• Proceedings of the Korea Information Processing Society Conference
• /
• 2003.05a
• /
• pp.725-728
• /
• 2003

사용자의 감정에 관련된 정보를 처리하는 것은 인간과 컴퓨터와의 상호작용(HCI)에 있어서 매우 중요한 역할을 한다. 특히 비디오 데이터에 대한 사용자의 감정을 처리하는 것은 비디오 검색이나 요약본 구성에 매우 중요하다. 사용자의 감정을 처리하기 위해서는 감정에 관련된 특징들을 추출 및 측정하고 이를 기반으로 비디오 장면을 분류하는 것이 필요하다. 본 논문에서는 칼라 정보를 바탕으로 Fisher의 Linear Discriminant Analysis 방식 및 Mahalanobis Distance 측정을 이용하여 기본 감정의 분류 방식을 제안한다. 공포 감정의 경우 77.8%의 의미 있는 결과를 얻었다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07b
• /
• pp.520-522
• /
• 2005

본 논문에서는 인간과 컴퓨터 사이의 상호작용을 하는 방법중의 하나인 제스처를 인식할 때 필요한 정확한 손 검출 방법을 제안한다. 이를 위해 기존의 다수의 손 영상들 가장 잘 표현하면서도 효과적으로 압축할 수 있는 PCA를 이용해서 특징 벡터를 추출한다. 이어서 특징 벡터간의 Mahalanobis distance를 이용한 분류기에 가중치를 적용하여 사용한다. 또한 시간에 따른 연속적인 영상에서 검출된 이전 영상의 중심점의 위치와 중심점의 motion vector를 이용해서 손이 검출되지 않은 영상의 검출 성능을 보상한다.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.14 no.6
• /
• pp.1073-1080
• /
• 2011

In this study, a target detection algorithm was proposed for using hyperspectral imagery. The proposed algorithm is designed to have minimal processing time, low false alarm rate, and flexible threshold selection. The target detection procedure can be divided into two steps. Initially, candidates of target pixel are extracted using matching ratio of spectral pattern that can be calculated by spectral derivation. Secondly, spectral distance is computed only for those candidates using Euclidean distance. The proposed two-step method showed lower false alarm rate than the Euclidean distance detector applied over the whole image. It also showed much lower processing time as compared to the Mahalanobis distance detector.

• Proceedings of the Korea Institute of Fire Science and Engineering Conference
• /
• 1997.11a
• /
• pp.484-491
• /
• 1997

In this paper, an approach to determine the in-ordinal condition of a room, which is based on multi variable analysis, is proposed. According to this approach, the distance of a state from the ordinal condition is thought to be evaluated by the Mahalanobis' distance. The temperature changes of a room were measured and their statistical characteristics such as distribution type, the mean value and the standard deviation are studied. The applicability of the method for the fire detection is also investigated.

• Bulletin of the Korean Chemical Society
• /
• v.20 no.9
• /
• pp.1021-1025
• /
• 1999

Near-infrared (NIR) spectroscopy has been successfully utilized for the rapid identification of six typical petroleum products such as light straight-run (LSR), naphtha, kerosine, light gas oil (LGO), gasoline, and diesel. The spectral features of each product were reasonably differentiated in the NIR region, and the spectral differences provided enough qualitative spectral information for discrimination. For discrimination, principal component analysis (PCA) combined with Mahalanobis distance was used to identify each petroleum product from NIR spectra. The results showed that each product was accurately identified with an accuracy over 95%. Most noticeably, LSR, kerosine, gasoline, and diesel samples were predicted with identification accuracy of 99%. The overall results ensure that a portable NIR instrument combined with a multivariate qualitative discrimination method can be efficiently utilized for rapid and simple identification of petroleum products. This is especially important when local at-site measurements are necessary, such as accidental petroleum leakage and regulation of illegal product blending.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2015.05a
• /
• pp.239-239
• /
• 2015

This study presents a bivariate extension of the goodness-of-fit measure for regional frequency distributions developed by Hosking and Wallis [1993] for use with the method of L-moments. Utilising the approximate joint normal distribution of the regional L-skewness and L-kurtosis, a graphical representation of the confidence region on the L-moment diagram can be constructed as an ellipsoid. Candidate distributions can then be accepted where the corresponding the oretical relationship between the L-skewness and L-kurtosis intersects the confidence region, and the chosen distribution would be the one that minimises the Mahalanobis distance measure. Based on a set of Monte Carlo simulations it is demonstrated that the new bivariate measure generally selects the true population distribution more frequently than the original method. An R-code implementation of the method is available for download free-of-charge from the GitHub code depository and will be demonstrated on a case study of annual maximum series of peak flow data from a homogeneous region in Italy.

• Journal of Korea Multimedia Society
• /
• v.24 no.10
• /
• pp.1319-1325
• /
• 2021

It is important to remove fog for accurate object recognition and detection during preprocessing because images taken in foggy adverse weather suffer from poor quality of images due to scattering and absorption of light, resulting in poor performance of various vision-based applications. This paper proposes an end-to-end deep learning-based single image de-fogging method using U-Net architecture. The loss function used in the algorithm is a loss function based on Mahalanobis distance with fog features, which solves the problem of domain shifts, and demonstrates superior performance by comparing qualitative and quantitative numerical evaluations with conventional methods. We also design it to generate fog through the VGG19 loss function and use it as the next training dataset.

• Proceedings of the Korean Society of Near Infrared Spectroscopy Conference
• /
• 2001.06a
• /
• pp.1121-1121
• /
• 2001

A previous study (Berzaghi et al., 2001) evaluated the performance of 3 calibration methods, modified partial least squares (MPLS), local PLS (LOCAL) and artificial neural networks (ANN) on the prediction of the chemical composition of forages, using a large NIR database. The study used forage samples (n=25,977) from Australia, Europe (Belgium, Germany, Italy and Sweden) and North America (Canada and U.S.A) with reference values for moisture, crude protein and neutral detergent fibre content. The spectra of the samples were collected using 10 different Foss NIR Systems instruments, only some of which had been standardized to one master instrument. The aim of the present study was to evaluate the behaviour of these different calibration methods when predicting the same samples measured on different instruments. Twenty-two sealed samples of different kind of forages were measured in duplicate on seven instruments (one master and six slaves). Three sets of near infrared spectra (1100 to 2500nm) were created. The first set consisted of the spectra in their original form (unstandardized); the second set was created using a single sample standardization (Clone1); the third was created using a multiple sample procedure (Clone6). WinISI software (Infrasoft International Inc., Port Mathilda, PA, USA) was used to perform both types of standardization, Clone1 is just a photometric offset between a “master” instrument and the “slave” instrument. Clone6 modifies both the X-axis through a wavelength adjustment and the Y-axis through a simple regression wavelength by wavelength. The Clone1 procedure used one sample spectrally close to the centre of the population. The six samples used in Clone 6 were selected to cover the range of spectral variation in the sample set. The remaining fifteen samples were used to evaluate the performances of the different models. The predicted values for dry matter, protein and neutral detergent fibre from the master Instrument were considered as “reference Y values” when computing the statistics RMSEP, SEPC, R, Bias, Slope, mean GH (global Mahalanobis distance) and mean NH (neighbourhood Mahalanobis distance) for the 6 slave instruments. From the results we conclude that i) all the calibration techniques gave satisfactory results after standardization. Without standardization the predicted data from the slaves would have required slope and bias correction to produce acceptable statistics. ii) Standardization reduced the errors for all calibration methods and parameters tested, reducing not only systematic biases but also random errors. iii) Standardization removed slope effects that were significantly different from 1.0 in most of the cases. iv) Clone1 and Clone6 gave similar results except for NDF where Clone6 gave better RMSEP values than Clone1. v) GH and NH were reduced by half even with very large data sets including unstandardized spectra.

• The Journal of Society for e-Business Studies
• /
• v.23 no.2
• /
• pp.111-121
• /
• 2018

Many problems in rotating machinery such as aircraft engines, wind turbines and motors are caused by bearing defects. The abnormalities of the bearing can be detected by analyzing signal data such as vibration or noise, proper pre-processing through a few signal processing techniques is required to analyze their frequencies. In this paper, we introduce the condition monitoring method for diagnosing the failure of the rotating machines by analyzing the vibration signal of the bearing. From the collected signal data, the normal states are trained, and then normal or abnormal state data are classified based on the trained normal state. For preprocessing, a Hamming window is applied to eliminate leakage generated in this process, and the cepstrum analysis is performed to obtain the original signal of the signal data, called the formant. From the vibration data of the IMS bearing dataset, we have extracted 6 statistic indicators using the cepstral coefficients and showed that the application of the Mahalanobis distance classifier can monitor the bearing status and detect the failure in advance.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.4
• /
• pp.253-258
• /
• 2016

This paper proposes a method that utilizes optimization approach for localization of an indoor mobile robot. Bayesian filters which have been widely used for localization of a mobile robot use many control parameters to take the uncertainties in measurement and environment into account. The estimation performance depends on the selection of these parameter values. Also, the performance of the Bayesian filters deteriorate as the non-linearity of the motion and measurement increases. On the other hand, the optimization approach uses fewer control parameters and is less influenced by the non-linearity than the Bayesian methods. This paper compares the localization performance of the proposed method with the performance of the extended Kalman filter to verify the feasibility of the proposed method. Measurements of ranges from beacons of ultrasonic satellite to the robot are used for localization. Mahalanobis distance is used for detection and rejection of outlier in the measurements. The optimization method sets performance index as a function of the measured range values, and finds the optimized estimation of the location through iteration. The method can improve the localization performance and reduce the computation time in corporation with Bayesian filter which provides proper initial location for the iteration.