• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.11
• /
• pp.2365-2373
• /
• 2011

This paper propose the hardware IP of real-time face detection system for mobile devices and digital cameras required for high speed, smaller size and lower power. The proposed face detection system is robust against illumination changes, face size, and various face angles as the main cause of the face detection performance. Input image is transformed to LBP(Local Binary Pattern) image to obtain face characteristics robust against illumination changes, and detected the face using face feature data that was adopted to learn and generate in the various face angles using the Adaboost algorithm. The proposed face detection system can be detected maximum 36 faces at the input image size of QVGA($320{\times}240$), and designed by Verilog-HDL. Also, it was verified hardware implementation by using Virtex5 XC5VLX330 FPGA board and HD CMOS image sensor(CIS) for FPGA verification.

• Journal of KIISE:Computer Systems and Theory
• /
• v.37 no.6
• /
• pp.354-367
• /
• 2010

There are many methods for analyzing patterns in time series data. Although stock data represents a time series, there are few studies on stock pattern analysis and prediction. Since people believe that stock price changes randomly we cannot predict stock prices using a scientific method. In this paper, we measured the degree of the randomness of stock prices using Kolmogorov complexity, and we showed that there is a strong correlation between the degree and the accuracy of stock price prediction using our semi-global alignment method. We transformed the stock price data to quantized string sequences. Then we measured randomness of stock prices using Kolmogorov complexity of the string sequences. We use KOSPI 690 stock data during 28 years for our experiments and to evaluate our methodology. When a high Kolmogorov complexity, the stock price cannot be predicted, when a low complexity, the stock price can be predicted, but the prediction ratio of stock price changes of interest to investors, is 12% prediction ratio for short-term predictions and a 54% prediction ratio for long-term predictions.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.14 no.3
• /
• pp.139-146
• /
• 2014

This paper proposes an efficient method for automatically distinguishing various facial expressions. To recognize the emotions from facial expressions, the facial images are obtained by digital cameras, and a number of feature points were extracted. The extracted feature points are then transformed to 49-dimensional feature vectors which are robust to scale and translational variations, and the facial emotions are recognized by statistical pattern classifiers such Naive Bayes, MLP (multi-layer perceptron), and SVM (support vector machine). Based on the experimental results with 5-fold cross validation, SVM was the best among the classifiers, whose performance was obtained by 50.8% for 6 emotion classification, and 78.0% for 3 emotions.

• Journal of Korean Society for Geospatial Information Science
• /
• v.23 no.1
• /
• pp.39-45
• /
• 2015

The housing market is transformed by a variety of socio-economic characteristics, also appeared differently according to regional characteristics. This study aims to draw out the change factors influencing on the housing market structure and to analyze the drawn factors' distribution pattern by area. For this purpose, First, targeting 251 areas in the units of city, county and districts nationwide, this study drew out demographic, socio-economic variables influencing on the housing market structure for 5 years ranging 2005 to 2010. For that, the factor analysis was conducted. Second, this study grasped the change factors of the housing market structure's spatial patterns using the kriging method, a spatial statistical method. Third, this study used the Moran I, one of spatial autocorrelation analysis methods in order to grasp whether the factors had statistically significant concentration or dispersion or showed a random distribution pattern.

• Journal of Korean Society for Geospatial Information Science
• /
• v.17 no.3
• /
• pp.41-48
• /
• 2009

This study investigated the characteristics of spatial expansion/centralization and the spatial structural change of urban. The data used in analysis were urban population, employment, building floor area, and land price. The analysis was performed for the data of 1995, 2000, and 2005 during 10 years after 1995. The method of research was as follows; The movement of mean center and standard distance/standard deviation ellipse was estimated to investigate the urban growth change. The result of Moran's I analysis showed a clustered pattern, not a dispersed pattern, however; the effect was not significant. The town area requires the well-ordered urban planning such as land use. The contours map demonstrates that a monopole structure was generally transformed into a multicentralization structure. The development of mutural connection axis among central street roads was fragile.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.8
• /
• pp.85-93
• /
• 2011

In this paper, we analyzed the function elements of the Integrated meter reading system based on PLC which is working in Mok-dong, Seoul and studied how to improve the vulnerability. Also we propose an efficient method for the estimation of abnormal life status through frequency domain processing of utility meter readings. We found out that even after removing the high-frequency components from the raw meter data, the shape of the graph still maintains the original graph characteristics. The graph of the inverse transformed data has simpler and smoother curve than the original graph pattern. The original graph is not good to be used in deciding whether the residence's life pattern is normal or not. We could find out that the graph which is processed frequency signal has simple and intuitive graph pattern.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.5
• /
• pp.1047-1054
• /
• 2012

Atrial fibrillation (AF) is the most common arrhythmia encountered in clinical practice, and its risk increases with age. Conventionally, the way of detecting AF was the time·frequency domain analysis of RR variability. However, the detection of ECG signal is difficult because of the low amplitude of the P wave and the corruption by the noise. Also, the time·frequency domain analysis of RR variability has disadvantage to get the details of irregular RR interval rhythm. In this study, we describe an atrial fibrillation pattern analysis based on symbolization and information entropy. We transformed RR interval data into symbolic sequence through differential partition, analyzed RR interval pattern, quantified the complexity through Shannon entropy and detected atrial fibrillation. The detection algorithm was tested using the threshold between 10ms and 100ms on two databases, namely the MIT-BIH Atrial Fibrillation Database.

• Journal of the Korean Society of Costume
• /
• v.55 no.7 s.98
• /
• pp.142-155
• /
• 2005

This study shows historical Gagye(가계) The process of change and Characteristics through analysis on the old documents, related papers, and visual data, and represents its meaning in Korean Clothing history through analysis on originality of Korean Gagye(가계) style. Gagye(가계) is the cubic hair style which add other accessories on hair and is divided into two; Gagye(가계) and Chegye(체계) according to its material, role, and function. And Korean Gagye(가계) has been transformed suited to the times and showed various features according to pattern, wearing, and decoration aspect. In its style aspect, Korean Gagye(가계) style shows Hwangye type, Sseugae type, Gogye type, Dagye type, and Braided & coiled hair type. Each shows historical features. In its Wearing aspect, Gagye(가계) style shows Wearing ornamental hairpin on the head, Wearing Rag Ribbon on the head, and Attaching (Detaching) Wearing. And in its Decoration aspect, Gagye(가계) style shows decoration with accessories, one with flower arrangement, and one with shaking.

• Journal of the Korea Furniture Society
• /
• v.24 no.2
• /
• pp.121-130
• /
• 2013

Nature and technology are very popular themes in the everydayness of modern world. In our industrial age which is based on technology nature becomes an lost origin and basic environment. On the other hand, technology is conceived as future hope and realistic environment. Through 1960s they had been transformed as signs and connoted into furniture design. As signs, they structured environment, organized space, and bred their own aesthetics. In this context, Danish designer Verner Panton presented nature as experiential landscape and Italian designer Joe Colombo expressed technology as amusing machine. What they showed were not real but sign of nature and machine. Nonetheless they were successful to create aesthetic atmosphere and meaningful projects. Also they showed the potentiality that furniture design might include discoursive issues and values. They also extended functional interesting between furniture and body to cultural domain of social viewpoint in behavioral pattern.

• Journal of Plant Biology
• /
• v.39 no.3
• /
• pp.161-166
• /
• 1996

The hairy root cultures of Centella asiatica were established by infection leaf explants with Agrobacterium rhizogenes A4, 15834 in 1/2 Murashing and skoog liquid medium supplemented with 50 $\mu$M acetosyringone. The induced hairy roots were subjected to paper electrophoresis for the detection of opine and opine-positive clones which were considered to have been transformed. Five hairy root clones were selected according to the different bacterial strains used, growth rate and pattern. Among media tested, MS basal medium substituted phosphate concentration by 2.5mM K2HPO4 showed the highest growth rate in the dark condition.