• Journal of Information Processing Systems
• /
• 제14권1호
• /
• pp.218-227
• /
• 2018

Vocal effort detection is important for both robust speech recognition and speaker recognition. In this paper, the spectral information entropy feature which contains more salient information regarding the vocal effort level is firstly proposed. Then, the model fusion method based on complementary model is presented to recognize vocal effort level. Experiments are conducted on isolated words test set, and the results show the spectral information entropy has the best performance among the three kinds of features. Meanwhile, the recognition accuracy of all vocal effort levels reaches 81.6%. Thus, potential of the proposed method is demonstrated.

• 생약학회지
• /
• 제22권2호
• /
• pp.78-84
• /
• 1991

From the whole plants of Orostachys japonicus(Crassulaceae), fatty acid ester mixture, seco-A-triterpene mixture, glutinone, friedelin, ${\beta}-amyrin$, glutinol, epifridelanol, 1-hexatriacontanol, sterol mixture, steryl glucoside mixture were isolated and characterized by spectral data.

• 대한원격탐사학회지
• /
• 제21권3호
• /
• pp.189-211
• /
• 2005

This paper makes an effort to compare the recently evolved soft classification method based on Linear Spectral Mixture Modeling (LSMM) with the traditional hard classification methods based on Iterative Self-Organizing Data Analysis (ISODATA) and Maximum Likelihood Classification (MLC) algorithms in order to achieve appropriate results for mapping, monitoring and preserving valuable coastal wetland ecosystems of southern India using Indian Remote Sensing Satellite (IRS) 1C/1D LISS-III and Landsat-5 Thematic Mapper image data. ISODATA and MLC methods were attempted on these satellite image data to produce maps of 5, 10, 15 and 20 wetland classes for each of three contrast coastal wetland sites, Pitchavaram, Vedaranniyam and Rameswaram. The accuracy of the derived classes was assessed with the simplest descriptive statistic technique called overall accuracy and a discrete multivariate technique called KAPPA accuracy. ISODATA classification resulted in maps with poor accuracy compared to MLC classification that produced maps with improved accuracy. However, there was a systematic decrease in overall accuracy and KAPPA accuracy, when more number of classes was derived from IRS-1C/1D and Landsat-5 TM imagery by ISODATA and MLC. There were two principal factors for the decreased classification accuracy, namely spectral overlapping/confusion and inadequate spatial resolution of the sensors. Compared to the former, the limited instantaneous field of view (IFOV) of these sensors caused occurrence of number of mixture pixels (mixels) in the image and its effect on the classification process was a major problem to deriving accurate wetland cover types, in spite of the increasing spatial resolution of new generation Earth Observation Sensors (EOS). In order to improve the classification accuracy, a soft classification method based on Linear Spectral Mixture Modeling (LSMM) was described to calculate the spectral mixture and classify IRS-1C/1D LISS-III and Landsat-5 TM Imagery. This method considered number of reflectance end-members that form the scene spectra, followed by the determination of their nature and finally the decomposition of the spectra into their endmembers. To evaluate the LSMM areal estimates, resulted fractional end-members were compared with normalized difference vegetation index (NDVI), ground truth data, as well as those estimates derived from the traditional hard classifier (MLC). The findings revealed that NDVI values and vegetation fractions were positively correlated ($r^2$= 0.96, 0.95 and 0.92 for Rameswaram, Vedaranniyam and Pitchavaram respectively) and NDVI and soil fraction values were negatively correlated ($r^2$ =0.53, 0.39 and 0.13), indicating the reliability of the sub-pixel classification. Comparing with ground truth data, the precision of LSMM for deriving moisture fraction was 92% and 96% for soil fraction. The LSMM in general would seem well suited to locating small wetland habitats which occurred as sub-pixel inclusions, and to representing continuous gradations between different habitat types.

• 대한원격탐사학회지
• /
• 제22권6호
• /
• pp.553-563
• /
• 2006

본 연구의 목적은 MODIS 다중시기영상과 선형분광혼합화소분석(Linear Spectral Mixture Analysis : LSMA)을 이용하여 한반도의 토지피복도를 작성하는 것이다. 다양한 공간해상도와 광역적인 촬영스케일의 MODIS 영상에 LSMA를 이용하여 토지피복분류기 정확도의 향상과 한반도 생물계절적인 특성을 분석하고자 하였다. LSMA는 하나의 화소를 단일의 지표물로 가정하여 영상을 처리하는 기존의 기법과 달리 대상지의 토지피복 특성을 가장 잘 반영하는 순수한 물체의 화소값(Endmember)을 선택하여 자연환경요소들의 하나하나를 분리하는 기법이다. 본 연구에서 MODIS 다중시기 영상에 LSMA를 적용한 결과 남, 북한의 농경지 및 산림지역에 대한 서로 다른 생물계절적인 특성을 파악 할 수 있었으며, 이러한 결과 영상을 ISODATA 무감독분류기법을 통해서 대분류와 중분류하였다. 대분류에서는 79.94%의 전체 정확도를 보였으며, 농업지역은 85.45%, 산림지역은 88.12%로 다른 분류군들에 비해서 가장 높은 정확도를 보였다. 중분류에서는 산림지역과, 농업지역을 더욱 세분화하여 분류하였다. 전체정확도는 82.09%였으며, 활엽수림 86.96%, 논 85.38%로 분류군중 가장 높은 정확도를 나타냈다.

• 대한원격탐사학회지
• /
• 제22권6호
• /
• pp.565-574
• /
• 2006

넓은 면적의 유역에 대한홍수유출모형 및 수문분석에서 중요한 인자로 이용되는 토지피복 정보를 얻기 위하여 인공위성 영상이 많이 활용되고 있다. 도시지역과 같이 다양한 형태의 토지피복이 혼재하는 공간에서는 보다 세분화된 토지피복 정보가 필요하나, 기존의 다중분광영상을 이용한 수문학적 토지피복분류에는 한계가 있다. 이 연구에서는 초분광영상을 이용하여 도시지역의 수문학적 토지피복 분류에 있어서 기존의 다중분광영상 보다 분류등급을 세분화하고 분류정확도를 향상시킬 수 있는 가능성을 밝히고자 한다. 미국 농무부 토양보전국(USDA SCS)의 도시지역 수문학적 토지피복분류를 목표로 서울지역의 Hyperion 영상을 분석하였다. 도시지역의 피복특성을 감안한여 투수성 및 불투수성 표면특성을 대표하는 8개의 endmember를 선정하여 분광혼합분석을 수행하였다. 분광혼합분석 결과 얻어진 각 endmember의 점유비율을 조합하여 17개 등급의 수문학적 토지피복도를 제작하였다. 분광혼합분석을 적용하여 얻어진 토지피복도의 정확도를 10곳의 표본점에 대한 항공사진 판독 결과를 통하여 검정한 결과, 미국 농무부에서 제시한 수문학적 토지피복등급이 비교적 정확하게 분류되었다.

• 약학회지
• /
• 제30권4호
• /
• pp.185-192
• /
• 1986

Authors developed the computer application program (language: APPLE SOFT BASIC) for derivative spectrophotometry. By means of this program, derivative of spectral absorbance with respect to wavelength is recorded versus wavelength. To try this program in connection with spectrophotometer system, the authors have done the simultaneous quantitation of pyridoxine center dot HCl and nicotinamide in the mixture, and the result was compared with that of absorbance method.

• 한국전기전자재료학회:학술대회논문집
• /
• 한국전기전자재료학회 2002년도 추계학술대회 논문집 Vol.15
• /
• pp.492-494
• /
• 2002

The fundamental principles of the operation of microwave discharges that are used to convert microwave energy to broad spectrum visual light are known. In this paper, emission dependance of microwave discharges in mixture content of sulfur with noble gases was studied. It is shown that the excitation of this gaseous mixture is carried out in two phases: (1) ionization of noble gas atoms by a microwave field and (2) the consequent maintenance of slightly ionized nonequilibrium plasma by the field. These two processes have essentially various thresholds for the microwave pump. The purpose of this work is to investigate spectral properties of the high frequency discharges in a mixture sulfur vapors with noble gases.

• 한국근적외분광분석학회:학술대회논문집
• /
• 한국근적외분광분석학회 2001년도 NIR-2001
• /
• pp.1289-1289
• /
• 2001

Water-methanol and water-acetonitrile mixtures are frequently used as HPLC solvent system and strong hydrogen bonding is well-known. But a detailed aspect of water-methanol and/or water-acetonitrile mixtures have not been shown with direct spectral evidence. Recently, near infrared spectroscopy and chemometric data refinery have been successfully combined in many applications. On the basis of factor analytical methods, the spectral features of water-methanol and water-acetonitrile mixtures were studied to reveal the detail of mixtures. Water-methanol and water-acetonitrile mixtures were prepared with varying concentration of each constituent and near infrared spectral data were acquired in the range of 1100-2500nm with 2-nm interval. The data matrices were analysed with ITTFA(Iterative Target Transform Factor Analysis) algorithm implemented as MATLAB codes. As a result, the concentration profiles of water, methanol and water-methanol complex were resolved and the spectra of water-methanol complexes were calculated, which cannot be acquired with pure complexes. A similar result was obtained with NIR spectral data of water-acetonitrile mixtures. Moreover, pure spectra of hydrogen-bonding complexes of water-methanol and water-acetonitrile can be computed, while any other usual physical methods cannot isolated those complexes for acquiring pure component spectra.

• 대한공간정보학회지
• /
• 제22권4호
• /
• pp.53-61
• /
• 2014

Landsat OLI 위성영상은 다양한 분광정보 밴드를 포함하고 있기 때문에, 토지피복지도 생성, 도심지역의 분석, 식생지수의 추출, 변화탐지 모니터링 등과 같은 다양한 원격탐사 분야에 활용할 수 있다. 또한, 토지피복지도는 GIS 및 국토 모니터링에 있어서 필수적인 정보이다. 본 연구에서는 Landsat OLI 위성과 기존의 토지피복지도를 활용하여 토지피복지도를 생성하고자 하였다. 이를 위해, 기존의 토지피복지도와 K-means 기법의 상관관계를 활용하여 훈련자료를 자동으로 생성하였으며, 생성된 훈련자료를 이용하여 각 클래스 별 분광 반사율 값을 추정하였다. 최종적으로, 반복적인 분광혼합분석을 통하여 각 클래스 별 점유 비율 영상과 토지피복지도를 생성하였다. 청주시 일대에 대한 토지피복지도와 Landsat OLI 위성영상을 활용한 실험을 수행하였으며, 감독분류 기법에 대한 결과 및 기존 토지피복지도와의 비교평가를 통하여 본 연구에서 제안된 기법이 수동으로 취득한 훈련자료가 없어도 효과적으로 토지피복지도를 생성할 수 있음을 정량적, 시각적으로 확인하였다.

• 대한원격탐사학회지
• /
• 제22권3호
• /
• pp.175-182
• /
• 2006

Because of the phenological variation of vegetation growth in temperate region, it is often difficult to accurately assess the surface conditions of agricultural croplands, grasslands, and disturbed forests by multi-spectral remote sensor data. In particular, the spectral similarity between soil and dry vegetation has been a primary problem to correctly appraise the surface conditions during the non-growing seasons in temperature region. This study analyzes the spectral characteristics of the mixture of dry vegetation and soil. The reflectance spectra were obtained from laboratory spectroradiometer measurement (GER-2600) and from EO-1 Hyperion image data. The reflectance spectra of several samples having different level of dry vegetation fractions show similar pattern from both lab measurement and hyperspectral image. Red-edge near 700nm and shortwave IR near 2,200nm are more sensitive to the fraction of dry vegetation. The use of hyperspectral data would allow us for better separation between bare soils and other surfaces covered by dry vegetation during the leaf-off season.