• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.12
• /
• pp.1150-1158
• /
• 2010

In this study, the Polynomial-based Radial Basis Function Neural Networks is proposed as one of the recognition part of overall face recognition system that consists of two parts such as the preprocessing part and recognition part. The design methodology and procedure of the proposed pRBFNNs are presented to obtain the solution to high-dimensional pattern recognition problem. First, in preprocessing part, we use a CCD camera to obtain a picture frame in real-time. By using histogram equalization method, we can partially enhance the distorted image influenced by natural as well as artificial illumination. We use an AdaBoost algorithm proposed by Viola and Jones, which is exploited for the detection of facial image area between face and non-facial image area. As the feature extraction algorithm, PCA method is used. In this study, the PCA method, which is a feature extraction algorithm, is used to carry out the dimension reduction of facial image area formed by high-dimensional information. Secondly, we use pRBFNNs to identify the ID by recognizing unique pattern of each person. The proposed pRBFNNs architecture consists of three functional modules such as the condition part, the conclusion part, and the inference part as fuzzy rules formed in 'If-then' format. In the condition part of fuzzy rules, input space is partitioned with Fuzzy C-Means clustering. In the conclusion part of rules, the connection weight of pRBFNNs is represented as three kinds of polynomials such as constant, linear, and quadratic. Coefficients of connection weight identified with back-propagation using gradient descent method. The output of pRBFNNs model is obtained by fuzzy inference method in the inference part of fuzzy rules. The essential design parameters (including learning rate, momentum coefficient and fuzzification coefficient) of the networks are optimized by means of the Particle Swarm Optimization. The proposed pRBFNNs are applied to real-time face recognition system and then demonstrated from the viewpoint of output performance and recognition rate.

• The Journal of Korean Academy of Prosthodontics
• /
• v.36 no.1
• /
• pp.166-182
• /
• 1998

The purposes of this study are to evaluate the Korean mandibular dental arch and classify the mandibular dental arch shape and size based on the incisal angle, canine angle, inter second molar width and height. In this study the mandibular study models were fabricated using irreversible hydrocolloid impression material from 225 volunteers with a mean age 23.62 (range 19-29). And the study models were measured with 3-dimensional measuring device and the mandibular dental arch was classified by means of K-means clustering method and visual inspection, then obtained data were analyzed with t-test for the statistical analysis. The results were as follows ; 1. The average canine height was 5.19mm(s.d. 1.17) in both sex, 5.34mm in male, and 4.95mnm in female. And the sexual difference was significant($0). 2. The average second molar height was 39.81mm(s.d. 2.44) in both sex, 40.19mm in male, and 39.21mm in female. And the sexual difference was significant($0). 3. The average inter-canine width was 27.16mm(s.d. 1.78) in both sex, 27.41mm in male, and 26.77mm in female. And the sexual difference was significant($0). 4. The average inter-first molar width was 46.93mm(s.d. 2.67) in both sex, 47.72mm in male, and 45.7mm in female. And the sexual difference was significant($0). 5. The inter-second molar width was average 56.09mm(s.d. 3.01) in both sex, 57.24mm in male, and 54.32mn in woma. And the sexual difference was significant($0). 6. The arch form was classified into three shapes based on the incisal and canine angle. V-shape showed $124.88^{\circ}$ of incisal angle and $141.64^{\circ}$ of canine angle, U-shape showed $152.76^{\circ}\;and\;125.35^{\circ}$, and O-shape showed $138.03^{\circ}\;and \;33.66^{\circ}$ respectively. Each shape distribution was that the V-shape was 14.2%, the U-Shape was 14.7%, and the O-shape was 71.1% of the 225 study models. 7. It was thought that the use of second molar width is more reasonable than height for classifying the dental arch size. The arch size was classified into four sizes based on the second molar width. Size 1 showed range of 42.24-48.23mm, size 2 showed 48.24-54.23mm, size 3 showed 54.24-60.23mm, and size 4 showed 60.24-66.23mm respectively. Each arch size distribution was that the size 1 was 1.3%, the size 2 was 27.1%, the size 3 was 63.6%, and the size 4 was 8.0% of the 225 study models.

• Journal of Veterinary Clinics
• /
• v.33 no.5
• /
• pp.278-285
• /
• 2016

Epidemiological studies have shown the association between transportation of live animals and the potential transmission of infectious disease between premises. This finding was also observed in the 2014-2015 foot-and-mouth disease (FMD) outbreak in Korea. Furthermore, slaughterhouses played a key role in the global spread of the FMD virus during the epidemic. In this context, in-depth knowledge of the structure of direct and indirect contact between slaughterhouses is paramount for understanding the dynamics of FMD transmission. But the social network structure of vehicle movements to slaughterhouses in Korea remains unclear. Hence, the aim of this study was to configure a social network topology of vehicle movements between slaughterhouses for a better understanding of how they are potentially connected, and to explore whether FMD outbreaks can be explained by the network properties constructed in the study. We created five monthly directed networks based on the frequency and chronology of on- and off-slaughterhouse vehicle movements. For the monthly network, a node represented a slaughterhouse, and an edge (or link) denoted vehicle movement between two slaughterhouses. Movement data were retrieved from the national Korean Animal Health Integrated System (KAHIS) database, which tracks the routes of individual vehicle movements using a global positioning system (GPS). Electronic registration of livestock movements has been a mandatory requirement since 2013 to ensure traceability of such movements. For each of the five studied networks, the network structures were characterized by small-world properties, with a short mean distance, a high clustering coefficient, and a short diameter. In addition, a strongly connected component was observed in each of the created networks, and this giant component included 94.4% to 100% of all network nodes. The characteristic hub-and-spoke type of structure was not identified. Such a structural vulnerability in the network suggests that once an infectious disease (such as FMD) is introduced in a random slaughterhouse within the cohesive component, it can spread to every other slaughterhouse in the component. From an epidemiological perspective, for disease management, empirically derived small-world networks could inform decision-makers on the higher potential for a large FMD epidemic within the livestock industry, and could provide insights into the rapid-transmission dynamics of the disease across long distances, despite a standstill of animal movements during the epidemic, given a single incursion of infection in any slaughterhouse in the country.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.11
• /
• pp.1599-1607
• /
• 2022

The data mainly used for the model are as follows: the personal information, the information of insurance product, etc. With the data, we suggest three types of models: content-based filtering model, collaborative filtering model and classification models-based model. The content-based filtering model finds the cosine of the angle between the users and items, and recommends items based on the cosine similarity; however, before finding the cosine similarity, we divide into several groups by their features. Segmentation is executed by K-means clustering algorithm and manually operated algorithm. The collaborative filtering model uses interactions that users have with items. The classification models-based model uses decision tree and random forest classifier to recommend items. According to the results of the research, the contents-based filtering model provides the best result. Since the model recommends the item based on the demographic and user features, it indicates that demographic and user features are keys to offer more appropriate items.

• Economic and Environmental Geology
• /
• v.34 no.4
• /
• pp.355-373
• /
• 2001

Palaeomagnesim of Paleozoic Tuwibong Type Sequence in Yemi area was studied with a total of 256 core-samples collected from 23 sites. The study area (geographical coordinates: 37.l8$^{\circ}$N, l28.610E) is located between Taebaek and Yongwol belonging to the northeastern part of the Okchon Belt. Thermal cleaning was a most effective method to extract stable characteristic remanent magnetization (ChRM) direction, even though AF cleaning also worked on some specimens. Mean ChRM direction of the Cambrian Hwajol Formation was different from the present-day field direction and showed maximum clustering (max. k value) at 100% bedding-tilt correction. However, it could not pass the fold test. Ordovician Makkol and Kosong Limestones as well as Permian Sadong and Kobangsan Formations have very weak NRM, and were remagnetized into the present-day field direction. ChRM directions from the Carboniferous Hongjom Formation passed both fold and reversal tests. IRM experiments and blocking temperature spectrum indicate that both magnetite and haematite are carrier of the primary magnetization. Palaeomagnetic pole position from the Carboniferous Hongjom Formation is very similar to that of contemporary North China Block (NCB) suggesting that the study area was a part of, or located very near to, the NCB during Carboniferous.

• Korean Journal of Radiology
• /
• v.23 no.5
• /
• pp.539-547
• /
• 2022

Objective: To investigate the association between functional tumor burden of peritoneal carcinomatosis (PC) derived from diffusion-weighted imaging (DWI) and overall survival in patients with advanced ovarian carcinoma (OC). Materials and Methods: This prospective study was approved by the local research ethics committee, and informed consent was obtained. Fifty patients (mean age ± standard deviation, 57 ± 12 years) with stage III-IV OC scheduled for primary or interval debulking surgery (IDS) were recruited between June 2016 and December 2021. DWI (b values: 0, 400, and 800 s/mm²) was acquired with a 16-channel phased-array torso coil. The functional PC burden on DWI was derived based on K-means clustering to discard fat, air, and normal tissue. A score similar to the surgical peritoneal cancer index was assigned to each abdominopelvic region, with additional scores assigned to the involvement of critical sites, denoted as the functional peritoneal cancer index (fPCI). The apparent diffusion coefficient (ADC) of the largest lesion was calculated. Patients were dichotomized by immediate surgical outcome into high- and low-risk groups (with and without residual disease, respectively) with subsequent survival analysis using the Kaplan-Meier curve and log-rank test. Multivariable Cox proportional hazards regression was used to evaluate the association between DWI-derived results and overall survival. Results: Fifteen (30.0%) patients underwent primary debulking surgery, and 35 (70.0%) patients received neoadjuvant chemotherapy followed by IDS. Complete tumor debulking was achieved in 32 patients. Patients with residual disease after debulking surgery had reduced overall survival (p = 0.043). The fPCI/ADC was negatively associated with overall survival when accounted for clinicopathological information with a hazard ratio of 1.254 for high fPCI/ADC (95% confidence interval, 1.007-1.560; p = 0.043). Conclusion: A high DWI-derived functional tumor burden was associated with decreased overall survival in patients with advanced OC.

• Korean Journal of Poultry Science
• /
• v.45 no.3
• /
• pp.229-236
• /
• 2018

The aim of this study was to evaluate the genetic diversity and relationships of Ogye populations in Korea. A total of 243 genomic DNA samples from 6 Ogye population (Yeonsan Ogye; YSO, Animal Genetic Resources Research Center Ogye; ARO, Chungbuk Ogye; CBO, Chungnam Ogye; CNO, Gyeongbuk Ogye; GBO, Seoul National University Ogye; SUO) and 3 introduced chicken breeds (Rhode Island Red; RIR, White Leghorn; LG, Cornish; CN) were used. Sizes of 25 microsatellite markers were decided using GeneMapper Software(v 5.0) after analyzing ABI 3130XL. A total of 153 alleles were observed and the range was 2 to 10 per each locus. The mean of expected and observed heterozygosity and PIC (Polymorphism Information Content) value was 0.53, 0.50, 0.46 respectively. The lowest genetic distance (0.073) was observed between YSO and SUO, and the highest distance (0.937) between the RIR and CBO. The results of clustering analysis suggested 3 clusters (${\Delta}K=7.96$). Excluding GBO population, 5 Ogye populations (YSO, ARO, CBO, CNO, SUO) were grouped in same cluster with high genetic uniformity (0.990, 0.979, 0.989, 0.994, 0.985 respectively). But GBO population was grouped in cluster 1 with low genetic uniformity (0.340). The results of this study can be use to basic data for the genetic evaluation and management of Ogye populations in Korea.

• Journal of Intelligence and Information Systems
• /
• v.17 no.1
• /
• pp.139-152
• /
• 2011

Recommender systems have become an important research field since the emergence of the first paper on collaborative filtering in the mid-1990s. In general, recommender systems are defined as the supporting systems which help users to find information, products, or services (such as books, movies, music, digital products, web sites, and TV programs) by aggregating and analyzing suggestions from other users, which mean reviews from various authorities, and user attributes. However, as academic researches on recommender systems have increased significantly over the last ten years, more researches are required to be applicable in the real world situation. Because research field on recommender systems is still wide and less mature than other research fields. Accordingly, the existing articles on recommender systems need to be reviewed toward the next generation of recommender systems. However, it would be not easy to confine the recommender system researches to specific disciplines, considering the nature of the recommender system researches. So, we reviewed all articles on recommender systems from 37 journals which were published from 2001 to 2010. The 37 journals are selected from top 125 journals of the MIS Journal Rankings. Also, the literature search was based on the descriptors "Recommender system", "Recommendation system", "Personalization system", "Collaborative filtering" and "Contents filtering". The full text of each article was reviewed to eliminate the article that was not actually related to recommender systems. Many of articles were excluded because the articles such as Conference papers, master's and doctoral dissertations, textbook, unpublished working papers, non-English publication papers and news were unfit for our research. We classified articles by year of publication, journals, recommendation fields, and data mining techniques. The recommendation fields and data mining techniques of 187 articles are reviewed and classified into eight recommendation fields (book, document, image, movie, music, shopping, TV program, and others) and eight data mining techniques (association rule, clustering, decision tree, k-nearest neighbor, link analysis, neural network, regression, and other heuristic methods). The results represented in this paper have several significant implications. First, based on previous publication rates, the interest in the recommender system related research will grow significantly in the future. Second, 49 articles are related to movie recommendation whereas image and TV program recommendation are identified in only 6 articles. This result has been caused by the easy use of MovieLens data set. So, it is necessary to prepare data set of other fields. Third, recently social network analysis has been used in the various applications. However studies on recommender systems using social network analysis are deficient. Henceforth, we expect that new recommendation approaches using social network analysis will be developed in the recommender systems. So, it will be an interesting and further research area to evaluate the recommendation system researches using social method analysis. This result provides trend of recommender system researches by examining the published literature, and provides practitioners and researchers with insight and future direction on recommender systems. We hope that this research helps anyone who is interested in recommender systems research to gain insight for future research.

• Journal of Intelligence and Information Systems
• /
• v.16 no.2
• /
• pp.19-32
• /
• 2010

Volatility plays a central role in both academic and practical applications, especially in pricing financial derivative products and trading volatility strategies. This study presents a novel mechanism based on generalized autoregressive conditional heteroskedasticity (GARCH) models that is able to enhance the performance of intelligent volatility trading systems by predicting Korean stock market volatility more accurately. In particular, we embedded the concept of the volatility asymmetry documented widely in the literature into our model. The newly developed Korean stock market volatility index of KOSPI 200, VKOSPI, is used as a volatility proxy. It is the price of a linear portfolio of the KOSPI 200 index options and measures the effect of the expectations of dealers and option traders on stock market volatility for 30 calendar days. The KOSPI 200 index options market started in 1997 and has become the most actively traded market in the world. Its trading volume is more than 10 million contracts a day and records the highest of all the stock index option markets. Therefore, analyzing the VKOSPI has great importance in understanding volatility inherent in option prices and can afford some trading ideas for futures and option dealers. Use of the VKOSPI as volatility proxy avoids statistical estimation problems associated with other measures of volatility since the VKOSPI is model-free expected volatility of market participants calculated directly from the transacted option prices. This study estimates the symmetric and asymmetric GARCH models for the KOSPI 200 index from January 2003 to December 2006 by the maximum likelihood procedure. Asymmetric GARCH models include GJR-GARCH model of Glosten, Jagannathan and Runke, exponential GARCH model of Nelson and power autoregressive conditional heteroskedasticity (ARCH) of Ding, Granger and Engle. Symmetric GARCH model indicates basic GARCH (1, 1). Tomorrow's forecasted value and change direction of stock market volatility are obtained by recursive GARCH specifications from January 2007 to December 2009 and are compared with the VKOSPI. Empirical results indicate that negative unanticipated returns increase volatility more than positive return shocks of equal magnitude decrease volatility, indicating the existence of volatility asymmetry in the Korean stock market. The point value and change direction of tomorrow VKOSPI are estimated and forecasted by GARCH models. Volatility trading system is developed using the forecasted change direction of the VKOSPI, that is, if tomorrow VKOSPI is expected to rise, a long straddle or strangle position is established. A short straddle or strangle position is taken if VKOSPI is expected to fall tomorrow. Total profit is calculated as the cumulative sum of the VKOSPI percentage change. If forecasted direction is correct, the absolute value of the VKOSPI percentage changes is added to trading profit. It is subtracted from the trading profit if forecasted direction is not correct. For the in-sample period, the power ARCH model best fits in a statistical metric, Mean Squared Prediction Error (MSPE), and the exponential GARCH model shows the highest Mean Correct Prediction (MCP). The power ARCH model best fits also for the out-of-sample period and provides the highest probability for the VKOSPI change direction tomorrow. Generally, the power ARCH model shows the best fit for the VKOSPI. All the GARCH models provide trading profits for volatility trading system and the exponential GARCH model shows the best performance, annual profit of 197.56%, during the in-sample period. The GARCH models present trading profits during the out-of-sample period except for the exponential GARCH model. During the out-of-sample period, the power ARCH model shows the largest annual trading profit of 38%. The volatility clustering and asymmetry found in this research are the reflection of volatility non-linearity. This further suggests that combining the asymmetric GARCH models and artificial neural networks can significantly enhance the performance of the suggested volatility trading system, since artificial neural networks have been shown to effectively model nonlinear relationships.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.65 no.3
• /
• pp.199-213
• /
• 2020

Grain size and shape are the two important components contributing to rice yield and quality. To analyze traits related to grain-shape, a total of 272 varieties derived from japonica, japonica black and Tongil-type rice accession in Korea were evaluated in this study. The traits, grain length (GL), grain width (GW), grain thickness (GT), length to width ratio (RLW), and 1000-grain weight (TGW) were measured and replicated 10 times. Genes (GW2, GS3, qGL3, qSW5, GS5, TGW6, GW7, and GW8) related to grain-shape were validated in the accessions using specific DNA marker sets. K-mean clustering of the accession based on phenotypic data revealed three groups: group 1 was classified by GW and GT and included most of japonica type, group 2 was classified by RLW and GL reached a medium size and possessed a half spindle-shaped type, and group 3 was classified by TGW, reached a long size and possessed a semi-round shape. In validation tests using the marker sets, both gw2 and tgw6 were validated in less than 1% of the tested accessions and two allelic types, qgl3 and gw8, were only verified in Tongil-type accessions. For GW8 and GW2, any different amplicons were not amplified in any japonica or Tongil-type accessions, respectively. In order to suggest the representative grain-shape gene combinations for each ecotype, the allelic combinations were evaluated by PCR analysis. Cj1 and 2 in japonica (Cj1-7), Cj_b1 and 2 in japonica-black (Cj_b1-3), and CT3 in Tongil-type (CT1-13) turned out to be the dominant combination in each ecotype, respectively. In addition, the results revealed that introgression of four genes (gw2, gs3, qSW5, and GS5) would expand the diversity of grain shape in Korean japonica varieties. The gene combinations information could be utilized practically to understand or enhance grain shape in japonica rice breeding program.