• Journal of Korea Multimedia Society
• /
• v.16 no.7
• /
• pp.870-878
• /
• 2013

In this paper, we propose a novel fingerprint classification method to enhance the accuracy and efficiency of the fingerprint identification system, one of biometrics systems. According to the previous researches, fingerprints can be categorized into the several patterns based on their pattern of ridges and valleys. After construction of fingerprint database based on their patters, fingerprint classification approach can help to accelerate the fingerprint recognition. The reason is that classification methods reduce the size of the search space to the fingerprints of the same category before matching. First, we suggest a method to extract region of interest (ROI) which have real information about fingerprint from the image. And then we propose a feature extraction method which combines gray level co-occurrence matrix (GLCM) and wavelet features. Finally, we compare the performance of our proposed method with the existing method which use only GLCM as the feature of fingerprint by using the multi-layer perceptron and support vector machine.

• Journal of Advanced Navigation Technology
• /
• v.24 no.1
• /
• pp.47-52
• /
• 2020

Direction of arrival (DoA) estimation is a scheme of estimating the directions of targets by analyzing signals generated or reflected from the targets and is used in various fields. Artificial neural networks (ANN) is a field of machine learning that mimics the neural network of living organisms. They show good performance in pattern recognition. Although researches has been using ANNs to estimate the DoAs, there are limitationsin dealing with variations of the signal-to-noise ratio (SNR) of the target signals. In this paper, we propose a three-stage ANN algorithm for DoA estimation. The proposed algorithm can minimize the performance reduction by applying the model trained in a single SNR environment to various environments through a 'noise reduction process'. Furthermore, the scheme reduces the difficulty in learning and maintains efficiency in estimation, by employing a process of DoA shift. We compare the performance of the proposed algorithm with Cramer-Rao bound (CRB) and the performances of existing subspace-based algorithms and show that the proposed scheme exhibits better performance than other schemes in some severe environments such as low SNR environments or situations in which targets are located very close to each other.

• Proceedings of the Microbiological Society of Korea Conference
• /
• 2009.05a
• /
• pp.78-78
• /
• 2009

$^1H$ NMR spectroscopy coupled with multivariate statistical analysis was used for the first time to investigate metabolic changes in musts during alcoholic fermentation and wines during ageing. Three Saccharomyces cerevisiae yeast strains (RC-212, KIV-1116 and KUBY-501) were also evaluated for their impacts on the metabolic changes in must and wine. Pattern recognition (PR) methods, including PCA, PLS-DA and OPLS-DA scores plots, showed clear differences for metabolites among musts or wines for each fermentation stage up to 6 months. Metabolites responsible for the differentiation were identified to valine, 2,3-butanediol (2,3-BD), pyruvate, succinate, proline, citrate, glycerol, malate, tartarate, glucose, N-methylnicotinic acid (NMNA), and polyphenol compounds. PCA scores plots showed continuous movements away from days 1 to 8 in all musts for all yeast strains, indicating continuous and active fermentation. During alcoholic fermentation, highest levels of 2,3-BD, succinate and glycerol were found in musts with the KIV-1116 strain, which showed the fastest fermentation or highest fermentative activity of the 3 strains, whereas the KUBY-501 strain showed the slowest fermentative activity. This study highlights the applicability of NMR-based metabolomics for monitoring wine fermentation and evaluating the fermentative characteristics of yeast strains.

• Journal of KIISE:Software and Applications
• /
• v.32 no.5
• /
• pp.416-427
• /
• 2005

Web navigation mining is a method of discovering Web navigation patterns by analyzing the Web access log data. However, it is admitted that the log data contains noisy information that leads to the incorrect recognition of user navigation path on the Web's hyperlink structure. As a result, previous Web navigation mining systems that exploited solely the log data have not shown good performance in discovering correct Web navigation patterns efficiently, mainly due to the complex pre-processing procedure. To resolve this problem, this paper proposes a technique of amalgamating the Web's hyperlink structure information with the Web access log data to discover navigation patterns correctly and efficiently. Our implemented Web navigation mining system called SPMiner produces a WebTree from the hyperlink structure of a Web site that is used trl eliminate the possible noises in the Web log data caused by the user's abnormal navigational activities. SPMiner remarkably reduces the pre-processing overhead by using the structure of the Web, and as a result, it could analyze the user's search patterns efficiently.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.4C
• /
• pp.388-396
• /
• 2009

This paper proposes a new fire-smoke detection method by using extracted features from camera images and pattern recognition technique. First, moving regions are detected by analyzing the frame difference between two consecutive images and generate candidate smoke regions by applying smoke color model. A smoke region generally has a few characteristics such as similar color, simple texture and upward motion. From these characteristics, we extract brightness, wavelet high frequency and motion vector as features. Also probability density functions of three features are generated using training data. Probabilistic models of smoke region are then applied to observation nodes of our proposed Dynamic Bayesian Networks (DBN) for considering time continuity. The proposed algorithm was successfully applied to various fire-smoke tasks not only forest smokes but also real-world smokes and showed better detection performance than previous method.

• The Journal of the Korea Contents Association
• /
• v.6 no.12
• /
• pp.105-112
• /
• 2006

In this study, we propose a simple preprocessing method for classification of basal cell carcinoma (BCC), which is one of the most common skin cancer. The preprocessing step consists of data clipping with a half Hanning window and dimension reduction with principal components analysis (PCA). The application of the half Hanning window deemphasizes the peak near $1650cm^{-1}$ and improves classification performance by lowering the false negative ratio. Classification results with various classifiers are presented to show the effectiveness of the proposed method. The classifiers include maximum a posteriori probability (MAP), k-nearest neighbor (KNN), probabilistic neural network (PNN), multilayer perceptron(MLP), support vector machine (SVM) and minimum squared error (MSE) classification. Classification results with KNN involving 216 spectra preprocessed with the proposed method gave 97.3% sensitivity, which is very promising results for automatic BCC detection.

• Journal of Biosystems Engineering
• /
• v.36 no.1
• /
• pp.40-47
• /
• 2011

Image analysis algorithm for the quality evaluation of ginseng seedling was investigated. The images of ginseng seedling were acquired with a color CCD camera and processed with the image analysis methods, such as binary conversion, labeling, and thinning. The processed images were used to calculate the length and weight of ginseng seedlings. The length and weight of the samples could be predicted with standard errors of 0.343 mm, and 0.0214 g respectively, $R^2$ values of 0.8738 and 0.9835 respectively. For the evaluation of the three quality grades of Gab, Eul, and abnormal ginseng seedlings, features from the processed images were extracted. The features combined with the ratio of the lengths and areas of the ginseng seedlings efficiently differentiate the abnormal shapes from the normal ones of the samples. The grade levels were evaluated with an efficient pattern recognition method of support vector machine analysis. The quality grade of ginseng seedling could be evaluated with an accuracy of 95% and 97% for training and validation, respectively. The result indicates that color image analysis with support vector machine algorithm has good potential to be used for the development of an automatic sorting system for ginseng seedling.

• The Korean Journal of Applied Statistics
• /
• v.16 no.2
• /
• pp.321-333
• /
• 2003

Self-organizing map (SOM), a unsupervised learning neural network, has been developed by T. Kohonen since 1980's. Main application areas were pattern recognition and text retrieval. Because of that, it has not been spread to statisticians until late. Recently, SOM's are frequently drawn in data mining fields. Kohonen's SOM, however, needs improvements to become a statistician's standard tool. First, there should be a good guideline as for the size of map. Second, an enhanced visualization mode is wanted. In this study, principal components self-organizing map (PC-SOM), a modification of Kohonen's SOM, is proposed to meet such needs. PC-SOM performs one-dimensional SOM during the first stage to decompose input units into node weights and residuals. At the second stage, another one-dimensional SOM is applied to the residuals of the first stage. Finally, by putting together two stages, one obtains two-dimensional SOM. Such procedure can be easily expanded to construct three or more dimensional maps. The number of grid lines along the second axis is determined automatically, once that of the first axis is given by the data analyst. Furthermore, PC-SOM provides easily interpretable map axes. Such merits of PC-SOM are demonstrated with well-known Fisher's iris data and a simulated data set.

• Biomolecules & Therapeutics
• /
• v.20 no.5
• /
• pp.433-445
• /
• 2012

During the course of evolution, animals encountered the harmful effects of fungi, which are strong pathogens. Therefore, they have developed powerful mechanisms to protect themselves against these fungal invaders. ${\beta}$-Glucans are glucose polymers of a linear ${\beta}$(1,3)-glucan backbone with ${\beta}$(1,6)-linked side chains. The immunostimulatory and antitumor activities of ${\beta}$-glucans have been reported; however, their mechanisms have only begun to be elucidated. Fungal and particulate ${\beta}$-glucans, despite their large size, can be taken up by the M cells of Peyer's patches, and interact with macrophages or dendritic cells (DCs) and activate systemic immune responses to overcome the fungal infection. The sampled ${\beta}$-glucans function as pathogen-associated molecular patterns (PAMPs) and are recognized by pattern recognition receptors (PRRs) on innate immune cells. Dectin-1 receptor systems have been incorporated as the PRRs of ${\beta}$-glucans in the innate immune cells of higher animal systems, which function on the front line against fungal infection, and have been exploited in cancer treatments to enhance systemic immune function. Dectin-1 on macrophages and DCs performs dual functions: internalization of ${\beta}$-glucan-containing particles and transmittance of its signals into the nucleus. This review will depict in detail how the physicochemical nature of ${\beta}$-glucan contributes to its immunostimulating effect in hosts and the potential uses of ${\beta}$-glucan by elucidating the dectin-1 signal transduction pathway. The elucidation of ${\beta}$-glucan and its signaling pathway will undoubtedly open a new research area on its potential therapeutic applications, including as immunostimulants for antifungal and anti-cancer regimens.

• Journal of Plant Biotechnology
• /
• v.38 no.1
• /
• pp.9-14
• /
• 2011

To determine whether pattern recognition based on metabolite fingerprinting for whole cell extracts can be used to discriminate cultivars metabolically, leaves of nine commercial Orostachys plants were subjected to Fourier transform infrared spectroscopy (FT-IR). FT-IR spectral data from leaves were analyzed by principal component analysis (PCA) and Partial least square discriminant analysis (PLS-DA). The dendrogram based on hierarchical clustering analysis of these PLS-DA data separated the nine Orostachys species into five major groups. The first group consisted of O. iwarenge 'Yimge', 'Jeju', 'Jeongsun' and O. margaritifolius 'Jinju' whereas in the second group, 'Sacheon' was clustered with 'Busan,' both of which belong to O. malacophylla species. However, 'Samchuk', belong to O. malacophylla was not clustered with the other O. malacophylla species. In addition, O. minuta and O. japonica were separated to the other Orostachys plants. Thus we suggested that the hierarchical dendrogram based on PLS-DA of FT-IR spectral data from leaves represented the most probable chemotaxonomical relationship between commercial Orostachys plants. Furthermore these metabolic discrimination systems could be applied for reestablishment of precise taxonomic classification of commercial Orostachys plants.