• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.2 no.1
• /
• pp.21-30
• /
• 1997

The present study reports the density, growth and production of a razor clam, Sinollovacula constricta, which is known to be one of the important fishreies catches from the Korean tidal flat. The annual yield reached to about 6,000 metric tons per year till 1994. The study was conducted on the Hwaseong tidal flat located on the central west coast, 40 kilometers south-west from Seoul. The annual yield of the razor clam in this area reached to about 50% of the total catch from the whole Korean coast. Samples were colleted monthly at 14 occasions from May 1992 to August 1993. Density of S. constricta ranged from 92~165 individuals per square meter during the study period. General trend of decreasing density was observed when the animal became older, but an exception was the year class of 1991 whose density was lower than that of 1990. The size of the shell was clearly separated into two classes during fall and winter (from September to February), however, the maximum frequency of the length of small size classes moved to right after February. It indicates a fast growth of young clams from spring to summer. Fast growth of the shell could also be examined by the growth curve. The shell growth of the whole life span was described by the von Bertalanffy equation of $L_t=89.3{\times}[1{\exp}\{-0.58{\times}(t+0.73\}]$. The growth in flesh dry weight was well fitted to the Gompertz growth model with the equation, $W_t=5.00{\times}{\exp}\{-4.31{\times}{\exp}(-0.043{\times}t)\}$. The clam lost about 30% of the body weight during spawning in August. The annual production calculated based on the data from September 1992 to August 1993 amounted to 150 g $DW{\cdot}m^{-2}{\cdot}yr^{-1}$ which was 2~50 fold higher than those of other bivalves occurred in Korea. This estimate was patitioned by each year classes; 87.5 by 1992, 53.4 by 1991, 59.0 by 1990 and -30.0 g $DW{\cdot}m^{-2}{\cdot}yr^{-1}$ by 1989 year class.

• Journal of Environmental Impact Assessment
• /
• v.27 no.3
• /
• pp.307-321
• /
• 2018

Fish fauna and lentic ecosystem health assessment in freshwater were analyzed in the two reservoirs (Uirim Reservoir(Ur) and Solbangjuk Reservoir(Sr)) of the Jecheon City during May-September 2017. Total numbers of the species and genus (7 family) sampled were 21 and 16, respectively. Cyprinidae was most dominant taxa, which accounted for 11 species (52.4%) of the total species, and the relative abundance, based on the number of individuals, was 318 individuals (46.2%). Subdominant families were taxa of Centrachidae (2 species; 264 ind. (38.4%). The dominant species, based on the relative abundance, were Squalidus chankaensistsuchigae(22.7%). Subdominant species were Lepomis macrochirus(19.5%, 134 ind.) and Micropterus salmoides(18.9%, 134 ind.). Trophic state index of Korea ($TSI_{KO}$), based on chemical oxygen demand (COD), total phosphorus (TP) and chlorophyll-a (CHL),ranged mesotrophic state. The purpose of this study was to apply a multi-metric model of Lentic Ecosystem Health Assessments (LEHA) for environmental impact assessments of two reservoirs and assessed the ecological health model values. Trophic composition's metrics showed that tolerant species (56.8%, 98.3%) and omnivore species (43.9%, 65.6%) dominated the fish fauna in the two reservoirs (Ur and Sr) of Jecheon City, indicating a biological degradation in the aquatic ecosystem. The relative proportions of Micropterus salmoides, also showed greater than 16.3% (Ur), 31.1% (Sr) of the total, indicating a ecological disturbance. The average value of LEHA model was 22 (Ur) and 12 (Sr) in the reservoirs, indicating a "poor condition (Ur)" and "very poor condition (Sr)" by the criteria of MOE (2014).

• Korean Journal of Social Welfare
• /
• v.66 no.1
• /
• pp.333-361
• /
• 2014

By viewing donors for social welfare organization as both givers and beneficiaries, this study aims to address the correlations between the continuity of donors' contributions and enhanced sense of satisfaction as a consequence of participating in donation activities. The predominant concern of this study centers on: (1) the direct effects of individuals' emotional utility, demonstrable utility, trust toward donee organization, self acceptance on the continuation of their donation; (2) the direct effects of individuals' emotional utility, demonstrable utility, trust toward donee organizations on individuals' self-acceptance; (3) the direct effects of individuals' emotional utility, demonstrable utility on their trust toward a donee organization; (4) the indirect effects of individuals' self acceptance on two paths i.e. emotional utility${\rightarrow}$trust${\rightarrow}$self acceptance, and demonstrable utility${\rightarrow}$trust${\rightarrow}$self acceptance; (5) the indirect effects of individuals' individuals' trust toward donee organization on self acceptance on four paths i.e. emotional utility${\rightarrow}$trust${\rightarrow}$continuity of donation; demonstrable utility${\rightarrow}$trust${\rightarrow}$continuity of donation; emotional utility${\rightarrow}$trust${\rightarrow}$self-acceptance, and demonstrable utility${\rightarrow}$trust${\rightarrow}$self-acceptance; (6) the moderating effects of 'financial status' on the causal relationships in the prescribed structural equation model(SEM). In order to verify the moderating effect of 'financial status', multi-group analysis between each of the two groups were conducted. Research is based on a survey among 1116 donors who had made charitable, monetary contributions to social welfare organizations in Daegu and Kyungpook province. Data was collected from 29 organizations. In order to address the research questions, structural equation were employed. A variety of tests are conducted(metric invariance, critical ratio for difference, structural invariance, multi-group analysis, bias-corrected boot-strapping, latent mean analysis including Cohen's effect test).

• Tuberculosis and Respiratory Diseases
• /
• v.63 no.5
• /
• pp.405-411
• /
• 2007

Background: The objective of this study was to evaluate the clinical applicability of the repeatability criteria recommended by the American Thoracic Society/European Respiratory Society (ATS/ERS) spirometry guidelines and to determine which factors affect the repeatability of spirometry in Korean adults. Methods: We reviewed the spirometry data of 4,663 Korean adults from the Korean National Health and Nutritional Examination Survey (KNHANES) Chronic Obstructive Pulmonary Disease Cohort (COPD cohort) and the Community-based Cohort Study VI-Fishing village/Islands (community cohort). We measured the anthropometric factors and differences between the highest and second-highest FVC (dFVC) and $FEV_1$ ($dFEV_1$) from prebronchodilator spirometry. Analyses included the distribution of dFVC and $dFEV_1$, comparison of the values meeting the 1994 ATS repeatability criteria with the values meeting the 2005 ATS/ERS repeatability criteria, and the performance of linear regression for evaluating the influence of subject characteristics and the change of criteria on the spiro-metric variability. Results: About 95% of subjects were able to reproduce FVC and $FEV_1$ within 150 ml. The KNHANES based on the 1994 ATS guidelines showed poorer repeatability than the COPD cohort and community cohort based on the 2005 ATS/ERS guidelines. Demographic and anthropometric factors had little effect on repeatability, explaining only 0.5 to 3%. Conclusion: We conclude that the new spirometry repeatability criteria recommended by the 2005 ATS/ERS guidelines is also applicable to Korean adults. The repeatability of spirometry depends little on individual characteristics when an experienced technician performs testing. Therefore, we suggest that sustained efforts for public awareness of new repeatability criteria, quality control of spirograms, and education of personnel are needed for reliable spirometric results.

• Journal of the Korean Society of Child Welfare
• /
• no.36
• /
• pp.165-196
• /
• 2011

With the increasing concerns of victimization of school violence, this paper is intended to present a pioneering study on the victims' conscientization which may result from their own experience of school violence by peers. The predominant concern of the study consists in: (1) the direct effects of individuals' perception toward violence in general, non-assertiveness, school violence experience by peers, and prosocial behavioral tendency on the individual conscientization of school violence problems; (2) the indirect effects of both individual prosocial behavioral tendency and perceptions toward violence through non-assertiveness on individual conscientization of school violence problems;(3) the sexual differences of the five latent variables(perceptions toward violence in general, non-assertiveness, prosocial behavioral tendency, school violence experience by peers, and conscientization of school violence problems; (4) the sexual differences of both direct and indirect correlates on conscientization of school violence problems. Research is based on a survey conducted with 526 adolescents (268 males and 258 females) from 16 middle schools located in different districts of the city of Pohang. In order to address the research questions, structural equation models on adolescents' conscientization of school violence are explored. A variety of tests are conducted (configural invariance, metric invariance and structural invariance, intercept invariance, critical ratio for difference test, multi-group analysis, latent mean analysis including Cohen's effect test). The major findings of the study support the significance of both direct effects and indirect effects of the four latent factors(perceptions of violence in general, non-assertiveness, prosocial behavioral tendency, school violence experience by peers). The individual prosocial behavioral tendency has a positive mediating effect on the enhancement of individual conscientization toward school violence problems. However, we fail to find the direct positive effect of individual violence experience on the conscientization of school violence problems. In conclusion, a range of practical implications for social workers and other related professionals who are engaged in helping out the adolescents with school violence by peers are suggested based on the study findings.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.19 no.4
• /
• pp.243-255
• /
• 2014

This study was investigated to estimate the relations between benthic environments and benthic polychaetous community from April 2012 to February 2013. Twenty four stations were selected sequentially with Seomjin River Estuary from the northern part of Gwangyang Bay. The study area could be divided into three characteristic zones based on salinity, water temperature, dissolved oxygen and pH such as Saline Water Zone (SWZ), Brackish Water Zone (BWZ), and Fresh Water Zone (FWZ). Salinity was above 30.0 psu in SWZ, drastically decreased toward inland in BWZ, and nearly zero psu in FWZ. SWZ showed its specific environmental characters like that water temperature fluctuated with little seasonal change and DO showed the lowest values among three zones, and pH maintained as consistent value without seasonal fluctuation. In FWZ, on the other hand, water temperature showed high seasonal fluctuation, DO showed the highest values among three zones, and pH fluctuated greatly. In sedimentary environment, mud, sand and sand/gravel were found as dominant sedimentary deposits in SWZ, BWZ and FWZ, respectively. Organic matter content and AVS in surface sediment were high in SWZ, while Chl-a content high in FWZ. This study area showed a marked environmental difference between FWZ and SWZ as follows: FWZ has coarse sediment and low salinity, low organic matter content, low AVS in FWZ but SWZ has fine sediment and high salinity, high organic matter content and AVS. Species number and mean density of benthic polychaete community was highest in Saline Water Zone (SWZ), drastically decreased in Brackish Water Zone (BWZ), and lowest in Fresh Water Zone (FWZ). Dominant polychates above 5.0% of individual numbers were 6 taxa. Lumbrineris longifolia, Prionospio cirrifera, Tharyx sp. occurred as main dominant species of all study periods, and Hediste sp., Praxillella affinis, Tylorrhynchus sp. dominantly occurred at some seasons. Inhabiting areas of dominant species were separated characteristically. Representative species in SWZ were Lumbrineris longifolia, Tharyx sp., Mediomastus sp.. Wide-appearing species between SWZ and BWZ were Prionospio cirrifera, Heteromastus filiformis, Aricidea sp.. Characteristic species in FWZ were Tylorrhynchus sp. and Hediste sp.. As the results of cluster analysis and nMDS based on the species composition of polychaetous community, unique station groups were established in SWZ and FWZ. Stations in BWZ were sub-divided into several groups with season. Pearson's correlation analysis and PCA between benthic environments and ecological characteristics of polychaetous community showed that salinity, sediment composition, organic content and dissolved oxygen played a role to determine the temporal and spatial distribution of the ecological characteristics as species number, mean density, abundance of main species, and ecological indices.

• Journal of Intelligence and Information Systems
• /
• v.27 no.1
• /
• pp.23-46
• /
• 2021

Collaborative filtering, which is often used in personalization recommendations, is recognized as a very useful technique to find similar customers and recommend products to them based on their purchase history. However, the traditional collaborative filtering technique has raised the question of having difficulty calculating the similarity for new customers or products due to the method of calculating similaritiesbased on direct connections and common features among customers. For this reason, a hybrid technique was designed to use content-based filtering techniques together. On the one hand, efforts have been made to solve these problems by applying the structural characteristics of social networks. This applies a method of indirectly calculating similarities through their similar customers placed between them. This means creating a customer's network based on purchasing data and calculating the similarity between the two based on the features of the network that indirectly connects the two customers within this network. Such similarity can be used as a measure to predict whether the target customer accepts recommendations. The centrality metrics of networks can be utilized for the calculation of these similarities. Different centrality metrics have important implications in that they may have different effects on recommended performance. In this study, furthermore, the effect of these centrality metrics on the performance of recommendation may vary depending on recommender algorithms. In addition, recommendation techniques using network analysis can be expected to contribute to increasing recommendation performance even if they apply not only to new customers or products but also to entire customers or products. By considering a customer's purchase of an item as a link generated between the customer and the item on the network, the prediction of user acceptance of recommendation is solved as a prediction of whether a new link will be created between them. As the classification models fit the purpose of solving the binary problem of whether the link is engaged or not, decision tree, k-nearest neighbors (KNN), logistic regression, artificial neural network, and support vector machine (SVM) are selected in the research. The data for performance evaluation used order data collected from an online shopping mall over four years and two months. Among them, the previous three years and eight months constitute social networks composed of and the experiment was conducted by organizing the data collected into the social network. The next four months' records were used to train and evaluate recommender models. Experiments with the centrality metrics applied to each model show that the recommendation acceptance rates of the centrality metrics are different for each algorithm at a meaningful level. In this work, we analyzed only four commonly used centrality metrics: degree centrality, betweenness centrality, closeness centrality, and eigenvector centrality. Eigenvector centrality records the lowest performance in all models except support vector machines. Closeness centrality and betweenness centrality show similar performance across all models. Degree centrality ranking moderate across overall models while betweenness centrality always ranking higher than degree centrality. Finally, closeness centrality is characterized by distinct differences in performance according to the model. It ranks first in logistic regression, artificial neural network, and decision tree withnumerically high performance. However, it only records very low rankings in support vector machine and K-neighborhood with low-performance levels. As the experiment results reveal, in a classification model, network centrality metrics over a subnetwork that connects the two nodes can effectively predict the connectivity between two nodes in a social network. Furthermore, each metric has a different performance depending on the classification model type. This result implies that choosing appropriate metrics for each algorithm can lead to achieving higher recommendation performance. In general, betweenness centrality can guarantee a high level of performance in any model. It would be possible to consider the introduction of proximity centrality to obtain higher performance for certain models.

• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.107-122
• /
• 2017

Volatility in the stock market returns is a measure of investment risk. It plays a central role in portfolio optimization, asset pricing and risk management as well as most theoretical financial models. Engle(1982) presented a pioneering paper on the stock market volatility that explains the time-variant characteristics embedded in the stock market return volatility. His model, Autoregressive Conditional Heteroscedasticity (ARCH), was generalized by Bollerslev(1986) as GARCH models. Empirical studies have shown that GARCH models describes well the fat-tailed return distributions and volatility clustering phenomenon appearing in stock prices. The parameters of the GARCH models are generally estimated by the maximum likelihood estimation (MLE) based on the standard normal density. But, since 1987 Black Monday, the stock market prices have become very complex and shown a lot of noisy terms. Recent studies start to apply artificial intelligent approach in estimating the GARCH parameters as a substitute for the MLE. The paper presents SVR-based GARCH process and compares with MLE-based GARCH process to estimate the parameters of GARCH models which are known to well forecast stock market volatility. Kernel functions used in SVR estimation process are linear, polynomial and radial. We analyzed the suggested models with KOSPI 200 Index. This index is constituted by 200 blue chip stocks listed in the Korea Exchange. We sampled KOSPI 200 daily closing values from 2010 to 2015. Sample observations are 1487 days. We used 1187 days to train the suggested GARCH models and the remaining 300 days were used as testing data. First, symmetric and asymmetric GARCH models are estimated by MLE. We forecasted KOSPI 200 Index return volatility and the statistical metric MSE shows better results for the asymmetric GARCH models such as E-GARCH or GJR-GARCH. This is consistent with the documented non-normal return distribution characteristics with fat-tail and leptokurtosis. Compared with MLE estimation process, SVR-based GARCH models outperform the MLE methodology in KOSPI 200 Index return volatility forecasting. Polynomial kernel function shows exceptionally lower forecasting accuracy. We suggested Intelligent Volatility Trading System (IVTS) that utilizes the forecasted volatility results. IVTS entry rules are as follows. If forecasted tomorrow volatility will increase then buy volatility today. If forecasted tomorrow volatility will decrease then sell volatility today. If forecasted volatility direction does not change we hold the existing buy or sell positions. IVTS is assumed to buy and sell historical volatility values. This is somewhat unreal because we cannot trade historical volatility values themselves. But our simulation results are meaningful since the Korea Exchange introduced volatility futures contract that traders can trade since November 2014. The trading systems with SVR-based GARCH models show higher returns than MLE-based GARCH in the testing period. And trading profitable percentages of MLE-based GARCH IVTS models range from 47.5% to 50.0%, trading profitable percentages of SVR-based GARCH IVTS models range from 51.8% to 59.7%. MLE-based symmetric S-GARCH shows +150.2% return and SVR-based symmetric S-GARCH shows +526.4% return. MLE-based asymmetric E-GARCH shows -72% return and SVR-based asymmetric E-GARCH shows +245.6% return. MLE-based asymmetric GJR-GARCH shows -98.7% return and SVR-based asymmetric GJR-GARCH shows +126.3% return. Linear kernel function shows higher trading returns than radial kernel function. Best performance of SVR-based IVTS is +526.4% and that of MLE-based IVTS is +150.2%. SVR-based GARCH IVTS shows higher trading frequency. This study has some limitations. Our models are solely based on SVR. Other artificial intelligence models are needed to search for better performance. We do not consider costs incurred in the trading process including brokerage commissions and slippage costs. IVTS trading performance is unreal since we use historical volatility values as trading objects. The exact forecasting of stock market volatility is essential in the real trading as well as asset pricing models. Further studies on other machine learning-based GARCH models can give better information for the stock market investors.

• Journal of Global Scholars of Marketing Science
• /
• v.19 no.1
• /
• pp.23-35
• /
• 2009

A hypermarket as the one of the most globally standardized retailing format is also the type of store among various types of stores that the most active in expanding into other foreign markets. Recently, as several Korean retailing companies start to penetrate into Chinese market they differentiate themselves with modern facilities and customers service oriented high-end concept. China and Korea as Far East Asian countries share many common values, however precise and careful analysis should be carried out since there may also be critical differences in socio-economic aspects as well as in consumption patterns due to the level of development stages of retail industry among two countries. Even though precise and careful study is crucial on Chinese retailing market and consumers, none of researches and studies on 'how the quality of service dimensional structure is different between Korea and China', and 'what will be the most important and influential service dimensional factors for Chinese consuers compared to the hypermarkets customers in Korea' in order to improve the level of Chinese consumers satisfaction' have been fulfilled At this point of view, this study uses KD-SQS (Rho Eun Jung & Sir Yong Gu, 2008) which is a measure of Korean hypermarkets service quality to set up a hypothesis on Korean and Chinese consumers, and an empirical analysis is conducted. We try to get the answers about how the comparative importance of Service quality dimensions which decides the level of customer satisfaction is different depending on the cultural dimensions and socio-economic factors among two countries, Korea and China. Based upon the results, we try to give a valuable suggestion of what service dimensional factors should be reinforced to improve the level of CS in Chinese retailing market. Hypotheses for this study are as follows : H1. Each dimension of Service Quality significantly affects the level of CS H2. The effect of 'Basic Benefit' in service quality dimensions on the level of CS is greater in China than in Korea H3. The effect of 'Promotion' in service quality dimensions on the level of CS is greater in China than in Korea H4. The effect of 'Physical Aspects'in service quality dimensions on the level of CS is greater in Korea than in China. H5. The effect of 'Personal Interaction' in service quality dimensions on the level of CS is greater in China than in Korea H6. The effect of 'Policy' in service quality dimensions on the level of CS will be greater in Korean than in China H7. The effect of additional convenience in service quality dimensions on the level of CS will be greater in Korean than in China. More than 1,100 data were collected directly from the surveys of Chinese and Korean consumers in order to verify the hypotheses above. In Korea, stores which have floor space of over $9,000m^2$and opened later than year 2000 were selected for the samples, and thus Gayang, Wolgye, Sangbong, Eunpyeong, Suh-Suwon, Gojan stores and their customers were surveyed. In China, notable differences in the income levels and consumer behaviors between cities and regions were considered, and thus the research area was limited to the stores only in Shanghai. 6 stores which have the size of over $6,000m^2$ and opened later than 2000, such as Ruihong, Intu, Mudanjang, Sanrin, Raosimon, and Ranchao stores were selected for the survey. SPSS 12.0 and AMOS 7.0 were used as statistical tools, and exploratory factor analysis, confirmatory factor analysis, and multi-group analysis were conducted. In order to carry out a multi group analysis that decides whether the structure variables which shows the different effects of 6 service dimensions in Korean and Chinese groups is statistically valid, configural invariance, metric invariance, and structural invariance are tested in order. At the results of the tests, 3 out of 7 hypotheses were supported and other 4 hypotheses were denied. According to the study, 4 dimensions (Basic Benefit, Physical Environment, Policy, and additional convenience) were positively correlated with CS in Korea, and 3 dimensions (i.e. basic benefit, policy, additional convenience) were significant in China. However, the significance of the service-dimensions was turned out to be partially different in Korea and China. The Basic Benefit is more influential in deciding the level of CS in china than Korea, however Physical Aspect is more important factor in Korea. 'Policy dimension' did not make significant difference between two countries. In the 'additional convenience dimension', the differences in 'socio-economic factors' than in'cultural background' were considered as more important in Chinese consumers than Korean. Overall, the improvement of Service quality will be crucial factors to increase the level of CS in Chinese market same as Korean market. In addition, more emphases need to be placed on the service qualities of 'Basic Benefit' and 'additional convenience' dimensions in China. In particular, 'low price' and 'product diversity' that constitute 'Basic Benefit' are proved to be comparatively disadvantageous and weak points of Korean companies compared to global players, and thus the prompt strengthening those dimensions would be urgent for Korean retailers. Moreover, additional conveniences such as various tenants and complex service and entertaining area will be more important in China than in Korea. Besides, Applying advanced Korean Hypermaret`s customer policy to Chinese consumers will help to get higher reliability and to differentiate themselves to other competitors. However, as personal interaction, physical aspect, promotions were proved as not significant for the level of CS in China, Korean companies need to reconsider the priority order of resource allocations when they tap into Chinese market.

• 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.