• Journal of information and communication convergence engineering
• /
• v.20 no.1
• /
• pp.22-30
• /
• 2022

The reinforcement learning algorithm has proven its potential in solving sequential decision-making problems under uncertainties, such as finding paths to route data packets in wireless sensor networks. With reinforcement learning, the computation of the optimum path requires careful definition of the so-called reward function, which is defined as a linear function that aggregates multiple objective functions into a single objective to compute a numerical value (reward) to be maximized. In a typical defined linear reward function, the multiple objectives to be optimized are integrated in the form of a weighted sum with fixed weighting factors for all learning agents. This study proposes a reinforcement learning -based routing protocol for wireless sensor network, where different learning agents prioritize different objective goals by assigning weighting factors to the aggregated objectives of the reward function. We assign appropriate weighting factors to the objectives in the reward function of a sensor node according to its hop-count distance to the sink node. We expect this approach to enhance the effectiveness of multi-objective reinforcement learning for wireless sensor networks with a balanced trade-off among competing parameters. Furthermore, we propose SDN (Software Defined Networks) architecture with multiple controllers for constant network monitoring to allow learning agents to adapt according to the dynamics of the network conditions. Simulation results show that our proposed scheme enhances the performance of wireless sensor network under varied conditions, such as the node density and traffic intensity, with a good trade-off among competing performance metrics.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.58 no.3
• /
• pp.281-287
• /
• 2022

The distributions of common minke whales observed in the East Sea in ten surveys in May of 2003, 2005, 2006, 2007, 2009, 2010, 2012, 2015, 2016 and 2020 were investigated using satellite sea surface temperature (SST) derived from the Moderate Resolution Imaging Spectrometer (MODIS). Most of the minke whales were observed in the waters off the Korean Peninsula at 36-38.5° N, which is expected as the highly productive coastal upwelling area. Yet, no minke whale was observed in 2006 when a relatively larger scale coastal upwelling occurred with SST at 11℃. In 2016 and 2020, the warm water higher than 17℃ extended widely in the area, and the minke whales were observed in the offshore waters, deeper than 1,000 m. 87.5% of minke whales observed in May appeared in the SST from 13 to 16℃, and they seemed to avoid relatively high temperatures. This suggests that optimum habitat water temperature of minke whales in May is 13-16℃. The SST in the area had risen 1.67℃ from 2003 to 2021, and it was remarkably higher than in other parts of the surrounding areas. The future temperature rising may change the route and timing of the migration of minke whales in the study area.

• Journal of Energy Engineering
• /
• v.19 no.4
• /
• pp.215-220
• /
• 2010

Hydrogen is a clean and efficient energy source and is expected to take an important role in future energy demand. A possibly good route to produce hydrogen is by using biomass and organic wastes as a source through thermo-chemical conversion technology. In this study, pyrolysis of wood Pellet(Oregon pine) has been carried out in batch type fixed-bed reactor in $N_2$ atmosphere during 20 minutes to determine the optimum hydrogen generating conditions. At the influence of temperature, hydrogen yield was increased with increasing temperature. For the influence of Steam/Biomass Ratio(SBR), hydrogen yield was increased by steam addition at low temperature condition. However, effect of steam addition was insignificant over at SBR = 1. The hydrogen yield was increased with increasing SBR at high temperature condition. From result of $H_2$/CO and $H_2/CH_4$ ratio, dominant reaction was steam reforming in this experimental condition. The optimum condition for hydrogen production was determined as follows: $H_2$ yield = 38.3 vol.% (56.01 L/min kg) at $900^{\circ}C$, SBR=3.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.17 no.6
• /
• pp.40-53
• /
• 2018

In smart card data, movement of railway passengers appears in order of smart card terminal ID. The initial terminal ID holds information on the entering station's tag-in railway line, the final terminal ID the exit station tag-out railway line, and the middle terminal ID the transfer station tag subway line. During the past, when the metropolitan city rail consisted of three public corporations (Seoul Metro, Incheon Transit Corporation, and Korail), OD data was expressed in two metrics of initial and final smart card terminal ID. Recently, with the entrance of private corporations like Shinbundang Railroad Corporation, and UI Corporation, inclusion of entering transfer line terminal ID and exiting transfer line terminal ID as part of Chain OD has become standard. Exact route construction using Chain OD has thus become integral as basic data for revenue allocation amongst metropolitan railway transport corporations. Accordingly, path detection in railway networks has evolved to an optimal path detection problem using Chain OD, hence calling for a renewed solution method. This research proposes an optimal path detection method between the initial terminal ID and final terminal ID of Chain OD terminal IDs within the railway network. Here, private line transfer TagIn/Out must be reflected in optimal path detection using Chain OD. To achieve this, three types of link-based optimum path detection methods are applied in order of 1. node-link, 2. link-link, 3. link-node. The method proposed based on additional path costs is shown to satisfy the optimal conditions.

• Korean Chemical Engineering Research
• /
• v.44 no.6
• /
• pp.588-596
• /
• 2006

The surface of polystyrene membrane treated by Ar, $O_2$ plasma, and the effects were observed before and after the treatment and permeability of $CO_2$, $N_2$ and selectivity of $CO_2$ relative to $N_2$ was measured using continuous flow gas permeation analyzer (GPA). The mole ratio of O over C in the surface was increased from 0 to 0.179 with Ar plasma treatment and route mean square of surface was increased from $15.86{\AA}$ to $71.64{\AA}$. Therefore the contact angle was decreased from $89.16^{\circ}$ to $18.1^{\circ}$. Thus Plasma treatments made surface of membrane tend to be highly hydrophilic. The optimum condition for the $CO_2$ permeability and ideal selectivity of the plasma treated membrane was as follows: the measurement of Ar (60 W, 2 min, $70^{\circ}C$) plasma treatment was $1.14{\times}10^{-12}[m^3(STP){\cdot}m/m^2{\cdot}sec{\cdot}atm]$ and 4.22. In the case of $O_2$ plasma treatment, the contact angle was decreased at $13.56^{\circ}$ with increase of O/C ratio ($0.189{\AA}$) and route mean square of surface ($57.10{\AA}$). The optimum condition for the $CO_2$ permeability and ideal selectivity of the plasma treated membrane was as follows: the measurement of $O_2$ (90 W, 2 min, $70^{\circ}C$) plasma treatment was $7.1{\times}10^{-12}[m^3(STP){\cdot}m/m^2{\cdot}sec{\cdot}atm]$ and 11.5. After plasma treatment, the changes of membrane surface were all subtly linked with both cross-linking and etching effects. Finally, it was confirmed that the gas permeation capacity and selectivity of the modified membrane with plasma could be improved by an appropriate control of the plasma conditions such as treatment time, the power input and sort of plasma gas.

• Journal of Korean Society of Transportation
• /
• v.22 no.5
• /
• pp.89-97
• /
• 2004

The Korea Air Force(KAF) has operated freight flights based on the prefixed time and route schedule, which is adjusted once in a month. The major purpose of the operation of freight flights in the KAF is to distribute necessary supplies from the home air base to other air bases. The secondary purpose is to train the young pilots to get more experiences in navigation. Each freight flight starts from and returned to the home air base everyday except holidays, while it visits several other air bases to accomplish its missions. The study aims to forecast freight demand at each base by using time series analysis, and then it tried to optimize the cost of operating flights by solving vehicle routing problem. For more specifically, first, several constraints in operating cargos were defined by reviewing the Korea Air Force manuals and regulation. With such constraints, an integer programming problem was formulated for this specific routing problem allowing several visits in a tour with limitation of maximum number of visits. Then, an algorithm to solve the routing problem was developed. Second, the time series analysis method was applied to find out the freight demand at each air base from the mother air base in the next month. With the forecasted demands and the developed solution algorithm, the oprimum routes are calculated for each flight. Finally, the study compared the solved routing system by the developed algorithm with the existing routing system of the Korea Air Force. Through this comparison, the study proved that the proposed method can provide more (economically) efficient routing system than the existing system in terms of computing and monetary cost. In summary, the study suggested objective criteria for air routing plan in the KAF. It also developed the methods which could forecast properly the freight demands at each bases by using time series analysis and which could find the optimum routing which minimizes number of cargo needed. Finally, the study showed the economical savings with the optimized routing system by using real case example.

• Journal of Korean Society of Transportation
• /
• v.22 no.5
• /
• pp.139-149
• /
• 2004

As the expansion of road capacity has become impractical in many urban areas, congestion pricing has been widely considered as an effective method to reduce urban traffic congestion in recent years. The principal reason is that the congestion pricing may lead the user equilibrium (UE) flow pattern to system optimum (SO) pattern in road network. In the context of network equilibrium, the link tolls according to the marginal cost pricing principle can user an UE flow to a SO pattern. Thus, the pricing method offers an efficient tool for moving toward system optimal traffic conditions on the network. This paper proposes a continuous network design program (CNDP) in network equilibrium condition, in order to find optimal congestion toll for maximizing net economic benefit (NEB). The model could be formulated as a bi-level program with continuous variable(congestion toll) such that the upper level problem is for maximizing the NEB in elastic demand, while the lower level is for describing route choice of road users. The bi-level CNDP is intrinsically nonlinear, non-convex, and hence it might be difficult to solve. So, we suggest a heuristic solution algorithm, which adopt derivative information of link flow with respect to design parameter, or congestion toll. Two example networks are used for test of the model proposed in the paper.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.29 no.1
• /
• pp.11-20
• /
• 2011

This study aimed to devise the method to construct safe and convenient bicycle road by considering the peripheral environmental factor related to using bicycle. Analyzing the existing design of bicycle road and construction case, this study established the method to design bicycle road that reflects site condition and presented the optimal design method for each type of bicycle road to construct safe and convenient bicycle road by analyzing the type of traffic accident for each type of bicycle road, surveying present situation and local survey. It was found that the optimum design of bicycle road for specification, width, curve radius, ascending slope, etc in consideration of peripheral environment and separating traffic between users of traffic means should be done by installing safety sign, safe facilities and separation facilities to design safe bicycle road. Further, the minimum traffic space of bicycle users and connection between bicycle roads should be ensured to design safe bicycle road. It is judged that information related to safety and convenience of bicycle road such as slope, route information, location of convenience facilities, information to the public traffic should be provided so as to activate the users of bicycle.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.21 no.2
• /
• pp.179-187
• /
• 2015

The purpose of this study is to identify the aspect that the traffic distribution function changes, according to the direction of the datum line and the horizontal and vertical positions of the datum point applied when it is calculated. Targeting routes at the entrance of Mokpo Harbor, this study tested using AIS survey data of January 2013 the effects of the three variables-direction of the datum line(${\theta}$), horizontal position($\mathfrak{L}_H$) and vertical position($\mathfrak{L}_V$) on mean ($\bar{x}$) and standard deviation (${\delta}$). The test result showed that $\bar{x}$ and ${\delta}$ were changed according to the change of ${\theta}$, because the extracted sample data were changed according to ${\theta}$; and the changes of $\bar{x}$ and ${\delta}$ according to ${\theta}$ were drawn as the relation of the sine function' sum. In addition, it was found that setting up ${\theta}$ that the change value of ${\delta}$ becomes the least as the direction of the datum line was valid, to determine the optimum passage distribution function on complex waters with multiple branches of route. The result of this study is expected to be used as basic data to understand maritime traffic flow based on more quantified data of normal distribution and make decisions related to maritime traffic safety management.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.13 no.2
• /
• pp.357-368
• /
• 2018

For well over 100 years, oil has enabled remote communities to generate electricity and enjoy the benefits of a consistent electrical supply. Relying solely on oil for electricity generation has left island and remote communities exposed to several risks and drawbacks. Oil-based electricity generation is often more expensive and subject to price volatility, which can result in the use of risky fuel hedging strategies. The residents of islands and remote communities express concern over the future impacts of climate change or insist on their opinions for the corresponding action with reduction of carbon emissions. These risks and drawbacks can be overcomed with continuing cost reductions in solar, wind, and energy storage technologies by maker. Reducing costs is not always a straightforward process, relying on more diversely and renewably arranged renewable energy sources led to reduced local construction cost in every situation reviewed in this study. In this paper, a convenient and simple design solution which will facilitate the optimum location and transmission route of renewable energy facility using GIS(Geographic Information System) is proposed. The suggested solutions exercised to the case of geomoon island using GIS and identified by local site survey.