• Journal of the Korea Society of Computer and Information
• /
• v.21 no.5
• /
• pp.79-89
• /
• 2016

In this paper, we proposed the object classification method using genetic and dynamic random forest consisting of optimal combination of unit tree. The random forest can ensure good generalization performance in combination of large amount of trees by assigning the randomization to the training samples and feature selection, etc. allocated to the decision tree as an ensemble classification model which combines with the unit decision tree based on the bagging. However, the random forest is composed of unit trees randomly, so it can show the excellent classification performance only when the sufficient amounts of trees are combined. There is no quantitative measurement method for the number of trees, and there is no choice but to repeat random tree structure continuously. The proposed algorithm is composed of random forest with a combination of optimal tree while maintaining the generalization performance of random forest. To achieve this, the problem of improving the classification performance was assigned to the optimization problem which found the optimal tree combination. For this end, the genetic algorithm methodology was applied. As a result of experiment, we had found out that the proposed algorithm could improve about 3~5% of classification performance in specific cases like common database and self infrared database compare with the existing random forest. In addition, we had shown that the optimal tree combination was decided at 55~60% level from the maximum trees.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.2
• /
• pp.57-64
• /
• 2021

This study presents a method for realtime fuel consumption prediction using real data collected from OBDII. With the advent of the era of self-driving cars, electronic control units(ECU) are getting more complex, and various studies are being attempted to extract and analyze more accurate data from vehicles. But since ECU is getting more complex, it is getting harder to get the data from ECU. To solve this problem, the firmware was developed for acquiring accurate vehicle data in this study, which extracted 53,580 actual driving data sets from vehicles from January to February 2019. Using these data, the ensemble stacking technique was used to increase the accuracy of the realtime fuel consumption prediction model. In this study, Ridge, Lasso, XGBoost, and LightGBM were used as base models, and Ridge was used for meta model, and the predicted performance was MAE 0.011, RMSE 0.017.

• Bulletin of the Korean Chemical Society
• /
• v.32 no.11
• /
• pp.3909-3913
• /
• 2011

In this paper we have carried out molecular dynamics simulations (MD) for model systems of liquid n-alkane oligomers ($C_{12}{\sim}C_{80}$) at high temperatures (~2300 K) in a canonical ensemble to calculate viscosity ${\eta}$, self-diffusion constants D, and monomeric friction constant ${\zeta}$. We found that the long chains of these n-alkanes at high temperatures show an abnormality in density and in monomeric friction constant. The behavior of both activation energies, $E_{\eta}$ and $E_D$, and the mass and temperature dependence of ${\eta}$, D, and ${\zeta}$ are discussed.

• Bulletin of the Korean Chemical Society
• /
• v.35 no.5
• /
• pp.1469-1478
• /
• 2014

Use of acetonitrile in electrolytes promotes better operation of supercapacitors. Recent efforts show that electrolytes containing acetonitrile can also function in a wide range of operating temperatures. Therefore, this paper addresses the dielectric relaxation processes, structure and dynamic properties of the bulk acetonitrile at various temperatures. Systems of acetonitrile were modeled using canonical ensemble and simulated by employing Molecular Dynamics method. Results show that interactions among the molecules were correlated within a cut-off radius while parallel and anti-parallel arrangements are observed beyond this radius at relatively high and low temperatures respectively. Furthermore, effects of C-C-N and C-H bending modes were greatly appreciated on the power spectral density of time rate change of dipole-dipole correlations whereas frequency shifts were observed on all modes at the lowest temperature under consideration. Linear variations with temperature were depicted for reorientation times and self-diffusion coefficients. Shear viscosity was also computed with a good accuracy within a certain range of the temperature as well.

• Fashion & Textile Research Journal
• /
• v.17 no.4
• /
• pp.635-645
• /
• 2015

This study analyzed the range of motion of upper body in different configurations of firefighters' protective clothing and equipment. The purpose of this study was to understand the influence of firefighters' protective clothing and equipment over upper body motion in order to improve design of firefighters' protective clothing and equipment. 12 firefighters' upper body range of motion was analyzed while performing standing and walking trials in five different garment configurations including turnout ensemble, fire boots and the self-contained breathing apparatus. Analysis of upper body range of motion included spinal joints of L5S1, L4L3, T1C7, and C1Head. During standing trials, garment configurations caused a significant difference in range of motions at joints of L5S1, L4L3, T1C7, and C1Head. Analysis on the mean of range of motions at L5S1 and L4L3, showed that firefighters' waist bent forward significantly to a greater extent while they wore a self-contained breathing apparatus. A significantly increased range of motion was found for T1C7 and C1Head while carrying a self-contained breathing apparatus, which indicated an increase in the extension of the trunk and neck backward to stand upright and look squarely. A significant difference in range of motion was also found for L5S1 and L4L3 during walking trials.

• Smart Structures and Systems
• /
• v.26 no.2
• /
• pp.241-251
• /
• 2020

Due to the undeniable importance of approximating the concrete compressive strength (CSC) in civil engineering, this paper focuses on presenting four novel optimizations of multi-layer perceptron (MLP) neural network, namely artificial bee colony (ABC-MLP), grasshopper optimization algorithm (GOA-MLP), shuffled frog leaping algorithm (SFLA-MLP), and salp swarm algorithm (SSA-MLP) for predicting this crucial parameter. The used dataset consists of 103 rows of information concerning seven influential parameters (cement, slag, water, fly ash, superplasticizer, fine aggregate, and coarse aggregate). In this work, the best-fitted complexity of each ensemble is determined by a population-based sensitivity analysis. The GOA distinguished its self by the least complexity (population size = 50) and emerged as the second time-effective optimizer. Referring to the prediction results, all tested algorithms are able to construct reliable networks. However, the SSA (Correlation = 0.9652 and Error = 1.3939) and GOA (Correlation = 0.9629 and Error = 1.3922) performed more accurately than ABC (Correlation = 0.7060 and Error = 4.0161) and SFLA (Correlation = 0.8890 and Error = 2.5480). Therefore, the SSA-MLP and GOA-MLP can be promising alternatives to laboratorial and traditional CSC evaluative methods.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2011.02a
• /
• pp.38-38
• /
• 2011

Covalently bonded halogen ligands possess unusual charge distributions, attracting both electrophilic and nucleophilic molecular ligands to form halogen bonds. In many biochemical systems, halogen bonds and hydrogen bonds coexist. The interplay between halogen and hydrogen bonds has been actively studied in various three-dimensional bulk molecular co-crystals. It was found that halogen bonds could be complementary to hydrogen bonds due to their similar bond strength and dissimilar directionality. In those ensemble-averaging approaches, however, it was not possible to extract local information such as individual bond configurations and nano-level domain structures, which is a crucial part of supramolecular studies. In this study, we directly visualize the individual molecular configuration of a brominated molecule and the role of halogen bonds on Au(111) using scanning tunneling microscopy. The precise arrangement of observed molecular structures was reproduced by first-principle studies and explained in the context of halogen and hydrogen bonds. We discuss the distances and the strengths of the observed halogen bonds and hydrogen bonds, which are consistent with previous bulk data.

• Journal of Information Processing Systems
• /
• v.13 no.5
• /
• pp.1135-1148
• /
• 2017

Speech recognition is one of the fascinating fields in the area of Computer science. Accuracy of speech recognition system may reduce due to the presence of noise present in speech signal. Therefore noise removal is an essential step in Automatic Speech Recognition (ASR) system and this paper proposes a new technique called combined thresholding for noise removal. Feature extraction is process of converting acoustic signal into most valuable set of parameters. This paper also concentrates on improving Mel Frequency Cepstral Coefficients (MFCC) features by introducing Discrete Wavelet Packet Transform (DWPT) in the place of Discrete Fourier Transformation (DFT) block to provide an efficient signal analysis. The feature vector is varied in size, for choosing the correct length of feature vector Self Organizing Map (SOM) is used. As a single classifier does not provide enough accuracy, so this research proposes an Ensemble Support Vector Machine (ESVM) classifier where the fixed length feature vector from SOM is given as input, termed as ESVM_SOM. The experimental results showed that the proposed methods provide better results than the existing methods.

• Asia pacific journal of information systems
• /
• v.29 no.4
• /
• pp.789-816
• /
• 2019

Text classification is a challenging task, especially when dealing with a huge amount of text data. The performance of a classification model can be varied depending on what type of words contained in the document corpus and what type of features generated for classification. Aside from proposing a new modified version of the existing algorithm or creating a new algorithm, we attempt to modify the use of data. The classifier performance is usually affected by the quality of learning data as the classifier is built based on these training data. We assume that the data from different domains might have different characteristics of noise, which can be utilized in the process of learning the classifier. Therefore, we attempt to enhance the robustness of the classifier by injecting the heterogeneous data artificially into the learning process in order to improve the classification accuracy. Semi-supervised approach was applied for utilizing the heterogeneous data in the process of learning the document classifier. However, the performance of document classifier might be degraded by the unlabeled data. Therefore, we further proposed an algorithm to extract only the documents that contribute to the accuracy improvement of the classifier.

• Journal of KIISE:Software and Applications
• /
• v.31 no.1
• /
• pp.61-70
• /
• 2004

It is difficult to find an appropriate web site because exponentially growing web contains millions of web documents. Personalization of web search can be realized by recommending proper web sites using user profile but more efficient method is needed for estimating preference because user's evaluation on web contents presents many aspects of his characteristics. As user profile has a property of non-linearity, estimation by classifier is needed and combination of classifiers is necessary to anticipate diverse properties. Structure adaptive self-organizing map (SASOM) that is suitable for Pattern classification and visualization is an enhanced model of SOM and might be useful for web mining. Fuzzy integral is a combination method using classifiers' relevance that is defined subjectively. In this paper, estimation of user profile is conducted by using ensemble of SASOM's teamed independently based on fuzzy integral and evaluated by Syskill ＆ Webert UCI benchmark data. Experimental results show that the proposed method performs better than previous naive Bayes classifier as well as voting of SASOM's.