• Journal of Korean Society for Quality Management
• /
• v.48 no.1
• /
• pp.171-186
• /
• 2020

Purpose: The purpose of this study is conducting of predictive models that considered multicollinearity of independent variables in order to carry out more efficient and reliable predictions about differential pressure in seawater reverse osmosis. Methods: The main variables of each RO system are extracted through factor analysis. Common variables are derived through comparison of RO system # 1 and RO system # 2. In order to carry out the prediction modeling about the differential pressure, which is the target variable, we constructed the prediction model reflecting the regression analysis, the artificial neural network, and the support vector machine in R package, and figured out the superiority of the model by comparing RMSE. Results: The number of factors extracted from factor analysis of RO system #1 and RO system #2 is same. And the value of variability(% Var) increased as step proceeds according to the analysis procedure. As a result of deriving the average RMSE of the models, the overall prediction of the SVM was superior to the other models. Conclusion: This study is meaningful in that it has been conducting a demonstration study of considering the multicollinearity of independent variables. Before establishing a predictive model for a target variable, it would be more accurate predictive model if the relevant variables are derived and reflected.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.3 no.1
• /
• pp.185-196
• /
• 1999

In this dissertation, a new off-line recognition system is proposed using a subgraph pattern, neural network. After thinning is applied to input characters, balance having a noise elimination function on location is performed. Then as the first step for recognition procedure, circular elements are extracted and recognized. From the subblock HT, space feature points such as endpoint, flex point, bridge point are extracted and a subgraph pattern is formed observing the relations among them. A region where vowel can exist is allocated and a candidate point of the vowel is extracted. Then, using the subgraph pattern dictionary, a vowel is recognized. A same method is applied to extract horizontal vowels and the vowel is recognized through a simple structural analysis. For verification of recognition subgraph in this paper, experiments are done with the most frequently used Myngjo font, Gothic font for printed characters and handwritten characters. In case of Gothic font, character recognition rate was 98.9%. For Myngjo font characters, the recognition rate was 98.2%. For handwritten characters, the recognition rate was 92.5%. The total recognition rate was 94.8% with mixed handwriting and printing characters for multi-font recognition.

• Journal of the Korean Geotechnical Society
• /
• v.35 no.9
• /
• pp.37-45
• /
• 2019

Quick identification of the condition of tunnel face and optimized determination of support patterns during tunnel excavation in underground construction projects help engineers prevent tunnel collapse and safely excavate tunnels. This study investigates a CNN technique for quick determination of rock quality classification depending on the condition of tunnel face, and presents the procedure for rock quality classification using a deep learning technique and the improved method for accurate prediction. The VGG16 model developed by tens of thousands prestudied images was used for deep learning, and 1,469 tunnel face images were used to classify the five types of rock quality condition. In this study, the prediction accuracy using this technique was up to 83.9%. It is expected that this technique can be used for an error-minimizing rock quality classification system not depending on experienced professionals in rock quality rating.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.6
• /
• pp.2168-2187
• /
• 2021

The smart grid replaces the traditional power structure with information inventiveness that contributes to a new physical structure. In such a field, malicious information injection can potentially lead to extreme results. Incorrect, FDI attacks will never be identified by typical residual techniques for false data identification. Most of the work on the detection of FDI attacks is based on the linearized power system model DC and does not detect attacks from the AC model. Also, the overwhelming majority of current FDIA recognition approaches focus on FDIA, whilst significant injection location data cannot be achieved. Building on the continuous developments in deep learning, we propose a Deep Learning based Locational Detection technique to continuously recognize the specific areas of FDIA. In the development area solver gap happiness is a False Data Detector (FDD) that incorporates a Convolutional Neural Network (CNN). The FDD is established enough to catch the fake information. As a multi-label classifier, the following CNN is utilized to evaluate the irregularity and cooccurrence dependency of power flow calculations due to the possible attacks. There are no earlier statistical assumptions in the architecture proposed, as they are "model-free." It is also "cost-accommodating" since it does not alter the current FDD framework and it is only several microseconds on a household computer during the identification procedure. We have shown that ANN-MLP, SVM-RBF, and CNN can conduct locational detection under different noise and attack circumstances through broad experience in IEEE 14, 30, 57, and 118 bus systems. Moreover, the multi-name classification method used successfully improves the precision of the present identification.

• Advances in Computational Design
• /
• v.7 no.2
• /
• pp.113-128
• /
• 2022

Water consumption is strongly affected by numerous factors, such as population, climatic, geographic, and socio-economic factors. Therefore, the implementation of a reliable predictive model of water consumption pattern is challenging task. This study investigates the performance of predictive models based on multi-layer perceptron (MLP), multiple linear regression (MLR), and support vector regression (SVR). To understand the significant factors affecting water consumption, the stepwise regression (SW) procedure is used in MLR to obtain suitable variables. Then, this study also implements three predictive models based on these significant variables (e.g., SWMLR, SWMLP, and SWSVR). Annual data of water consumption in Thailand during 2006 - 2015 were compiled and categorized by provinces and distributors. By comparing the predictive performance of models with all variables, the results demonstrate that the MLP models outperformed the MLR and SVR models. As compared to the models with selected variables, the predictive capability of SWMLP was superior to SWMLR and SWSVR. Therefore, the SWMLP still provided satisfactory results with the minimum number of explanatory variables which in turn reduced the computation time and other resources required while performing the predictive task. It can be concluded that the MLP exhibited the best result and can be utilized as a reliable water demand predictive model for both of all variables and selected variables cases. These findings support important implications and serve as a feasible water consumption predictive model and can be used for water resources management to produce sufficient tap water to meet the demand in each province of Thailand.

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.12
• /
• pp.1150-1158
• /
• 2010

In this study, the Polynomial-based Radial Basis Function Neural Networks is proposed as one of the recognition part of overall face recognition system that consists of two parts such as the preprocessing part and recognition part. The design methodology and procedure of the proposed pRBFNNs are presented to obtain the solution to high-dimensional pattern recognition problem. First, in preprocessing part, we use a CCD camera to obtain a picture frame in real-time. By using histogram equalization method, we can partially enhance the distorted image influenced by natural as well as artificial illumination. We use an AdaBoost algorithm proposed by Viola and Jones, which is exploited for the detection of facial image area between face and non-facial image area. As the feature extraction algorithm, PCA method is used. In this study, the PCA method, which is a feature extraction algorithm, is used to carry out the dimension reduction of facial image area formed by high-dimensional information. Secondly, we use pRBFNNs to identify the ID by recognizing unique pattern of each person. The proposed pRBFNNs architecture consists of three functional modules such as the condition part, the conclusion part, and the inference part as fuzzy rules formed in 'If-then' format. In the condition part of fuzzy rules, input space is partitioned with Fuzzy C-Means clustering. In the conclusion part of rules, the connection weight of pRBFNNs is represented as three kinds of polynomials such as constant, linear, and quadratic. Coefficients of connection weight identified with back-propagation using gradient descent method. The output of pRBFNNs model is obtained by fuzzy inference method in the inference part of fuzzy rules. The essential design parameters (including learning rate, momentum coefficient and fuzzification coefficient) of the networks are optimized by means of the Particle Swarm Optimization. The proposed pRBFNNs are applied to real-time face recognition system and then demonstrated from the viewpoint of output performance and recognition rate.

• Analytical Science and Technology
• /
• v.24 no.6
• /
• pp.544-555
• /
• 2011

The acute toxicity in the rainbow trout (Oncorhynchus mykiss) was analyzed and predicted using quantitative structure-activity relationships (QSAR). The aquatic toxicity, 96h $LC_{50}$ (median lethal concentration) of 275 organic pesticides, was obtained from EU-funded project DEMETRA. Prediction models were derived from 558 2D molecular descriptors, calculated in PreADMET. The linear (multiple linear regression) and nonlinear (support vector machine and artificial neural network) learning methods were optimized by taking into account the statistical parameters between the experimental and predicted p$LC_{50}$. After preprocessing, population based forward selection were used to select the best subsets of descriptors in the learning methods including 5-fold cross-validation procedure. The support vector machine model was used as the best model ($R^2_{CV}$=0.677, RMSECV=0.887, MSECV=0.674) and also correctly classified 87% for the training set according to EU regulation criteria. The MLR model could describe the structural characteristics of toxic chemicals and interaction with lipid membrane of fish. All the developed models were validated by 5 fold cross-validation and Y-scrambling test.

• Proceedings of the Korean Society of Near Infrared Spectroscopy Conference
• /
• 2001.06a
• /
• pp.1141-1141
• /
• 2001

The aim of the study was to evaluate the performance of 3 calibration methods, modified partial least squares (MPLS), local PLS (LOCAL) and artificial neural network (ANN) on the prediction of chemical composition of forages, using a large NIR database. The study used forage samples (n=25,977) from Australia, Europe (Belgium, Germany, Italy and Sweden) and North America (Canada and U.S.A) with information relative to moisture, crude protein and neutral detergent fibre content. The spectra of the samples were collected with 10 different Foss NIR Systems instruments, which were either standardized or not standardized to one master instrument. The spectra were trimmed to a wavelength range between 1100 and 2498 nm. Two data sets, one standardized (IVAL) and the other not standardized (SVAL) were used as independent validation sets, but 10% of both sets were omitted and kept for later expansion of the calibration database. The remaining samples were combined into one database (n=21,696), which was split into 75% calibration (CALBASE) and 25% validation (VALBASE). The chemical components in the 3 validation data sets were predicted with each model derived from CALBASE using the calibration database before and after it was expanded with 10% of the samples from IVAL and SVAL data sets. Calibration performance was evaluated using standard error of prediction corrected for bias (SEP(C)), bias, slope and R2. None of the models appeared to be consistently better across all validation sets. VALBASE was predicted well by all models, with smaller SEP(C) and bias values than for IVAL and SVAL. This was not surprising as VALBASE was selected from the calibration database and it had a sample population similar to CALBASE, whereas IVAL and SVAL were completely independent validation sets. In most cases, Local and ANN models, but not modified PLS, showed considerable improvement in the prediction of IVAL and SVAL after the calibration database had been expanded with the 10% samples of IVAL and SVAL reserved for calibration expansion. The effects of sample processing, instrument standardization and differences in reference procedure were partially confounded in the validation sets, so it was not possible to determine which factors were most important. Further work on the development of large databases must address the problems of standardization of instruments, harmonization and standardization of laboratory procedures and even more importantly, the definition of the database population.

• 한국지구물리탐사학회:학술대회논문집
• /
• 2009.10a
• /
• pp.147-154
• /
• 2009

Physical properties of rocks, such as velocity, are strongly dependant on detailed pore structures, and recently, pore micro-structures by X-ray tomography techniques have been used to simulate and understand the physical properties. However, the smoothing effect during the tomographic reconstruction procedure often causes an artifact - overestimating the contact areas between grains. The pore nodes near a grain contact are affected by neighboring grain nodes, and are classified into grain nodes. By this artifact, the pore structure has higher contact areas between grains and thus higher velocity estimation than the true one. To reduce this artifact, we tried two image processing techniques - sharpening filter and neural network classification. Both methods gave noticeable improvement on contact areas between grains visually; however, the estimated velocities showed only incremental improvement. We then tried to change the resolutions of tomogram and quantify its impact on velocity estimation. The estimated velocity from the tomogram with higher spatial resolution was improved significantly, and with around 2 micron spatial resolution, the calculated velocity was very close to the lab measurement. In conclusion, the resolution of pore micro-structure is the most important parameter for accurate estimation of velocity using pore-scale simulation techniques. Also the estimation can be incrementally improved if combined with image processing techniques during the pore-grain classification.

• Journal of KIISE
• /
• v.43 no.10
• /
• pp.1085-1093
• /
• 2016

Community-based Question Answering system is a system which provides answers for each question from the documents uploaded on web communities. In order to enhance the capacity of question analysis, former methods have developed specific rules suitable for a target region or have applied machine learning to partial processes. However, these methods incur an excessive cost for expanding fields or lead to cases in which system is overfitted for a specific field. This paper proposes a multiple machine learning method which automates the overall process by adapting appropriate machine learning in each procedure for efficient processing of community-based Question Answering system. This system can be divided into question analysis part and answer selection part. The question analysis part consists of the question focus extractor, which analyzes the focused phrases in questions and uses conditional random fields, and the question type classifier, which classifies topics of questions and uses support vector machine. In the answer selection part, the we trains weights that are used by the similarity estimation models through an artificial neural network. Also these are a number of cases in which the results of morphological analysis are not reliable for the data uploaded on web communities. Therefore, we suggest a method that minimizes the impact of morphological analysis by using character features in the stage of question analysis. The proposed system outperforms the former system by showing a Mean Average Precision criteria of 0.765 and R-Precision criteria of 0.872.