• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.49 no.1
• /
• pp.16-22
• /
• 2012

In this paper, we proposed a method of baseline correction for analysis of Raman spectra of platelets from Alzheimer's disease (AD) transgenic mice. Measured Raman spectra include the meaningful information and unnecessary noise which is composed of baseline and additive noise. The Raman spectrum is divided into the local region including several peaks and the spectrum of the region is modeled by curve fitting using Gaussian model. The additive noise is clearly removed from the process of replacing the original spectrum with the fitted model. The baseline correction after interpolating the local minima of the fitted model with linear, piecewise cubic Hermite and cubic spline algorithm. The baseline corrected models extract the feature with principal component analysis (PCA). The classification result of support vector machine (SVM) and maximum $a$ posteriori probability (MAP) using linear interpolation method showed the good performance about overall number of principal components, especially SVM gave the best performance which is about 97.3% true classification average rate in case of piecewise cubic Hermite algorithm and 5 principal components. In addition, it confirmed that the proposed baseline correction method compared with the previous research result could be effectively applied in the analysis of the Raman spectra of platelet.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.9
• /
• pp.817-821
• /
• 2001

In this paper, a new learning methodology for kernel methods that results in a sparse representation of kernel space from the training patterns for classification problems is suggested. Among the traditional algorithms of linear discriminant function, this paper shows that the relaxation procedure can obtain the maximum margin separating hyperplane of linearly separable pattern classification problem as SVM(Support Vector Machine) classifier does. The original relaxation method gives only the necessary condition of SV patterns. We suggest the sufficient condition to identify the SV patterns in the learning epoches. For sequential learning of kernel methods, extended SVM and kernel discriminant function are defined. Systematic derivation of learning algorithm is introduced. Experiment results show the new methods have the higher or equivalent performance compared to the conventional approach.

• Journal of KIISE:Software and Applications
• /
• v.30 no.3_4
• /
• pp.339-346
• /
• 2003

This paper proposes a multiple classifier system having massive micro classifiers. The micro classifiers are trained by using a local set of training patterns. The k nearest neighboring training patterns of one training pattern comprise the local region for training a micro classifier. Each training pattern is incorporated with one or more micro classifiers. Two types of micro classifiers are adapted in this paper. SVM with linear kernel and SVM with RBF kernel. Classification is done by selecting the best micro classifier among the micro classifiers in vicinity of incoming test pattern. To measure the goodness of each micro classifier, the weighted sum of correctly classified training patterns in vicinity of the test pattern is used. Experiments have been done on Elena database. Results show that the proposed method gives better classification accuracy than any conventional classifiers like SVM, k-NN and the conventional classifier combination/selection scheme.

• The Korean Journal of Applied Statistics
• /
• v.31 no.5
• /
• pp.539-554
• /
• 2018

Effective interaction between user and device is considered an important ability of IoT devices. For some applications, it is necessary to recognize human facial expressions in real time and make accurate judgments in order to respond to situations correctly. Therefore, many researches on facial image analysis have been preceded in order to construct a more accurate and faster recognition system. In this study, we constructed an automatic recognition system for facial expressions through two steps - a facial recognition step and a classification step. We compared various models with different sets of data with pixel information, landmark coordinates, Euclidean distances among landmark points, and arctangent angles. We found a fast and efficient prediction model with only 30 principal components of face landmark information. We applied several prediction models, that included linear discriminant analysis (LDA), random forests, support vector machine (SVM), and bagging; consequently, an SVM model gives the best result. The LDA model gives the second best prediction accuracy but it can fit and predict data faster than SVM and other methods. Finally, we compared our method to Microsoft Azure Emotion API and Convolution Neural Network (CNN). Our method gives a very competitive result.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.13 no.6
• /
• pp.1333-1342
• /
• 2018

Until now, Electroencephalography(: EEG) has been the most important and convenient method for the diagnosis and treatment of epilepsy. However, it is difficult to identify the wave characteristics of an epileptic EEG signals because it is very weak, non-stationary and has strong background noise. In this paper, we analyse the effect of dimensionality reduction methods on Epileptic EEG feature selection and classification. Three dimensionality reduction methods: Pincipal Component Analysis(: PCA), Kernel Principal Component Analysis(: KPCA) and Linear Discriminant Analysis(: LDA） were investigated. The performance of each method was evaluated by using Support Vector Machine SVM, Logistic Regression(: LR), K-Nearestneighbor(: K-NN), Decision Tree(: DR) and Random Forest(: RF). From the experimental result, PCA recorded 75% of highest accuracy in SVM, LR and K-NN. KPCA recorded 85% of best performance in SVM and K-KNN while LDA achieved 100% accuracy in K-NN. Thus, LDA dimensionality reduction is found to provide the best classification result for epileptic EEG signal.

• Structural Engineering and Mechanics
• /
• v.83 no.3
• /
• pp.293-304
• /
• 2022

In this work, a novel reliability approach for combined high and low cycle fatigue (CCF) estimation is developed by combining active learning strategy with least squares support vector machines (LS-SVM) (named as ALS-SVM) surrogate model to address the multi-resources uncertainties, including working loads, material properties and model itself. Initially, a new active learner function combining LS-SVM approach with Monte Carlo simulation (MCS) is presented to improve computational efficiency with fewer calls to the performance function. To consider the uncertainty of surrogate model at candidate sample points, the learning function employs k-fold cross validation method and introduces the predicted variance to sequentially select sampling. Following that, low cycle fatigue (LCF) loads and high cycle fatigue (HCF) loads are firstly estimated based on the training samples extracted from finite element (FE) simulations, and their simulated responses together with the sample points of model parameters in Coffin-Manson formula are selected as the MC samples to establish ALS-SVM model. In this analysis, the MC samples are substituted to predict the CCF reliability of turbine blades by using the built ALS-SVM model. Through the comparison of the two approaches, it is indicated that the reliability model by linear cumulative damage rule provides a non-conservative result compared with that by the proposed one. In addition, the results demonstrate that ALS-SVM is an effective analysis method holding high computational efficiency with small training samples to gain accurate fatigue reliability.

• IEIE Transactions on Smart Processing and Computing
• /
• v.6 no.1
• /
• pp.10-17
• /
• 2017

We propose classification algorithms for human and dog movement. The proposed algorithms use micro-Doppler signals obtained from humans and dogs moving in four different directions. A two-stage classifier based on a support vector machine (SVM) is proposed, which uses a radial-based function (RBF) kernel and $16^{th}$-order linear predictive code (LPC) coefficients as feature vectors. With the proposed algorithms, we obtain the best classification results when a first-level SVM classifies the type of movement, and then, a second-level SVM classifies the moving object. We obtain the correct classification probability 95.54% of the time, on average. Next, to deal with the difficult classification problem of human and dog running, we propose a two-layer convolutional neural network (CNN). The proposed CNN is composed of six ($6{\times}6$) convolution filters at the first and second layers, with ($5{\times}5$) max pooling for the first layer and ($2{\times}2$) max pooling for the second layer. The proposed CNN-based classifier adopts an auto regressive spectrogram as the feature image obtained from the $16^{th}$-order LPC vectors for a specific time duration. The proposed CNN exhibits 100% classification accuracy and outperforms the SVM-based classifier. These results show that the proposed classifiers can be used for human and dog classification systems and also for classification problems using data obtained from an ultra-wideband (UWB) sensor.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.6
• /
• pp.852-859
• /
• 2009

Normally, to extract the defect in TFT-LCD inspection system, the image is obtained by using line scan camera or area scan camera which is achieved by CCD or CMOS sensor. Because of the limited dynamic range of CCD or CMOS sensor as well as the effect of the illumination, these images are frequently degraded and the important features are hard to decern by a human viewer. In order to overcome this problem, the feature vectors in the image are obtained by using the average intensity difference between defect and background based on the weber's law and the standard deviation of the background region. The defect detection method uses non-linear SVM (Supports Vector Machine) method using the extracted feature vectors. The experiment results show that the proposed method yields better performance of defect classification methods over conveniently method.

• Korean Journal of Remote Sensing
• /
• v.35 no.6_3
• /
• pp.1285-1298
• /
• 2019

Drought is one of the factors that can cause wildfires. Drought is related to not only the occurrence of wildfires but also their frequency, extent and severity. In South Korea, most wildfires occur in dry seasons (i.e. spring and autumn), which are highly correlated to drought events. In this study, we examined the relationship between wildfire occurrence and drought factors, and developed satellite-based new drought indices for assessing wildfire risk over South Korea. Drought factors used in this study were high-resolution downscaled soil moisture, Normalized Different Water Index (NDWI), Normalized Multi-band Drought Index (NMDI), Normalized Different Drought Index (NDDI), Temperature Condition Index (TCI), Precipitation Condition Index (PCI) and Vegetation Condition Index (VCI). Drought indices were then proposed through weighted linear combination and one-class support vector machine (One-class SVM) using the drought factors. We found that most drought factors, in particular, soil moisture, NDWI, and PCI were linked well to wildfire occurrence. The validation results using wildfire cases in 2018 showed that all five linear combinations produced consistently good performance (> 88% in occurrence match). In particular, the combination of soil moisture and NDWI, and the combination of soil moisture, NDWI, and precipitation were found to be appropriate for representing wildfire risk.

• The Journal of the Korea Contents Association
• /
• v.10 no.8
• /
• pp.11-17
• /
• 2010

In this paper, we propose HMM-based upper-body gesture. First, to recognize gesture of space, division about pose that is composing gesture once should be put priority. In order to divide poses which using interface, we used two IR cameras established on front side and side. So we can divide and acquire in front side pose and side pose about one pose in each IR camera. We divided the acquired IR pose image using SVM's non-linear RBF kernel function. If we use RBF kernel, we can divide misclassification between non-linear classification poses. Like this, sequences of divided poses is recognized by gesture using HMM's state transition matrix. The recognized gesture can apply to existent application to do mapping to OS Value.