• Journal of Advanced Information Technology and Convergence
• /
• v.9 no.1
• /
• pp.127-134
• /
• 2019

In terms of deep Reinforcement Learning (RL), exploration can be worked stochastically in the action of a state space. On the other hands, exploitation can be done the proportion of well generalization behaviors. The balance of exploration and exploitation is extremely important for better results. The randomly selected action with ε-greedy for exploration has been regarded as a de facto method. There is an alternative method to add noise parameters into a neural network for richer exploration. However, it is not easy to predict or detect over-fitting with the stochastically exploration in the perturbed neural network. Moreover, the well-trained agents in RL do not necessarily prevent or detect over-fitting in the neural network. Therefore, we suggest a novel design of a deep RL by the balance of the exploration with drop-out to reduce over-fitting in the perturbed neural networks.

• Coupled systems mechanics
• /
• v.13 no.3
• /
• pp.219-229
• /
• 2024

By introducing optimization algorithms into the machining process, product quality can be improved, time saved, and costs reduced. The cutting speed and feed can be handled by the turning machine. The approach of optimizing is used to manage pyrotechnics, Lawler's, greedy, bacterial colony, elephant herding, ant lion, spiral, auction, and pattern search for these ten odd ways. Ten artificial optimization methodologies were used to investigate the time and cost of a turning machine. It has been discovered how to create the optimal turning machine procedure. The best solution approach for the turning machine process problem is found, and the results are verified using ANSYS.

• Journal of the Economic Geographical Society of Korea
• /
• v.14 no.2
• /
• pp.116-128
• /
• 2011

Some subway passengers may want to have their fresh vegetables purchased through internet at a service facility within the subway station of the Metropolitan Seoul subway system on the way to home, which raises further questions about which stations are chosen to locate service facilities and how many passengers can use the facilities. This problem is well known as the pickup problem, and it can be solved on a traffic network with traffic flows which should be identified from origin stations to destination stations. Since flows of the subway passengers can be found from the smart card transaction database of the Metropolitan Seoul smart card system, the pickup problem in the Metropolitan Seoul subway system is to select subway stations for the service facilities such that captured passenger flows are maximized. In this paper, we have formulated a model of the pickup problem on the Metropolitan Seoul subway system with subway passenger flows, and have proposed a fast heuristic algorithm to select pickup stations which can capture the most passenger flows in each step from an origin-destination matrix which represents the passenger flows. We have applied the heuristic algorithm to select the pickup stations from a large volume of traffic network, the Metropolitan Seoul subway system, with about 400 subway stations and five millions passenger transactions daily. We have obtained not only the experimental results in fast response time, but also displayed the top 10 pickup stations in a subway guide map. In addition, we have shown that the resulting solution is nearly optimal by a few more supplementary experiments.

• Journal of KIISE:Information Networking
• /
• v.36 no.1
• /
• pp.12-23
• /
• 2009

Sensor networks deployed in battlefields to support military operations or deployed in natural habitats to monitor the rare wildlifes must take account of protection of the location of valuable assets(i.e., soldiers or wildlifes) from an adversary or malicious tracing as well as the security of messages in transit. In this paper we propose a routing protocol GSLP(GPSR-based Source-Location Privacy) that is capable of enhancing the location privacy of an active source node(i.e., message-originating node) in the presence of multiple dormant sources(i.e., nodes lying nearby an asset whose location needs to be secured). Extended is a simple, yet scalable, routing scheme GPSR(greedy perimeter stateless routing) to select randomly a next-hop node with a certain probability for randomizing paths and to perform perimeter routing for detouring dormant sources so that the privacy strength of the active source, defined as safety period, keeps enhanced. The simulation results obtained by increasing the number of dormant sources up to 1.0% of the total number of nodes show that GSLP yields increased and nearly invariant safety periods, while those of PR-SP(Phantom Routing, Single Path), a notable existing protocol for source-location privacy, rapidly drop off as the number of dormant sources increases. It turns out that delivery latencies of GSLP are roughly less than two-fold of the shortest path length between the active source and the destination.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.12 no.1
• /
• pp.121-135
• /
• 2013

This paper propose an efficient algorithm for selecting electric bus charging facility location. In nature, the optimal charging facility location problem is similar to Set Covering Problem. Set Covering Problem is the problem of covering all the rows of an $m{\times}n$ matrix of ones and zeros by a subset of columns with a minimal cost. It has many practical applications of modeling of real world problems. The Set Covering Problem has been proven to be NP-Complete. In order to overcome the computational complexity involved in seeking optimal solutions, this paper present an enhanced greedy algorithm and simulated annealing algorithm. In this paper, we apply the developed algorithm to Seoul's public bus system.

• Journal of Korean Society of Transportation
• /
• v.29 no.2
• /
• pp.91-100
• /
• 2011

Hub network design for freight transportation is a decision process that determines hub locations together with freight transportation routes among shippers so as to ultimately minimize total logistics cost. This study presents the optimal location of hubs by strict hub network design policy with single allocation, which overcomes the limitation of Kim et al. (2008) that does not allow direct transportation among shippers. The greedy-interchange algorithm is employed for hub location decision process, and EMME/2 is adopted for the route searching process. Application of the processes to the nationwide highway network shows that the best hub locations in order are Seoul metropolitan, GyeongNam, Chung-nam, Jeon-Nam, Gyeong-Buk, Chung-Buk, and the locations are concentrated on the Seoul-Busan corridor. The strict hubnetwork design policy with single allocation increases the transportation distance but decreases the transportation cost by passing through the hubs instead of direct transportation. The reduction in total transportation cost can be achieved as the number of hubs increases, but the amount of the reduction gradually decreases because the cost reduction from the decrease in detour transportation distance between non-hubs and hubs becomes less than the discount reduction from dispersion of inter-hubs transportation volumes.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.5 no.3
• /
• pp.27-45
• /
• 2010

It is strongly believed that multicast will become one of the most promising services on internet for the next generation. Multicast service can be deployed either on network-layer or application-layer. IP multicast (network-layer multicast) is implemented by network nodes (i.e., routers) and avoids multiple copies of the same datagram on the same link. Despite the conceptual simplicity of IP multicast and its obvious benefits, it has not been widely deployed since there remain many unresolved issues. As an alternative to IP multicast, overlay multicast (application-layer multicast) implements the multicast functionality at end hosts rather than routers. This may require more overall bandwidth than IP multicast because duplicate packets travel the same physical links multiple times, but it provides an inexpensive, deployable method of providing point-to-multipoint group communication. In this paper we develop an efficient method applied greedy algorithm for solving two models of overlay multicast routing protocol that is aimed to construct MDST (Minimum Diameter Spanning Tree : minimum cost path from a source node to all its receivers) and MST (Minimum Spanning Tree : minimum total cost spanning all the members). We also simulate and analyze MDST and MST.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.10B
• /
• pp.1050-1061
• /
• 2009

The Tactical Internet(TI) managed by Infantry Brigades is used for the purpose of sharing information of Command Control and Situation Awareness. When there are more than two destinations to transmit data in the TI system, a multicasting is utilized based on pre-defined multicast groups. However even in the case when a source node needs to send some messages like weathercast and attack alarm etc to only a part of Battalion or Brigades in a specific geographical region (destination region), the current TI multicasting protocol is designed to transmit the messages to the pre-defined group or all of the Battalion/Brigade nodes, resulting in inefficiency in terms of end-to-end delay and overhead. In this paper, we propose more efficient protocol for such cases, named as "Tactical Internet Geocasting (TIG)". The proposed scheme firstly checks whether the destination region belongs to one Battalion region or more than two Battalion regions using location information, and then performs a greedy forwarding from the source node to the destination region, followed by a local flooding inside of the destination region. With performance analysis and simulations using NS-2, TIG is compared to the current TI multicasting protocol (i.e., Simplified MDP) and the LBM (Location-based Multicast). The simulation results show that the proposed TIG is more efficient than both in terms of delay and network overhead.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.6
• /
• pp.1-11
• /
• 2015

Recently, NAND flash memories are used for storage devices because of fast access speed and low-power. However, applications of FTL on low power computing devices lead to heavy workloads which result in a memory requirement and an implementation overhead. Consequently, studies of B+-Tree on embedded devices without the FTL have been proposed. The studies of B+-Tree are optimized for performance of inserting and updating records, considering to disadvantages of the NAND flash memory that it can not support in-place update. However, if a general garbage collection method is applied to the previous studies of B+-Tree, a performance of the B+-Tree is reduced, because it generates a rearrangement of the B+-Tree by changing of page positions on the NAND flash memory. Therefor, we propose a novel garbage collection method which can apply to the B+-Tree based on the NAND flash memory without the FTL. The proposed garbage collection method does not generate a rearrangement of the B+-Tree by using a block information table and a proxy block. We implemented the B+-Tree and ${\mu}$-Tree with the proposed garbage collection on physical devices with the NAND flash memory. In experiment results, the proposed garbage collection scheme compared to greedy algorithm garbage collection scheme increased the number of inserted keys by up to about 73% on B+-Tree and decreased elapsed time of garbage collection by up to about 39% on ${\mu}$-Tree.

• 한국벤처창업학회:학술대회논문집
• /
• 2010.08a
• /
• pp.71-89
• /
• 2010

It is strongly believed that multicast will become one of the most promising services on internet for the next generation. Multicast service can be deployed either on network-layer or application-layer. IP multicast (network-layer multicast) is implemented by network nodes (i.e., routers) and avoids multiple copies of the same datagram on the same link. Despite the conceptual simplicity of IP multicast and its obvious benefits, it has not been widely deployed since there remain many unresolved issues. As an alternative to IP multicast, overlay multicast (application-layer multicast) implements the multicast functionality at end hosts rather than routers. This may require more overall bandwidth than IP multicast because duplicate packets travel the same physical links multiple times, but it provides an inexpensive, deployable method of providing point-to-multipoint group communication. In this paper we develop an efficient method applied greedy algorithm for solving two models of overlay multicast tree building problem that is aimed to construct MDST (Minimum Diameter Spanning Tree : minimum cost path from a source node to all its receivers) and MST (Minimum Spanning Tree : minimum total cost spanning all the members). We also simulate and analyze MDST and MST.