• Journal of Environmental Impact Assessment
• /
• v.29 no.6
• /
• pp.403-413
• /
• 2020

A mathematical model comprised with eight simultaneous quasi-linear partial differential equations was suggested to provide optimal chlorination strategy. Upstream weighted finite element method was employed to construct multidimensional numerical code. The code was verified against measured concentrations in three type of reactors. Boundary conditions and reaction rate were calibrated for the sixteen cases of experimental results to regenerate the measured values. Eight reaction rate coefficients were estimated from the modeling result. The reaction rate coefficients were expressed in terms of pH and temperature. Automatic optimal algorithm was invented to estimate the reaction rate coefficients by minimizing the sum of squares of the numerical errors and combined with the model. In order to minimize the concentration of chlorine and pollutants at the final usage sites, a real-time predictive control system is imperative which can predict the water quality variables from the chlorine disinfection process at the water purification plant to the customer by means of a model and operate the disinfection process according to the influent water quality. This model can be used to build such a system in water treatment plants.

• Smart Media Journal
• /
• v.10 no.3
• /
• pp.39-47
• /
• 2021

Enhanced index tracking is a problem of optimizing the objective function to generate returns above the index based on the index tracking that follows the market return. In order to avoid problems such as large transaction costs and illiquidity, we used a method of constructing a portfolio by selecting only some of the stocks included in the index. Commonly used enhanced index tracking methods tried to find the optimal portfolio with only one objective function in all tested periods, but it is almost impossible to find the ultimate strategy that always works well in the volatile financial market. In addition, it is important to improve generalization performance beyond optimizing the objective function for training data due to the nature of the financial market, where statistical characteristics change significantly over time, but existing methods have a limitation in that there is no direct discussion for this. In order to solve these problems, this paper proposes ensemble learning that composes a portfolio by combining several objective functions and a 3-stage portfolio selection algorithm that can select a portfolio by applying criteria other than the objective function to the training data. The proposed method in an experiment using the S&P500 index shows Sharpe ratio that is 27% higher than the index and the existing methods, showing that the 3-stage portfolio selection algorithm and ensemble learning are effective in selecting an enhanced index portfolio.

• The Journal of Bigdata
• /
• v.9 no.1
• /
• pp.101-113
• /
• 2024

Federated learning has garnered attention as an efficient method for training machine learning models in a distributed environment while maintaining data privacy and security. This study proposes a novel FedRFBagging algorithm to optimize the performance of random forest models in such federated learning environments. By dynamically adjusting the trees of local random forest models based on client-specific data characteristics, the proposed approach reduces communication costs and achieves high prediction accuracy even in environments with numerous clients. This method adapts to various data conditions, significantly enhancing model stability and training speed. While random forest models consist of multiple decision trees, transmitting all trees to the server in a federated learning environment results in exponentially increasing communication overhead, making their use impractical. Additionally, differences in data distribution among clients can lead to quality imbalances in the trees. To address this, the FedRFBagging algorithm selects only the highest-performing trees from each client for transmission to the server, which then reselects trees based on impurity values to construct the optimal global model. This reduces communication overhead and maintains high prediction performance across diverse data distributions. Although the global model reflects data from various clients, the data characteristics of each client may differ. To compensate for this, clients further train additional trees on the global model to perform local optimizations tailored to their data. This improves the overall model's prediction accuracy and adapts to changing data distributions. Our study demonstrates that the FedRFBagging algorithm effectively addresses the communication cost and performance issues associated with random forest models in federated learning environments, suggesting its applicability in such settings.

• Journal of Korean Society of Transportation
• /
• v.20 no.7
• /
• pp.177-183
• /
• 2002

Current state-of-the-art of VMS control is based upon simple knowledge-based inference engine with message set and each message's priority. And R&Ds of the VMS control are focused on the accurate detection and estimation of traffic condition of the subject roadways. However VMS display itself cannot achieve a desirable traffic allocation among alternative routes in the network In this context, VMS display strategy is the most crucial part in the VMS control. VMS itself has several limitations in its nature. It is generally known that VMS causes overreaction and concentration problems, which may be more serious in urban network than highway network because diversion should be more easily made in urban network. A feedback control algorithm is proposed in this paper to address the above-mentioned issues. It is generally true that feedback control approach requires low computational effort and is less sensitive to models inaccuracy and disturbance uncertainties. Major features of the proposed algorithm are as follows: Firstly, a regulator is designed to attain system optimal traffic allocation among alternative routes for each VMS in the network. Secondly, strategic messages should be prepared to realize the desirable traffic allocation, that is, output of the above regulator. VMS display strategy module is designed in this context. To evaluate Probable control benefit and to detect logical errors of the Proposed feedback algorithm, a offline simulation test is performed using real network in Daejon, Korea.

• Journal of Internet Computing and Services
• /
• v.10 no.3
• /
• pp.9-15
• /
• 2009

It takes quite amount of time to study a board game because there are many game characters and different stages are exist for board games. Also, the opponent is not just a single character that means it is not one on one game, but group vs. group. That is why strategy is needed, and therefore applying optimum learning is a must. This paper used reinforcement learning algorithm for board characters to learn, and so they can move intelligently. If there were equal result that both are considered to be best ones during the course of learning stage, Heuristic which utilizes learning of problem area of Jul-Gonu was used to improve the speed of learning. To compare a normal character to an improved one, a board game was created, and then they fought against each other. As a result, improved character's ability was far more improved on learning speed.

• Journal of Korean Society of Transportation
• /
• v.21 no.2
• /
• pp.83-94
• /
• 2003

Many cities, recently, have convertedoptimized fixed-time control to adaptive traffic system in the control of their signalized traffic network. The expected benefit from the adaptive traffic system is its ability to constantly modify signal timing to most effectively accommodate changed traffic conditions. While the potential benefits from this control structure may be significant, few studies have compared the effect of implementing this method of signal control against other alternative signal control strategies, because it is too difficult to evaluate the efficiency of the real-time adaptive system. The objectives of this research are : to develop a microscopic simulator and to compare the effect at isolated intersections, corridors, and networks between the fixed signal timing plan and adaptive traffic signal system. This simulator will have allowed more sophisticated analysis techniques for the study of traffic control. Also, this research using this simulator evaluated a real-time traffic responsive signal system used in Seoul Korea

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.27 no.3
• /
• pp.303-310
• /
• 2009

We processed seven years data of 142 IGS(International GNSS Service) stations were processed, which have been selected with an optimal network algorithm, to realize terrestrial reference system. To verify the result, a comparison with the ITRF2005 was given both in positions and velocities with transformation parameters estimation. The transformation parameters are within 4.3 mm in length, while the RMS(root mean square) difference of positions and velocities are 6.7 mm and 1.3 mm/yr in horizontal and 13.3 mm and 2.4 mm/yr in vertical, respectively, which represent good coincidences with ITRF2005. This research would help developing our own geodetic reference frame and may be applied for the global earth observations such as the global tectonics. A further improved TRF would be expected by applying various data processing strategies and with extension of data in number and observation period.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.27 no.2
• /
• pp.50-57
• /
• 2023

Autonomous driving technologies have been gradually improved for road traffic owing to the development of artificial intelligence. Since the truck platooning is beneficial in terms of the associated transporting expenses, the Connected-Automated Vehicle technology is rapidly evolving. The structural performance is, however, rarely investigated to capture the effect of truck platooning on civil infrastructures.In this study, the dynamic behavior of bridges under truck platooning was investigated, and the amplification factor of responses was estimated considering several parameters associated with the driving conditions. Artificial intelligence techniques were used to estimate the maximum response of the mid span of a bridge as the platooning vehicles passing, and the importance of the parameters was evaluated. The most suitable algorithm was selected by evaluating the consistency of the estimated displacement.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.5
• /
• pp.177-188
• /
• 2018

The scale of graph data has been increased rapidly because of the growth of mobile Internet applications and the proliferation of social network services. This brings upon the imminent necessity of efficient distributed and parallel graph processing approach since the size of these large-scale graphs are easily over a capacity of a single machine. Currently, there are two popular parallel graph processing approaches, vertex-centric graph processing and block centric processing. While a vertex-centric graph processing approach can easily be applied to the parallel processing system, a block-centric graph processing approach is proposed to compensate the drawbacks of the vertex-centric approach. In these systems, the initial quality of graph partition affects to the overall performance significantly. However, it is a very difficult problem to divide the graph into optimal states at the initial phase. Thus, several dynamic load balancing techniques have been studied that suggest the progressive partitioning during the graph processing time. In this paper, we present a load balancing algorithms for the block-centric graph processing approach where most of dynamic load balancing techniques are focused on vertex-centric systems. Our proposed algorithm focus on an improvement of the graph partition quality by dynamically reassigning blocks in runtime, and suggests block split strategy for escaping local optimum solution.

• The Journal of Bigdata
• /
• v.5 no.2
• /
• pp.77-84
• /
• 2020

In this study, we conducted a study on the win-loss predicton analysis of korean professional baseball by artificial intelligence models. Based on the model, we predicted the winner as well as each team's final rank in the league. Additionally, we developed a website for viewers' understanding. In each game's first, third, and fifth inning, we analyze to select the best model that performs the highest accuracy and minimizes errors. Based on the result, we generate the rankings. We used the predicted data started from May 5, the season's opening day, to August 30, 2020 to generate the rankings. In the games which Kia Tigers did not play, however, we used actual games' results in the data. KNN and AdaBoost selected the most optimized machine learning model. As a result, we observe a decreasing trend of the predicted results' ranking error as the season progresses. The deep learning model recorded 89% of the model accuracy. It provides the same result of decreasing ranking error trends of the predicted results that we observe in the machine learning model. We estimate that this study's result applies to future KBO predictions as well as other fields. We expect broadcasting enhancements by posting the predicted winning percentage per inning which is generated by AI algorism. We expect this will bring new interest to the KBO fans. Furthermore, the prediction generated at each inning would provide insights to teams so that they can analyze data and come up with successful strategies.