• Korean Chemical Engineering Research
• /
• v.48 no.4
• /
• pp.483-489
• /
• 2010

An image analysis-based soft sensor is designed and applied to automatic quality classification of product appearance with color-textural characteristics. In this work, multiresolutional multivariate image analysis (MR-MIA) is used in order to analyze product images with color as well as texture. Fisher's discriminant analysis (FDA) is also used as a supervised learning method for automatic classification. The use of FDA, one of latent variable methods, enables us not only to classify products appearance into distinct classes, but also to numerically and consistently estimate product appearance with continuous variations and to analyze characteristics of appearance. This approach is successfully applied to automatic quality classification of intermediate and final products in industrial manufacturing of engineered stone countertops.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.1
• /
• pp.53-62
• /
• 2010

This paper introduces a classification algorithm which can be applied to a learning problem with incomplete data sets, missing variable values or a class value. This algorithm uses a data expansion method which utilizes weighted values and probability techniques. It operates by extending a classifier which are considered to be in the optimal projection plane based on Fisher's formula. To do this, some equations are derived from the procedure to be applied to the data expansion. To evaluate the performance of the proposed algorithm, results of different measurements are iteratively compared by choosing one variable in the data set and then modifying the rate of missing and non-missing values in this selected variable. And objective evaluation of data sets can be achieved by comparing, the result of a data set with non-missing variable with that of C4.5 which is a known knowledge acquisition tool in machine learning.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.1
• /
• pp.123-129
• /
• 2017

New mobile phones with high tech-camera and a large size memory have been recently launched and people upload pictures of beautiful scenes or unknown flowers in SNS. This paper develops a flower recognition system that can get information on flowers in the place where mobile communication is not even available. It consists of a registration part for reference flowers and a recognition part based on OpenCV for Android platform. A new color classification method using RGB color channel and K-means clustering is proposed to reduce the recognition processing time. And ORB for feature extraction and Brute-Force Hamming algorithm for matching are used. We use 12 kinds of flowers with four color groups, and 60 images are applied for reference DB design and 60 images for test. Simulation results show that the success rate is 83.3% and the average recognition time is 2.58 s on Huawei ALEUL00 and the proposed system is suitable for a mobile phone without a network.

• Journal of the Korea Convergence Society
• /
• v.9 no.6
• /
• pp.183-190
• /
• 2018

With decreasing the number of high school graduates, it is vital for each college to maintain its enrollment number as well as to preserve its dropout rate in a lower level. It is true that all universities and colleges have experienced inevitable dropouts that were in fact more serious in 2 to 3-year colleges. There have been prior studies to examine what factors affected to students' dropout in various ways. However, no specific programs were employed to mitigate the rates of dropout. In this study, new encouraging program is introduced for the students who were not ready to study and isolated from classroom. The result showed that the program led to the GPA enhancement in larger number of participants. Nevertheless, the sustainablity of the program would be unclear unless it combines with other existing programs.

• The Korean Journal of Ecology
• /
• v.17 no.1
• /
• pp.37-47
• /
• 1994

A study was conducted to examine the leaf expansion forms and to analyze the leaf growth in early growing season of 1992 in a temperate deciduous forest in central region of Korea. After the winter bud scale fell off, the expansion forms of 11 woody species were divided into 3 groups, spreading fan form, opening form from half folding, and unrolling form from main vein. The ratios of leaf area at the end of growing season to that of leaf expantion time varied among species, and were related closely to expansion forms. The leaves reached to full size between the third ten days of April and the middle ten days of May, except for a few species. Leaf weight, however, increased steadily during the growing season. Specific leaf area (SLA) increased rapidly for 10-20 days after leaf expansion and decreased rapidly for 10 days after reaching maximum values, and thereafter decreased slowly. The SLA values of trees were smaller than $200cm^2/g$, but those of subtree and shrub were larger than $200cm^2/g$.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.39 no.3
• /
• pp.32-43
• /
• 2002

In this paper, we propose a pattern classification system for digital signal which is based on neural networks. The proposed system consists of two models of neural network. The first part is a wavelet neural network whose role is a feature extraction. For this part, we compare existing models of wavelet networks and propose a new model for feature extraction. The other part is a wavelet network for pattern classification. We modify the structure of previous wavelet network for pattern classification and propose a learning method. The inputs of the pattern classification wavelet network is connection weights, dilation and translation parameters in hidden nodes of feature extraction network. And the output is a class of the signal which is input of feature extraction network. The proposed system is, applied to classification of EEG signal based on frequency.

• 전자공학회논문지 IE
• /
• v.43 no.2
• /
• pp.80-86
• /
• 2006

The wireless communication based on LDPC and adaptive spatial-subcarrier coded modulation using MQAM for orthogonal frequency division multiplexing (OFDM) wireless transmission by using instantaneous channel state information and employing multiple antennas at both the transmitter and the receiver. Adaptive coded modulation is a promising idea for bandwidth-efficient transmission on time-varying, narrowband wireless channels. On power limited Additive White Gaussian Noise (AWGN) channels, low density parity check (LDPC) codes are a class of error control codes which have demonstrated impressive error correcting qualities, under some conditions performing even better than turbo codes. The paper demonstrates OFDM with LDPC and adaptive modulation applied to Multiple-Input Multiple-Output (MIMO) system. An optimization algorithm to obtain a bit and power allocation for each subcarrier assuming instantaneous channel knowledge is used. The experimental results are shown the potential of our proposed system.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.27 no.3
• /
• pp.13-20
• /
• 1990

This paper describes an interframe image coding using motion compensated and classified vector quantizer (MC-CVQ). It is essential to carefully encode blocks with significant pels in motion compensated vector quantizers (MCVQ). In this respect, we propose a new CVQ algorithm which is appropriate to the coding of interframe prediction error after motion compensation. In order to encode an image efficiently at a low bit rate, we partition each block, which is the processing element in MC, into equally sized 4 vectors, and classify vectors into 15 classes according to the position of significant pels. Vectors in each class are then encoded by the vector quantizer with the codebook independently designed for the class. The computer simulation shows that the signal-to-noise ratio and the average bit rate of MC-CVQ are 35-37dB and 0.2-0.25bit/pel, respectively, for the videophone or video conference type image.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.40 no.5
• /
• pp.303-311
• /
• 2003

Since the MPEG-4 visual standard enables content-based functionalities, it is necessary to extract video object from natural video sequences. Segmentation algorithms can largely be classified into automatic segmentation and user-assisted segmentation. In this paper, we propose a user-assisted VOP generation method based on the geometric active contour. Since the geometric active contour, unlike the parametric active contour, employs the level set method to evolve the curve, we can draw the initial curve independent of the shape of the object. In order to generate the edge function from a smoothed image, we propose a vector-valued diffusion process in the LUV color space. We also present a discrete 3-D diffusion model for easy implementation. By combining the curve shrinkage in the vector field space with the curve expansion in the empty vector space, we can make accurate extraction of visual objects from video sequences.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.2 s.34
• /
• pp.113-121
• /
• 2005

In this paper, we design the hybrid learning algorithm of LVQ which is to perform EMG pattern recognition. The proposed hybrid LVQ learning algorithm is the modified Counter Propagation Networks(C.p Net. ) which is use SOM to learn initial reference vectors and out-star learning algorithm to determine the class of the output neurons of LVa. The weights of the proposed C.p. Net. which is between input layer and subclass layer can be learned to determine initial reference vectors by using SOM algorithm and to learn reference vectors by using LVd algorithm, and pattern vectors is classified into subclasses by neurons which is being in the subclass layer, and the weights which is between subclass layer and class layer of C.p. Net. is learned to classify the classified subclass. which is enclosed a class . To classify the pattern vectors of EMG. the proposed algorithm is simulated with ones of the conventional LVQ, and it was a confirmation that the proposed learning method is more successful classification than the conventional LVQ.