• Journal of the Korean Society of Radiology
• /
• 제83권5호
• /
• pp.1090-1103
• /
• 2022

Purpose To evaluate the diagnostic performance of digital breast tomosynthesis (DBT) with the two-dimensional synthesized mammogram (2DSM), compared to full-field digital mammography (FFDM), for suspicious microcalcifications in the breast ahead of stereotactic biopsy and to assess the diagnostic image visibility of the images. Materials and Methods This retrospective study involved 189 patients with microcalcifications, which were histopathologically verified by stereotactic breast biopsy, who underwent DBT with 2DSM and FFDM between January 8, 2015, and January 20, 2020. Two radiologists assessed all cases of microcalcifications based on Breast Imaging Reporting and Data System (BI-RADS) independently. They were blinded to the histopathologic outcome and additionally evaluated lesion visibility using a fivepoint scoring scale. Results Overall, the inter-observer agreement was excellent (0.9559). Under the setting of category 4A as negative due to the low possibility of malignancy and to avoid the dilution of malignancy criteria in our study, McNemar tests confirmed no significant difference between the performances of the two modalities in detecting microcalcifications with a high potential for malignancy (4B, 4C, or 5; p = 0.1573); however, the tests showed a significant difference between their performances in detecting microcalcifications with a high potential for benignancy (4A; p = 0.0009). DBT with 2DSM demonstrated superior visibility and diagnostic performance than FFDM in dense breasts. Conclusion DBT with 2DSM is superior to FFDM in terms of total diagnostic accuracy and lesion visibility for benign microcalcifications in dense breasts. This study suggests a promising role for DBT with 2DSM as an accommodating tool for stereotactic biopsy in female with dense breasts and suspicious breast microcalcifications.

• Korean Journal of Environment and Ecology
• /
• 제38권3호
• /
• pp.277-292
• /
• 2024

In order to manage large-scale forest fires concentrated in Gangwon-do and Gyeongsangbuk-do with severe topographical heterogeneity, a decision-making process through efficient and rapid damage assessment using satellite images is essential. Accordingly, this study targets a large-scale forest fire that ignited in Gangneung and the Donghae, Gangwon-do on March 5, 2022, and was extinguished around 19:00 on March 8, to estimate the fire severity using dNBR and derive environmental factors that affect the grade. As environmental factors, we quantified the regular vegetation index representing vegetation or fuel type, the forest index that classifies tree species, the regular moisture index representing moisture content, and DEM in relation to topography, and then analyzed the correlation with the fire severity. In terms of fire severity, the widest range was 'Unbured' at 52.4%, followed by low severity at 42.9%, medium-low severity at 4.3%, and medium-high severity at 0.4%. Environmental factors showed a negative correlation with dNDVI and dNDWI, and a positive correlation with slope. Regarding vegetation, the differences between coniferous, broad-leaved, and other groups in dNDVI, dNIWI, and slope, which were analyzed to affect the fire severity, were analyzed to be significant with p-value < 2.2e-16. In particular, the difference between coniferous and broad-leaved forests was clear, and it was confirmed that coniferous forest suffered more damage than broad-leaved forest due to the higher fire severity in the Gangwon-do region, including Pinus densiflora, which are dominant species, as well as P. koraiensis, P. rigida and P. thunbergii.

• Journal of Intelligence and Information Systems
• /
• 제23권1호
• /
• pp.95-108
• /
• 2017

Recently, AlphaGo which is Bakuk (Go) artificial intelligence program by Google DeepMind, had a huge victory against Lee Sedol. Many people thought that machines would not be able to win a man in Go games because the number of paths to make a one move is more than the number of atoms in the universe unlike chess, but the result was the opposite to what people predicted. After the match, artificial intelligence technology was focused as a core technology of the fourth industrial revolution and attracted attentions from various application domains. Especially, deep learning technique have been attracted as a core artificial intelligence technology used in the AlphaGo algorithm. The deep learning technique is already being applied to many problems. Especially, it shows good performance in image recognition field. In addition, it shows good performance in high dimensional data area such as voice, image and natural language, which was difficult to get good performance using existing machine learning techniques. However, in contrast, it is difficult to find deep leaning researches on traditional business data and structured data analysis. In this study, we tried to find out whether the deep learning techniques have been studied so far can be used not only for the recognition of high dimensional data but also for the binary classification problem of traditional business data analysis such as customer churn analysis, marketing response prediction, and default prediction. And we compare the performance of the deep learning techniques with that of traditional artificial neural network models. The experimental data in the paper is the telemarketing response data of a bank in Portugal. It has input variables such as age, occupation, loan status, and the number of previous telemarketing and has a binary target variable that records whether the customer intends to open an account or not. In this study, to evaluate the possibility of utilization of deep learning algorithms and techniques in binary classification problem, we compared the performance of various models using CNN, LSTM algorithm and dropout, which are widely used algorithms and techniques in deep learning, with that of MLP models which is a traditional artificial neural network model. However, since all the network design alternatives can not be tested due to the nature of the artificial neural network, the experiment was conducted based on restricted settings on the number of hidden layers, the number of neurons in the hidden layer, the number of output data (filters), and the application conditions of the dropout technique. The F1 Score was used to evaluate the performance of models to show how well the models work to classify the interesting class instead of the overall accuracy. The detail methods for applying each deep learning technique in the experiment is as follows. The CNN algorithm is a method that reads adjacent values from a specific value and recognizes the features, but it does not matter how close the distance of each business data field is because each field is usually independent. In this experiment, we set the filter size of the CNN algorithm as the number of fields to learn the whole characteristics of the data at once, and added a hidden layer to make decision based on the additional features. For the model having two LSTM layers, the input direction of the second layer is put in reversed position with first layer in order to reduce the influence from the position of each field. In the case of the dropout technique, we set the neurons to disappear with a probability of 0.5 for each hidden layer. The experimental results show that the predicted model with the highest F1 score was the CNN model using the dropout technique, and the next best model was the MLP model with two hidden layers using the dropout technique. In this study, we were able to get some findings as the experiment had proceeded. First, models using dropout techniques have a slightly more conservative prediction than those without dropout techniques, and it generally shows better performance in classification. Second, CNN models show better classification performance than MLP models. This is interesting because it has shown good performance in binary classification problems which it rarely have been applied to, as well as in the fields where it's effectiveness has been proven. Third, the LSTM algorithm seems to be unsuitable for binary classification problems because the training time is too long compared to the performance improvement. From these results, we can confirm that some of the deep learning algorithms can be applied to solve business binary classification problems.

• The Journal of Korean Society for Radiation Therapy
• /
• 제23권1호
• /
• pp.31-39
• /
• 2011

Purpose: Helical Tomotherapy allows only coplanar beam delivery because it does not allow couch rotation. We investigated a method to introduce non-coplanar beam by tilting a patient's head for Tomotherapy. The aim of this study was to compare intrafractional movement during Tomotherapy between coplanar and non-coplanar patient's setup. Materials and Methods: Helical Tomotherapy was used for treating eight patients with intracranial tumor. The subjects were divided into three groups: one group (coplanar) of 2 patients who lay on S-plate with supine position and wore thermoplastic mask for immobilizing the head, second group (non-coplanar) of 3 patients who lay on S-plate with supine position and whose head was tilted with Variable Axis Baseplate and wore thermoplastic mask, and third group (non-coplanar plus mouthpiece) of 3 patients whose head was tilted and wore a mouthpiece immobilization device and thermoplastic mask. The patients were treated with Tomotherapy after treatment planning with Tomotherapy Planning System. Megavoltage computed tomography (MVCT) was performed before and after treatment, and the intrafractional error was measured with lateral(X), longitudinal(Y), vertical(Z) direction movements and vector ($\sqrt{x^2+y^2+z^2}$) value for assessing overall movement. Results: Intrafractional error was compared among three groups by taking the error of MVCT taken after the treatment. As the correction values (X, Y, Z) between MVCT image taken after treatment and CT-simulation image are close to zero, the patient movement is small. When the mean values of movement of each direction for non-coplanar setup were compared with coplanar setup group, X-axis movement was decreased by 13%, but Y-axis and Z-axis movement were increased by 109% and 88%, respectively. Movements of Y-axis and Z-axis with non-coplanar setup were relatively greater than that of X-axis since a tilted head tended to slip down. The mean of X-axis movement of the group who used a mouthpiece was greater by 9.4% than the group who did not use, but the mean of Y-axis movement was lower by at least 64%, and the mean of Z-axis was lower by at least 67%, and the mean of Z-axis was lower by at least 67%, and the vector was lower by at least 59% with the use of a mouthpiece. Among these 8 patients, one patient whose tumor was located on left frontal lobe and left basal ganglia received reduced radiation dose of 38% in right eye, 23% in left eye, 30% in optic chiasm, 27% in brain stem, and 8% in normal brain with non-coplanar method. Conclusion: Tomotherapy only allows coplanar delivery of IMRT treatment. To complement this shortcoming, Tomotherapy can be used with non-coplanar method by artificially tilting the patient's head and using an oral immobilization instrument to minimize the movement of patient, when intracranial tumor locates near critical organs or has to be treated with high dose radiation.

• Journal of Intelligence and Information Systems
• /
• 제24권1호
• /
• pp.167-181
• /
• 2018

Over the past decade, deep learning has been in spotlight among various machine learning algorithms. In particular, CNN(Convolutional Neural Network), which is known as the effective solution for recognizing and classifying images or voices, has been popularly applied to classification and prediction problems. In this study, we investigate the way to apply CNN in business problem solving. Specifically, this study propose to apply CNN to stock market prediction, one of the most challenging tasks in the machine learning research. As mentioned, CNN has strength in interpreting images. Thus, the model proposed in this study adopts CNN as the binary classifier that predicts stock market direction (upward or downward) by using time series graphs as its inputs. That is, our proposal is to build a machine learning algorithm that mimics an experts called 'technical analysts' who examine the graph of past price movement, and predict future financial price movements. Our proposed model named 'CNN-FG(Convolutional Neural Network using Fluctuation Graph)' consists of five steps. In the first step, it divides the dataset into the intervals of 5 days. And then, it creates time series graphs for the divided dataset in step 2. The size of the image in which the graph is drawn is $40(pixels){\times}40(pixels)$, and the graph of each independent variable was drawn using different colors. In step 3, the model converts the images into the matrices. Each image is converted into the combination of three matrices in order to express the value of the color using R(red), G(green), and B(blue) scale. In the next step, it splits the dataset of the graph images into training and validation datasets. We used 80% of the total dataset as the training dataset, and the remaining 20% as the validation dataset. And then, CNN classifiers are trained using the images of training dataset in the final step. Regarding the parameters of CNN-FG, we adopted two convolution filters ($5{\times}5{\times}6$ and $5{\times}5{\times}9$) in the convolution layer. In the pooling layer, $2{\times}2$ max pooling filter was used. The numbers of the nodes in two hidden layers were set to, respectively, 900 and 32, and the number of the nodes in the output layer was set to 2(one is for the prediction of upward trend, and the other one is for downward trend). Activation functions for the convolution layer and the hidden layer were set to ReLU(Rectified Linear Unit), and one for the output layer set to Softmax function. To validate our model - CNN-FG, we applied it to the prediction of KOSPI200 for 2,026 days in eight years (from 2009 to 2016). To match the proportions of the two groups in the independent variable (i.e. tomorrow's stock market movement), we selected 1,950 samples by applying random sampling. Finally, we built the training dataset using 80% of the total dataset (1,560 samples), and the validation dataset using 20% (390 samples). The dependent variables of the experimental dataset included twelve technical indicators popularly been used in the previous studies. They include Stochastic %K, Stochastic %D, Momentum, ROC(rate of change), LW %R(Larry William's %R), A/D oscillator(accumulation/distribution oscillator), OSCP(price oscillator), CCI(commodity channel index), and so on. To confirm the superiority of CNN-FG, we compared its prediction accuracy with the ones of other classification models. Experimental results showed that CNN-FG outperforms LOGIT(logistic regression), ANN(artificial neural network), and SVM(support vector machine) with the statistical significance. These empirical results imply that converting time series business data into graphs and building CNN-based classification models using these graphs can be effective from the perspective of prediction accuracy. Thus, this paper sheds a light on how to apply deep learning techniques to the domain of business problem solving.

• Journal of Intelligence and Information Systems
• /
• 제25권1호
• /
• pp.1-19
• /
• 2019

Artificial intelligence (AI) is one of the main driving forces leading the Fourth Industrial Revolution. The technologies associated with AI have already shown superior abilities that are equal to or better than people in many fields including image and speech recognition. Particularly, many efforts have been actively given to identify the current technology trends and analyze development directions of it, because AI technologies can be utilized in a wide range of fields including medical, financial, manufacturing, service, and education fields. Major platforms that can develop complex AI algorithms for learning, reasoning, and recognition have been open to the public as open source projects. As a result, technologies and services that utilize them have increased rapidly. It has been confirmed as one of the major reasons for the fast development of AI technologies. Additionally, the spread of the technology is greatly in debt to open source software, developed by major global companies, supporting natural language recognition, speech recognition, and image recognition. Therefore, this study aimed to identify the practical trend of AI technology development by analyzing OSS projects associated with AI, which have been developed by the online collaboration of many parties. This study searched and collected a list of major projects related to AI, which were generated from 2000 to July 2018 on Github. This study confirmed the development trends of major technologies in detail by applying text mining technique targeting topic information, which indicates the characteristics of the collected projects and technical fields. The results of the analysis showed that the number of software development projects by year was less than 100 projects per year until 2013. However, it increased to 229 projects in 2014 and 597 projects in 2015. Particularly, the number of open source projects related to AI increased rapidly in 2016 (2,559 OSS projects). It was confirmed that the number of projects initiated in 2017 was 14,213, which is almost four-folds of the number of total projects generated from 2009 to 2016 (3,555 projects). The number of projects initiated from Jan to Jul 2018 was 8,737. The development trend of AI-related technologies was evaluated by dividing the study period into three phases. The appearance frequency of topics indicate the technology trends of AI-related OSS projects. The results showed that the natural language processing technology has continued to be at the top in all years. It implied that OSS had been developed continuously. Until 2015, Python, C ++, and Java, programming languages, were listed as the top ten frequently appeared topics. However, after 2016, programming languages other than Python disappeared from the top ten topics. Instead of them, platforms supporting the development of AI algorithms, such as TensorFlow and Keras, are showing high appearance frequency. Additionally, reinforcement learning algorithms and convolutional neural networks, which have been used in various fields, were frequently appeared topics. The results of topic network analysis showed that the most important topics of degree centrality were similar to those of appearance frequency. The main difference was that visualization and medical imaging topics were found at the top of the list, although they were not in the top of the list from 2009 to 2012. The results indicated that OSS was developed in the medical field in order to utilize the AI technology. Moreover, although the computer vision was in the top 10 of the appearance frequency list from 2013 to 2015, they were not in the top 10 of the degree centrality. The topics at the top of the degree centrality list were similar to those at the top of the appearance frequency list. It was found that the ranks of the composite neural network and reinforcement learning were changed slightly. The trend of technology development was examined using the appearance frequency of topics and degree centrality. The results showed that machine learning revealed the highest frequency and the highest degree centrality in all years. Moreover, it is noteworthy that, although the deep learning topic showed a low frequency and a low degree centrality between 2009 and 2012, their ranks abruptly increased between 2013 and 2015. It was confirmed that in recent years both technologies had high appearance frequency and degree centrality. TensorFlow first appeared during the phase of 2013-2015, and the appearance frequency and degree centrality of it soared between 2016 and 2018 to be at the top of the lists after deep learning, python. Computer vision and reinforcement learning did not show an abrupt increase or decrease, and they had relatively low appearance frequency and degree centrality compared with the above-mentioned topics. Based on these analysis results, it is possible to identify the fields in which AI technologies are actively developed. The results of this study can be used as a baseline dataset for more empirical analysis on future technology trends that can be converged.

• The Korean Journal of Nuclear Medicine Technology
• /
• 제14권2호
• /
• pp.3-8
• /
• 2010

Purpose: $^{11}C$-Acetate PET/CT is useful in detecting lesions that are related to livers in the human body and leads to a sensitivity of 87.3%. On the other hand, $^{18}F$-FDG PET/CT has a sensitivity of 47.3% and it has been reported that if both $^{18}F$-FDG and $^{11}C$-Acetate PET/CT are carried out together, their cumulative sensitivity is around 100%. However, the normal intake of the pancreas and the spleen in $^{11}C$-Acetate PET/CT can influence the $^{18}F$-FDG PET/CT leading to an inaccurate diagnosis. This research was aimed at the verification of the usefulness of how much influence these two radioactive medical supplies can cause on the medical images through comparative analysis between the one-day and two-day protocol. Materials and Methods: This research was carried out based on 46 patients who were diagnosed with liver cancer and have gone through the PET/CT (35 male, 11 female participants, average age: $54{\pm}10.6$ years, age range: 29-69 years). The equipment used for this test was the Biograph TruePoint40 PET/CT (Siemens Medical Systems, USA) and 21 participants who went through the one-day protocol test were first given the $^{11}C$-Acetate PET/CT and the $^{18}F$-FDG PET/CT, the latter exactly after one hour. The other 25 participants who went through the two-day protocol test were given the $^{11}C$-Acetate PET/CT on the first day and the $^{18}F$-FDG PET/CT on the next day. These two groups were then graded comparatively by assigning identical areas of interest of the pancreas and the spleen in the $^{18}F$-FDG images and by measuring the Standard Uptake Value (SUV). SPSS Ver.17 (SPSS Inc., USA) was used for statistical analysis, where statistical significance was found through the unpaired t-test. Results: After analyzing the participants' medical images from each of the two different protocol types, the average${\pm}$standard deviation of the SUV of the pancreas carried out under the two-day protocol were as follows: head $1.62{\pm}0.32$ g/mL, body $1.57{\pm}0.37$ g/mL, tail $1.49{\pm}0.33$ g/mL and the spleen $1.53{\pm}0.28$ g/mL. Whereas, the results for participants carried out under the one-day protocol were as follows: head $1.65{\pm}0.35$ g/mL, body $1.58{\pm}0.27$ g/mL, tail $1.49{\pm}0.28$ g/mL and the spleen $1.66{\pm}0.29$ g/mL. Conclusion: It was found that no statistical significant difference existed between the one-day and two-day protocol SUV in the pancreas and the spleen (p<0.05), and nothing which could be misconceived as false positive were found from the PET/CT medical image analysis. From this research, it was also found that no overestimation of the SUV occurred from the influence of $^{11}C$-Acetate on the $^{18}F$-FDG medical images where those two tests were carried out for one day. This result was supported by the statistical significance of the SUV of measurement. If $^{11}C$-Acetate becomes commercialized in the future, the diagnostic ability of liver diseases can be improved by $^{18}F$-FDG and one-day protocol. It is from this result where tests can be accomplished in one day without the interference phenomenon of the two radioactive medical supplies and furthermore, could reduce the waiting time improving customer satisfaction.

• Nuclear Medicine and Molecular Imaging
• /
• 제40권4호
• /
• pp.218-227
• /
• 2006

Purpose: The HSV1-tk reporter gene system is the most widely used system because of its advantage that direct monitoring is possible without the introduction of a separate reporter gene in case of HSV1-tk suicide gene therapy. In this study, we investigate the usefulness of the reporter probe (substrate), $9-(4-[^{18}F]Fluoro-3-hydroxymethylbutyl)$guanine ($[^{18}F]FHBG$) for non-invasive reporter gene imaging using PET in HSV1-tk expressing hepatoma model. Materials and Methods: Radiolabeled FHBG was prepared in 8 steps from a commercially available triester. The labeling reaction was carried out by NCA nucleophilic substitution with $K[^{18}F]/K2.2.2.$ in acetonitrile using N2-monomethoxytrityl-9-14-(tosyl)-3-monomethoxytritylmethylbutyl]guanine as a precursor, followed by deprotection with 1 N HCl. Preliminary biological properties of the probe were evaluated with MCA cells and MCA-tk cells transduced with HSV1-tk reporter gene. In vitro uptake and release-out studies of $[^{18}F]FHBG$ were performed, and was analyzed correlation between $[^{18}F]FHBG$ uptake ratio according to increasing numeric count of MCA-tk cells and degree of gene expression. MicroPET scan image was obtained with MCA and MCA-tk tumor bearing Balb/c-nude mouse model. Results: $[^{18}F]FHBG$ was purified by reverse phase semi-HPLC system and collected at around 16-18 min. Radiothemical yield was about 20-25%) (corrected for decay), radiochemical purity was >95% and specific activity was around >55.5 $GBq/{\mu}\;mol$. Specific accumulation of $[^{18}F]FHBG$ was observed in HSV1-tk gene transduced MCA-tk cells but not in MCA cells, and consecutive 1 hour release-out results showed more than 86% of uptaked $[^{18}F]FHBG$ was retained inside of cells. The uptake of $[^{18}F]FHBG$ was showed a highly significant linear correlation ($R^2=0.995$) with increasing percentage of MCA-tk numeric cell count. In microPET scan images, remarkable difference of accumulation was observed for the two type of tumors. Conclusion: $[^{18}F]FHBG$ appears to be a useful as non-invasive PET imaging substrate in HSV1-tk expressing hepatoma model.

• Journal of radiological science and technology
• /
• 제33권2호
• /
• pp.109-120
• /
• 2010

The purpose of this study was first to analyze the utilization of dental examination through questionnaire to develop a diagnostic reference level of patient doses for dental radiography in korea. 77 dental institutions were classified into three groups: A group for the dental hospitals of the college of dentistry (11 institutions), B group for dental hospitals (30 institutions) and C group for dental clinics (36 institutions). The results were as follows : The mean numbers of unit chairs and medical staffs were 140.2, 15.3 and 5.8 sets, 112.6, 7.3 and 1.7 dentists, 3.1, 0.5 and no one radiologic technologists, and 19.7, 12.5 and 3.3 dental hygienists in A, B and C groups, respectively. The mean numbers of dental X-ray equipments were 14.64, 3.21 and 2.19 in A, B and C groups, respectively. Intraoral dental X-ray unit was used the most, the following equipments were panoramic, cephalometric, and cone-beam CT units. The most used X-ray imaging system was also digital system (above 50%) in all three groups. Insight dental film (Kodak, USA) having high sensitivity was routinely used for periapical radiography. The automatic processor was not used in many dental institutions, but the film-holding device was used in many dental institutions. The utilization rates of PACS in A, B and C groups were 90.9%, 83.3% and 16.7% respectively, and the PACS software program was used the most PiView STAR (Infinitt, Korea). The annual mean number of radiographic cases in one dental institution in 2008 for A group was 6.8 times and 21.2 times more than those for B and C groups, and periapical and panoramic radiographs were taken mostly. Tube voltage (kVp) and tube current (mA) for periapical radiography were similar in all three groups, but exposure time in C group was 12.0 times and 3.5 times longer than those in B and C groups. The amount of radiation exposure in C group, in which dental hygienists take dental radiographs, was more than those in other groups. The exposure parameters for panoramic radiography were similar in all three groups. In conclusion, the exposure parameters in dental radiography should be determined with reference level, not past experiences. Use of automatic processor and film-holding devices reduces the radiation exposure in film system. The quality assurance of dental equipments are necessary for the reduction of the patient dose and the improvement of X-ray image quality.

• Journal of Distribution Research
• /
• 제15권3호
• /
• pp.1-34
• /
• 2010

Introduction The purpose of this research is to develop overall model which involves the effect of ongoing support services by franchisor on franchisee's relationship quality(trust, satisfaction, and commitment) and business performance(financial and non-financial performance), and to investigate the relationships among trust, satisfaction, commitment, financial and non-financial performance. This study also suggests franchise business or franchise system should be based on long-term orientation between franchisor and franchisee rather than short-term orientation, or transactional relationship, and proposes the most effective way of providing on-going support services by franchisor with franchisee thru symbiotic relationship among franchisor and franchisee Research Model and Hypothesis The research model as Figure 1 shows the variables on-going support services which affect the relationship quality between franchisor and franchisee such as trust, satisfaction, and commitment, and also analyze the effects of relationship quality on business performance including financial and non-financial performance We established 12 hypotheses to test as follows; Relationship between on-going support services and trust H1: On-going support services factors (product category & price, logistics service, promotion, information providing & problem solving capability, supervisor's support, and education & training support) have positive effect on franchisee's trust. Relationship between on-going support services and satisfaction H2: On-going support services factors (product category & price, logistics service, promotion, information providing & problem solving capability, supervisor's support, and education & training support) have positive effect on franchisee's satisfaction. Relationship between on-going support services and commitment H3: On-going support services factors (product category & price, logistics service, promotion, information providing & problem solving capability, supervisor's support, and education & training support) have positive effect on franchisee's commitment. Relationship among relationship quality: trust, satisfaction, and commitment H4: Franchisee's trust has positive effect on franchisee's satisfaction. H5: Franchisee's trust has positive effect on franchisee's commitment. H6: Franchisee's satisfaction has positive effect on franchisee's commitment. Relationship between relationship quality and business performance H7: Franchisee's trust has positive effect on franchisee's financial performance. H8: Franchisee's trust has positive effect on franchisee's non-financial performance. H9: Franchisee's satisfaction has positive effect on franchisee's financial performance. H10: Franchisee's satisfaction has positive effect on franchisee's non-financial performance. H11: Franchisee's commitment has positive effect on franchisee's financial performance. H12: Franchisee's commitment has positive effect on franchisee's non-financial performance. Method The on-going support services were defined as an organized system of continuous supporting services by franchisor for the purpose of satisfying the expectation of franchisee based on long-term orientation and classified into six constructs such as product category & price, logistics service, promotion, providing information & problem solving capability, supervisor's support, and education & training support. The six constructs were measured agreement using a 7-point Likert-type scale (1 = strongly disagree to 7 = strongly agree)as follows. The product category & price was measured by four items: menu variety, price of food material provided by franchisor, and support for developing new menu. The logistics service was measured by six items: distribution system of franchisor, return policy for provided food materials, timeliness, inventory control level of franchisor, accuracy of order, and flexibility of emergency order. The promotion was measured by five items: differentiated promotion activities, brand image of franchisor, promotion effect such as customer increase, long-term plan of promotion, and micro-marketing concept in promotion. The providing information & problem solving capability was measured by information providing of new products, information of competitors, information of cost reduction, and efforts for solving problems in franchisee's operations. The supervisor's support was measured by supervisor operations, frequency of visiting franchisee, support by data analysis, processing the suggestions by franchisee, diagnosis and solutions for the franchisee's operations, and support for increasing sales in franchisee. Finally, the of education & training support was measured by recipe training by specialist, service training for store people, systemized training program, and tax & human resources support services. Analysis and results The data were analyzed using Amos. Figure 2 and Table 1 present the result of the structural equation model. Implications The results of this research are as follows: Firstly, the factors of product category, information providing and problem solving capacity influence only franchisee's satisfaction and commitment. Secondly, logistic services and supervising factors influence only trust and satisfaction. Thirdly, continuing education and training factors influence only franchisee's trust and commitment. Fourthly, sales promotion factor influences all the relationship quality representing trust, satisfaction, and commitment. Fifthly, regarding relationship among relationship quality, trust positively influences satisfaction, however, does not directly influence commitment, but satisfaction positively affects commitment. Therefore, satisfaction plays a mediating role between trust and commitment. Sixthly, trust positively influence only financial performance, and satisfaction and commitment influence positively both financial and non-financial performance.