• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.3
• /
• pp.1243-1263
• /
• 2018

The two-stage linear discrimination analysis (TSLDA) is a feature extraction technique to solve the small size sample problem in the field of image recognition. The TSLDA has retained all subspace information of the between-class scatter and within-class scatter. However, the feature information in the four subspaces may not be entirely beneficial for classification, and the regularization procedure for eliminating singular metrics in TSLDA has higher time complexity. In order to address these drawbacks, this paper proposes an improved two-stage linear discriminant analysis (Improved TSLDA). The Improved TSLDA proposes a selection and compression method to extract superior feature information from the four subspaces to constitute optimal projection space, where it defines a single Fisher criterion to measure the importance of single feature vector. Meanwhile, Improved TSLDA also applies an approximation matrix method to eliminate the singular matrices and reduce its time complexity. This paper presents comparative experiments on five face databases and one handwritten digit database to validate the effectiveness of the Improved TSLDA.

• The Bulletin of The Korean Astronomical Society
• /
• v.38 no.1
• /
• pp.61.1-61.1
• /
• 2013

In this study we apply Support Vector Machine (SVM) to the prediction of geo-effective halo coronal mass ejections (CMEs). The SVM, which is one of machine learning algorithms, is used for the purpose of classification and regression analysis. We use halo and partial halo CMEs from January 1996 to April 2010 in the SOHO/LASCO CME Catalog for training and prediction. And we also use their associated X-ray flare classes to identify front-side halo CMEs (stronger than B1 class), and the Dst index to determine geo-effective halo CMEs (stronger than -50 nT). The combinations of the speed and the angular width of CMEs, and their associated X-ray classes are used for input features of the SVM. We make an attempt to find the best model by using cross-validation which is processed by changing kernel functions of the SVM and their parameters. As a result we obtain statistical parameters for the best model by using the speed of CME and its associated X-ray flare class as input features of the SVM: Accuracy=0.66, PODy=0.76, PODn=0.49, FAR=0.72, Bias=1.06, CSI=0.59, TSS=0.25. The performance of the statistical parameters by applying the SVM is much better than those from the simple classifications based on constant classifiers.

• Smart Structures and Systems
• /
• v.30 no.4
• /
• pp.385-395
• /
• 2022

Detecting cracks on a concrete structure is crucial for structural maintenance, a crack being an indicator of possible damage. Conventional crack detection methods which include visual inspection and non-destructive equipment, are typically limited to a small region and require time-consuming processes. Recently, to reduce the human intervention in the inspections, various researchers have sought computer vision-based crack analyses: One class is filter-based methods, which effectively transforms the image to detect crack edges. The other class is using deep-learning algorithms. For example, convolutional neural networks have shown high precision in identifying cracks in an image. However, when the objective is to classify not only the existence of crack but also the types of cracks, only a few studies have been reported, limiting their practical use. Thus, the presented study develops an image processing procedure that detects cracks and classifies crack types; whether the image contains a crazing-type, single crack, or multiple cracks. The properties and steps in the algorithm have been developed using field-obtained images. Subsequently, the algorithm is validated from additional 227 images obtained from an open database. For test datasets, the proposed algorithm showed accuracy of 92.8% in average. In summary, the developed algorithm can precisely classify crazing-type images, while some single crack images may misclassify into multiple cracks, yielding conservative results. As a result, the successful results of the presented study show potentials of using vision-based technologies for providing crack information with reduced human intervention.

• Korean Journal of Remote Sensing
• /
• v.37 no.3
• /
• pp.409-418
• /
• 2021

The land cover map is a very important data that is used as a basis for decision-making for land policy and environmental policy. The land cover map is mapped using remote sensing data, and the classification results may vary depending on the acquisition time of the data used even for the same area. In this study, to overcome the classification accuracy limit of single-period data, multi-series satellite images were used to learn the difference in the spectral reflectance characteristics of the land surface according to seasons on a U-Net model, one of the deep learning algorithms, to improve classification accuracy. In addition, the degree of improvement in classification accuracy is compared by comparing the accuracy of single-period data. Seoul, which consists of various land covers including 30% of green space and the Han River within the area, was set as the research target and quarterly Sentinel-2 satellite images for 2020 were aquired. The U-Net model was trained using the sub-class land cover map mapped by the Korean Ministry of Environment. As a result of learning and classifying the model into single-period, double-series, triple-series, and quadruple-series through the learned U-Net model, it showed an accuracy of 81%, 82% and 79%, which exceeds the standard for securing land cover classification accuracy of 75%, except for a single-period. Through this, it was confirmed that classification accuracy can be improved through multi-series classification.

• Journal of Animal Science and Technology
• /
• v.51 no.2
• /
• pp.97-104
• /
• 2009

Complement of test standard, evaluation methods and models are needed to improve national competitiveness and to exchange superior genetic resources through the comparison of genetic evaluation score among nations in dairy cattle. Therefore, this study was conducted for the application of international standard to Korea considering domestic circumstance by changing linear-classification test score system of 50 classes which is currently used in Korea to system of 9 classes which is used in advanced nations of dairy. 15,230 of holstein cow linear type records with first parity records for the fifteen linear type and one total score from 2001 to 2006 and pedigree data which were collected by the Korean Animal Improvement Association were used in this study. Population classified by 9 levels was more normal distributed than 50 levels. Correlation coefficients between 50 and 9 score system showed over 0.98 by each classification scheme. Therefore, the 50 point system can be substituted with 9 point system due to their highly positive correlation. However, scores in all traits were still very contingent on classifier under the 9 point system (p<0.001), and F values between foot angle and front teat attachment showed high fluctuation depending on classifier. It means that subjective opinions of classifier would influence on linear type score as ever even if class scheme transformed to system of 9 class. Therefore, the relevance of transformation to the 9 point system should be assessed after analyses about various environmental factors.

• The Korean Journal of Nuclear Medicine
• /
• v.28 no.3
• /
• pp.307-312
• /
• 1994

Interictal single photon emission computed tomography of regional cerebral blood flow (rCBF SPECT) in 18 intractable temporal lobe epilepsy patients(8 male and 10 female patients: average 23.5 years old) were compared with 2.0 T magnetic resonance imaging (MRI). And surgical outcome was analysed with the findings, symptom duration and lateralization of temporal lobe. Preoperatively rCBF SPECT was done in all 18 patients with intravenous injection of 740 MBq 99mTc-HMPAO. MRI was also done preoperatively in 13 patients. Surgical outcome was classified by Engel's outcome classification(four-part classification recommended at the first Palm Desert conference). rCBF SPECT detected correctly lateralising abnormality of temporal lobe hypoperfusion in 13/18(72.2%), contralateral temporal lobe hypoperfusion in 2/18(11.1%) and showed no def-inite abnormality in 3/18(16.7%). The positive predictive value of unilateral temporal lobe hypoperfusion was 87%. MRI detected correct localising abnormality in 8/13(61.5%), such as hippocampal atrophy(7/13), asymmetric temporal horn(6/13), anterior temporal lobe atrophy(1/13), increased signal intensity from hippocampus(1/13) and calcific density(1/13), and no abnormal finding was noted in 5/13(38.5%). There was no false positive findings and the positive predictive value of MRI was 100%. Only 2 cases showed same lateralization findings in rCBF SPECT and MRI. There was no significant correlation between symptom duration and no abnormal findings on SPECT or MRI. Surgical outcome showed class I in 15/18(83.3%), and class II in 2/18(11.1%). One case of no abnormal finding in both SPECT and MRI showed class III surgical outcome. No class IV surgical outcome was noted. Surgical outcome, lateralization of epileptic focus in temporal lobe and abnormal findings in rCBR SPECT or MRI were not significantly correlated.

• Journal of the Korea Convergence Society
• /
• v.9 no.7
• /
• pp.1-7
• /
• 2018

Feature selection, one of data preprocessing techniques, is one of major research areas in many applications dealing with large dataset. It has been used in pattern recognition, machine learning and data mining, and is now widely applied in a variety of fields such as text classification, image retrieval, intrusion detection and genome analysis. The proposed method is based on a genetic algorithm which is one of meta-heuristic algorithms. There are two methods of finding feature subsets: a filter method and a wrapper method. In this study, we use a wrapper method, which evaluates feature subsets using a real classifier, to find an optimal feature subset. The training dataset used in the experiment has a severe class imbalance and it is difficult to improve classification performance for rare classes. After preprocessing the training dataset with SMOTE, we select features and evaluate them with various machine learning algorithms.

• Journal of Dental Anesthesia and Pain Medicine
• /
• v.17 no.3
• /
• pp.199-204
• /
• 2017

Background: Anxiety control remains an important concern in dental practice. We evaluated the incidence, nature, and sequelae of complications during and after minor oral surgeries performed under intravenous midazolam and fentanyl sedation using the titration technique. Method: The medical records of patients who had undergone minor oral surgeries under moderate intravenous midazolam and fentanyl sedation at our institution between January 1, 2015 and December 31, 2015 were retrospectively evaluated. Age, sex, body mass index, medical history, American Society of Anesthesiologists (ASA) classification, indications for sedation, amount of sedative used, surgical duration, and recovery time were evaluated for all patients. Results: In total, 107 patients aged 9-84 years were included. ASA class I and class II were observed for 56.1% and 43.9% patients, respectively. Complications associated with sedation occurred in 11 (10.2%) patients. There were no serious adverse events. Oxygen saturation reached 95% during the procedure in six patients; this was successfully managed by stimulating the patients to take a deep breath. Two patients exhibited deep sedation and one exhibited paradoxical excitement. After the procedure, one patient experienced nausea without vomiting and one exhibited a prolonged recovery time. The surgical procedures were completed in all patients. Obesity was found to be significantly associated with sedation-related complications. Conclusion: Our results suggest that complications associated with intravenous midazolam and fentanyl sedation using the titration technique for minor oral surgeries are mostly minor and can be successfully managed with no prolonged sequelae.

• Journal of Intelligence and Information Systems
• /
• v.23 no.1
• /
• pp.47-67
• /
• 2017

Steel plate faults is one of important factors to affect the quality and price of the steel plates. So far many steelmakers generally have used visual inspection method that could be based on an inspector's intuition or experience. Specifically, the inspector checks the steel plate faults by looking the surface of the steel plates. However, the accuracy of this method is critically low that it can cause errors above 30% in judgment. Therefore, accurate steel plate faults diagnosis system has been continuously required in the industry. In order to meet the needs, this study proposed a new steel plate faults diagnosis system using Simultaneous MTS (S-MTS), which is an advanced Mahalanobis Taguchi System (MTS) algorithm, to classify various surface defects of the steel plates. MTS has generally been used to solve binary classification problems in various fields, but MTS was not used for multiclass classification due to its low accuracy. The reason is that only one mahalanobis space is established in the MTS. In contrast, S-MTS is suitable for multi-class classification. That is, S-MTS establishes individual mahalanobis space for each class. 'Simultaneous' implies comparing mahalanobis distances at the same time. The proposed steel plate faults diagnosis system was developed in four main stages. In the first stage, after various reference groups and related variables are defined, data of the steel plate faults is collected and used to establish the individual mahalanobis space per the reference groups and construct the full measurement scale. In the second stage, the mahalanobis distances of test groups is calculated based on the established mahalanobis spaces of the reference groups. Then, appropriateness of the spaces is verified by examining the separability of the mahalanobis diatances. In the third stage, orthogonal arrays and Signal-to-Noise (SN) ratio of dynamic type are applied for variable optimization. Also, Overall SN ratio gain is derived from the SN ratio and SN ratio gain. If the derived overall SN ratio gain is negative, it means that the variable should be removed. However, the variable with the positive gain may be considered as worth keeping. Finally, in the fourth stage, the measurement scale that is composed of selected useful variables is reconstructed. Next, an experimental test should be implemented to verify the ability of multi-class classification and thus the accuracy of the classification is acquired. If the accuracy is acceptable, this diagnosis system can be used for future applications. Also, this study compared the accuracy of the proposed steel plate faults diagnosis system with that of other popular classification algorithms including Decision Tree, Multi Perception Neural Network (MLPNN), Logistic Regression (LR), Support Vector Machine (SVM), Tree Bagger Random Forest, Grid Search (GS), Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). The steel plates faults dataset used in the study is taken from the University of California at Irvine (UCI) machine learning repository. As a result, the proposed steel plate faults diagnosis system based on S-MTS shows 90.79% of classification accuracy. The accuracy of the proposed diagnosis system is 6-27% higher than MLPNN, LR, GS, GA and PSO. Based on the fact that the accuracy of commercial systems is only about 75-80%, it means that the proposed system has enough classification performance to be applied in the industry. In addition, the proposed system can reduce the number of measurement sensors that are installed in the fields because of variable optimization process. These results show that the proposed system not only can have a good ability on the steel plate faults diagnosis but also reduce operation and maintenance cost. For our future work, it will be applied in the fields to validate actual effectiveness of the proposed system and plan to improve the accuracy based on the results.

• Journal of the Korean Academy of Esthetic Dentistry
• /
• v.25 no.1
• /
• pp.15-24
• /
• 2016

It is considered an implant failure when there is esthetic problems in the anterior area although the prosthesis function normally. In 2003, Dr. Kan et al stated that implant bone level is determined by the adjacent teeth. After that many scholars have studied how can achieve the esthetics result on adjacent teeth bone loss cases. In 2012, Dr. Takino published an article in Quintessence. He summarized previous articles and reclassified the defects from class 1 through 4. Class 1 and 2 depicts a situation where there is no bone loss on adjacent teeth. In Class 3 and 4, interproximal bone loss extends to the adjacent tooth. If one side is involved, it is Class 3. If both sides are involved, it is Class 4. The clue for esthetic implant restoration is whether bone loss extends to adjacent tooth or not. If the bone level of adjacent tooth is sound, we can easily achieve the esthetic but the bone level is not sound, the surgery will be complicated and the esthetic result will be unpredictable. So regenerative surgery for adjacent tooth is necessary for long-term maintenance. But the options and process were so complicated, the purpose of this article is to report the method simplify the surgery and gain a similar outcome.