• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.18 no.1
• /
• pp.57-60
• /
• 2008

Since human listening is very sensitive to sound, for evaluating of a sound quality is required. Therefore, in the analysis for each situation, the sound evaluation is composed with sound quality factor. My researchers spends their effort to make a more reliable and more accurate of sound in term of sound quality index for various system noise. The previous methods to evaluation of the SQ about vehicle interior noise are linear regression analysis of subjective SQ metrics by statistics and the estimation of the subjective SQ values by neural network. But these are highly dependent on jury test and have many difficulties due to various environmental factors. So, to reduce jury test weight. we suggested a new method using Mahalanobis distance for SQ evaluation. Threrefore, in this study Mahalanobis distance for the vehicle interior noise was derived using the objective SQ except jury test. Finnaly, the results of the SQ evaluation was analyzed discrimination between reference and abnormal group.

• Analytical Science and Technology
• /
• v.34 no.3
• /
• pp.134-141
• /
• 2021

In this study, the fatty acid (FA) composition of commercial sesame oils (n = 62) was investigated using gas chromatography with flame ionization detector (GC-FID). Multivariate statistical techniques, including principal component analysis (PCA) and linear discriminant analysis (LDA), were applied to the chromatographic data of the FAs to discriminate the geographical origin of sesame oils. A statistically significant difference was observed in the content of C16:0, C18:0, C18:1, and C18:2 between domestic and imported sesame oils. A satisfactory recovery rate of 82.8-100.2 % was achieved for C16:0, C18:0, C18:1, C18:2, and C18:3. The correlation of C16:0, C18:1, and C18:2 in domestic sesame oils showed opposite trends compared to imported oils. The PCA plot demonstrated that sesame oils were clustered in distinct groups according to their origin. LDA was used to predict sesame oil samples in one of the two groups. C16:0 (Wilks λ = 0.361) and C18:1 (Wilks λ = 0.637) demonstrated the highest discriminant power for classifying the origin of the samples. The correct prediction rates were 88.9 % and 100 % for the domestic and imported samples, respectively. Further, 60 of the 62 sesame oil samples (96.8 %) were correctly classified, indicating that this approach can be used as a valuable tool to predict and classify the geographical origin of sesame oils.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.9
• /
• pp.1337-1346
• /
• 2015

In this paper, pattern classifier is designed to classify precipitation and non-precipitation events from weather radar data. The proposed classifier is based on Fuzzy Neural Network(FNN) and consists of three FNNs which operate in parallel. In the proposed network, the connection weights of the consequent part of fuzzy rules are expressed as two polynomial types such as constant or linear polynomial function, and their coefficients are learned by using Least Square Estimation(LSE). In addition, parametric as well as structural factors of the proposed classifier are optimized through Differential Evolution(DE) algorithm. After event classification between precipitation and non-precipitation echo, non-precipitation event is to get rid of all echo, while precipitation event including non-precipitation echo is to get rid of non-precipitation echo by classifier that is also based on Fuzzy Neural Network. Weather radar data obtained from meteorological office is to analysis and discuss performance of the proposed event and echo patter classifier, result of echo pattern classifier compare to QC(Quality Control) data obtained from meteorological office.

• International Journal of Computer Science & Network Security
• /
• v.21 no.11
• /
• pp.89-96
• /
• 2021

This work is an extension of my work presented a robust and economically efficient method for the Discrimination of four Mung-Beans [1] varieties based on quantitative parameters. Due to the advancement of technology, users try to find the solutions to their daily life problems using smartphones but still for computing power and memory. Hence, there is a need to find the best classifier to classify the Mung-Beans using already suggested features in previous work with minimum memory requirements and computational power. To achieve this study's goal, we take the experiments on various supervised classifiers with simple architecture and calculations and give the robust performance on the most relevant 10 suggested features selected by Fisher Co-efficient, Probability of Error, Mutual Information, and wavelet features. After the analysis, we replace the Artificial Neural Network and Deep learning with a classifier that gives approximately the same classification results as the above classifier but is efficient in terms of resources and time complexity. This classifier is easily implemented in the smartphone environment.

• ETRI Journal
• /
• v.45 no.1
• /
• pp.105-118
• /
• 2023

We tested the feasibility of automated discrimination of patients with panic disorder (PD) from healthy controls (HCs) based on multimodal physiological responses using machine learning. Electrocardiogram (ECG), electrodermal activity (EDA), respiration (RESP), and peripheral temperature (PT) of the participants were measured during three experimental phases: rest, stress, and recovery. Eleven physiological features were extracted from each phase and used as input data. Logistic regression (LoR), k-nearest neighbor (KNN), support vector machine (SVM), random forest (RF), and multilayer perceptron (MLP) algorithms were implemented with nested cross-validation. Linear regression analysis showed that ECG and PT features obtained in the stress and recovery phases were significant predictors of PD. We achieved the highest accuracy (75.61%) with MLP using all 33 features. With the exception of MLP, applying the significant predictors led to a higher accuracy than using 24 ECG features. These results suggest that combining multimodal physiological signals measured during various states of autonomic arousal has the potential to differentiate patients with PD from HCs.

• Journal of Conservation Science
• /
• v.21
• /
• pp.89-100
• /
• 2007

This study analyze concentration of minor and trace elements on 47 white porcelains excavated from Dudong-ri, Baekryeon-ri, Sachon-ri kilns in Gyeonsangnam-do by NAA(neutron activation analysis) and try to classify the provenance and characteristics according to the analytical result. Each kilns are divided into the group by PCA(principal component analysis) and LDA(linear discrimination analysis) using 17 elements; Ba Ce, Co, Cr, Cs, Dy, Eu, Hf, La Lu, Rb, Sc, Sm, Ta, Th, V, Yb. The contribution elements are Dy, Sm, La, Ce, Lu, Sc. And soft and hard white porcelains are similar with the chemical composition of the use materials therefore the difference of the chemical composition not confirmed a cause. The analytical results of the fine(I) and poor(II) quality white porcelains presume the difference of the povenance of clay materials or the poduction process such as difference purify and additive materials.

• Korean Journal of Soil Science and Fertilizer
• /
• v.34 no.3
• /
• pp.173-177
• /
• 2001

This study was conducted to investigate a potential utilitization of multivariate statistical analysis(Factor analysis, Discrimination analysis) on interpretation of rice plant lodging reason. Rice plants were sampled in paddy around Taegu city at from 25 to 29 of September in 2000. Mineral nutrient content(phosphate, potassium) of rice plant were significantly higher at 99% level, Silicate content were lower at 95% level in lodged samples than in normal. Plant characteristics associate with lodging(Culm length, second and third internode length, bight of center gravity) were significantly longer in lodged rice plant than in non lodged. Result of Factor analysis were that first principle component were culm length, second(N2) and third internode length(N3), second principle component were Ca content, first internode length(N1) and N3/culm length, third principle component were center gravity length(G) and G/culm length, fourth were nitrogen, phosphate, and potassium content, fifth were N2/culm length, N2+N3/culm length, Sixth was silicate content of rice plant. Linear discriminant equation distinguished lodged rice plants with non lodged rice plants very well. Prediction value was 100%, most explainable variable were phosphate content, culm length and third length.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.4
• /
• pp.169-174
• /
• 2024

This study purports to identify the factors that contribute to the classification of age groups or generations of Koreans. Independent variables such as respondents' attitudes toward welfare, attitudes toward equity, education level, perception of inequality in Korean society, tax awareness, and health status are included in the model that were put into the analysis with the main interest. Since this study does not construct any hypothesis prior to analysis, the nature of this study can be said exploratory. The data utilized for the analysis are from the 17th year of the Korean Welfare Panel collected in 2022, and a linear discrimination analysis technique will be used. First and foremost, a theoretical review of the generational classification will be conducted through domestic and international literature in the past. To date, there is no quantitative studies in Korea that have a significant influence on the generational classification. Therefore, in this study, a theoretical review of political tendencies and values, which are estimated to have a significant influence on the generational classification, that is, the difference between generations, will be significant. The perception and attitude toward welfare will be discussed in the review of values. Next, analysis models, analysis techniques, and variables to be used in the analysis will be introduced. After

• Journal of Korean Society of Environmental Engineers
• /
• v.29 no.3
• /
• pp.317-324
• /
• 2007

Fluorescence measurements of dissolved organic matter(DOM) have the superior advantages over other analysis tools for applying to water quality management. A preliminary study was conducted to test the feasibility of applying synchronous fluorescence measurements for tracing and monitoring pollution sources in a small stream located in an upstream area of the Sooyoung watershed in Busan. The water quality of the small stream is affected by leachate from sawdust pile and discharge of untreated sewage. The sampling sites included an upstream site, two pipes discharging untreated sewage, leachate from sawdust, and a downstream site. Of the five field samples, the leachate was distinguished from the other samples by a high peak at a lower wavelength range and a blunt peak at 350nm, suggesting that synchronous fluorescence can be used as a discrimination tool for monitoring the pollution. The efficacy of various indices derived from the spectral features to discriminate the pollution source was tested for well-defined mixture of the sawdust leachate and the upstream stream by comparing (1)the difference between measured values and those predicted based on mass balance and the characteristics of the two samples and (2)the linear correlations between index values and mass ratios of the sample mixtures. Of various discrimination indices selected, fluorescence intensities at 276 nm$({\Delta}\lambda=30nm)$and 347 nm$({\Delta}\lambda=60nm)$ were suggested as promising potential discrimination indices for the sawdust pollution source. Despite the limited number of samples and the study area, this study illustrates the evaluation process that should be followed to develop rapid, low-cost discrimination indices to monitor pollution sources based on end member mixing analyses.

• Journal of Educational Research in Mathematics
• /
• v.25 no.1
• /
• pp.1-19
• /
• 2015

This paper aims to explore what we can improve in the curriculum, teaching-learning, and evaluation on the bases of the analyses of multiple-choice items set in National Assessment of Educational Achievement. For this goal, by using the distribution curves of the responses percentages, we will grasp the features of educational achievement which appear to students through an in-depth analysis about not only item itself but also the contents included in particular distracters. These analyses provide more information than the descriptive statistical values such as the mean of correct answer percentage and the discrimination of whole group and the mean of responses percentages of replies of subgroups. Because the distribution curves of the responses percentages reveal the transition from the lowest to the highest educational achievement very well. From these analyses we acquire the implications about the concept of prime factor or prime factorization, ratio(proportion) such as velocity, linear function, volume of cone, properties of solid figure, and probabilities of empty event and total event.