• Journal of Information Processing Systems
• /
• v.20 no.3
• /
• pp.345-359
• /
• 2024

A regression model represents the relationship between explanatory and response variables. In real life, explanatory variables often affect a response variable with a certain time lag, rather than immediately. For example, the marriage rate affects the birth rate with a time lag of 1 to 2 years. Although deep learning models have been successfully used to model various relationships, most of them do not consider the time lags between explanatory and response variables. Therefore, in this paper, we propose an extension of deep learning models, which automatically finds the time lags between explanatory and response variables. The proposed method finds out which of the past values of the explanatory variables minimize the error of the model, and uses the found values to determine the time lag between each explanatory variable and response variables. After determining the time lags between explanatory and response variables, the proposed method trains the deep learning model again by reflecting these time lags. Through various experiments applying the proposed method to a few deep learning models, we confirm that the proposed method can find a more accurate model whose error is reduced by more than 60% compared to the original model.

• Journal of Intelligence and Information Systems
• /
• v.17 no.4
• /
• pp.157-173
• /
• 2011

As the Internet use explodes recently, the malicious attacks and hacking for a system connected to network occur frequently. This means the fatal damage can be caused by these intrusions in the government agency, public office, and company operating various systems. For such reasons, there are growing interests and demand about the intrusion detection systems (IDS)-the security systems for detecting, identifying and responding to unauthorized or abnormal activities appropriately. The intrusion detection models that have been applied in conventional IDS are generally designed by modeling the experts' implicit knowledge on the network intrusions or the hackers' abnormal behaviors. These kinds of intrusion detection models perform well under the normal situations. However, they show poor performance when they meet a new or unknown pattern of the network attacks. For this reason, several recent studies try to adopt various artificial intelligence techniques, which can proactively respond to the unknown threats. Especially, artificial neural networks (ANNs) have popularly been applied in the prior studies because of its superior prediction accuracy. However, ANNs have some intrinsic limitations such as the risk of overfitting, the requirement of the large sample size, and the lack of understanding the prediction process (i.e. black box theory). As a result, the most recent studies on IDS have started to adopt support vector machine (SVM), the classification technique that is more stable and powerful compared to ANNs. SVM is known as a relatively high predictive power and generalization capability. Under this background, this study proposes a novel intelligent intrusion detection model that uses SVM as the classification model in order to improve the predictive ability of IDS. Also, our model is designed to consider the asymmetric error cost by optimizing the classification threshold. Generally, there are two common forms of errors in intrusion detection. The first error type is the False-Positive Error (FPE). In the case of FPE, the wrong judgment on it may result in the unnecessary fixation. The second error type is the False-Negative Error (FNE) that mainly misjudges the malware of the program as normal. Compared to FPE, FNE is more fatal. Thus, when considering total cost of misclassification in IDS, it is more reasonable to assign heavier weights on FNE rather than FPE. Therefore, we designed our proposed intrusion detection model to optimize the classification threshold in order to minimize the total misclassification cost. In this case, conventional SVM cannot be applied because it is designed to generate discrete output (i.e. a class). To resolve this problem, we used the revised SVM technique proposed by Platt(2000), which is able to generate the probability estimate. To validate the practical applicability of our model, we applied it to the real-world dataset for network intrusion detection. The experimental dataset was collected from the IDS sensor of an official institution in Korea from January to June 2010. We collected 15,000 log data in total, and selected 1,000 samples from them by using random sampling method. In addition, the SVM model was compared with the logistic regression (LOGIT), decision trees (DT), and ANN to confirm the superiority of the proposed model. LOGIT and DT was experimented using PASW Statistics v18.0, and ANN was experimented using Neuroshell 4.0. For SVM, LIBSVM v2.90-a freeware for training SVM classifier-was used. Empirical results showed that our proposed model based on SVM outperformed all the other comparative models in detecting network intrusions from the accuracy perspective. They also showed that our model reduced the total misclassification cost compared to the ANN-based intrusion detection model. As a result, it is expected that the intrusion detection model proposed in this paper would not only enhance the performance of IDS, but also lead to better management of FNE.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.62 no.4
• /
• pp.554-561
• /
• 2013

In this paper, we introduce a modeling and a process simulator developed with the aid of pRBFNNs for activated sludge process in the sewage treatment system. Activated sludge process(ASP) of sewage treatment system facilities is a process that handles biological treatment reaction and is a very complex system with non-linear characteristics. In this paper, we carry out modeling by using essential ASP factors such as water effluent quality, the manipulated value of various pumps, and water inflow quality, and so on. Intelligent algorithms used for constructing process simulator are developed by considering multi-output polynomial radial basis function Neural Networks(pRBFNNs) as well as Fuzzy C-Means clustering and Particle Swarm Optimization. Here, the apexes of the antecedent gaussian functions of fuzzy rules are decided by C-means clustering algorithm and the apexes of the consequent part of fuzzy rules are learned by using back-propagation based on gradient decent method. Also, the parameters related to the fuzzy model are optimized by means of particle swarm optimization. The coefficients of the consequent polynomial of fuzzy rules and performance index are considered by the Least Square Estimation and Mean Squared Error. The descriptions of developed process simulator architecture and ensuing operation method are handled.

• Transactions on Electrical and Electronic Materials
• /
• v.17 no.6
• /
• pp.341-350
• /
• 2016

The current study is dedicated to design a novel coordinated controller to effectively increase power system rotor angle stability. In doing so, the coordinated design of an AVR (automatic voltage regulator), PSS2B, and TCSC (thyristor controlled series capacitor)-based POD (power oscillation damping) controller is proposed. Although the recently employed coordination between a CPSS (conventional power system stabilizer) and a TCSC-based POD controller has been shown to improve power system damping characteristics, neglecting the negative impact of existing high-gain AVR on the damping torque by considering its parameters as given values, may reduce the effectiveness of a CPSS-POD controller. Thus, using a technologically viable stabilizer such as PSS2B rather than the CPSS in a coordinated scheme with an AVR and POD controller can constitute a well-established design with a structure that as a high potential to significantly improve the rotor angle stability. The design procedure is formulated as an optimization problem in which the ITSE (integral of time multiplied squared error) performance index as an objective function is minimized by employing an IPSO (improved particle swarm optimization) algorithm to tune adjustable parameters. The robustness of the coordinated designs is guaranteed by concurrently considering some operating conditions in the optimization process. To evaluate the performance of the proposed controllers, eigenvalue analysis and time domain simulations were performed for different operating points and perturbations simulated on 2A4M (two-area four-machine) power systems in MATLAB/Simulink. The results reveal that surpassing improvement in damping of oscillations is achieved in comparison with the CPSS-TCSC coordination.

• Journal of Navigation and Port Research
• /
• v.40 no.5
• /
• pp.241-247
• /
• 2016

The tracking filter plays a key role in the accurate estimation and prediction of maneuvering a vessel's position and velocity when attempting to enhance safety by avoiding collision. Therefore, in order to achieve accurate estimation and prediction, many oceangoing vessels are equipped with the Automatic Radar Plotting Aid (ARPA) system. However, the accuracy of prediction depends on the tracking filter's ability to reduce noise and maintain a stable transient response. The purpose of this paper is to derive the optimal values of the gain parameters used in tracking a High Dynamic Warship. The algorithm employs a ${\alpha}-{\beta}-{\gamma}$ filter to provide accurate estimates and updates of the state variables, that is, positions, velocity and acceleration of the high dynamic warship based on previously observed values. In this study, the filtering coefficients ${\alpha}$, ${\beta}$ and ${\gamma}$ are determined from set values of the damping parameter, ${\xi}$. Optimization of the damping parameter, ${\xi}$, is achieved experimentally by plotting the residual error against different values of the damping parameter to determine the least value of the damping parameter that results in the optimum smoothing coefficients leading to a reduction in the noise corruption effect. Further investigation of the performance of the filter indicates that optimal smoothing coefficients depend on the initial and average velocity of the target.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.33 no.6
• /
• pp.403-410
• /
• 2009

This paper proposes a new approach to find the optimum ratios between sizes of the heat exchangers of the heat recovery steam generator (HRSG) system with limited size to maximize the efficiency of the steam turbine (bottom) cycle of combined cycle power plants (CCPP), but without performing the bottom cycle analysis. This could be achieved by minimizing the unavailable exergy (the sum of the destroyed and the lost exergies) resulted from the heat transfer process of the HRSG system. The present approach is relatively simple and straightforward because the process of the trial-and-error method, typical in performing the bottom cycle analysis for the system optimization, could be avoided. To demonstrate the usefulness of the present method, a single-stage HRSG system was chosen and the optimum evaporation temperature was obtained corresponding to the condition of the maximum useful work. The results show that the optimum evaporation temperature based on the present exergy analysis appears similar to that based on the bottom cycle analysis. Also shown is the dependency of size (NTU) ratios between the heat exchangers on the inlet gas temperature, which is another important factor in determining the optimum condition once overall size of the heat recovery steam generator is given. The present approach turned out to be a useful tool for optimization of the singlestage HRSG systems and can easily be extended to multi-stage systems.

• Journal of the Korean Society for Precision Engineering
• /
• v.21 no.4
• /
• pp.39-47
• /
• 2004

In mold machining, there are many concave machining regions where chatter and tool deflection occur since MRR(material removal rate) increases as curvature increases even though cutting speed and depth of cut are constant. Boolean operation between stock and tool model is widely used to compute MRR in NC milling simulation. In finish cutting, the side step is reduced to about 0.3mm and tool path length is sometimes over loom, so Boolean operation takes long computation time and includes much error if the resolution of stock and tool model is larger than the side step. In this paper, curvature of CL (cutter location) surface and side step of tool path is used to compute the feedrate for constant MRR machining. The data structure of CL surface is Z-map generated from NC tool path. The algorithm to get local curvature from discrete data was developed and applied to compute local curvature of CL surface. The side step of tool path was computed by point density map which includes cutter location point density at each grid element. The feedrate computed from curvature and side step is inserted to new tool path to regulate MRR. The resultants were applied to feedrate optimization system which generates new tool path with feedrate from NC codes for finish cutting. The system was applied to the machining of speaker and cellular phone mold. The finishing time was reduced to 12.6%, tool wear was reduced from 2mm to 1.1mm and chatter marks and over cut on corner were reduced, compared to the machining by constant feedrate. The machining time was shorter to 17% and surface quality and tool was also better than the conventional federate regulation using curvature of the tool path.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.1
• /
• pp.19-24
• /
• 2009

Structural Dynamics Modification (SDM) is a very effective technique to improve structure's dynamic characteristics by adding or removing auxiliary structures, changing material properties and shape of structure. Among those of SDM technique, the method to change shape of structure has been mostly relied on engineer's experience and trial-and-error process which are very time consuming. In order to develop a systematic method to change structure shape, surface grooving technique is studied and successfully applied to HDD cover model. To verify Surface Grooving Technique, fully embossed HDD cover model was optimized. And comparing with previous optimization result, the effectiveness of this surface grooving technique was checked. The shape of groove and 1 st natural frequency were converged to the same result of previous optimization.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.7
• /
• pp.562-572
• /
• 2003

A matched-target model inversion method was developed for a passive sonar to estimate the position of moving targets. Based on the well known matched-field processing in underwater acoustics, the method finds target position by matching the measured target directions and frequencies with the corresponding values of the proposed target model. For the efficient and accurate estimations, the parameter searching was accomplished using a hybrid optimizing method, which first starts with a global optimization such as generic algorithm or simulated annealing then applies a local optimization of a simple down hill algorithm. The suggested method was testified using simulations for three different moving scenarios. The simulation results showed that the method is robust in convergence, even under the situation of over 5 times standard deviation of Gaussian distribution of measured error, and is practical in calculation time as well.

• Nuclear Engineering and Technology
• /
• v.52 no.4
• /
• pp.846-855
• /
• 2020

A loose part monitoring system is used to detect unexpected loose parts in a reactor coolant system in a nuclear power plant. It is still necessary to develop a new methodology for the localization and mass estimation of loose parts owing to the high estimation error of conventional methods. In addition, model-based diagnostics recently emphasized the importance of a model describing the behavior of a mechanical system or component. The purpose of this study is to propose a new localization and mass-estimation method based on finite element analysis (FEA) and optimization technique. First, an FEA model to simulate the propagation behavior of the bending wave generated by a metal sphere impact is validated by performing an impact test and a corresponding FEA and optimization for a downsized steam-generator structure. Second, a novel methodology based on FEA and optimization technique was proposed to estimate the impact location and mass of a loose part at the same time. The usefulness of the methodology was then validated through a series of FEAs and some blind tests. A new feature vector, the cross-correlation function, was also proposed to predict the impact location and mass of a loose part, and its usefulness was then validated. It is expected that the proposed methodology can be utilized in model-based diagnostics for the estimation of impact parameters such as the mass, velocity, and impact location of a loose part. In addition, the FEA-based model can be used to optimize the sensor position to improve the collected data quality in the site of nuclear power plants.