• International Journal of Contents
• /
• v.8 no.4
• /
• pp.56-63
• /
• 2012

In recent decades, analyzing the activities of human brain achieved some accomplishments by using the functional Magnetic Resonance Imaging (fMRI) technique. fMRI data provide a sequence of three-dimensional images related to human brain's activity which can be used to detect instantaneous cognitive states by applying machine learning methods. In this paper, we propose a new approach for distinguishing human's cognitive states such as "observing a picture" versus "reading a sentence" and "reading an affirmative sentence" versus "reading a negative sentence". Since fMRI data are high dimensional (about 100,000 features in each sample), extremely sparse and noisy, feature selection is a very important step for increasing classification accuracy and reducing processing time. We used the Fisher Discriminant Ratio to select the most powerful discriminative features from some Regions of Interest (ROIs). The experimental results showed that our approach achieved the best performance compared to other feature extraction methods with the average accuracy approximately 95.83% for the first study and 99.5% for the second study.

• Smart Media Journal
• /
• v.5 no.1
• /
• pp.30-37
• /
• 2016

In recent decades, the study of human brain function has dramatically increased thanks to the advent of Functional Magnetic Resonance Imaging. This is a powerful tool which provides a deep view of the activities of the brain. From fMRI data, the neuroscientists analyze which parts of the brain have responsibility for a particular action and finding the common pattern representing each state involved in these tasks. This is one of the most challenges in neuroscience area because of noisy, sparsity of data as well as the differences of anatomical brain structure of each person. In this paper, we propose the use of appropriate discriminant methods, such as Fisher Discriminant Ratio and hypothesis testing, together with strong boosting ability of Adaboost classifier. We prove that discriminant methods are effective in classifying cognitive states. The experiment results show significant better accuracy than previous works. We also show that it is possible to train a successful classifier without prior anatomical knowledge and use only a small number of features.

• Geomechanics and Engineering
• /
• v.13 no.5
• /
• pp.861-879
• /
• 2017

Coal and gas outburst is a serious dynamic disaster that occurs during coal mining and threatens the lives of coal miners. Currently, coal and gas outburst is commonly predicted using single indicator and its critical value. However, single indicator is unable to fully reflect all of the factors impacting outburst risk and has poor prediction accuracy. Therefore, a more accurate prediction method is necessary. In this work, we first analyzed on-site impacting factors and precursors of coal and gas outburst; then, we constructed a Fisher discriminant analysis (FDA) index system using the gas adsorption index of drilling cutting ${\Delta}h_2$, the drilling cutting weight S, the initial velocity of gas emission from borehole q, the thickness of soft coal h, and the maximum ratio of post-blasting gas emission peak to pre-blasting gas emission $B_{max}$; finally, we studied an FDA-based multiple indicators discriminant model of coal and gas outburst, and applied the discriminant model to predict coal and gas outburst. The results showed that the discriminant model has 100% prediction accuracy, even when some conventional indexes are lower than the warning criteria. The FDA method has a broad application prospects in coal and gas outburst prediction.

• MALSORI
• /
• no.64
• /
• pp.77-88
• /
• 2007

Nowadays, mel-frequency cesptral coefficients (MFCCs) and Gaussian mixture models (GMMs) are used for the pathological voice detection. This paper suggests a method to improve the performance of the pathological/normal voice classification based on the MFCC-based GMM. We analyze the characteristics of the mel frequency-based filterbank energies using the fisher discriminant ratio (FDR). And the feature vectors through the linear discriminant analysis (LDA) transformation of the filterbank energies (FBE) and the MFCCs are implemented. An accuracy is measured by the GMM classifier. This paper shows that the FBE LDA-based GMM is a sufficiently distinct method for the pathological/normal voice classification, with a 96.6% classification performance rate. The proposed method shows better performance than the MFCC-based GMM with noticeable improvement of 54.05% in terms of error reduction.

• Proceedings of the KSPS conference
• /
• 2007.05a
• /
• pp.123-126
• /
• 2007

This paper suggests a method to improve the performance of the pathological/normal voice classification. The effectiveness of the mel frequency-based filter bank energies using the fisher discriminant ratio (FDR) is analyzed. And mel frequency cepstrum coefficients (MFCCs) and the feature vectors through the linear discriminant analysis (LDA) transformation of the filter bank energies (FBE) are implemented. This paper shows that the FBE LDA-based GMM is more distinct method for the pathological/normal voice classification than the MFCC-based GMM.

• Proceedings of the Korean Society of Near Infrared Spectroscopy Conference
• /
• 2001.06a
• /
• pp.1244-1244
• /
• 2001

In linear discriminant analysis there are two important properties concerning the effectiveness of discriminant function modeling. The first is the separability of the discriminant function for different classes. The separability reaches its optimum by maximizing the ratio of between-class to within-class variance. The second is the stability of the discriminant function against noises present in the measurement variables. One can optimize the stability by exploring the discriminant variates in a principal variation subspace, i. e., the directions that account for a majority of the total variation of the data. An unstable discriminant function will exhibit inflated variance in the prediction of future unclassified objects, exposed to a significantly increased risk of erroneous prediction. Therefore, an ideal discriminant function should not only separate different classes with a minimum misclassification rate for the training set, but also possess a good stability such that the prediction variance for unclassified objects can be as small as possible. In other words, an optimal classifier should find a balance between the separability and the stability. This is of special significance for multivariate spectroscopy-based classification where multicollinearity always leads to discriminant directions located in low-spread subspaces. A new regularized discriminant analysis technique, the principal discriminant variate (PDV) method, has been developed for handling effectively multicollinear data commonly encountered in multivariate spectroscopy-based classification. The motivation behind this method is to seek a sequence of discriminant directions that not only optimize the separability between different classes, but also account for a maximized variation present in the data. Three different formulations for the PDV methods are suggested, and an effective computing procedure is proposed for a PDV method. Near-infrared (NIR) spectra of blood plasma samples from mastitic and healthy cows have been used to evaluate the behavior of the PDV method in comparison with principal component analysis (PCA), discriminant partial least squares (DPLS), soft independent modeling of class analogies (SIMCA) and Fisher linear discriminant analysis (FLDA). Results obtained demonstrate that the PDV method exhibits improved stability in prediction without significant loss of separability. The NIR spectra of blood plasma samples from mastitic and healthy cows are clearly discriminated between by the PDV method. Moreover, the proposed method provides superior performance to PCA, DPLS, SIMCA and FLDA, indicating that PDV is a promising tool in discriminant analysis of spectra-characterized samples with only small compositional difference, thereby providing a useful means for spectroscopy-based clinic applications.

• Proceedings of the Korean Society of Near Infrared Spectroscopy Conference
• /
• 2001.06a
• /
• pp.1042-1042
• /
• 2001

In linear discriminant analysis there are two important properties concerning the effectiveness of discriminant function modeling. The first is the separability of the discriminant function for different classes. The separability reaches its optimum by maximizing the ratio of between-class to within-class variance. The second is the stability of the discriminant function against noises present in the measurement variables. One can optimize the stability by exploring the discriminant variates in a principal variation subspace, i. e., the directions that account for a majority of the total variation of the data. An unstable discriminant function will exhibit inflated variance in the prediction of future unclassified objects, exposed to a significantly increased risk of erroneous prediction. Therefore, an ideal discriminant function should not only separate different classes with a minimum misclassification rate for the training set, but also possess a good stability such that the prediction variance for unclassified objects can be as small as possible. In other words, an optimal classifier should find a balance between the separability and the stability. This is of special significance for multivariate spectroscopy-based classification where multicollinearity always leads to discriminant directions located in low-spread subspaces. A new regularized discriminant analysis technique, the principal discriminant variate (PDV) method, has been developed for handling effectively multicollinear data commonly encountered in multivariate spectroscopy-based classification. The motivation behind this method is to seek a sequence of discriminant directions that not only optimize the separability between different classes, but also account for a maximized variation present in the data. Three different formulations for the PDV methods are suggested, and an effective computing procedure is proposed for a PDV method. Near-infrared (NIR) spectra of blood plasma samples from daily monitoring of two Japanese cows have been used to evaluate the behavior of the PDV method in comparison with principal component analysis (PCA), discriminant partial least squares (DPLS), soft independent modeling of class analogies (SIMCA) and Fisher linear discriminant analysis (FLDA). Results obtained demonstrate that the PDV method exhibits improved stability in prediction without significant loss of separability. The NIR spectra of blood plasma samples from two cows are clearly discriminated between by the PDV method. Moreover, the proposed method provides superior performance to PCA, DPLS, SIMCA md FLDA, indicating that PDV is a promising tool in discriminant analysis of spectra-characterized samples with only small compositional difference.

• Smart Structures and Systems
• /
• v.23 no.1
• /
• pp.71-79
• /
• 2019

In general, it may be advantageous to measure the pressure pulsation near a valve to detect a valve defect in a linear compressor. However, the acceleration signals are more advantageous for rapid classification in a mass-production line. This paper deals with the performance improvement of fault classification using only the compressor-shell acceleration signal based on the relation between the refrigerant pressure pulsation and the shell acceleration of the compressor. A transfer function was estimated experimentally to take into account the signal noise ratio between the pressure pulsation of the refrigerant in the suction pipe and the shell acceleration. The shell acceleration signal of the compressor was modified using this transfer function to improve the defect classification performance. The defect classification of the modified signal was evaluated in the acceleration signal in the frequency domain using Fisher's discriminant ratio (FDR). The defect classification method was validated by experimental data. By using the method presented, the classification of valve defects can be performed rapidly and efficiently during mass production.

• Proceedings of the IEEK Conference
• /
• 2002.07c
• /
• pp.1674-1677
• /
• 2002

In this paper, the new method to extract the features of iris signals is proposed; Multiresolution ICA (M-ICA) provides good properties to represent signals with time-frequency. The conventional methods were to use the technique of filter bank analysis, while ICA is unsupervised learning algorithm using high-order statistics. M-ICA could make use of strengths of learn- ing method and multiresolution. Also, we performed comparative studies of different feature extraction techniques applied to personal identification using iris pat- tern. To measure goodness of methods, we use Fisher’s discriminant ratio to quantify the class-separability of features generated by various techniques.

• Journal of Institute of Control, Robotics and Systems
• /
• v.15 no.1
• /
• pp.94-98
• /
• 2009

In this paper, we deal with a face recognition method for the emotional face images. Since the face recognition is one of the most natural and straightforward biometric methods, there have been various research works. However, most of them are focused on the expressionless face images and have had a very difficult problem if we consider the facial expression. In real situations, however, it is required to consider the emotional face images. Here, three basic human emotions such as happiness, sadness, and anger are investigated for the face recognition. And, this situation requires a robust face recognition algorithm then we use a fuzzy Fisher's Linear Discriminant (FLD) algorithm with the wavelet transform. The fuzzy Fisherface is a statistical method that maximizes the ratio of between-scatter matrix and within-scatter matrix and also handles the fuzzy class information. The experimental results obtained for the CBNU face databases reveal that the approach presented in this paper yields better recognition performance in comparison with the results obtained by other recognition methods.