• Journal of the Korean Society of Marine Environment & Safety
• /
• v.24 no.7
• /
• pp.870-874
• /
• 2018

In the worst maritime accidents, people should abandon ship, but ship structures are narrow and complex and operation takes place on rough seas, so escape is not easy. In particular, passengers on cruise ships are untrained and varied, making evacuation prospects worse. In such a case, the evacuation management of the crew plays a very important role. If a rescuer enters a ship at distress and conducts rescue activities, which zones represent the most effective entry should be examined. Generally, crew and rescuers take the shortest route, but if an accident occurs along the shortest route, it is necessary to select the second-best alternative. To solve this situation, this study aims to calculate evacuation routes using Q-Learning of Reinforcement Learning, which is a machine learning technique. Reinforcement learning is one of the most important functions of artificial intelligence and is currently used in many fields. Most evacuation analysis programs developed so far use the shortest path search method. For this reason, this study explored optimal paths using reinforcement learning. In the future, machine learning techniques will be applicable to various marine-related industries for such purposes as the selection of optimal routes for autonomous vessels and risk avoidance.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.50 no.7
• /
• pp.339-349
• /
• 2001

This paper suggests an optimal identification method for complex and nonlinear system modeling that is based on Fuzzy-Neural Networks(FNN). The proposed Hybrid Identification Algorithm is based on Yamakawa's FNN and uses the simplified inference as fuzzy inference method and Error Back Propagation Algorithm as learning rule. In this paper, the FNN modeling implements parameter identification using HCM algorithm and hybrid structure combined with two types of optimization theories for nonlinear systems. We use a HCM(Hard C-Means) clustering algorithm to find initial apexes of membership function. The parameters such as apexes of membership functions, learning rates, and momentum coefficients are adjusted using hybrid algorithm. The proposed hybrid identification algorithm is carried out using both a genetic algorithm and the improved complex method. Also, an aggregated objective function(performance index) with weighting factor is introduced to achieve a sound balance between approximation and generalization abilities of the model. According to the selection and adjustment of a weighting factor of an aggregate objective function which depends on the number of data and a certain degree of nonlinearity(distribution of I/O data), we show that it is available and effective to design an optimal FNN model structure with mutual balance and dependency between approximation and generalization abilities. To evaluate the performance of the proposed model, we use the time series data for gas furnace, the data of sewage treatment process and traffic route choice process.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.05a
• /
• pp.367-370
• /
• 2017

This paper proposes a method for selecting efficient relay nodes in stochastic DTN model. Delay Tolerant Network (DTN) uses the Carry and Forward method, which creates a bundle layer for efficient communication, selects relay nodes between different networks and heterogeneous networks, and forwards messages. DTN is basically composed of mobile nodes so DTN has no fixed routing route and it has long latency due to intermittent connection. Therefore, the nodes constituting the DTN necessarily have the characteristics to store the messages, and the capacity of the stored messages and nodes affects the performance of the network. Stochastic DTN model proposed a Markov model that changes randomly over time to analyze the performance of DTN. In this paper, we use stochastic message distribution and node contact probabilities using contact time analyzed through message generation and extinction in order to select efficient relay nodes in stochastic DTN model.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.6
• /
• pp.65-72
• /
• 2010

In ad-hoc network, the technique to efficiently consume the limited amounts of energy is an important issue since the wireless terminal node is operated on batteries as their energy resource. In order to extend the system lifetime, through a balanced energy consumption, we must delay the situation in which a particular terminal node's energy is depleted and results in system disconnection. Also, the link, which has low reliability due to the mobility of the node, should be avoided considering the key element when setting up the route. The proposed CMLR method in this paper enables to increase the efficiency of energy consumption with a new cost function considering the residue energy of node, error rate of link, and transmission energy consumption. This method is extending the network lifetime and increasing the energy efficiency by compromising the value between the minimization of the transmission energy consumption and maximization of the node's lifetime. Through the simulations the proposed CMLR algorithm was verified by showing better performance over the conventional methods in terms of network lifetime and path efficiency.

• Journal of Korea Multimedia Society
• /
• v.7 no.5
• /
• pp.689-697
• /
• 2004

Rapid advances in mobile computing and the availability of wireless communications will soon provide mobile users with the ability to access data regardless of the location of the user or of the data. SRA(Static Replica Allocation) that is traditional scheme has been used for the replication method on the server. This replicates the data on the replica server after a moving host has been transferred to the cell. This strategy is simple and can easily relocate data. However, if a mobile user does not exist in the cell, the replicated data can be deleted in order to maintain data consistency. In addition to, if the mobile host leaves from replicated cell, it is difficult to access data in terms of replication route. Therefore, this paper proposes a new method of relocation based on data consistency strategy called USRAC(User Selection Replica Allocation based on Consistency) and also analyzes access cost according to the moving rate of mobile users, according to the access rate of mobile hosts, and according to the number of cells of mobile users and mobile hosts.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.6
• /
• pp.83-90
• /
• 2009

Since traffic is aggregated to a MPP that acts as an Internet gateway, if traffic load is not balanced among the MPPs in a WMN, the overall performance of a WMN becomes poor even though the total traffic load is far below the capacity of the WMN. Therefore, in this paper, we propose a stochastic load balancing scheme where each MP (Mesh Point) probabilistically selects its serving MPP according to the congestion levels of MPPs. Through extensive simulations using ns-2, we have verified that our scheme can stabilize a WMN fast when congestion occurs and reduce packet loss rate by distributing traffic load of a congested MPP to multiple MPPs in the inverse proportional to their congestion levels. Compared to queue-based load balancing scheme, our method can decrease network stabilization time by 34 seconds, and reduce packet loss rate by 7.6%. Since the proposed scheme can reduce network stabilization time by efficiently using network resource, it is expected to contribute to the reliable operation of a WMN.

• Journal of the Korea Society for Simulation
• /
• v.27 no.4
• /
• pp.47-60
• /
• 2018

Today's unmanned technology, which is being used in various industries, is expected to be able to make autonomous judgements as autonomous technology matures, in the long run aspects. In order to improve the usability of unmanned system in the military field, it is necessary to develop a technique for systematically and quantitatively analyzing the efficiency and effectiveness of the unmanned system by means of a substitute for the tasks performed by humans. In this paper, we propose the method of representing rule-based tactical behavior and modeling manned and unmanned reconnaissance agents that can effectively analyze the path alternatives which is required for the future armored cavalry to establish a reconnaissance mission plan. First, we model the unmanned ground vehicle, small tactical vehicle, and combatant as an agent concept. Next, we implement the proposed agent behavior rules, e.g., maneuver, detection, route determination, and combatant's dismount point selection, by NetLogo. Considering the conditions of maneuver, enemy threat elements, reconnaissance assets, appropriate routes are automatically selected on the operation area. It is expected that it will be useful in analyzing unmanned ground system effects by calculating reconnaissance conducted area, time, and combat contribution ratio on the route.

• Journal of Korean Academy of Nursing Administration
• /
• v.12 no.3
• /
• pp.444-453
• /
• 2006

Purpose: The purpose of the study was to identify critical indicators for the development of efficient patient classification system in a emergency room. Method: This study involved following five steps. Step 1. Selection of the lists direct nursing services in the ER. Step 2. Measurement of the time of direct nursing services from Aug. 31st to Nov. 30th, 2005. Step 3. Classification of the patients according to the nursing care time. Step 4. The determination the critical indicators for different patient classes. Result: Determinate indicators were as follow: 3 items in the first group (vital sign checking, IV route starting, blood sampling), 3 items in the second group (vital sign checking, fluid infusion, blood sampling), 9 items in the third group (I/O checking, $O_{2}$ inhalation, suction, fluid infusion, IV bolus, Central catheter preparation & management, blood sampling, intubation preparation & management, postmortem management), 7 items in the fourth group (EKG monitoring, BP monitoring, $O_{2}$ inhalation, fluid infusion, using the specific drugs, CPR, postmortem management). Conclusion: This study can help future studies which measure nursing services standard time or assigns value to emergency nursing services.

• The KIPS Transactions:PartD
• /
• v.12D no.4 s.100
• /
• pp.569-582
• /
• 2005

As information and business communication via Internet are growing up, web-based software is wide spread and more important on the viewpoint of software qualify than stand-alone. Research on verification of web content links and web-based Program was tried, but has short on covering various types of web based software and making experiments to be applied in real testing practice. This paper suggests a modeling technique to be applied to dynamic and various types of web-based software. First, it identifies each elements consisting of web-based software and then construct a model of Object Control Flow Graph and Object Relationship Diagram. We can generate test cases covering all test paths of ORD or invoking key points test route. Suggested modeling method and test case selection technique are verified by applying five types of web-based software and compared with other web-based test techniques.

• Journal of the Korean Society of Propulsion Engineers
• /
• v.4 no.1
• /
• pp.65-73
• /
• 2000

Casting of metal matrix composites is an attractive process since it offers a wide selection of materials and processing conditions. Among the casting methods, melt-stirring technology is much attractive route in industrial application because it is more simple and inexpensive compared to squeeze casting or powder metallurgy. In the present work, effects of particle size, volume fraction of particles and mg addition on mechanical properties and thermal expansion coefficients of $\alpha$ -$Al_2O_{3(p)}$/LXA composites were studied. It is shown that $\alpha$ -$Al_2O_3$ particles formed at the interface of $\alpha$ -$Al_2O_3$ particles and matrix made an important role on mechanical properties. Ultimate tensile strength of most composite materials was not increased. But in the case of 5vol% addition of 16$\mu\textrm{m}$ $\alpha$ -$Al_2O_3$ Particle, Ultimate tensile strength of composite materials with 3wt.% Mg was increased. Volume fraction of reinforcements and mg content were thermal expansion coefficients of composite materials were decreased.