• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.45 no.5
• /
• pp.15-24
• /
• 2008

For high-dimensional classification tasks, such as face recognition, the number of samples is smaller than the dimensionality of the samples. In such cases, a problem encountered in linear discriminant analysis-based methods for dimension reduction is what is known as the small sample size (SSS) problem. Recently, to solve the SSS problem, a way of employing a dissimilarity-based classification(DBC) has been investigated. In DBC, an object is represented based on the dissimilarity measures among representatives extracted from training samples instead of the feature vector itself. In this paper, we propose a new method of optimizing DBCs using multi-level fusion strategies(MFS), in which fusion strategies are employed to represent features as well as to design classifiers. Our experimental results for benchmark face databases demonstrate that the proposed scheme achieves further improved classification accuracies.

• KIISE Transactions on Computing Practices
• /
• v.21 no.6
• /
• pp.424-429
• /
• 2015

This research proposes a new system for calculating the total amount of coins in an image. The proposed system identified and classified the coins in the image in realtime. The image was obtained using a USB camera. Most previous coin calculation systems only used size information. If the size of an object was incorrectly detected, it caused a misclassification. Especially, in case of the former 10 won, it had high error rate because it was similar in size to the 50 won and 100 won coin. The proposed system combines hue histogram information with size information to reduce errors in the classification process. When we only used size information in the classification experiment of 2,290 coins, the recognition rate was on average about 88.2%. When we combined hue information with size information the recognition rate increased to about 99.3%.

• The Journal of Sustainable Design and Educational Environment Research
• /
• v.11 no.2
• /
• pp.28-37
• /
• 2012

The purpose of this study is to suggest improvement plans of School Green Building Certification System by comparing items of domestic system with those of foreign system. Especially, we focused on school use classification. Use classification of Green Building Certification System must be based on Building Codes and reflect the nature of building use and size. Schools are divided into three groups ; preschool, school(elementary, junior high school, high school), university and ect. Also they must be set up assessment method reflecting the nature of school use and size.

• Proceedings of the Safety Management and Science Conference
• /
• 2007.04a
• /
• pp.125-132
• /
• 2007

The purpose of this study is to provide foot classification on young men and women by factor analysis. The sample for this work was chosen from data which were collected and measured by Size Korea during two years ($2003{\sim}2004$). In order to analyze and compare features of the foot of young men and women, analysis was performed about 911 subjects (male: 467, female: 444) on 24 parts such as height (8 parts), width (5 parts), thickness (1 part), circumference (3 parts), length (3 parts) and angle (4 parts). The result of this study can be applied in manufacturing and design of shoes and socks. Also, it will enable us to have fruitful information on considerable items during manufacturing and design of shoes and socks.

• Journal of the Korean Wood Science and Technology
• /
• v.49 no.4
• /
• pp.328-335
• /
• 2021

Considerable differences exist in the characteristics of size reduction and classification because of biomass species. Miscanthus sacchariflorus (M. sacchariflorus) Goedae-Uksae 1 is not used efficiently because of the imperfections of the processing technology for this biomass. Therefore, for the best use of specific biomass, improvement in the feedstock preparation of the biomass for processing, such as pellet manufacturing, is necessary. In this study, a laboratory-scale cone grinder and air classifier were designed and combined to investigate the performance of the combination system for M. sacchariflorus. The average equivalent spherical diameter of particles showed a close relationship with air velocity for air classification. The air velocity range to classify proper particles for pelletization was determined to be 6.0-6.8 m/s. The mass ratios of the collected particles to feed mass for four lengths of chopped M. sacchariflorus were 45.1%:46.1%, 39.1%:46.6%, and 44.1%:52.8% at the first, second, and third steps in simulating the multistep combination system, respectively.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.26 no.10
• /
• pp.1443-1454
• /
• 2002

The purposes of this study were to classify body type of adult males into several kind of shape and to provide the characteristics of size of each group which has same shape. As the sample, subjects were 1290 males of 20 to 54 year-old. The procedure and results were follows; 1. As the result of the previous reserch, the front line of body was classified in X, H, Y and A types. 2. The principal component analysis was used to obtain the shape factor of the side line of the trunk. 9 factors in the side were extracted. As the result of the cluster analysis of factor scores, the side line of body was classified in 5 types. It was named X, A, Y and H type in the front and S, D1, d, I and D2 type in the side. 3. In order to consider the shape of body as a whole, the body shape of the front and side were compounded. The whole body shapes of adult male were very various, and 6 body shapes, XS, YS, Yd, YI, AD2 and HD1 were selected as the basic types. In each type of body, several groups were classified by size factor, height and chest girth and master size was selected considering appearance frequency.

• Journal of the Korean Society for Library and Information Science
• /
• v.40 no.2
• /
• pp.415-434
• /
• 2006

This study aim to develop a classification system to classify the descriptors, which is been in korean literatures. Firstly this classification structure is categorized on six facets and the classification system is constructed on a deductive method based on korean literature knowledge. The study compared the classification system with various thesaurus's classification system in humane studies and by the comparison, the classification system of korean literature's terms find out having some merits as using the facet method. On account of these merits the classification system has achieved a consistency of categorization independently and reduced a complexity of classification structure. And by categorizing the common categories, the study has reduced the size of schedules. Finally, the classification system has advanced the structure in the process of classifying the descriptors.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2008.11a
• /
• pp.241-242
• /
• 2008

• The Journal of the Korea Contents Association
• /
• v.14 no.10
• /
• pp.463-471
• /
• 2014

In this paper, emotion classification was performed by using four ocular features extracted from near-infrared camera image. According to comparing with previous work, the proposed method used more ocular features and each feature was validated as significant one in terms of emotion classification. To minimize side effects on ocular features caused by using visual stimuli, auditory stimuli for causing two opposite emotion pairs such as "positive-negative" and "arousal-relaxation" were used. As four features for emotion classification, pupil size, pupil accommodation rate, blink frequency, and eye cloased duration were adopted which could be automatically extracted by using lab-made image processing software. At result, pupil accommodation rate and blink frequency were statistically significant features for classification arousal-relaxation. Also, eye closed duration was the most significant feature for classification positive-negative.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.05a
• /
• pp.229-232
• /
• 2008

A Neural network classification of human activity data is presented. The data acquisition system involves a tri-axial accelerometer in wireless sensor network environment. The wireless ad-hoc system has the advantage of small size, convenience for wearability and cost effectiveness. The system can further improve the range of user mobility with the inclusion of ad-hoc environment. The classification is based on the frequencies of the involved activities. The most significant Fast Fourier coefficients, of the acceleration of the body movement, are used for classification of the daily activities like, Rest walk and Run. A supervised learning approach is used. The work presents classification accuracy with the available fast batch training algorithms i.e. Levenberg-Marquardt and Resilient back propagation scheme is used for training and calculation of accuracy.