• Journal of the Korean Data and Information Science Society
• /
• v.27 no.2
• /
• pp.549-557
• /
• 2016

In this paper we propose multiclassification method for large data sets by ensembling least squares support vector machines (LS-SVM) with principal components instead of raw input vector. We use the revised one-vs-all method for multiclassification, which is one of voting scheme based on combining several binary classifications. The revised one-vs-all method is performed by using the hat matrix of LS-SVM ensemble, which is obtained by ensembling LS-SVMs trained using each random sample from the whole large training data. The leave-one-out cross validation (CV) function is used for the optimal values of hyper-parameters which affect the performance of multiclass LS-SVM ensemble. We present the generalized cross validation function to reduce computational burden of leave-one-out CV functions. Experimental results from real data sets are then obtained to illustrate the performance of the proposed multiclass LS-SVM ensemble.

• Journal of KIISE:Software and Applications
• /
• v.33 no.10
• /
• pp.886-895
• /
• 2006

Fingerprint classification reduces the number of matches required in automated fingerprint identification systems by categorizing fingerprints into a predefined class. Support vector machines (SVMs), widely used in pattern classification, have produced a high accuracy rate when performing fingerprint classification. In order to effectively apply SVMs to multi-class fingerprint classification systems, we propose a novel method in which SVMs are generated with the one-vs-all (OVA) scheme and dynamically ordered with $na{\ddot{i}}ve$ Bayes classifiers. More specifically, it uses representative fingerprint features such as the FingerCode, singularities and pseudo ridges to train the OVA SVMs and $na{\ddot{i}}ve$ Bayes classifiers. The proposed method has been validated on the NIST-4 database and produced a classification accuracy of 90.8% for 5-class classification. Especially, it has effectively managed tie problems usually occurred in applying OVA SVMs to multi-class classification.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.5
• /
• pp.716-721
• /
• 2010

In this work we address the use of support vector machine (SVM) in the multi-class gas classification system. The objective is to classify single gases and their mixture with a semiconductor-type electronic nose. The SVM has some typical multi-class classification models; One vs. One (OVO) and One vs. All (OVA). However, studies on those models show weaknesses on calculation time, decision time and the reject region. We propose a hierarchical clustering method (HCM) based on the SVM for real-time gas mixture classification. Experimental results show that the proposed method has better performance than the typical multi-class systems based on the SVM, and that the proposed method can classify single gases and their mixture easily and fast in the embedded system compared with BP-MLP and Fuzzy ARTMAP.

• Korean Journal of Poultry Science
• /
• v.23 no.4
• /
• pp.193-201
• /
• 1996

This experiment was carried out to find out the effect of packing methods on physico-chemical properties of breast and thigh meats in chicken, which was dried by air spray chilling method. The chicken carcass was cut into breast and thigh muscles, which were either vacuum packed or atmosphere packed, and stored at -2O˚C for 1, 4, 8, 12 and 16 wk after quick freezing at -45˚C for 35 min. The pH values of atmosphere-packed breast meat and vacuum-packed breast meat after one wk of storage were higher than those of atmosphere-packed thigh meat and vacuum-packed thigh meat(P< .05). The pH values increased as storage period extended, but no significant difference was detected between two packing method(vacuum vs. atmosphere). Total moisture contents of breast meats after one wk of storage were higher than those of thigh meats. The total moisture contents decreased slowly as storage period extended, but no significant difference was detected between two packing method(vacuum vs. atmosphere). The shear force value of thigh meat was higher than that of breast meat. The shear force values of both meats decreased as storage period extended, regardless of packing method. The water soluble protein extractability of thigh meats was higher than that of breast meat, and the water soluble protein extractability of all treatments decreased until 8 wk after storage, but increased gradually after 8 wk of storage period. The salt soluble protein extractability of breast meat was higher than that of thigh meat, and the salt soluble protein extractability of all treatments decreased as storage period extended. With regard to the packing method, the vacuum packing showed higher value than that of atmosphere packing method until 8 wk of storage. Total lipid contents of atmosphere- and vacuum-packed thigh meats at 1 wk of storage were higher than those of breast meats, and the total lipid contents of all of treatments decreased as storage period extended. However, no significant difference was detected between two packing methods. The fatty acid contents of breast and thigh meats were in order of o1eic(33,5~42.4), palmitic(19.7~30.8) and linoleic acid(10.8~17.4).

• 한국지구물리탐사학회:학술대회논문집
• /
• 2006.06a
• /
• pp.17-22
• /
• 2006

Shear modulus is directly linked to material's stiffness and is one of the most critical engineering parameters. Seismically, shear-wave velocity (Vs) is its best indicator. Although methods like refraction, down-hole, and cross-hole shear-wave surveys can be used, they are generally known to be tougher than any other seismic methods in field operation, data analysis, and overall cost. On the other hand, surface waves, commonly known as ground roll, are always generated in all seismic surveys with the strongest energy, and their propagation velocities are mainly determined by Vs of the medium. Furthermore, sampling depth of a particular frequency component of surface waves is in direct proportion to its wavelength and this property makes the surface wave velocity frequency dependent, i.e., dispersive. The multichannel analysis of surface waves (MASW) method tries to utilize this dispersion property of surface waves for the purpose of Vs profiling in 1-D (depth) or 2-D (depth and surface location) format. The active MASW method generates surface waves actively by using an impact source like sledgehammer, whereas the passive method utilizes those generated passively by cultural (e.g., traffic) or natural (e.g., thunder and tidal motion) activities. Investigation depth is usually shallower than 30 m with the active method, whereas it can reach a few hundred meters with the passive method. Overall procedures with both methods are briefly described.

• Korean Journal of Radiology
• /
• v.21 no.4
• /
• pp.431-441
• /
• 2020

Objective: To compare the diagnostic performance and interobserver variability of strain ratio obtained from one or two regions of interest (ROI) on breast elastography. Materials and Methods: From April to May 2016, 140 breast masses in 140 patients who underwent conventional ultrasonography (US) with strain elastography followed by US-guided biopsy were evaluated. Three experienced breast radiologists reviewed recorded US and elastography images, measured strain ratios, and categorized them according to the American College of Radiology breast imaging reporting and data system lexicon. Strain ratio was obtained using the 1-ROI method (one ROI drawn on the target mass), and the 2-ROI method (one ROI in the target mass and another in reference fat tissue). The diagnostic performance of the three radiologists among datasets and optimal cut-off values for strain ratios were evaluated. Interobserver variability of strain ratio for each ROI method was assessed using intraclass correlation coefficient values, Bland-Altman plots, and coefficients of variation. Results: Compared to US alone, US combined with the strain ratio measured using either ROI method significantly improved specificity, positive predictive value, accuracy, and area under the receiver operating characteristic curve (AUC) (all p values < 0.05). Strain ratio obtained using the 1-ROI method showed higher interobserver agreement between the three radiologists without a significant difference in AUC for differentiating breast cancer when the optimal strain ratio cut-off value was used, compared with the 2-ROI method (AUC: 0.788 vs. 0.783, 0.693 vs. 0.715, and 0.691 vs. 0.686, respectively, all p values > 0.05). Conclusion: Strain ratios obtained using the 1-ROI method showed higher interobserver agreement without a significant difference in AUC, compared to those obtained using the 2-ROI method. Considering that the 1-ROI method can reduce performers' efforts, it could have an important role in improving the diagnostic performance of breast US by enabling consistent management of breast lesions.

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.11
• /
• pp.4609-4614
• /
• 2015

Background: In recent decades, the prognosis for childhood leukemia has improved, especially for acute lymphoblastic leukemia (ALL). In Thailand, though, the survival rate for ALL is unimpressive. In 2006, standard national protocols for childhood leukemia treatment were implemented. We herein report the outcome of the ALL national protocols and explanations behind discrepancies in outcomes between institutions. Materials and Methods: Between March 2006 and February 2008, 486 children with ALL from 12 institutions were enrolled in the Thai national protocols. There were 3 different protocols based on specific criteria: one each for standard risk, high risk and Burkitt's ALL. We classified participating centers into 4 groups of institutions, namely: medical schools in Bangkok, provincial medical schools, hospitals in Bangkok and provincial hospitals. We also evaluated supportive care, laboratory facilities in participating centers, socioeconomics, and patient compliance. Overall and event-free survival were determined for each group using the Kaplan Meier method. Statistical differences were determined using the log-rank test. Previous outcomes of Thai childhood ALL treatment between 2003 and 2005 served as the historic control. Results: Five-year overall survival of ALL treated using the Thai national protocol was 67.2%; an improvement from the 63.7% of the 12-institute historical control (p-value=0.06). There were discrepancies in event-free survival of ALL between centers in Bangkok and up-country provinces (69.9% vs 51.2%, p-value <0.01). Socioeconomics and patient compliance were key elements in determining the outcome (65.5% vs 47.5%, 59.4% vs 42.9%) (p-value < 0.02). Conclusions: Implementation of standard national protocols for childhood leukemia in Thailand did not significantly improve the outcome of ALL. Factors leading to better outcomes included (a) improvement of treatment compliance (b) prevention of treatment abandonment and (c) financial support to the family.

• Journal of the Korean Data and Information Science Society
• /
• v.19 no.1
• /
• pp.25-36
• /
• 2008

Error Correcting Output Codes (ECOC) can improve generalization performance when applied to multicategory classification problem. In this study we propose a new criterion to select hyperparameters included in ECOC scheme. Instead of margins of a data we propose to use the probability of misclassification error since it makes the criterion simple. Using this we obtain an upper bound of leave-one-out error of OVA(one vs all) method. Our experiments from real and synthetic data indicate that the bound leads to good estimates of parameters.

• Journal of the Korean Data and Information Science Society
• /
• v.21 no.5
• /
• pp.959-965
• /
• 2010

For multiclassification, it is often the case that some variables are not important while some variables are more important than others. We propose a novel algorithm for selecting such relevant variables for multiclassification. This algorithm is base on multiclass least squares support vector machine (LS-SVM), which uses results of multiclass LS-SVM using one-vs-all method. Experimental results are then presented which indicate the performance of the proposed method.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.3
• /
• pp.22-28
• /
• 2010

Adaboost is well known for a representative learner as one of the kernel methods. Adaboost which is based on the statistical learning theory shows good generalization performance and has been applied to various pattern recognition problems. However, Adaboost is basically to deal with a two-class classification problem, so we cannot solve directly a multi-class problem with Adaboost. One-Vs-All and Pair-Wise have been applied to solve the multi-class classification problem, which is one of the multi-class problems. The two methods above are ones of the output coding methods, a general approach for solving multi-class problem with multiple binary classifiers, which decomposes a complex multi-class problem into a set of binary problems and then reconstructs the outputs of binary classifiers for each binary problem. However, two methods cannot show good performance. In this paper, we propose the method to solve a multi-target classification problem by using radial basis function of Adaboost weak classifier.