• Journal of ILASS-Korea
• /
• v.27 no.2
• /
• pp.57-65
• /
• 2022

The purpose of this study is to use machine learning to build a model capable of predicting the flash boiling spray characteristics. In this study, the flash boiling spray was visualized using Shadowgraph visualization technology, and then the spray image was processed with MATLAB to obtain quantitative data of spray characteristics. The experimental conditions were used as input, and the spray characteristics were used as output to train the machine learning model. For the machine learning model, the XGB (extreme gradient boosting) algorithm was used. Finally, the performance of machine learning model was evaluated using R² and RMSE (root mean square error). In order to have enough data to train the machine learning model, this study used 12 injectors with different design parameters, and set various fuel temperatures and ambient pressures, resulting in about 12,000 data. By comparing the performance of the model with different amounts of training data, it was found that the number of training data must reach at least 7,000 before the model can show optimal performance. The model showed different prediction performances for different spray characteristics. Compared with the upstream spray angle and the downstream spray angle, the model had the best prediction performance for the spray tip penetration. In addition, the prediction performance of the model showed a relatively poor trend in the initial stage of injection and the final stage of injection. The model performance is expired to be further enhanced by optimizing the hyper-parameters input into the model.

• Earthquakes and Structures
• /
• v.23 no.1
• /
• pp.35-57
• /
• 2022

This article presents a computationally efficient framework for multi-objective seismic design optimization of steel moment-resisting frame (MRF) structures based on the nonlinear dynamic analysis procedure. This framework employs the uniform damage distribution philosophy to minimize the weight (initial cost) of the structure at different levels of damage. The preliminary framework was recently proposed by the authors based on the single excitation and the nonlinear static (pushover) analysis procedure, in which the effects of record-to-record variability as well as higher-order vibration modes were neglected. The present study investigates the reliability of the previous framework by extending the proposed algorithm using the nonlinear dynamic design procedure (optimization under multiple ground motions). Three benchmark structures, including 4-, 8-, and 12-story steel MRFs, representing the behavior of low-, mid-, and high-rise buildings, are utilized to evaluate the proposed framework. The total weight of the structure and the maximum inter-story drift ratio (IDRmax) resulting from the average response of the structure to a set of seven ground motion records are considered as two conflicting objectives for the optimization problem and are simultaneously minimized. The results of this study indicate that the optimization under several ground motions leads to almost similar outcomes in terms of optimization objectives to those are obtained from optimization under pushover analysis. However, investigation of optimal designs under a suite of 22 earthquake records reveals that the damage distribution in buildings designed by the nonlinear dynamic-based procedure is closer to the uniform distribution (desired target during the optimization process) compared to those designed according to the pushover procedure.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.5 no.1
• /
• pp.43-53
• /
• 1985

This study proposes a reliability based design criteria for the steel bridge (H-beam, plate-girder and composite-beam), which is most common type of steel bridge, and also proposes the theoretical bases of nominal safety factors as well as load and rasistance factors based on the reliability theory. Major 2nd moment reliability analysis and design theories including both Cornell's MFOSM (Mean First Order 2nd Moment) Methods and Lind-Hasofer's AFOSM(Advanced First Order 2nd Moment) Methods are summarized and compared, and it has been found that Lind-Hasofer's approximate and an approximate Log-normal type reliability formula are well suited for the proposed reliability study. A target reliability index (${\beta}_0=3.5$) is selected as an optimal value considering our practice based on the calibration with the safety pravisions of the current steel bridge design code. Galambo's theory is used for the derivation of the algorithm for the evaluation of uncertainties associated with resistences by LRFD Format and SGST Format, whereas the magnitude of the uncertainties associated with load effects are chosen primarily by considering our level of practice. It may be concluded that the proposed LRFD reliability based design provisions for the steel highway bridge give more rational design than the current standard code for steel highway bridge.

• The KIPS Transactions:PartB
• /
• v.10B no.6
• /
• pp.673-680
• /
• 2003

In this paper, we study the enhancement of VQ (Vector Quantization) design for text independent speaker recognition. In a concrete way, we present a non-iterative method which makes a vector quantization codebook and this method performs non-iterative learning so that the computational complexity is epochally reduced The proposed Classified Space VQ (CSVQ) design method for text Independent speaker recognition is generalized from Semi-noniterative VQ design method for text dependent speaker recognition. CSVQ contrasts with the existing desiEn method which uses the iterative learninE algorithm for every traininE speaker. The characteristics of a CSVQ design is as follows. First, the proposed method performs the non-iterative learning by using a Classified Space Codebook. Second, a quantization region of each speaker is equivalent for the quantization region of a Classified Space Codebook. And the quantization point of each speaker is the optimal point for the statistical distribution of each speaker in a quantization region of a Classified Space Codebook. Third, Classified Space Codebook (CSC) is constructed through Sample Vector Formation Method (CSVQ1, 2) and Hyper-Lattice Formation Method (CSVQ 3). In the numerical experiment, we use the 12th met-cepstrum feature vectors of 10 speakers and compare it with the existing method, changing the codebook size from 16 to 128 for each Classified Space Codebook. The recognition rate of the proposed method is 100% for CSVQ1, 2. It is equal to the recognition rate of the existing method. Therefore the proposed CSVQ design method is, reducing computational complexity and maintaining the recognition rate, new alternative proposal and CSVQ with CSC can be applied to a general purpose recognition.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.6
• /
• pp.1252-1260
• /
• 2017

As digital communication technology evolves, the diversity of maritime communication methods has benn increasing due to the emergence of new maritime communication technologies such as digital very high frequency (VHF) communication systems and LTE-M as well as traditional conventional maritime communication systems. At sea, all maritime communication methods may be available, but only some communication methods may be available depending on the location. In this paper, we propose a multi-band network selection (MNS) system that can provide seamless maritime communication service by switching to an optimal communication band among available communication systems, depending on network environment and user requirements. The proposed MNS system in the middleware layer is designed to be able to interface with two types of digital VHF communication systems that satisfy Annex 1 and Annex 4 of ITU-R M. 1842-1, LTE, and high frequency (HF) communication systems. We assign priority to each communication band, and design an optimal communication band determination algorithm based on this priority.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.40 no.1
• /
• pp.24-36
• /
• 2003

The digital mobile communication will be developed till getting multimedia service in anyone, any where, any time. Theses requiring items are going to be come true via IMT-2000 system. Transmitting signal bandwidth of IMT-2000 system is 3 times as large as IS-95 system. That is mean peak to average of signal is higher than IS-95A system. So we have to design it carefully not to effect in adjacent channel. HPA(High Power Amplifier) located in the end point of system is operated in 1-㏈ compression point(Pl㏈), then it generates 3rd and 5th inter modulation signals. Theses signals affect at adjacent channel and RF signal is distorted by compressed signal which is operated near by Pl㏈ point. Then the most important design factor is how we make HPA having high linearity. Feedback, Pre-distorter and Feed-forward methods are presented to solve theses problems. Feed-forward of these methods is having excellent improving capacity, but composed with complex structure. Generally, Linearity and Efficiency in power amplifier operate in the contrary, then it is difficult for us to find optimal operating point. In this paper we applied algorithm which searches optimal point of linear characteristics, which is key in Power Amplifier, using minimum current point of error amplifier in 1st loop. And we made 2nd loop compose with new structure. We confirmed fabricated LPA is operated by having high linearity and minimum current condition with ACPR of -26 ㏈m max. @ 30㎑ BW in 3.515㎒ and ACLR of 48 ㏈c max@${\pm}$㎒ from 1W to 40W.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.9
• /
• pp.304-315
• /
• 2018

Harmony Search (HS) is a recently developed metaheuristic algorithm that is widely known to many researchers. However, due to the increasing complexity of optimization problems, the optimal solution cannot be efficiently found by HS. To overcome this problem, there have been many studies that have improved the performance of HS by modifying the parameter settings and incorporating other metaheuristic algorithms. In this study, Copycat HS (CcHS) is suggested, which improves the parameter setting method and the performance of searching for the optimal solution. To verify the performance of CcHS, the results were compared to those of HS variants with a set of well-known mathematical benchmark problems. The effectiveness of CcHS was proven by finding final solutions that are closer to the global optimum than other algorithms in all problems. To analyze the applicability of CcHS to engineering optimization problems, it was applied to a design problem for Water Distribution Systems (WDS), which is widely applied in previous research. As a result, CcHS proposed the minimum design cost, which was 21.91% cheaper than the cost suggested by simple HS.

• Journal of Intelligence and Information Systems
• /
• v.17 no.4
• /
• pp.241-254
• /
• 2011

Financial time-series forecasting is one of the most important issues because it is essential for the risk management of financial institutions. Therefore, researchers have tried to forecast financial time-series using various data mining techniques such as regression, artificial neural networks, decision trees, k-nearest neighbor etc. Recently, support vector machines (SVMs) are popularly applied to this research area because they have advantages that they don't require huge training data and have low possibility of overfitting. However, a user must determine several design factors by heuristics in order to use SVM. For example, the selection of appropriate kernel function and its parameters and proper feature subset selection are major design factors of SVM. Other than these factors, the proper selection of instance subset may also improve the forecasting performance of SVM by eliminating irrelevant and distorting training instances. Nonetheless, there have been few studies that have applied instance selection to SVM, especially in the domain of stock market prediction. Instance selection tries to choose proper instance subsets from original training data. It may be considered as a method of knowledge refinement and it maintains the instance-base. This study proposes the novel instance selection algorithm for SVMs. The proposed technique in this study uses genetic algorithm (GA) to optimize instance selection process with parameter optimization simultaneously. We call the model as ISVM (SVM with Instance selection) in this study. Experiments on stock market data are implemented using ISVM. In this study, the GA searches for optimal or near-optimal values of kernel parameters and relevant instances for SVMs. This study needs two sets of parameters in chromosomes in GA setting : The codes for kernel parameters and for instance selection. For the controlling parameters of the GA search, the population size is set at 50 organisms and the value of the crossover rate is set at 0.7 while the mutation rate is 0.1. As the stopping condition, 50 generations are permitted. The application data used in this study consists of technical indicators and the direction of change in the daily Korea stock price index (KOSPI). The total number of samples is 2218 trading days. We separate the whole data into three subsets as training, test, hold-out data set. The number of data in each subset is 1056, 581, 581 respectively. This study compares ISVM to several comparative models including logistic regression (logit), backpropagation neural networks (ANN), nearest neighbor (1-NN), conventional SVM (SVM) and SVM with the optimized parameters (PSVM). In especial, PSVM uses optimized kernel parameters by the genetic algorithm. The experimental results show that ISVM outperforms 1-NN by 15.32%, ANN by 6.89%, Logit and SVM by 5.34%, and PSVM by 4.82% for the holdout data. For ISVM, only 556 data from 1056 original training data are used to produce the result. In addition, the two-sample test for proportions is used to examine whether ISVM significantly outperforms other comparative models. The results indicate that ISVM outperforms ANN and 1-NN at the 1% statistical significance level. In addition, ISVM performs better than Logit, SVM and PSVM at the 5% statistical significance level.

• Journal of Korean Society of Transportation
• /
• v.22 no.3 s.74
• /
• pp.145-157
• /
• 2004

The cycle length design model of the Korean traffic responsive signal control systems is devised to vary a cycle length as a response to changes in traffic demand in real time by utilizing parameters specified by a system operator and such field information as degrees of saturation of through phases. Since no explicit guideline is provided to a system operator, the system tends to include ambiguity in terms of the system optimization. In addition, the cycle lengths produced by the existing model have yet been verified if they are comparable to the ones minimizing delay. This paper presents the studies conducted (1) to find shortcomings embedded in the existing model by comparing the cycle lengths produced by the model against the ones minimizing delay and (2) to propose a new direction to design a cycle length minimizing delay and excluding such operator oriented parameters. It was found from the study that the cycle lengths from the existing model fail to minimize delay and promote intersection operational conditions to be unsatisfied when traffic volume is low, due to the feature of the changed target operational volume-to-capacity ratio embedded in the model. The 64 different neural network based cycle length design models were developed based on simulation data surrogating field data. The CORSIM optimal cycle lengths minimizing delay were found through the COST software developed for the study. COST searches for the CORSIM optimal cycle length minimizing delay with a heuristic searching method, a hybrid genetic algorithm. Among 64 models, the best one producing cycle lengths close enough to the optimal was selected through statistical tests. It was found from the verification test that the best model designs a cycle length as similar pattern to the ones minimizing delay. The cycle lengths from the proposed model are comparable to the ones from TRANSYT-7F.

• Composites Research
• /
• v.36 no.1
• /
• pp.53-58
• /
• 2023

The PIC design method is assigning different stacking sequences for each shell element through the preliminary FE analysis. In previous study, machine learning was applied to the PIC design method in order to assign the region efficiently, and the training data is labeled by dividing each region into tension, compression, and shear through the preliminary FE analysis results value. However, since buckling is not considered, when buckling occurs, it can't be divided into appropriate loading type. In the present study, it was proposed PIC-NTL (PIC design using novel technique for analyzing load type) which is method for applying a novel technique for analyzing load type considering buckling to the conventional PIC design. The stress triaxiality for each ply were analyzed for buckling analysis, and the representative loading type was designated through the determined loading type within decision area divided into two regions of the same size in the thickness direction of the elements. The input value of the training data and label consisted in coordination of element and representative loading type of each decision area, respectively. A machine learning model was trained through the training data, and the hyperparameters that affect the performance of the machine learning model were tuned to optimal values through Bayesian algorithm. Among the tuned machine learning models, the SVM model showed the highest performance. Most effective stacking sequence were mapped into PIC tube based on trained SVM model. FE analysis results show the design method proposed in this study has superior external loading resistance and energy absorption compared to previous study.