• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1125-1139
• /
• 2022

In an unmanned aerial vehicles (UAVs) system, a physical offset can be existed between the global positioning system/inertial measurement unit (GPS/IMU) sensor and the observation sensor such as a hyperspectral sensor, and a lidar sensor. As a result of the physical offset, a misalignment between each image can be occurred along with a flight direction. In particular, in a case of multi-sensor system, an observation sensor has to be replaced regularly to equip another observation sensor, and then, a high cost should be paid to acquire a calibration parameter. In this study, we establish a precise sensor model equation to apply for a multiple sensor in common and propose an independent physical offset estimation method. The proposed method consists of 3 steps. Firstly, we define an appropriate rotation matrix for our system, and an initial sensor model equation for direct-georeferencing. Next, an observation equation for the physical offset estimation is established by extracting a corresponding point between a ground control point and the observed data from a sensor. Finally, the physical offset is estimated based on the observed data, and the precise sensor model equation is established by applying the estimated parameters to the initial sensor model equation. 4 region's datasets(Jeon-ju, Incheon, Alaska, Norway) with a different latitude, longitude were compared to analyze the effects of the calibration parameter. We confirmed that a misalignment between images were adjusted after applying for the physical offset in the sensor model equation. An absolute position accuracy was analyzed in the Incheon dataset, compared to a ground control point. For the hyperspectral image, root mean square error (RMSE) for X, Y direction was calculated for 0.12 m, and for the point cloud, RMSE was calculated for 0.03 m. Furthermore, a relative position accuracy for a specific point between the adjusted point cloud and the hyperspectral images were also analyzed for 0.07 m, so we confirmed that a precise data mapping is available for an observation without a ground control point through the proposed estimation method, and we also confirmed a possibility of multi-sensor fusion. From this study, we expect that a flexible multi-sensor platform system can be operated through the independent parameter estimation method with an economic cost saving.

• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.249-263
• /
• 2023

Collaborative Filtering, a representative recommendation system methodology, consists of two approaches: neighbor methods and latent factor models. Among these, the latent factor model using matrix factorization decomposes the user-item interaction matrix into two lower-dimensional rectangular matrices, predicting the item's rating through the product of these matrices. Due to the factor vectors inferred from rating patterns capturing user and item characteristics, this method is superior in scalability, accuracy, and flexibility compared to neighbor-based methods. However, it has a fundamental drawback: the need to reflect the diversity of preferences of different individuals for items with no ratings. This limitation leads to repetitive and inaccurate recommendations. The Adaptive Deep Latent Factor Model (ADLFM) was developed to address this issue. This model adaptively learns the preferences for each item by using the item description, which provides a detailed summary and explanation of the item. ADLFM takes in item description as input, calculates latent vectors of the user and item, and presents a method that can reflect personal diversity using an attention score. However, due to the requirement of a dataset that includes item descriptions, the domain that can apply ADLFM is limited, resulting in generalization limitations. This study proposes a Generalized Adaptive Deep Latent Factor Recommendation Model, G-ADLFRM, to improve the limitations of ADLFM. Firstly, we use item ID, commonly used in recommendation systems, as input instead of the item description. Additionally, we apply improved deep learning model structures such as Self-Attention, Multi-head Attention, and Multi-Conv1D. We conducted experiments on various datasets with input and model structure changes. The results showed that when only the input was changed, MAE increased slightly compared to ADLFM due to accompanying information loss, resulting in decreased recommendation performance. However, the average learning speed per epoch significantly improved as the amount of information to be processed decreased. When both the input and the model structure were changed, the best-performing Multi-Conv1d structure showed similar performance to ADLFM, sufficiently counteracting the information loss caused by the input change. We conclude that G-ADLFRM is a new, lightweight, and generalizable model that maintains the performance of the existing ADLFM while enabling fast learning and inference.

• Analytical Science and Technology
• /
• v.22 no.6
• /
• pp.488-497
• /
• 2009

In this study, analytical methodology for several organic fatty acids (OFA: propionic acid (PA), butyric acid (BA), isovaleric acid (IA), and valeric acid (VA)) designated as new offensive odorants in Korea (as of year 2010) was investigated along with some odorous VOCs (styrene, toluene, xylene, methyl ethyl ketone, methyl isobutyl ketone, butyl acetate, and isobutyl alcohol). For this purpose, working standards (WS) containing all of these 13 compounds were loaded into adsorption tube filled with Tenax TA, and analyzed by gas chromatography (GC) system thermal desorber interfaced with. The analytical sensitivities of organic fatty acids expressed in terms of detection limit (both in absolute mass (ng) and concentration (ppb)) were lower by 1.5-2 times than other compounds (PA: 0.24 ng (0.16 ppb), BA: 0.19 ng (0.11 ppb), IA: 0.15 ng (0.07 ppb), and VA: 0.28 ng (0.13 ppb)). The precision of BA, IA, and VA, if assessed in terms of relative standard error (RSE), maintained above 5%, while the precison of other compounds were below 5%. The reproducibility of analysis improved with the aid of internal standard calibration (PA: $1.1{\pm}0.4%$, BA: $10{\pm}0.46$, IA; $12{\pm}0.3%$, VA: $4{\pm}0.1%$), respectively. The results of this study showed that organic fatty acid can be analyzed using adsorption tube and thermal desorber in a more reliable way to replace alkali absorption method introduced in the odor prevention law of the Korea Ministry of Environment (KMOE).

• Journal of Korean Society of Forest Science
• /
• v.112 no.4
• /
• pp.417-425
• /
• 2023

The aim of this study was to derive stem taper equations for Quercus acuta, one of main evergreen broad-leaved tree species found in warm temperate regions, and to prepare a stem volume table using those stem taper equations. A total of 688 individual trees were used in the analysis, which were collected from Jeonnam-do, Gyeongnam-do, and Jeju-do. The stem taper models applied to derive the stem curve pattern were the Max and Burkhart, Kozak, and Lee models. Among the three stem taper models, the best explanation of the stem curve shape of Q. acuta was found to be given by the Kozak model, which showed a fitness index of 0.9583, bias of 0.0352, percentage of estimated standard error of 1.1439, and mean absolute deviation of 0.6751. Thus, the stem taper of Q. acuta was estimated using the Kozak model. Moreover,thestemvolumecalculationwasperforme d by applying the Smalian formula to the diameter and height of each stem interval. In addition, an analysis of variance (ANOVA) was conducted to compare the two existing Q. acuta stem volume tables (2007 and 2010) and the newly created stem volume table (2023). This analysis revealed that the stem volume table constructed in the Wando region in 2007 included about twice as much as the stem volume tables constructed in 2010 and 2023. The stem volume table (2023) developed in this study is not only based on the regional collection range and number of utilized trees but also on a sound scientific basis. Therefore, it can be used at the national level as an official stem volume table for Q. acuta.

• Journal of Korea Water Resources Association
• /
• v.57 no.1
• /
• pp.1-8
• /
• 2024

Persistent droughts due to climate change will intensify water shortage problems in Korea. According to the 1st National Water Management Plan, the shortage of domestic and industrial waters is projected to be 0.07 billion m³/year under a 50-year drought event. A long-term prediction of water demand is essential for effectively responding to water shortage problems. Unlike industrial water, which has a relatively constant monthly usage, domestic water is analyzed on monthly basis due to apparent monthly usage patterns. We analyzed monthly water usage patterns using water usage data from 2017 to 2021 in Chungcheong, South Korea. The monthly water usage rate was calculated by dividing monthly water usage by annual water usage. We also calculated the water distribution rate considering correlations between water usage rate and climate variables. The division method that divided the monthly water usage rate by monthly average temperature resulted in the smallest absolute error. Using the division method with average temperature, we calculated the water distribution rates for the Chungcheong region. Then we predicted future water usage rates in the Chungcheong region by multiplying the average temperature of the SSP5-8.5 scenario and the water distribution rate. As a result, the average of the maximum water usage rate increased from 1.16 to 1.29 and the average of the minimum water usage rate decreased from 0.86 to 0.84, and the first quartile decreased from 0.95 to 0.93 and the third quartile increased from 1.04 to 1.06. Therefore, it is expected that the variability in monthly water usage rates will increase in the future.

• The Journal of Korean Society for Radiation Therapy
• /
• v.25 no.2
• /
• pp.115-121
• /
• 2013

Purpose: Latest linear accelerator and the introduction of new measurement equipment to the agency that the introduction of this equipment in the future, by analyzing the process of confirming the usefulness of the preparation process for applying it in the clinical causes some problems, should be helpful. Materials and Methods: All measurements TrueBEAM STX (Varian, USA) was used, and a file specific to each energy, irradiation conditions, the dose distribution was calculated using a computerized treatment planning equipment (Eclipse ver 10.0.39, Varian, USA). Measuring performance and cause errors in MapCHECK 2 were analyzed and measured against. In order to verify the performance of the MapCHECK 2, 6X, 6X-FFF, 10X, 10X-FFF, 15X field size $10{\times}10$ cm, gantry $0^{\circ}$, $180^{\circ}$ direction was measured by the energy. IGRT couch of the CT values affect the measurements in order to confirm, CT number values : -800 (Carbon) & -950 (COUCH in the air), -100 & 6X-950 in the state for FFF, 15X of the energy field sizes $10{\times}10$, gantry $180^{\circ}$, $135^{\circ}$, $275^{\circ}$ directionwas measured at, MapPHAN allocated to confirm the value of HU were compared, using the treatment planning computer for, Measurement error problem by the sharp edges MapPHAN Learn gantry direction MapPHAN of dependence was measured in three ways. GANTRY $90^{\circ}$, $270^{\circ}$ in the direction of the vertically erected settings 6X-FFF, 15X respectively, and Setting the state established as a horizontal field sizes $10{\times}10$, $90^{\circ}$, $45^{\circ}$, $315^{\circ}$, $270^{\circ}$ of in the direction of the energy-6X-FFF, 15X, respectively, were measured. Without intensity modulated beam of the third open arc were investigated. Results: Of basic performance MapCHECK confirm the attenuation measured by Couch, measured from the measured HU values that are assigned to the MAP-PHAN, check for calculation accuracy for the angled edge of the MapPHAN all come in a range of valid measurement errors do not affect the could see. three ways for the Gantry direction dependence, the first of the meter built into the value of the Gantry $270^{\circ}$ (relative $0^{\circ}$), $90^{\circ}$ (relative $180^{\circ}$), 6X-FFF, 15X from each -1.51, 0.83% and -0.63, -0.22% was not affected by the AP/PA direction represented. Setting the meter horizontally Gantry $90^{\circ}$, $270^{\circ}$ from the couch, Energy 6X-FFF 4.37, 2.84%, 15X, -9.63, -13.32% the difference. By-side direction measurements MapPHAN in value is not within the valid range can not, because that could be confirmed as gamma pass rate 3% of the value is greater than the value shown. You can check the Open Arc 6X-FFF, 15X energy, field size $10{\times}10$ cm $360^{\circ}$ rotation of the dose distribution in the state to look at nearly 90% pass rate to emerge. Conclusion: Based on the above results, the MapPHAN gantry direction dependence by side in the direction of the beam relative dose distribution suitable for measuring the gamma value, but accurate measurement of the absolute dose can not be considered is. this paper, a more accurate treatment plan in order to confirm, Reduce the tolerance for VMAT, such as lateral rotation investigation in order to measure accurate absolute isodose using a combination of IMF (Isocentric Mounting Fixture) MapCHEK 2, will be able to minimize the impact due to the angular dependence.

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.85-109
• /
• 2018

Recommender system recommends the items expected to be purchased by a customer in the future according to his or her previous purchase behaviors. It has been served as a tool for realizing one-to-one personalization for an e-commerce service company. Traditional recommender systems, especially the recommender systems based on collaborative filtering (CF), which is the most popular recommendation algorithm in both academy and industry, are designed to generate the items list for recommendation by using 'overall rating' - a single criterion. However, it has critical limitations in understanding the customers' preferences in detail. Recently, to mitigate these limitations, some leading e-commerce companies have begun to get feedback from their customers in a form of 'multicritera ratings'. Multicriteria ratings enable the companies to understand their customers' preferences from the multidimensional viewpoints. Moreover, it is easy to handle and analyze the multidimensional ratings because they are quantitative. But, the recommendation using multicritera ratings also has limitation that it may omit detail information on a user's preference because it only considers three-to-five predetermined criteria in most cases. Under this background, this study proposes a novel hybrid recommendation system, which selectively uses the results from 'traditional CF' and 'CF using multicriteria ratings'. Our proposed system is based on the premise that some people have holistic preference scheme, whereas others have composite preference scheme. Thus, our system is designed to use traditional CF using overall rating for the users with holistic preference, and to use CF using multicriteria ratings for the users with composite preference. To validate the usefulness of the proposed system, we applied it to a real-world dataset regarding the recommendation for POI (point-of-interests). Providing personalized POI recommendation is getting more attentions as the popularity of the location-based services such as Yelp and Foursquare increases. The dataset was collected from university students via a Web-based online survey system. Using the survey system, we collected the overall ratings as well as the ratings for each criterion for 48 POIs that are located near K university in Seoul, South Korea. The criteria include 'food or taste', 'price' and 'service or mood'. As a result, we obtain 2,878 valid ratings from 112 users. Among 48 items, 38 items (80%) are used as training dataset, and the remaining 10 items (20%) are used as validation dataset. To examine the effectiveness of the proposed system (i.e. hybrid selective model), we compared its performance to the performances of two comparison models - the traditional CF and the CF with multicriteria ratings. The performances of recommender systems were evaluated by using two metrics - average MAE(mean absolute error) and precision-in-top-N. Precision-in-top-N represents the percentage of truly high overall ratings among those that the model predicted would be the N most relevant items for each user. The experimental system was developed using Microsoft Visual Basic for Applications (VBA). The experimental results showed that our proposed system (avg. MAE = 0.584) outperformed traditional CF (avg. MAE = 0.591) as well as multicriteria CF (avg. AVE = 0.608). We also found that multicriteria CF showed worse performance compared to traditional CF in our data set, which is contradictory to the results in the most previous studies. This result supports the premise of our study that people have two different types of preference schemes - holistic and composite. Besides MAE, the proposed system outperformed all the comparison models in precision-in-top-3, precision-in-top-5, and precision-in-top-7. The results from the paired samples t-test presented that our proposed system outperformed traditional CF with 10% statistical significance level, and multicriteria CF with 1% statistical significance level from the perspective of average MAE. The proposed system sheds light on how to understand and utilize user's preference schemes in recommender systems domain.

• Journal of Intelligence and Information Systems
• /
• v.18 no.3
• /
• pp.185-202
• /
• 2012

.Since the value of information has been realized in the information society, the usage and collection of information has become important. A facial expression that contains thousands of information as an artistic painting can be described in thousands of words. Followed by the idea, there has recently been a number of attempts to provide customers and companies with an intelligent service, which enables the perception of human emotions through one's facial expressions. For example, MIT Media Lab, the leading organization in this research area, has developed the human emotion prediction model, and has applied their studies to the commercial business. In the academic area, a number of the conventional methods such as Multiple Regression Analysis (MRA) or Artificial Neural Networks (ANN) have been applied to predict human emotion in prior studies. However, MRA is generally criticized because of its low prediction accuracy. This is inevitable since MRA can only explain the linear relationship between the dependent variables and the independent variable. To mitigate the limitations of MRA, some studies like Jung and Kim (2012) have used ANN as the alternative, and they reported that ANN generated more accurate prediction than the statistical methods like MRA. However, it has also been criticized due to over fitting and the difficulty of the network design (e.g. setting the number of the layers and the number of the nodes in the hidden layers). Under this background, we propose a novel model using Support Vector Regression (SVR) in order to increase the prediction accuracy. SVR is an extensive version of Support Vector Machine (SVM) designated to solve the regression problems. The model produced by SVR only depends on a subset of the training data, because the cost function for building the model ignores any training data that is close (within a threshold ${\varepsilon}$) to the model prediction. Using SVR, we tried to build a model that can measure the level of arousal and valence from the facial features. To validate the usefulness of the proposed model, we collected the data of facial reactions when providing appropriate visual stimulating contents, and extracted the features from the data. Next, the steps of the preprocessing were taken to choose statistically significant variables. In total, 297 cases were used for the experiment. As the comparative models, we also applied MRA and ANN to the same data set. For SVR, we adopted '${\varepsilon}$-insensitive loss function', and 'grid search' technique to find the optimal values of the parameters like C, d, ${\sigma}^2$, and ${\varepsilon}$. In the case of ANN, we adopted a standard three-layer backpropagation network, which has a single hidden layer. The learning rate and momentum rate of ANN were set to 10%, and we used sigmoid function as the transfer function of hidden and output nodes. We performed the experiments repeatedly by varying the number of nodes in the hidden layer to n/2, n, 3n/2, and 2n, where n is the number of the input variables. The stopping condition for ANN was set to 50,000 learning events. And, we used MAE (Mean Absolute Error) as the measure for performance comparison. From the experiment, we found that SVR achieved the highest prediction accuracy for the hold-out data set compared to MRA and ANN. Regardless of the target variables (the level of arousal, or the level of positive / negative valence), SVR showed the best performance for the hold-out data set. ANN also outperformed MRA, however, it showed the considerably lower prediction accuracy than SVR for both target variables. The findings of our research are expected to be useful to the researchers or practitioners who are willing to build the models for recognizing human emotions.

• Journal of Intelligence and Information Systems
• /
• v.20 no.2
• /
• pp.73-92
• /
• 2014

An Adaptive Clustering-based Collaborative Filtering Technique was proposed to solve the fundamental problems of collaborative filtering, such as cold-start problems, scalability problems and data sparsity problems. Previous collaborative filtering techniques were carried out according to the recommendations based on the predicted preference of the user to a particular item using a similar item subset and a similar user subset composed based on the preference of users to items. For this reason, if the density of the user preference matrix is low, the reliability of the recommendation system will decrease rapidly. Therefore, the difficulty of creating a similar item subset and similar user subset will be increased. In addition, as the scale of service increases, the time needed to create a similar item subset and similar user subset increases geometrically, and the response time of the recommendation system is then increased. To solve these problems, this paper suggests a collaborative filtering technique that adapts a condition actively to the model and adopts the concepts of a context-based filtering technique. This technique consists of four major methodologies. First, items are made, the users are clustered according their feature vectors, and an inter-cluster preference between each item cluster and user cluster is then assumed. According to this method, the run-time for creating a similar item subset or user subset can be economized, the reliability of a recommendation system can be made higher than that using only the user preference information for creating a similar item subset or similar user subset, and the cold start problem can be partially solved. Second, recommendations are made using the prior composed item and user clusters and inter-cluster preference between each item cluster and user cluster. In this phase, a list of items is made for users by examining the item clusters in the order of the size of the inter-cluster preference of the user cluster, in which the user belongs, and selecting and ranking the items according to the predicted or recorded user preference information. Using this method, the creation of a recommendation model phase bears the highest load of the recommendation system, and it minimizes the load of the recommendation system in run-time. Therefore, the scalability problem and large scale recommendation system can be performed with collaborative filtering, which is highly reliable. Third, the missing user preference information is predicted using the item and user clusters. Using this method, the problem caused by the low density of the user preference matrix can be mitigated. Existing studies on this used an item-based prediction or user-based prediction. In this paper, Hao Ji's idea, which uses both an item-based prediction and user-based prediction, was improved. The reliability of the recommendation service can be improved by combining the predictive values of both techniques by applying the condition of the recommendation model. By predicting the user preference based on the item or user clusters, the time required to predict the user preference can be reduced, and missing user preference in run-time can be predicted. Fourth, the item and user feature vector can be made to learn the following input of the user feedback. This phase applied normalized user feedback to the item and user feature vector. This method can mitigate the problems caused by the use of the concepts of context-based filtering, such as the item and user feature vector based on the user profile and item properties. The problems with using the item and user feature vector are due to the limitation of quantifying the qualitative features of the items and users. Therefore, the elements of the user and item feature vectors are made to match one to one, and if user feedback to a particular item is obtained, it will be applied to the feature vector using the opposite one. Verification of this method was accomplished by comparing the performance with existing hybrid filtering techniques. Two methods were used for verification: MAE(Mean Absolute Error) and response time. Using MAE, this technique was confirmed to improve the reliability of the recommendation system. Using the response time, this technique was found to be suitable for a large scaled recommendation system. This paper suggested an Adaptive Clustering-based Collaborative Filtering Technique with high reliability and low time complexity, but it had some limitations. This technique focused on reducing the time complexity. Hence, an improvement in reliability was not expected. The next topic will be to improve this technique by rule-based filtering.

• Journal of Global Scholars of Marketing Science
• /
• v.17 no.2
• /
• pp.55-73
• /
• 2007

Festivals are an indispensable feature of cultural tourism(Formica & Uysal, 1998). Cultural tourism festivals are increasingly being used as instruments promoting tourism and boosting the regional economy. So much research related to festivals is undertaken from a variety of perspectives. Plans to revisit a particular festival have been viewed as an important research topic both in academia and the tourism industry. Therefore festivals have frequently been leveled as cultural events. Cultural tourism festivals have become a crucial component in constituting the attractiveness of tourism destinations(Prentice, 2001). As a result, a considerable number of tourist studies have been carried out in diverse cultural tourism festivals(Backman et al., 1995; Crompton & Mckay, 1997; Park, 1998; Clawson & Knetch, 1996). Much of previous literature empirically shows the close linkage between tourist satisfaction and behavioral intention in festivals. The main objective of this study is to investigate the effects of evaluation attributes of cultural tourism festivals on satisfaction and behavioral intention. accomplish the research objective, to find out evaluation items of cultural tourism festivals through the literature study an empirical study. Using a varimax rotation with Kaiser normalization, the research obtained four factors in the 18 evaluation attributes of cultural tourism festivals. Some empirical studies have examined the relationship between behavioral intention and actual behavior. To understand between tourist satisfaction and behavioral intention, this study suggests five hypotheses and hypothesized model. In this study, the analysis is based on primary data collected from visitors who participated in '2006 Gwangju Kimchi Festival'. In total, 700 self-administered questionnaires were distributed and 561 usable questionnaires were obtained. Respondents were presented with the 18 satisfactions item on a scale from 1(strongly disagree) to 7(strongly agree). Dimensionality and stability of the scale were evaluated by a factor analysis with varimax rotation. Four factors emerged with eigenvalues greater than 1, which explained 66.40% of the total variance and Cronbach' alpha raging from 0.876 to 0.774. And four factors named: advertisement and guides, programs, food and souvenirs, and convenient facilities. To test and estimate the hypothesized model, a two-step approach with an initial measurement model and a subsequent structural model for Structural Equation Modeling was used. The AMOS 4.0 analysis package was used to conduct the analysis. In estimating the model, the maximum likelihood procedure was used.In this study Chi-square test is used, which is the most common model goodness-of-fit test. In addition, considering the literature about the Structural Equation Modeling, this study used, besides Chi-square test, more model fit indexes to determine the tangibility of the suggested model: goodness-of-fit index(GFI) and root mean square error of approximation(RMSEA) as absolute fit indexes; normed-fit index(NFI) and non-normed-fit index(NNFI) as incremental fit indexes. The results of T-test and ANOVAs revealed significant differences(0.05 level), therefore H1(Tourist Satisfaction level should be different from Demographic traits) are supported. According to the multiple Regressions analysis and AMOS, H2(Tourist Satisfaction positively influences on revisit intention), H3(Tourist Satisfaction positively influences on word of mouth), H4(Evaluation Attributes of cultural tourism festivals influences on Tourist Satisfaction), and H5(Tourist Satisfaction positively influences on Behavioral Intention) are also supported. As the conclusion of this study are as following: First, there were differences in satisfaction levels in accordance with the demographic information of visitors. Not all visitors had the same degree of satisfaction with their cultural tourism festival experience. Therefore it is necessary to understand the satisfaction of tourists if the experiences that are provided are to meet their expectations. So, in making festival plans, the organizer should consider the demographic variables in explaining and segmenting visitors to cultural tourism festival. Second, satisfaction with attributes of evaluation cultural tourism festivals had a significant direct impact on visitors' intention to revisit such festivals and the word of mouth publicity they shared. The results indicated that visitor satisfaction is a significant antecedent of their intention to revisit such festivals. Festival organizers should strive to forge long-term relationships with the visitors. In addition, it is also necessary to understand how the intention to revisit a festival changes over time and identify the critical satisfaction factors. Third, it is confirmed that behavioral intention was enhanced by satisfaction. The strong link between satisfaction and behavioral intentions of visitors areensured by high quality advertisement and guides, programs, food and souvenirs, and convenient facilities. Thus, examining revisit intention from a time viewpoint may be of a great significance for both practical and theoretical reasons. Additionally, festival organizers should give special attention to visitor satisfaction, as satisfied visitors are more likely to return sooner. The findings of this research have several practical implications for the festivals managers. The promotion of cultural festivals should be based on the understanding of tourist satisfaction for the long- term success of tourism. And this study can help managers carry out this task in a more informed and strategic manner by examining the effects of demographic traits on the level of tourist satisfaction and the behavioral intention. In other words, differentiated marketing strategies should be stressed and executed by relevant parties. The limitations of this study are as follows; the results of this study cannot be generalized to other cultural tourism festivals because we have not explored the many different kinds of festivals. A future study should be a comparative analysis of other festivals of different visitor segments. Also, further efforts should be directed toward developing more comprehensive temporal models that can explain behavioral intentions of tourists.