• The Journal of the Acoustical Society of Korea
• /
• v.15 no.5
• /
• pp.38-43
• /
• 1996

This paper compares the recognition performances of feature vectors known to be robust to the environmental noise. And, the speech subtraction technique is combined with the noise robust feature to get more performance enhancement. The experiments using SMC(Short time Modified Coherence) analysis, root cepstral analysis, LDA(Linear Discriminant Analysis), PLP(Perceptual Linear Prediction), RASTA(RelAtive SpecTrAl) processing are carried out. An isolated word recognition system is composed using semi-continuous HMM. Noisy environment experiments usign two types of noises:exhibition hall, computer room are carried out at 0, 10, 20dB SNRs. The experimental result shows that SMC and root based mel cepstrum(root_mel cepstrum) show 9.86% and 12.68% recognition enhancement at 10dB in compare to the LPCC(Linear Prediction Cepstral Coefficient). And when combined with spectral subtraction, mel cepstrum and root_mel cepstrum show 16.7% and 8.4% enhanced recognition rate of 94.91% and 94.28% at 10dB.

• Korean Journal of Remote Sensing
• /
• v.27 no.4
• /
• pp.435-444
• /
• 2011

The land cover map derived from spectral features of high resolution optical images has low spectral resolution and heterogeneity in the same land cover class. For this reason, despite the same land cover class, the land cover can be classified into various land cover classes especially in vegetation area. In order to overcome these problems, detailed vegetation classification is applied to optical satellite image and SAR(Synthetic Aperture Radar) integrated data in vegetation area which is the result of pre-classification from optical image. The pre-classification and vegetation classification were performed with MLC(Maximum Likelihood Classification) method. The hierarchical land cover classification was proposed from fusion of detailed vegetation classes and non-vegetation classes of pre-classification. We can verify the facts that the proposed method has higher accuracy than not only general SAR data and GLCM(Gray Level Co-occurrence Matrix) texture integrated methods but also hierarchical GLCM integrated method. Especially the proposed method has high accuracy with respect to both vegetation and non-vegetation classification.

• Korean Journal of Remote Sensing
• /
• v.35 no.6_1
• /
• pp.959-971
• /
• 2019

CNN (Convolutional Neural Network) is one representative deep learning algorithm, which can extract high-level spatial and spectral features, and has been applied for hyperspectral image classification. However, one significant drawback behind the application of CNNs in hyperspectral images is the high dimensionality of the data, which increases the training time and processing complexity. To address this problem, several CNN based hyperspectral image classification studies have exploited PCA (Principal Component Analysis) for dimensionality reduction. One limitation to this is that the spectral information of the original image can be lost through PCA. Although it is clear that the use of PCA affects the accuracy and the CNN training time, the impact of PCA for CNN based hyperspectral image classification has been understudied. The purpose of this study is to analyze the quantitative effect of PCA in CNN for hyperspectral image classification. The hyperspectral images were first transformed through PCA and applied into the CNN model by varying the size of the reduced dimensionality. In addition, 2D-CNN and 3D-CNN frameworks were applied to analyze the sensitivity of the PCA with respect to the convolution kernel in the model. Experimental results were evaluated based on classification accuracy, learning time, variance ratio, and training process. The size of the reduced dimensionality was the most efficient when the explained variance ratio recorded 99.7%~99.8%. Since the 3D kernel had higher classification accuracy in the original-CNN than the PCA-CNN in comparison to the 2D-CNN, the results revealed that the dimensionality reduction was relatively less effective in 3D kernel.

• The Journal of Engineering Geology
• /
• v.12 no.4
• /
• pp.405-419
• /
• 2002

Fracture roughness of rock specimens is observed by a new confocal laser scanning microscope (CLSM; Olympus OLS1100). The wave length of laser is 488 nm, and the laser scanning is managed by a light polarization method using two galvano-meter scanner mirrors. The function of laser reflection auto-focusing enables us to measure line data fast and precisely. The system improves resolution in the light axis (namely z) direction because of the confocal optics. Using the CLSM, it is Possible to measure a specimen of the size up to $10{\;}{\times}{\;}10{\;}cm$ which is fixed on a specially designed stage. A sampling is managed in a spacing $2.5{\;}\mu\textrm{m}$ along x and y directions. The highest measurement resolution of z direction is $10{\;}\mu\textrm{m}$, which is more accurate than other methods. Core specimens of coarse and fine grained granite are provided. Fractures are artificially maneuvered by a Brazilian test method. Measurements are performed along three scan lines on each fracture surface. The measured data are represented as 2-D and 3-D digital images showing detailed features of roughness. Line profiles of the coarse granites represent more frequent change of undulation than those of the fine granite. Spectral analyses by the fast Fourier transform (FFT) are performed to characterize the roughness data quantitatively and to identify influential frequency of roughness. The FFT results suggest that a specimen loaded by large and low frequency energy tends to have high values of undulation change and large wave length of fracture roughness.

• Geophysics and Geophysical Exploration
• /
• v.8 no.1
• /
• pp.41-49
• /
• 2005

We have developed a random heterogeneous velocity model with bimodal distribution in methane hydrate-bearing Bones. The P-wave well-log data have a von Karman type autocorrelation function and non-Gaussian distribution. The velocity histogram has two peaks separated by several hundred metres per second. A random heterogeneous medium with bimodal distribution is generated by mapping of a medium with a Gaussian probability distribution, yielded by the normal spectral-based generation method. By using an ellipsoidal autocorrelation function, the random medium also incorporates anisotropy of autocorrelation lengths. A simulated P-wave velocity log reproduces well the features of the field data. This model is applied to two simulations of elastic wane propagation. Synthetic reflection sections with source signals in two different frequency bands imply that the velocity fluctuation of the random model with bimodal distribution causes the frequency dependence of the Bottom Simulating Reflector (BSR) by affecting wave field scattering. A synthetic cross-well section suggests that the strong attenuation observed in field data might be caused by the extrinsic attenuation in scattering. We conclude that random heterogeneity with bimodal distribution is a key issue in modelling hydrate-bearing Bones, and that it can explain the frequency dependence and scattering observed in seismic sections in such areas.

• Korean Journal of Remote Sensing
• /
• v.34 no.6_1
• /
• pp.1055-1066
• /
• 2018

Vegetation indices on the basis of optical characteristics of vegetation can represent various conditions such as canopy biomass and physiological activity. Those have been mostly developed with the large-scaled applications of multi-band optical sensors on-board satellites. However, the sensitivity of vegetation indices for detecting vegetation features will be different depending on the spatial scales. Therefore, in this study, the investigation of photochemical reflectance index (PRI), known as one of useful vegetation indices for detecting photosynthetic ability and vegetation stress, under the three spatial scales was conducted using multi-spectral camera installed in unmanned aerial vehicle (UAV),field spectrometer, and leaf reflectometer. In the leaf scale, diurnal PRI had minimum values at different local-time according to the compass direction of leaf face. It meant that each leaf in some moment had the different degree of light use efficiency (LUE). In early growth stage of crop, $PRI_{leaf}$ was higher than $PRI_{stands}$ and $PRI_{canopy}$ because the leaf scale is completely not governed by the vegetation cover fraction.In the stands and canopy scales, PRI showed a large spatial variability unlike normalized difference vegetation index (NDVI). However, the bias for the relationship between $PRI_{stands}$ and $PRI_{canopy}$ is lower than that in $NDVI_{stands}$ and $NDVI_{canopy}$. Our results will help to understand and utilize PRIs observed at different spatial scales.

• Phonetics and Speech Sciences
• /
• v.15 no.1
• /
• pp.25-34
• /
• 2023

This study examined the utility of the acoustic features of vowels as cues for the place of articulation of Korean nasal consonants. In the acoustic analysis, spectral and temporal parameters were measured at the 25%, 50%, and 75% time points in the vowels neighboring nasal consonants in samples extracted from a spontaneous Korean speech corpus. Using these measurements, linear discriminant analyses were performed and classification accuracies for the nasal place of articulation were estimated. The analyses were applied separately for vowels following and preceding a nasal consonant to compare the effects of progressive and regressive coarticulation in terms of place of articulation. The classification accuracies ranged between approximately 50% and 60%, implying that acoustic measurements of vowel intervals alone are not sufficient to predict or classify the place of articulation of adjacent nasal consonants. However, given that these results were obtained for measurements at the temporal midpoint of vowels, where they are expected to be the least influenced by coarticulation, the present results also suggest the potential of utilizing acoustic measurements of vowels to improve the recognition accuracy of nasal place. Moreover, the classification accuracy for nasal place was higher for vowels preceding the nasal sounds, suggesting the possibility of higher anticipatory coarticulation reflecting the nasal place.

• Journal of Korean Society for Geospatial Information Science
• /
• v.25 no.1
• /
• pp.9-17
• /
• 2017

Hyperspectral imagery is used in the land cover classification with the principle component analysis and minimum noise fraction to reduce the data dimensionality and noise. Recently, studies on the supervised classification using various features having spectral information and spatial characteristic have been carried out. In this study, principle component bands and normalized difference vegetation index(NDVI) was utilized in the supervised classification for the land cover classification. To utilize additional information not included in the principle component bands by the hyperspectral imagery, we tried to increase the classification accuracy by using the NDVI. In addition, the extended attribute profiles(EAP) generated using the morphological filter was used as the input data. The random forest algorithm, which is one of the representative supervised classification, was used. The classification accuracy according to the application of various features based on EAP was compared. Two areas was selected in the experiments, and the quantitative evaluation was performed by using reference data. The classification accuracy of the proposed algorithm showed the highest classification accuracy of 85.72% and 91.14% compared with existing algorithms. Further research will need to develop a supervised classification algorithm and additional input datasets to improve the accuracy of land cover classification using hyperspectral imagery.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.15 no.3
• /
• pp.66-80
• /
• 2012

It is necessary to normalize spectral image values derived from multi-temporal satellite data to a common scale in order to apply remote sensing methods for change detection, disaster mapping, crop monitoring and etc. There are two main approaches: absolute radiometric normalization and relative radiometric normalization. This study focuses on the multi-temporal satellite image processing by the use of relative radiometric normalization. Three scenes of KOMPSAT-2 imagery were processed using the Multivariate Alteration Detection(MAD) method, which has a particular advantage of selecting PIFs(Pseudo Invariant Features) automatically by canonical correlation analysis. The scenes were then applied to detect disaster areas over Sendai, Japan, which was hit by a tsunami on 11 March 2011. The case study showed that the automatic extraction of changed areas after the tsunami using relatively normalized satellite data via the MAD method was done within a high accuracy level. In addition, the relative normalization of multi-temporal satellite imagery produced better results to rapidly map disaster-affected areas with an increased confidence level.

• Journal of the Mineralogical Society of Korea
• /
• v.23 no.4
• /
• pp.403-411
• /
• 2010

Essentials of understanding the geochemical evolution and geophysical processes in Earth's system are macroscopic properties and atomistic (and electronic) structures of Earth materials. Recent advances in quantum calculations based on the density functional theory allow us to unveil the previously unknown details of local atomic structures in diverse silicates in Earth's interior. Here, we report the O K-edge ELNES (energy-loss near-edge structure; ELNES) spectra and PLDOS (partial local density of states) for oxygen atoms in ${\alpha}$-quartz and stishovite using the quantum calculations based on FP-LAPW (full potential linearized augmented plane wave). The calculated O K-edge ELNES spectrum of ${\alpha}$-quartz shows a strong peak at ~538 eV due to comer-sharing oxygen linking two $SiO_4$ tetrahedra and that for stishovite shows two distinct peaks at ~537 and ~543 eV corresponding to edge-sharing oxygen linking $SiO_6$ octahedra. The significant differences in spectral features of O K-edge ELNES spectra suggest that the O K-edge features can be useful indicator to distinguish various oxygen sites in diverse crystal and amorphous silicates in the Earth's interior.