construct a problem-solving environment for computational grids. To bridge the gap between the parallel processing technology and the heterogeneous computing environment, the grid computing resources are reorganized architecturally to form a virtual regular topology. In this research, we put emphasis on finding a heuristic algorithm of transferring an irregular grid resource topology into a mesh virtually.

In order to solve issues of grid network as a broadband wireless access network, such as high data transmission rate and long-distance signal coverage and so on, this paper proposes two heuristic algorithms with O (m3) time complexity, based on the user neighbors’ information and location information. The algorithm will meet transferring the minimum relay deployment problem required by users into the minimum clique partition problem of adjacency graph and gives specific algorithm steps. Experimental results show that: the proposed algorithm ensures network performance and reduces network cost.

The alongside replenishment scheduling problem with time constraint determining the partition of the ships, the order of replenishment and the allocation of time to the ships at the same time is analyzed. It is equivalent to a multi-stage flow shop scheduling problem with the object of maximizing the effectiveness value of ship fleet. The problem solving process is divided into three steps, and based on the analysis of the three steps, a heuristic algorithm is proposed. The algorithm firstly considers the time allocated to each ship, and then sequences the ships by heuristic rule combining greed with insertion, finally determines the ships partitioning to the port and standard side. Emulating example with different problems’ scale and time constraints shows that the proposed heuristic algorithm is superior to some other algorithms.

In this paper, we propose a novel approach to explore image denoising for patch based image process. The importance measurement model of Rough Entropy and the importance reduction method of wavelet coefficients are given. This paper combines the rough set theory with the denoising method of wavelet threshold, regarding the high-frequency information blocks in the transform domain as similar ones, and adopting importance Reduction Methods to contract the coefficients. The simulation results show that this method is effective.

With the development of the computer network technology and the electronic commerce, more and more firms establish the electronic sale channel and get great profits. The huge supply chain network is established through the new idea and technology. The node location selection is a planning process that chooses a location to set up a logistics node in an economy zone with multi demands. Hence, its location selection is a key link in the logistics system planning. In this paper, we consider the specific particularity of the e-commerce. Then, we constraints cost and delivery time of the logistics model. At last, we apply the heuristic algorithm to the location model. The results show that the algorithm can apply to the logistics distribution problem under the electronic commerce environment excellently.

Although meta-heuristic optimization algorithms have been used to solve many optimization problems, they still suffer from two main difficulties: What are the best parameters for a particular problem? How do we escape from the local optima? In this paper, a new, efficient meta-heuristic optimization algorithm inspired by wild dog packs is proposed. The main idea involves using three self-competitive parameters that are similar to the smell strength. The parameters are used to control the movement of the alpha dogs and, consequently, the movement of the whole pack. The rest of the pack is used to explore the neighboring area of the alpha dog, while the hoo procedure is used to escape from the local optima. The suggested method is applied to several unimodal and multimodal benchmark problems and is compared to five modern meta-heuristic algorithms. The experimental results show that the new algorithm outperforms other peer algorithms.

Grid resource scheduling policies directly affect the performance of the grid, so the grid resource scheduling algorithm for grid research has become a hot spot. In this paper, based on grid heterogeneity to resource scheduling of load balancing, effective resource utilization and minimize task sets the span of time (Makespan) as the goal, propose a heuristic grid resource scheduling algorithm based on Group of Task and Secondary Distribution, the basic idea is dividing the set of tasks into two groups by using the standard deviation, the one is long tasks group, another is short tasks group .The longest task in long tasks group will be allocated to the worst performance to execute, the rest can be done in the same manner. Tasks in short tasks group will be executed by the Min-Min algorithm , and then through secondary dispatch ideas to make the grid system to quickly reach each resource load balancing , improving resource utilization efficiency and minimizing the task set time span. Finally, the simulation model benchmark Braun et al. demonstrates the effectiveness of the algorithm.