• Radiation Oncology Journal
• /
• v.13 no.3
• /
• pp.215-223
• /
• 1995

Purpose : The aim of this study was to assess the effectiveness, survival rate and complication of radiation in nasopharyngeal cancer. Materials and Methods : From January 1980 to May 1989. Fifty patients who had nasopharyngeal carcinoma treated with curative radiation therapy at Kosin Medical Center were retrospectively studied. Thirty seven patients($74{\%}$) were treated with radiation therapy alone(Group I) and 13 patients ($26{\%}$) treated with combination of chemotherapy and radiation (Group II). Age distribution was 16-75 years(median : 45.8 years). In histologic type, squamous cell carcinoma was in 30 patients($60{\%}$), undifferentiated carcinoma in 17 patients($34{\%}$), and lymphoepithelioma in 3 patients($6{\%}$). According t AJCC staging system. 4 patients($8{\%}$) were in $T_1$, 13 patients($26{\%}$) in $T_2$. 20 patients($40{\%}$) in $T_3$, 13 patients($26{\%}$) in $T_4$ and 7 patients($14{\%}$) in $N_0$, 6 patients($12{\%}$) $N_1$, 23 patients($46{\%}$) in $N_2$, 14 patients($28{\%}$) in $N_3$. Total radiation dose ranges were 5250-9200cGy(median : 7355 cGy) in Group I and 5360-8400cGy(median : 6758cGy) in Group II Radiotherapy on 4-6MV linear accelerator and/or 6-12MeV electron in boost radiation was given with conventional technique to 26 patients($52{\%}$), with hyperfractionation(115-120cGy/fr., 2times/day) to 16 patients($32{\%}$), with accelerated fractionation(160cGy/fr., 2 times/day) to 8 patients($16{\%}$). In chemotherapy, 5 FU 1000mg daily for 5 consecutive days, pepleomycin 10mg on days 1 and 3, and cisplatin 100mg on day 1 were administered with 3weeks interval, total 1 to 3 cycles(average 1.8cycles) prior to radiation therapy. Follow up duration was 6-140 months(mean : 58 months). Statistics was calculated with Chi-square and Fisher's exact test. Results : Complete local control rates in Group I and II were $75.7{\%},\;69.2{\%} Overall 5 year survival rates in Group I and II were $56.8{\%},\;30.8{\%}$. Five year survival rates by histologic type in Group I and II were $52.2{\%},\;14.3{\%}$ is squamous cell carcinoma and $54.5{\%},\;50{\%}$ in undifferentiated carcinoma. Survival rates in Group I were superior to those of Group II though there were not statistically significant. In both group, survival rates seem to be increased according to increasing total dose of radiation up to 7500cGy, but not increased beyond it. There were not statistically significant differences in survival rates by age, stage, and radiation techniques in both group. Twenty four patients($48{\%}$) experienced treatment failures. Complications were found in 12 patients($24{\%}$). The most common one was osteomyelitis(4 patients, $33.3{\%}$) involving mandible (3 patients) and maxilla(1 patient). Conclusion : Chemotherapy in combination with radiotherapy was found to be not effective to nasopharyngeal cancer and the survival rate was also inferior to that of radiation alone group though it was statistically not significant due to small population in chemotherapy combined group.

• Restorative Dentistry and Endodontics
• /
• v.30 no.6
• /
• pp.450-460
• /
• 2005

The aim of this study was to evaluate the effect of cavity shape, bond quality of bonding agent and volume of resin composite on shrinkage stress developed at the cavity floor. This was done by measuring the shear bond strength with respect to iris materials (cavity shape , adhesive-coated dentin as a high C-factor and Teflon-coated metal as a low C-factor), bonding agents (bond quality: $Scotchbond^{TM}$ Multi-purpose and Xeno III) and iris hole diameters (volume; 1mm or 3mm in $diameter{\times}1.5mm$ in thickness). Ninety-six molars were randomly divided into 8 groups ($2{\times}2{\times}2$ experimental setup). In order to simulate a Class I cavity, shear bond strength was measured on the flat occlusal dentin surface with irises. The iris hole was filled with Z250 restorative resin composite in a bulk-filling manner. The data was analyzed using three-way ANOVA and the Tukey test. Fracture mode analysis was also done When the cavity had high C-factor, good bond quality and large volume, the bond strength decreased significantly The volume of resin composite restricted within the well-bonded cavity walls is also be suggested to be included in the concept of C-factor, as well as the cavity shape and bond quality. Since the bond quality and volume can exaggerate the effect of cavity shape on the shrinkage stress developed at the resin-dentin bond, resin composites must be filled in a method, which minimizes the volume that can increase the C-factor.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.22 no.1
• /
• pp.67-75
• /
• 2018

Purpose The purpose of this study is to investigate and analyze the external dose rates of $^{18}F-FDG$ Whole Body PET/CT patients by distance, and to identify the main factors that contribute to the reduction of radiation dose by checking the cumulative doses of nuclear medicine technologist(NMT). Materials and Methods After completion of the $^{18}F-FDG$ Whole Body PET/CT scan($75.4{\pm}3.3min$), the external dose rates of 106 patients were measured at a distance of 0, 10, 30, 50, and 100 cm from the chest. Gender, age, BMI(Body Mass Index), fasting time, diabetes mellitus, radiopharmaceutical injection information, creatine value were collected to analyze individual factors that could affect external dose rates from a patient's perspective. From the perspective of NMT, personal pocket dosimeters were worn on the chest to record accumulated dose of NMT who performed the injection task($T_1$, $T_2$ and $T_3$) and scan task($T_4$, $T_5$ and $T_6$). In addition, patient contact time with NMT was measured and analyzed. Results External dose rates from the patient for each distance were calculated as $246.9{\pm}37.6$, $129.9{\pm}16.7$, $61.2{\pm}9.1$, $34.4{\pm}5.9$, and $13.1{\pm}2.4{\mu}Sv/hr$ respectively. On the patient's aspect, there was a significant difference in the proximity of gender, BMI, Injection dose and creatine value, but the difference decreased as the distance increased. In case of dialysis patient, external dose rates for each distance were exceptionally higher than other patients. On the NMT aspect, the doses received from patients were 0.70, 1.09, $0.55{\mu}Sv/person$ for performing the injection task($T_1$, $T_2$, and $T_3$), and were 1.25, 0.82, $1.23{\mu}Sv/person$ for performing the scan task($T_4$, $T_5$, $T_6$). Conclusion we found that maintaining proper distance with patient and reducing contact time with patient had a significant effect on accumulated doses. Considering those points, efforts such as sufficient water intake and encourage of urination, maintaining the proper distance between the NMT and the patient(at least 100 cm), and reducing the contact time should be done for reducing dose rates not only patient but also NMT.

• Parasites, Hosts and Diseases
• /
• v.28 no.4
• /
• pp.241-252
• /
• 1990

In a basic attempt to develop the prophylactic and therapeutic measures on intestinal giantcystic disease of the Israel carp, C), prinks carpio nudum, the effects of physical and chemical factors on viability or survival of the spores of Thelchcnellus kiteuei were checked in vitro by means of extrusion test on the polar filament. When the fresh spores suspended with 0.45% and 0.9% scdium chloride solution and distilled water were laid at $5^{\circ}C$ and $28^{\circ}C$ for short terms, the extrusion rates increased until the 3rd day, meanwhile when son;e of them were suspended with Tyrode's solution at $-70^{\circ}C$ the rates increased gradually until the 8th day. Viabilities of the spores suspended with 0.9% saline and added antibiotics to the suspension at $5^{\circ}C$ for long terms lasted for 997 days and 1, 256 days (presumed values) at maximum, respectively. The spores suspended with distilled water at $28^{\circ}C$ for long terms survived 152.4 days, but the spores suspended with Tyrode's solution at $-70^{\circ}C$ for long terms showed almost the same viable pattern as early freezing stages up to 780 days. The spores suspended with Tyrode's solution, frozen at $-70^{\circ}C$ and thawed at $5^{\circ}C$, showed the highest rate of extrusion of the polar filament. In the case of frozen spores, the extrusion rates during heating tend to become higher in accordance with the increase of frozen period, and the critical points of 180 day-frozen spores to be killed were generally 78.5 hr. at $60^{\circ}C$, 23.4 hr. at $70^{\circ}C$, 189.1 min. at $80^{\circ}C$ or 10.5 min. at $90^{\circ}C$. The longer the spores were frozen, the more time was needed for the death of spores after thawing; 20 days-17.4 days, 100 days-33.2 days, and 400 days-37.8 days. The longer the spores were frozen, the more time was needed for the death of spores at a conventional when they were dried air drying condition, 540 days-23.5 days, 160 days-21.0 days, and 20 days-14.4 days. On the other hand, the longer the spores were frozen, the more spores were dead rapidly when they were irradiated with 10W UV-ray; 100 days-26.0 hr, 300 days-21.9 hr, and 540 days-13.9 hr. The time needed for killing 200 days-frozen spores by various disinfectants at 1, 000 ppd was 5.2 min. by calcium oxide, 10.4 min. by potassium permanganate, 27.8 min. by malachite green and 14.3 hr. by formalin. Transient inhibitory effects of the extrusion of the polar filament were observed by various antiprotozoal and antifungal agents in the descending order of ketoconazole. metronidasole and dapsone. The above results presume that full drying, followed by spraying CaO and maintaining sunny condition for a few days on the concrete bottoms of knish farm may be an effective method for the prevention of intestinal giant.cystic disease.

• 한국초등상담교육학회:학술대회논문집
• /
• 2004.01a
• /
• pp.223-245
• /
• 2004

The purpose of this study was to investigate the differences in depression, irrational faith and the school adaptation of elementary school students by their sex and region, to provide basic materials to teach children with the likelihood to be depressed by analyzing the correlation of depression, irrational faith and school adaptation, and help them to have healthy emotion and behaviors. To achieve these goals, following agenda were set. First, what are the differences in the depression, the irrational faith and the school adaptation of elementary school students by their sex and region? Second, what is the relationship between the depression characteristics and the irrational faith of elementary school students? Third, what is the relationship between the irrational faith and the school adaptation of elementary school students? Fourth, what is the relationship between the depression characteristics and school adaptation of elementary school students? : To resolve these agenda, the subjects were selected from Grade 6 students from the elementary schools locatec in Suwon and Hwaseong. The jubjects were selected from the two schools in Suwon and three schools in Hwaseong which were randomly chosen. The subjects were 670 in total. 70 insincere answers were excluded from the analysis. Therefore the subjects used in the analysis were 600 in total(150 male and female students in city respectively and 150 male and female students in rural area respectively). The tools used for this study were Children's Depression Inventory (CDI), Irrational Faith Test (over-self-reliance, dichotomy, determinism, over-concern, evasive faith, over dependent faith), School Adaptation Test (Attitudes to teachers and school environments, hobbies and specialties, academic achievements, peer relationship). Materials were processed with the SPSS program for ANOVA and correlation analysis. All the statistical values were verified at .05 level. The followings are the results of the analysis of the collected data. First, in the analysis of depression, there was significant difference between male and female students (F=4.75, p<.05). Female students (X =56.93) showed a little higher value than male students (X =53.83). There was significant difference between regions (F=13.02, p<.001), too. Rural area students (X =57.93) showed higher value than city area students (X =52.82). When analyzing irrational faith, there was significant difference between male and female students (F=S.60, p<.05). Female students (X =81.32) showed a little higher value than male students (X =77.72). There was no significant difference according to regions. When analyzing the school adaptation, there was no significant difference according to either sex or region. Second, depression and irrational faith showed highly positive correlations in all areas. In particular, over concern and evasive faith showed the highest correlation with depression inclination (r=.68, p<.001). When looking into the results by sex and by region, female students (r=.70, p<.001) and the rural area students (r=.69, p<.001) showed higher correlation between depression and irrational faith than male students and city area students (r=.63, p<.001). Additionally, in all areas including by sex and by region, a positive correlation was shown. In all variables such as male students (r=.63, p<.001), female students (r=.72, p<.001), city area students (r=.66, p<.001), and rural area students (r=.69, p<.001), over concern and evasive faith showed the highest correlation with depression inclinations. Third, irrational faith (overall) and its sub factors such as over-self-reliance, dichotomy, determinism, over-concern and evasive faith had significant negative correlations with school adaptation (overall) and its sub factors in the scope of $r=-.27{\sim}-.52$. Determinism out of the sub factors of the irrational faith had the highest negative correlation with school adaptation (overall) and sub factors at the scope of $r=-.37{\sim}-.51$. However, over-self-reliance showed the negative correlation with school adaptation (overall) and its sub factors only partially. When looking into the results by gender, both genders showed significant negative correlation between irrational faith (overall) and its sub factors with school adaptation. Male students showed highly negative correlations with school adaptation (overall) and its sub factors in determinism ($r=-.35{\sim}-52$) and over-concern and evasive faith($r=-.31{\sim}-.51$), and fern ale students showed in over-self-reliance ($r=-.27{\sim}-.45$). However over-self-reliance showed negative correlation with school adaptation and its sub factors only partially. When looking into by region, both city and rural areas showed significant negative correlation between irrational faith (overall) and it sub factors, and school adaptation. Rural areas showed higher negative correlation in irrational faith (overall) ($r=-.39{\sim}-.53$) and over-self-reliance ($r=-.32{\sim}-.44$) and dichotomy ($r=-.28{\sim}-.39$) than city areas. However over-self-reliance showed negative correlation with school adaptation and its sub factors only partially. Fourth, depression and school adaptation showed the negative correlation in all areas. In particular, academic achievements and peer relationship showed the highest negative correlation with depression (r=-.53 p<.001). When looking into the results by sex and by region, female students (r=-.62, p<.001) and rural area students (r=-.61, p<.001) showed higher negative correlation with depression and school adaptation than female students (r=-.56, p<.001) and city area students (r=-.57, p<.001). Although there was negative correlation in all areas by sex and by region, male students (r=-.52, p<.001) and rural area students (r=-.56, p<.001) showed the highest negative correlation in peer relationship and female students (r=-.57, p<.001) and city area students (r=-.56, p<.001) showed the highest negative correlation in academic records. Based on the results of the study, it is proposed to provide elementary school students sho are likely to be depressed very easily with careful counselling and teaching based on the attention and love in school fields so that they can adapt themselves to home, school and society with positive and reasonable thinking.

• The Korean Journal of Air & Space Law and Policy
• /
• v.29 no.2
• /
• pp.109-134
• /
• 2014

Regulation (EC) No 261/2004 of the European Parliament and of the Council of 11 February 2004 establishing common rules on compensation of assistance to passengers in the event of denied boarding and of cancellation or long delay of flights (Regulation No 261/2004) provides extra protection to air passengers in circumstances of denied boarding, cancellation and long-delay. The Regulation intends to provide a high level of protection to air passengers by imposing obligations on air carriers and, at the same time, offering extensive rights to air passengers. If denied boarding, cancellation and long-delay are caused by reasons other than extraordinary circumstances, passengers are entitled for compensation under Article 7 of Regulation No 261/2004. In Wallentin-Hermann v Alitalia-Linee Aeree Italiane SpA(Case C-549/07, [2008] ECR I-11061), the Court did, however, emphasize that this does not mean that it is never possible for technical problems to constitute extraordinary circumstances. It cited specific examples of where: an aircraft manufacturer or competent authority revealed that there was a hidden manufacturing defect on an aircraft which impacts on safety; or damage was caused to an aircraft as a result of an act of sabotage or terrorism. Such events are not inherent in the normal exercise of the activity of the air carrier concerned and is beyond the actual control of that carrier on account of its nature or origin. One further point arising out of the court's decision is worth mentioning. It is not just necessary to satisfy the extraordinary circumstances test for the airline to be excused from paying compensation. It must also show that the circumstances could not have been avoided even if all reasonable measures had been taken. It is clear from the language of the Court's decision that this is a tough test to meet: the airline will have to establish that, even if it had deployed all its resources in terms of staff or equipment and the financial means at its disposal, it would clearly not have been able - unless it had made intolerable sacrifices in the light of the capacities of its undertaking at the relevant time - to prevent the extraordinary circumstances with which it was confronted from leading to the cancellation of the flight.

• Journal of Intelligence and Information Systems
• /
• v.18 no.2
• /
• pp.29-45
• /
• 2012

Bond rating is regarded as an important event for measuring financial risk of companies and for determining the investment returns of investors. As a result, it has been a popular research topic for researchers to predict companies' credit ratings by applying statistical and machine learning techniques. The statistical techniques, including multiple regression, multiple discriminant analysis (MDA), logistic models (LOGIT), and probit analysis, have been traditionally used in bond rating. However, one major drawback is that it should be based on strict assumptions. Such strict assumptions include linearity, normality, independence among predictor variables and pre-existing functional forms relating the criterion variablesand the predictor variables. Those strict assumptions of traditional statistics have limited their application to the real world. Machine learning techniques also used in bond rating prediction models include decision trees (DT), neural networks (NN), and Support Vector Machine (SVM). Especially, SVM is recognized as a new and promising classification and regression analysis method. SVM learns a separating hyperplane that can maximize the margin between two categories. SVM is simple enough to be analyzed mathematical, and leads to high performance in practical applications. SVM implements the structuralrisk minimization principle and searches to minimize an upper bound of the generalization error. In addition, the solution of SVM may be a global optimum and thus, overfitting is unlikely to occur with SVM. In addition, SVM does not require too many data sample for training since it builds prediction models by only using some representative sample near the boundaries called support vectors. A number of experimental researches have indicated that SVM has been successfully applied in a variety of pattern recognition fields. However, there are three major drawbacks that can be potential causes for degrading SVM's performance. First, SVM is originally proposed for solving binary-class classification problems. Methods for combining SVMs for multi-class classification such as One-Against-One, One-Against-All have been proposed, but they do not improve the performance in multi-class classification problem as much as SVM for binary-class classification. Second, approximation algorithms (e.g. decomposition methods, sequential minimal optimization algorithm) could be used for effective multi-class computation to reduce computation time, but it could deteriorate classification performance. Third, the difficulty in multi-class prediction problems is in data imbalance problem that can occur when the number of instances in one class greatly outnumbers the number of instances in the other class. Such data sets often cause a default classifier to be built due to skewed boundary and thus the reduction in the classification accuracy of such a classifier. SVM ensemble learning is one of machine learning methods to cope with the above drawbacks. Ensemble learning is a method for improving the performance of classification and prediction algorithms. AdaBoost is one of the widely used ensemble learning techniques. It constructs a composite classifier by sequentially training classifiers while increasing weight on the misclassified observations through iterations. The observations that are incorrectly predicted by previous classifiers are chosen more often than examples that are correctly predicted. Thus Boosting attempts to produce new classifiers that are better able to predict examples for which the current ensemble's performance is poor. In this way, it can reinforce the training of the misclassified observations of the minority class. This paper proposes a multiclass Geometric Mean-based Boosting (MGM-Boost) to resolve multiclass prediction problem. Since MGM-Boost introduces the notion of geometric mean into AdaBoost, it can perform learning process considering the geometric mean-based accuracy and errors of multiclass. This study applies MGM-Boost to the real-world bond rating case for Korean companies to examine the feasibility of MGM-Boost. 10-fold cross validations for threetimes with different random seeds are performed in order to ensure that the comparison among three different classifiers does not happen by chance. For each of 10-fold cross validation, the entire data set is first partitioned into tenequal-sized sets, and then each set is in turn used as the test set while the classifier trains on the other nine sets. That is, cross-validated folds have been tested independently of each algorithm. Through these steps, we have obtained the results for classifiers on each of the 30 experiments. In the comparison of arithmetic mean-based prediction accuracy between individual classifiers, MGM-Boost (52.95%) shows higher prediction accuracy than both AdaBoost (51.69%) and SVM (49.47%). MGM-Boost (28.12%) also shows the higher prediction accuracy than AdaBoost (24.65%) and SVM (15.42%)in terms of geometric mean-based prediction accuracy. T-test is used to examine whether the performance of each classifiers for 30 folds is significantly different. The results indicate that performance of MGM-Boost is significantly different from AdaBoost and SVM classifiers at 1% level. These results mean that MGM-Boost can provide robust and stable solutions to multi-classproblems such as bond rating.

• Journal of Animal Science and Technology
• /
• v.45 no.2
• /
• pp.229-240
• /
• 2003

An in vitro test and a broiler feeding trial were conducted to test the effect of hydrothermal treatment of wheat bran on phytate-P degradation and it’s feeding effect on performance of broilers. Hydrothermal treatment of wheat bran was carried out at 55$^{\circ}C$ with pH 5.5 buffer solution. Phytate-P content of wheat bran decreased quadrically as the wheat bran: buffer solution ratio increased from 1:0.5 to 1:5. Phytate-P degradation was not significantly affected by incubation times above 10 min., drying temperature (55$^{\circ}C$, 65$^{\circ}C$ and 75$^{\circ}C$) or pH of the buffer solution (5.5 and 7.0). A feeding trial was conducted with 240 sex separated d-old broiler chickens (Ross$^{\circledR}$). Broilers were randomly housed to 24 cages of 10 birds each. Six cages (3 of each sex) were assigned to 4 treatments: Control-normal level of non-phytate-P (NPP); LP-low NPP treatment which had 0.1% lower NPP than Control; LPWB-LP with wheat bran which provided 475 IU of plant phytase per kg diet; LPHWB-LP with hydrothermally treated wheat bran. Results of the feeding trial showed that broilers in the LP treatment gained significantly less than other treatments in starter period (1-21d) but only male broilers for growing LP gained significantly less than Control in the grower (22-35d) and overall period. There were no significant differences in weight gain among the birds of LPWB, LPHWB and Control. Feed intake during the overall period was not significantly different between LPWB and Control but that of LP was lower than LPHWB and that of LPHWB was lower than Control. Feed/gain ratio was significantly lower in LPHWB and LP than in Control and LPWP. Mortality was highest in LPHWB. Availability of crude fat, crude ash and Ca was significantly lower in LP than other treatments. Availability of P and Zn was higher in LPWB and LPHWB than in Control and LP. Availability of P, Mg and Zn was highest in LPHWP treatment. Excretion of P was significantly lower in low NPP treatments than in Control. Serum Ca level was highest whereas serum P level was lowest in LP. Tibial crude ash content was higher in wheat bran treatments, but lower in LP than Control. However, tibial Ca content was higher in Control and LP than wheat bran treatments. Tibial P content of LP and LPWB was lower than Control. However, tibial content of Fe was highest in LP. It was concluded that wheat bran, a source of plant phytase, could be used in low NPP broiler diets to prevent the depression of performance. Reduction of P excretion can be achieved concomitantly. Hydrothermal treatment of wheat bran was effective in improving utilizability of some minerals but was not effective in improving performance of broilers.

• Information Systems Review
• /
• v.14 no.3
• /
• pp.75-97
• /
• 2012

Fostering trusting belief in financial transactions is a challenging task in Internet banking services. Authenticated Certificate had been regarded as an effective method to guarantee the trusting belief for online transactions. However, previous research claimed that this method has some loopholes for such abusers as hackers, who intend to attack the financial accounts of innocent transactors in Internet. Two types of methods have been suggested as alternatives for securing user identification and activity in online financial services. Control transparency uses information over the transaction process to verify and to control the transactions. Outcome feedback, which refers to the specific information about exchange outcomes, provides information over final transaction results. By using these two methods, financial service providers can send signals to involved parties about the robustness of their security mechanisms. These two methods-control transparency and outcome feedback-have been widely used in the IS field to enhance the quality of IS services. In this research, we intend to verify that these two methods can also be used to reduce risks and to increase the security protections in online banking services. The purpose of this paper is to empirically test the effects of the control transparency and the outcome feedback on the risk perceptions in Internet banking services. Our assumption is that these two methods-control transparency and outcome feedback-can reduce perceived risks involved with online financial transactions, while increasing perceived trust over financial service providers. These changes in user attitudes can increase the level of user satisfactions, which may lead to the increased user loyalty as well as users' willingness to pay for the financial transactions. Previous research in IS suggested that the increased level of transparency on the process and the result of transactions can enhance the information quality and decision quality of IS users. Transparency helps IS users to acquire the information needed to control the transaction counterpart and thus to complete transaction successfully. It is also argued that transparency can reduce the perceived transaction risks in IS usage. Many IS researchers also argued that the trust can be generated by the institutional mechanisms. Trusting belief refers to the truster's belief for the trustee to have attributes for being beneficial to the truster. Institution-based trust plays an important role to enhance the probability of achieving a successful outcome. When a transactor regards the conditions crucial for the transaction success, he or she considers the condition providers as trustful, and thus eventually trust the others involved with such condition providers. In this process, transparency helps the transactor complete the transaction successfully. Through the investigation of these studies, we expect that the control transparency and outcome feedback can reduce the risk perception on transaction and enhance the trust with the service provider. Based on a theoretical framework of transparency and institution-based trust, we propose and test a research model by evaluating research hypotheses. We have conducted a laboratory experiment in order to validate our research model. Since the transparency artifact(control transparency and outcome feedback) is not yet adopted in online banking services, the general survey method could not be employed to verify our research model. We collected data from 138 experiment subjects who had experiences with online banking services. PLS is used to analyze the experiment data. The measurement model confirms that our data set has appropriate convergent and discriminant validity. The results of testing the structural model indicate that control transparency significantly enhances the trust and significantly reduces the risk perception of online banking users. The result also suggested that the outcome feedback significantly enhances the trust of users. We have found that the reduced risk and the increased trust level significantly improve the level of service satisfaction. The increased satisfaction finally leads to the increased loyalty and willingness to pay for the financial services.

• Journal of Intelligence and Information Systems
• /
• v.23 no.4
• /
• pp.127-146
• /
• 2017

Services using artificial intelligence have begun to emerge in daily life. Artificial intelligence is applied to products in consumer electronics and communications such as artificial intelligence refrigerators and speakers. In the financial sector, using Kensho's artificial intelligence technology, the process of the stock trading system in Goldman Sachs was improved. For example, two stock traders could handle the work of 600 stock traders and the analytical work for 15 people for 4weeks could be processed in 5 minutes. Especially, big data analysis through machine learning among artificial intelligence fields is actively applied throughout the financial industry. The stock market analysis and investment modeling through machine learning theory are also actively studied. The limits of linearity problem existing in financial time series studies are overcome by using machine learning theory such as artificial intelligence prediction model. The study of quantitative financial data based on the past stock market-related numerical data is widely performed using artificial intelligence to forecast future movements of stock price or indices. Various other studies have been conducted to predict the future direction of the market or the stock price of companies by learning based on a large amount of text data such as various news and comments related to the stock market. Investing on commodity asset, one of alternative assets, is usually used for enhancing the stability and safety of traditional stock and bond asset portfolio. There are relatively few researches on the investment model about commodity asset than mainstream assets like equity and bond. Recently machine learning techniques are widely applied on financial world, especially on stock and bond investment model and it makes better trading model on this field and makes the change on the whole financial area. In this study we made investment model using Support Vector Machine among the machine learning models. There are some researches on commodity asset focusing on the price prediction of the specific commodity but it is hard to find the researches about investment model of commodity as asset allocation using machine learning model. We propose a method of forecasting four major commodity indices, portfolio made of commodity futures, and individual commodity futures, using SVM model. The four major commodity indices are Goldman Sachs Commodity Index(GSCI), Dow Jones UBS Commodity Index(DJUI), Thomson Reuters/Core Commodity CRB Index(TRCI), and Rogers International Commodity Index(RI). We selected each two individual futures among three sectors as energy, agriculture, and metals that are actively traded on CME market and have enough liquidity. They are Crude Oil, Natural Gas, Corn, Wheat, Gold and Silver Futures. We made the equally weighted portfolio with six commodity futures for comparing with other commodity indices. We set the 19 macroeconomic indicators including stock market indices, exports & imports trade data, labor market data, and composite leading indicators as the input data of the model because commodity asset is very closely related with the macroeconomic activities. They are 14 US economic indicators, two Chinese economic indicators and two Korean economic indicators. Data period is from January 1990 to May 2017. We set the former 195 monthly data as training data and the latter 125 monthly data as test data. In this study, we verified that the performance of the equally weighted commodity futures portfolio rebalanced by the SVM model is better than that of other commodity indices. The prediction accuracy of the model for the commodity indices does not exceed 50% regardless of the SVM kernel function. On the other hand, the prediction accuracy of equally weighted commodity futures portfolio is 53%. The prediction accuracy of the individual commodity futures model is better than that of commodity indices model especially in agriculture and metal sectors. The individual commodity futures portfolio excluding the energy sector has outperformed the three sectors covered by individual commodity futures portfolio. In order to verify the validity of the model, it is judged that the analysis results should be similar despite variations in data period. So we also examined the odd numbered year data as training data and the even numbered year data as test data and we confirmed that the analysis results are similar. As a result, when we allocate commodity assets to traditional portfolio composed of stock, bond, and cash, we can get more effective investment performance not by investing commodity indices but by investing commodity futures. Especially we can get better performance by rebalanced commodity futures portfolio designed by SVM model.