• Journal of Korean Society of Forest Science
• /
• v.76 no.2
• /
• pp.109-118
• /
• 1987

The purpose of this study was to investigate the inhabiting ecology of wild birds using artificial nests in Gyeongnam province. The sort of birds, the utilization of artificial nests by the materials, by the sites and by the forest type, and other inhabiting ecology of birds were investigated from 1984 to 1986. The results obtained were as follows; 1. Wild birds in surveyed areas were classified into 20 families and 35 species. Among them the birds inhabiting the artificial nests were 6 species and those using them most frequently were Parus ater (17.2%), P. major (16.7%) and P. palustris (12.2%). 2. The artificial nests installed on the top and at the toot of the mountain were chiefly utilized by P. ater and P. major, but the artificial nests in park area were mostly used by Passer montanus and Sturnus cineraceus. 3. Sixty-one percent of the artificial nests were utilized by the birds; 45.5% were used for breeding and 15.6% were inhabitation only. 4. When different nest materials and shapes were tested, mixed nests (sawdust and cement) were used most frequently, and C type. (Diamond shape) of wood nests was used more frequently compared with the A (Roof shape) and B (Box shape) types of wood nests. Meanwhile, the birds prefered the 3cm hole size (81.1% of utilization) to 4cm of hole (57.8%) and 5cm of hole (24.4%). 5. The artificial nests constructed in mixed forest were more frequently inhabited (73.3%) by the birds than coniferous forest (68.3%) and broad-leaved forest (63.3%). 6. The period of egg-laying in Parus species was from late April to early May, while Eophona migratoria, Lanius bucephalus, Motacilla alba and Passer montanus laid eggs generally in the middle of May. 7. Parus species, Passer montanus and Motacilla alba laid one egg every day for 5-10days, but Eopphona migratoria laied 4 eggs in 7 days and Lanius bucephalus laid 5 eggs in 4 days. The incubation period of Parus species was 16-18 days, while the others were about 11 to 14 days. 8. Thirteen days after the hatch of Parus major, chicks reached 13.9g of body weight, 72.0mm of wing-length and 20.9mm of tarsus length. P. montanus chicks reached 20.3g of weight, 66.2mm of wing-length and 20.2mm of tarsus length during the same period. 9. Food item of feeding chicks almost consisted of creatures (98.2%) with following composition; 55.2% of insect larvae, 37.2% adult insects, 2.8% of pupae and 2.8% of spiders. Vegetable items were 2% only. Among those creature food items, 95.2% were insect pests to forest.

• Korean Journal of Soil Science and Fertilizer
• /
• v.35 no.2
• /
• pp.93-104
• /
• 2002

A field survey and experiment was conducted from 1996 to 1998 to develop rational technology for turfgrass vegetation of runway side of Incheon International Airport on the reclaimed tidal land in Young-Jong Island. Backfill of the experimental site was finished on August 1995. The experimental site was 8 ha located in the middle of the construction place for the main parking lot in front of the terminal building construction. The experimental field was drained by main open ditch, and divided three main plots, no subsurface tile drain, subsurface tile drain spacing with 22.5m, and with 45 m, respectively. The 17 sub plots were designed to test the effect of soil covering with red earth loam by 5 cm and 20 cm depth, application of chemical compound fertilizers and livestock manures, dressing of artifical soils and hydrophylic soil conditioners. The tested turfgrasses were three transplanting indigenous turfgrasses, Zoysia koreana, Zoysia sinica and Zoysia japonica, and two hydroseeding mixed exotic turgrasses, cool type I(tall fescue 30%, kentucky blue grass 40%, perenial ryegrass 30%), and cool type II(tall fescue 40%, perenial ryegrass 20%, fine fescue 20%, alkaligrass 20%). The soil backfilled with dredged seasand was sand textured with high salt concentration and low fertility. The soil showed high pH, low organic matter and low available phophate contents. The percolation rate was fast with high hydraulic conductivity. Desalinization was fast after installation of the main open drainage system. No subsurface tile drainage effect was found showing little difference in turfgrass growth. The covering and visual growth of turfgrasses were the best in the 20-cm soil covering with compound fertilizer treatment. The covering and visual growth of turfgrasses were satisfactory in the 5 cm soil covering with compound fertilizer treatment and with livestock manure treatments. The hydrophillic soil conditioner treatments were effective but expensive at present. The coverage and visual quality of turfgrasses were good for Zoysia koreana and Zoysia japonica. The coverages of turfgrasses by the hydroseeding with the mixed exotic turfgrasses were less than transplanting of native turfgrasses. In conclusion, for the runway side vegetation purposes, the subsurface tile drainage might not necessary as main open ditch drainage be sufficient due to fast percolation rate of the backfilled dredged seasand. The 5 cm soil covering with red earth might be sufficient for the runway side, but the 20 cm soil covering might be necessary for the runway side where high density of turfgrass coverage was necessary to protect from the airplance air blow.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.39 no.12
• /
• pp.1880-1892
• /
• 2010

The purposes of this study were to: a) provide evidence concerning the effects of emotional intelligence on job outcomes, b) examine the impacts of emotional intelligence on employee-related variables such as 'job satisfaction', 'organizational commitment', 'organizational performance', and 'turnover intention' c) identify the conceptual framework underlying emotional intelligence. A survey was conducted to collect data from foodservice managers (N=231). Statistical analyses were completed using SPSS Win (16.0) for descriptive analysis, reliability analysis, factor analysis, t-test, correlation analysis, cluster analysis and AMOS (16.0) for confirmatory factor analysis and structural equation modeling. The concept of emotional intelligence (EI) has been on the radar screens of many leaders and managers over the last several decades. The emotional intelligence is generally accepted to be a combination of emotional and interpersonal competencies that influence behavior, thinking and interaction with others. The main results of this study were as follows. The four EI (Emotional Intelligence) dimensions correlated significantly with age. The means of job satisfaction score were above the midpoint (3.04 point) scale. The organizational commitment score was above the midpoint (3.41 point) scale and was higher at 'loyalty' factor than 'commitment' factor. The means of organizational performance score were above the midpoint (3.34) scale. The correlations among the four EI (emotional intelligence) factors were significant with job satisfaction; organizational commitment, organizational performance and turnover intention. The test of hypothesis using structural equation modeling found that emotional intelligence produced positive effects on job attitude and job performance. Emotional intelligence enhanced organizational commitment, and in turn, managers' attitude produced positive effects on organizational performance; emotional intelligence also had a direct impact on organizational performance. This study has identified the effect of emotional intelligence on organizational performance and attitudes toward one's job.

• Journal of Society of Preventive Korean Medicine
• /
• v.4 no.2
• /
• pp.72-92
• /
• 2000

This research has conducted studies on an Oriental medicine-based method of diagnosing of occupational musculoskeletal system diseases. This researcher has searched through existing relevant medical literature. Also, this researcher has worked on a moire topography using moire topography. In this course, this researcher has reached the following conclusion in relation to the possibility of using a moire topography as a diagnosing device of musculoskeletal system diseases under Oriental medicine . 1 The Western medicine outlines its criteria of screening occupational musculoskeletal system diseases as follows A. The occupational musculoskeletal diseases must clearly include one or more of the subjective symptoms characterized by pain, hypoesthesia dysaesthesia, anaesthesia. etc . B, There should be clinically admitted objective observations and diagnosis outlining that the disease concerned shows symptoms such as tenderness, induration. and edema that can appear with occupational musculoskeletal system diseases. dyscinesia should be admitted with the disease concerned, or there should be observations and diagnosis outlining that abnormality exists in electric muscular or nervous diagnosis and examination . C. It should be admitted that prior to the occurrence of symptoms or observations and diagnosis on musculoskeletal system-related diseases, a patient has been engaged in works with conditions requiring improper work posture or work movement. That is, this is an approach whereby they see abnormality in the musculoskeletal system come from material and structural defect, and adjust and control abnormality in the musculoskeletal system and secreta . 2. The Oriental medicines sees that a patient develops the pain of occupational musculoskeletal diseases as he cannot properly activate the flow of his life force and blood thus not only causing formation of lumps in the body and blocking the flow of life force and blood in some parts of the body. Hence, The Oriental medicine focuses on resolving the cause of weakening the flow of life force and blood, instead of taking material approach of correcting structural abnormality Furthermore , Oriental medicine sees that when muscle tension builds up, this presses blood vessels and nerves passing by, triggering circulation dyscrasia and neurological reaction and thus leading to lesion. Thus, instead of taking skeletal or neurophysiological approach. it seeks to fundamentally resolve the cause of the flow of the life force and blood in muscles not being activated. As a result Oriental medicine attributes the main cause of musculoskeletal system diseases to muscle tension and its build-up that stem from an individual's long formed chronicle habit and work environment. This approach considers not only the social structure aspect including companies owners and work environment that the existing methods have looked at, but also individual workers' responsibility and their environmental factors. Hence, this is a step forward method. 3 The diagnosis of musculoskeletal diseases under Oriental medicine is characterized by the fact that an Oriental medicine doctor uses not only photos taken by himself, but also various detection devices to gather information and pass comprehensive judgment on it. Thus, it is the core of diagnosis under Oriental medicine to develop diagnosing devices matching the characteristics of information to be induced and to interpret information so induced from the views of Oriental medicine. Diagnosis using diagnosing devices values the whole state of a patient and formal abnormality alike, and the whole balance and muscular state of a patient serves as the basis of diagnosis. Hence, this method, instead of depending on the information gathered from devices under Western medicine, requires devices that provide information on the whole state of a patient in addition to the local abnormality information that X-ray. CT, etc., can offer. This method sees muscle as the central part of the abnormality in the musculoskeletal system and thus requires diagnosing devices enabling the muscular state. 4. The diagnosing device using moire topography under Oriental medicine has advantages below and can be used for diagnosing musculoskeletal system diseases with industrial workers . First, the device can Provide information on the body in an unbalanced state. and thus identify the imbalance and difference of height in the left and right stature that a patient can not notice at normal times. Second, the device shows the twisting of muscles or induration regions in a contour map. This is not possible with existing shooting machines such as X-ray, CT, etc., thus differentiating itself from existing machines. Third, this device makes it possible for Oriental medicine to take its unique approach to the abnormality in the musculoskeletal system. Oriental medicine sees the state and imbalance state in muscles as major factors in determining the lesion of musculoskeletal system, and the device makes it possible to shoot the state of muscles in detail. In this respect, the device is significant. Fourth, the device has an advantage as non-aggression diagnosing device.

• Journal of Animal Science and Technology
• /
• v.44 no.1
• /
• pp.95-104
• /
• 2002

A study was conducted to evaluate feed intake of Hanwoo bulls and steers fed diets of compound feed and rice straw. Twenty bull calves and sixty steers at 5 to 7 months old were used. The experimental period was divided into three feeding stages which are growing period (〈300 kg body weight (BW)), early fattening period (300-450 kg BW) and late fattening period (〉450 kg BW). The animals were given the diets containing 14.1% crude protein (CP) and 70.0% total digestible nutrients (TDN) in the growing period, 12.1% CP and 70.6% TDN in the early fattening period, and 11.2% CP and 71.9% TDN in the late fattening period, respectively. Experiment 1 was designed to compare feed intake (as-fed basis) between Hanwoo bulls and steers fed the experimental diets ad libitum. In Experiment 2, Hanwoo steers were allocated in one of three compound feed feeding treatments to investigate feed intake (as-fed basis). The treatment groups were ① feeding level 1 group fed compound feed ad libitum through the whole periods; ② feeding level 2 group fed 1.0% compound feed per kg BW in the growing period, 1.5% compound feed per kg BW in the early fattening period and compound feed ad libitum in the late fattening period; and ③ feeding level 3 group fed 1.5% compound feed per kg BW in the growing period, 2.0% compound feed per kg BW in the early fattening period and compound feed ad libitum in the late fattening period. In Experiment 1, the average daily feed intake of bulls increased linearly through the whole experimental period while the feed intake of steers increased until their body weight was reached upto 521 kg, afterward reduced. Average daily feed intake was about 3.5% per kg BW of both bulls and steers at the beginning (150 kg BW) of Experiment 1 while bulls and steers at 600 kg BW consumed the diets of 2.0 and 1.5% per kg BW, respectively. In Experiment 2, the average daily feed intake of steers in the feeding level 1 group gradually increased through the growing and early fattening periods and then steadily reduced over the late fattening period. The average daily feed intake in the feeding level 2 group linearly increased through the whole period while the feed intake in the feeding level 3 group showed a relatively rapid increase and reached a peak at 455 kg BW, and then sharply dropped. The average daily feed intake of steers in the feeding level 1 at the beginning (150 kg BW) of Experiment 2 was about 3.5% per kg BW but there was a reduction (1.5% per kg BW) at 600 kg BW. Besides, The feed intake of steers in the feeding level 2 and 3 in which compound feed was given with limitation increased to 2.0-3.0% per kg BW in the growing period and then reduced to 1.5-2.0% per kg BW. The limited compound feed feeding of steers in Experiment 2 resulted in higher rice straw intakes up to two to three folds and two folds in the growing and early fattening periods, respectively, than the ad libitum feeding.

• Journal of Korea Technology Innovation Society
• /
• v.10 no.1
• /
• pp.73-97
• /
• 2007

R&D into future technologies should be conducted in conjunction with technological innovation strategies that are linked to corporate survival within a framework of information and knowledge-based competitiveness. As such, future technology strategies should be ensured through open R&D organizations. The development of future technologies should not be conducted simply on the basis of future forecasts, but should take into account customer needs in advance and reflect them in the development of the future technologies or services. This research aims to select as segmentation variables the customers' attitude towards accepting future telecommunication technologies and their value orientation in their everyday life, as these factors wilt have the greatest effect on the demand for future telecommunication services and thus segment the future telecom service market. Likewise, such research seeks to segment the market from the stage of technology R&D activities and employ the results to formulate technology development strategies. Based on the customer attitude towards accepting new technologies, two groups were induced, and a hierarchical customer segmentation model was provided to conduct secondary segmentation of the two groups on the basis of their respective customer value orientation. A survey was conducted in June 2006 on 800 consumers aged 15 to 69, residing in Seoul and five other major South Korean cities, through one-on-one interviews. The samples were divided into two sub-groups according to their level of acceptance of new technology; a sub-group demonstrating a high level of technology acceptance (39.4%) and another sub-group with a comparatively lower level of technology acceptance (60.6%). These two sub-groups were further divided each into 5 smaller sub-groups (10 total smaller sub-groups) through two rounds of segmentation. The ten sub-groups were then analyzed in their detailed characteristics, including general demographic characteristics, usage patterns in existing telecom services such as mobile service, broadband internet and wireless internet and the status of ownership of a computing or information device and the desire or intention to purchase one. Through these steps, we were able to statistically prove that each of these 10 sub-groups responded to telecom services as independent markets. We found that each segmented group responds as an independent individual market. Through correspondence analysis, the target segmentation groups were positioned in such a way as to facilitate the entry of future telecommunication services into the market, as well as their diffusion and transferability.

• Korean Journal of Soil Science and Fertilizer
• /
• v.12 no.3
• /
• pp.141-151
• /
• 1979

To investigate the relationship between the effect of potassium basal and top dressing amount on rice plant under the limed condition, a pot experiment was conducted with Milyang 21, rice variety. Growing status, yield components and chemical component of rice, plant were determined and soils were analyzed along with the growing stages and obtained results are as follows. 1. Control treatment, without lime application shows a good vegetative growth as compared with lime treated one. However grain yield was higher in lime treated pot when potassium was applied as basal and top dressing. 2. There was no big difference between potassium applied and control treatment on growing status of nice plant until 20 days after transplanting. However in case of lime treated pot big difference were observed 20 days after transplanting resulting lower grain yield as compared with control treatment. This trend were severe in a lime treated treatment. 3. In control treatment, potassium basal dressing shows higher grain yield as increase the amount of basal dressing and the highest yield obtained in all basal potassium application treatment. However in case of lime treated pot when two-third of potassium were applied as basal dressing, potassium content of rice became lower at reproductive stage and resulted lower yield. When we applied all the potassium as a basal dressing, there were no differences as compared with control treatment in terms of grain yield. 4. The soil condition that affects potassium absorption disorder in rice plant such as unlimed condition, potassium application should be done as a basal dressing. However in limed condition that potassium absorption disorder occurs scarcely, and potassium content exists unsufficient amount in soil, large amount of potassium as basal dressing and the rest as top dressing are recommended. 5. The higher content of potassium in rice plant at the reproductive growing stage results heavier tillers as compared with lower one so that heavier tillers produce more grain yield. 6. At vigorous growing stage there was a positive correlation between electric conductivity of soil and amount of potasium absorbed by rice plant. This fact suggests that to obtain higher yield large amount of potassium top dressing at late of vegetative growing stage are necessary so that the content of potassium in rice plant will increase and results higher yield.

• The Korean Journal of Food And Nutrition
• /
• v.29 no.6
• /
• pp.835-848
• /
• 2016

The purpose of this study was to find efficient and customized tools for delivering the benefit of health functional foods (HFFs). Delivery tools which could influence the impact of advertising were images, explanations of ingredients, diagrams of health benefit, patents, and comments from authority. Six advertisements were developed using these tools: "A": relevant image + explanation of ingredients + scientific diagram of efficacy; "B": relevant image + explanation of ingredients; "C": relevant image; "D": irrelevant image; "E": irrelevant image + explanation of ingredient + patent; "F": irrelevant image + explanation of ingredient + comments from authority. To analyze the consumer perceptions on HFFs and advertisement effects, 300 respondents were requested to answer a questionnaire comprising of the following questions: 5 questions of attitudes (necessity of HFFs, trust in HFFs, gathering information, watching advertisements and trust in advertisement claims) and 6 questions on the 6 developed advertisements (attention, understanding, sufficiency of information, sympathy, trust, and purchase). Scoring was done as per the 5 Likert scale. There was a higher proportion of females and the elderly, as compared to males and youngsters. The overall consumer attitudes were positive. Explanation of ingredients, scientific diagram of health benefit, patents and expert comments were helpful factors in increasing the advertisement evaluation by consumer, but the images were not. Advertisement evaluation of consumer did not differ with gender and age. However, differences were observed between some of the consumer attitudes (necessity of HFFs, trust in HFFs, gathering information and trust in advertisements claim) and advertisement evaluations (attention, understanding, sympathy and purchase). Our results indicate that for consumers utilizing the HFFs, advertisements with concrete tools such as diagrams, patent, and expert comments are more helpful. However, for consumers who do not have interest in HFFs, the scientific information was irrelevant. We believe that to maximize the effect of health information in advertisements, consumers should be segmented, and customized tools for each segment needs to be developed.

• Journal of Chest Surgery
• /
• v.40 no.4 s.273
• /
• pp.280-287
• /
• 2007

Background: We retrospectively evaluated the clinical results of surgically managing patients with Ebstein's anomaly. Material and Method: Between Feb. f 984 and June 2006, 50 patients who underwent surgical treatment for Ebstein's anomaly at Yonsei Cardiovascular Center were retrospectively reviewed. The mean age of the patients was 26.9 years and 19 patients were male, Associated anomalies included atrial septal defect (33), patent ductus arteriosus (2), ventricular septal defect (1), and pulmonary stenosis (4), and 90%, (45/50) of the patients had more than a moderate degree of tricuspid regurgitation. Carpentier type A was present in 6 patients, type B in 26, type C in 14 and type D in 4. Ten patients were associated with WPW syndrome. Conservative surgery was possible in 31 patients (tricuspid annuloplasty, plication of the atrialized RV), Fontan's operation was peformed in 4 patients, tricuspid valve replacement was done in 12 and palliative surgery was done in 2 patients. Thirteen patients were associated with hi-directional cavopulmonary shunt (BCPS: one and a half ventricular repairs): 10 patients with WPW syndrome and 4 patients with atrial fibrillation underwent concomitant ablation. Result: The postoperative median NYHA functional class $(3{\rightarrow}1)$ and the mean cardio-thoracic ratio $(0.65{\rightarrow}0.59)$ were decreased significantly (p<0.001, p=0.014). The mean oxygen saturation $(86.6{\rightarrow}94.1%)$, and median TR grade $(4{\rightarrow}1)$ were also significantly improved (p=0.004, p<0.001). For comparison of BCPS and conservative surgery, the preoperative right ventricular pressure (33.0 vs. 41.3 mmHg), the ICU stay (2.80 vs. 1.89 days), the hospital say (10.6 vs. 16.8 days), and the left ventricular ejection fraction (64.3 vs. 72.8%) were statistically different. Postoperative mortality occurred in 3 patients (6%) due to biventricular failure in 2 patients and sepsis in the other patient. The mean follow up duration was 101.5 months, and one patient died of Fontan failure and 6 patients required reoperation (bioprosthetic degenerative change (2) and Fontan conversion (4)). The overall survival rate at 10 years was 90.2%, the freedom from reoperation rate and rate of cardiac related events were 78.9% and 49.2%, respectively. Conclusion: Surgical management of Ebstein's anomaly can be performed safely, and the associated BCPS may be helpful for high-risk patients. Adequate application of surgical management may increase the long-term survival with a reduced rate of reoperation.

• Information Systems Review
• /
• v.16 no.3
• /
• pp.161-177
• /
• 2014

Corporate credit rating assessment consists of complicated processes in which various factors describing a company are taken into consideration. Such assessment is known to be very expensive since domain experts should be employed to assess the ratings. As a result, the data-driven corporate credit rating prediction using statistical and artificial intelligence (AI) techniques has received considerable attention from researchers and practitioners. In particular, statistical methods such as multiple discriminant analysis (MDA) and multinomial logistic regression analysis (MLOGIT), and AI methods including case-based reasoning (CBR), artificial neural network (ANN), and multiclass support vector machine (MSVM) have been applied to corporate credit rating.2) Among them, MSVM has recently become popular because of its robustness and high prediction accuracy. In this study, we propose a novel optimized MSVM model, and appy it to corporate credit rating prediction in order to enhance the accuracy. Our model, named 'GAMSVM (Genetic Algorithm-optimized Multiclass Support Vector Machine),' is designed to simultaneously optimize the kernel parameters and the feature subset selection. Prior studies like Lorena and de Carvalho (2008), and Chatterjee (2013) show that proper kernel parameters may improve the performance of MSVMs. Also, the results from the studies such as Shieh and Yang (2008) and Chatterjee (2013) imply that appropriate feature selection may lead to higher prediction accuracy. Based on these prior studies, we propose to apply GAMSVM to corporate credit rating prediction. As a tool for optimizing the kernel parameters and the feature subset selection, we suggest genetic algorithm (GA). GA is known as an efficient and effective search method that attempts to simulate the biological evolution phenomenon. By applying genetic operations such as selection, crossover, and mutation, it is designed to gradually improve the search results. Especially, mutation operator prevents GA from falling into the local optima, thus we can find the globally optimal or near-optimal solution using it. GA has popularly been applied to search optimal parameters or feature subset selections of AI techniques including MSVM. With these reasons, we also adopt GA as an optimization tool. To empirically validate the usefulness of GAMSVM, we applied it to a real-world case of credit rating in Korea. Our application is in bond rating, which is the most frequently studied area of credit rating for specific debt issues or other financial obligations. The experimental dataset was collected from a large credit rating company in South Korea. It contained 39 financial ratios of 1,295 companies in the manufacturing industry, and their credit ratings. Using various statistical methods including the one-way ANOVA and the stepwise MDA, we selected 14 financial ratios as the candidate independent variables. The dependent variable, i.e. credit rating, was labeled as four classes: 1(A1); 2(A2); 3(A3); 4(B and C). 80 percent of total data for each class was used for training, and remaining 20 percent was used for validation. And, to overcome small sample size, we applied five-fold cross validation to our dataset. In order to examine the competitiveness of the proposed model, we also experimented several comparative models including MDA, MLOGIT, CBR, ANN and MSVM. In case of MSVM, we adopted One-Against-One (OAO) and DAGSVM (Directed Acyclic Graph SVM) approaches because they are known to be the most accurate approaches among various MSVM approaches. GAMSVM was implemented using LIBSVM-an open-source software, and Evolver 5.5-a commercial software enables GA. Other comparative models were experimented using various statistical and AI packages such as SPSS for Windows, Neuroshell, and Microsoft Excel VBA (Visual Basic for Applications). Experimental results showed that the proposed model-GAMSVM-outperformed all the competitive models. In addition, the model was found to use less independent variables, but to show higher accuracy. In our experiments, five variables such as X7 (total debt), X9 (sales per employee), X13 (years after founded), X15 (accumulated earning to total asset), and X39 (the index related to the cash flows from operating activity) were found to be the most important factors in predicting the corporate credit ratings. However, the values of the finally selected kernel parameters were found to be almost same among the data subsets. To examine whether the predictive performance of GAMSVM was significantly greater than those of other models, we used the McNemar test. As a result, we found that GAMSVM was better than MDA, MLOGIT, CBR, and ANN at the 1% significance level, and better than OAO and DAGSVM at the 5% significance level.