• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.67-83
• /
• 2018

The Korean film industry with significant increase every year exceeded the number of cumulative audiences of 200 million people in 2013 finally. However, starting from 2015 the Korean film industry entered a period of low growth and experienced a negative growth after all in 2016. To overcome such difficulty, stakeholders like production company, distribution company, multiplex have attempted to maximize the market returns using strategies of predicting change of market and of responding to such market change immediately. Since a film is classified as one of experiential products, it is not easy to predict a box office record and the initial number of audiences before the film is released. And also, the number of audiences fluctuates with a variety of factors after the film is released. So, the production company and distribution company try to be guaranteed the number of screens at the opining time of a newly released by multiplex chains. However, the multiplex chains tend to open the screening schedule during only a week and then determine the number of screening of the forthcoming week based on the box office record and the evaluation of audiences. Many previous researches have conducted to deal with the prediction of box office records of films. In the early stage, the researches attempted to identify factors affecting the box office record. And nowadays, many studies have tried to apply various analytic techniques to the factors identified previously in order to improve the accuracy of prediction and to explain the effect of each factor instead of identifying new factors affecting the box office record. However, most of previous researches have limitations in that they used the total number of audiences from the opening to the end as a target variable, and this makes it difficult to predict and respond to the demand of market which changes dynamically. Therefore, the purpose of this study is to predict the weekly number of audiences of a newly released film so that the stakeholder can flexibly and elastically respond to the change of the number of audiences in the film. To that end, we considered the factors used in the previous studies affecting box office and developed new factors not used in previous studies such as the order of opening of movies, dynamics of sales. Along with the comprehensive factors, we used the machine learning method such as Random Forest, Multi Layer Perception, Support Vector Machine, and Naive Bays, to predict the number of cumulative visitors from the first week after a film release to the third week. At the point of the first and the second week, we predicted the cumulative number of visitors of the forthcoming week for a released film. And at the point of the third week, we predict the total number of visitors of the film. In addition, we predicted the total number of cumulative visitors also at the point of the both first week and second week using the same factors. As a result, we found the accuracy of predicting the number of visitors at the forthcoming week was higher than that of predicting the total number of them in all of three weeks, and also the accuracy of the Random Forest was the highest among the machine learning methods we used. This study has implications in that this study 1) considered various factors comprehensively which affect the box office record and merely addressed by other previous researches such as the weekly rating of audiences after release, the weekly rank of the film after release, and the weekly sales share after release, and 2) tried to predict and respond to the demand of market which changes dynamically by suggesting models which predicts the weekly number of audiences of newly released films so that the stakeholders can flexibly and elastically respond to the change of the number of audiences in the film.

• Journal of Intelligence and Information Systems
• /
• v.26 no.4
• /
• pp.1-25
• /
• 2020

Sentiment Analysis (SA) is a Natural Language Processing (NLP) task that analyzes the sentiments consumers or the public feel about an arbitrary object from written texts. Furthermore, Aspect-Based Sentiment Analysis (ABSA) is a fine-grained analysis of the sentiments towards each aspect of an object. Since having a more practical value in terms of business, ABSA is drawing attention from both academic and industrial organizations. When there is a review that says "The restaurant is expensive but the food is really fantastic", for example, the general SA evaluates the overall sentiment towards the 'restaurant' as 'positive', while ABSA identifies the restaurant's aspect 'price' as 'negative' and 'food' aspect as 'positive'. Thus, ABSA enables a more specific and effective marketing strategy. In order to perform ABSA, it is necessary to identify what are the aspect terms or aspect categories included in the text, and judge the sentiments towards them. Accordingly, there exist four main areas in ABSA; aspect term extraction, aspect category detection, Aspect Term Sentiment Classification (ATSC), and Aspect Category Sentiment Classification (ACSC). It is usually conducted by extracting aspect terms and then performing ATSC to analyze sentiments for the given aspect terms, or by extracting aspect categories and then performing ACSC to analyze sentiments for the given aspect category. Here, an aspect category is expressed in one or more aspect terms, or indirectly inferred by other words. In the preceding example sentence, 'price' and 'food' are both aspect categories, and the aspect category 'food' is expressed by the aspect term 'food' included in the review. If the review sentence includes 'pasta', 'steak', or 'grilled chicken special', these can all be aspect terms for the aspect category 'food'. As such, an aspect category referred to by one or more specific aspect terms is called an explicit aspect. On the other hand, the aspect category like 'price', which does not have any specific aspect terms but can be indirectly guessed with an emotional word 'expensive,' is called an implicit aspect. So far, the 'aspect category' has been used to avoid confusion about 'aspect term'. From now on, we will consider 'aspect category' and 'aspect' as the same concept and use the word 'aspect' more for convenience. And one thing to note is that ATSC analyzes the sentiment towards given aspect terms, so it deals only with explicit aspects, and ACSC treats not only explicit aspects but also implicit aspects. This study seeks to find answers to the following issues ignored in the previous studies when applying the BERT pre-trained language model to ACSC and derives superior ACSC models. First, is it more effective to reflect the output vector of tokens for aspect categories than to use only the final output vector of [CLS] token as a classification vector? Second, is there any performance difference between QA (Question Answering) and NLI (Natural Language Inference) types in the sentence-pair configuration of input data? Third, is there any performance difference according to the order of sentence including aspect category in the QA or NLI type sentence-pair configuration of input data? To achieve these research objectives, we implemented 12 ACSC models and conducted experiments on 4 English benchmark datasets. As a result, ACSC models that provide performance beyond the existing studies without expanding the training dataset were derived. In addition, it was found that it is more effective to reflect the output vector of the aspect category token than to use only the output vector for the [CLS] token as a classification vector. It was also found that QA type input generally provides better performance than NLI, and the order of the sentence with the aspect category in QA type is irrelevant with performance. There may be some differences depending on the characteristics of the dataset, but when using NLI type sentence-pair input, placing the sentence containing the aspect category second seems to provide better performance. The new methodology for designing the ACSC model used in this study could be similarly applied to other studies such as ATSC.

• Journal of Intelligence and Information Systems
• /
• v.26 no.4
• /
• pp.173-198
• /
• 2020

For a long time, many studies have been conducted on predicting the success of campaigns for customers in academia, and prediction models applying various techniques are still being studied. Recently, as campaign channels have been expanded in various ways due to the rapid revitalization of online, various types of campaigns are being carried out by companies at a level that cannot be compared to the past. However, customers tend to perceive it as spam as the fatigue of campaigns due to duplicate exposure increases. Also, from a corporate standpoint, there is a problem that the effectiveness of the campaign itself is decreasing, such as increasing the cost of investing in the campaign, which leads to the low actual campaign success rate. Accordingly, various studies are ongoing to improve the effectiveness of the campaign in practice. This campaign system has the ultimate purpose to increase the success rate of various campaigns by collecting and analyzing various data related to customers and using them for campaigns. In particular, recent attempts to make various predictions related to the response of campaigns using machine learning have been made. It is very important to select appropriate features due to the various features of campaign data. If all of the input data are used in the process of classifying a large amount of data, it takes a lot of learning time as the classification class expands, so the minimum input data set must be extracted and used from the entire data. In addition, when a trained model is generated by using too many features, prediction accuracy may be degraded due to overfitting or correlation between features. Therefore, in order to improve accuracy, a feature selection technique that removes features close to noise should be applied, and feature selection is a necessary process in order to analyze a high-dimensional data set. Among the greedy algorithms, SFS (Sequential Forward Selection), SBS (Sequential Backward Selection), SFFS (Sequential Floating Forward Selection), etc. are widely used as traditional feature selection techniques. It is also true that if there are many risks and many features, there is a limitation in that the performance for classification prediction is poor and it takes a lot of learning time. Therefore, in this study, we propose an improved feature selection algorithm to enhance the effectiveness of the existing campaign. The purpose of this study is to improve the existing SFFS sequential method in the process of searching for feature subsets that are the basis for improving machine learning model performance using statistical characteristics of the data to be processed in the campaign system. Through this, features that have a lot of influence on performance are first derived, features that have a negative effect are removed, and then the sequential method is applied to increase the efficiency for search performance and to apply an improved algorithm to enable generalized prediction. Through this, it was confirmed that the proposed model showed better search and prediction performance than the traditional greed algorithm. Compared with the original data set, greed algorithm, genetic algorithm (GA), and recursive feature elimination (RFE), the campaign success prediction was higher. In addition, when performing campaign success prediction, the improved feature selection algorithm was found to be helpful in analyzing and interpreting the prediction results by providing the importance of the derived features. This is important features such as age, customer rating, and sales, which were previously known statistically. Unlike the previous campaign planners, features such as the combined product name, average 3-month data consumption rate, and the last 3-month wireless data usage were unexpectedly selected as important features for the campaign response, which they rarely used to select campaign targets. It was confirmed that base attributes can also be very important features depending on the type of campaign. Through this, it is possible to analyze and understand the important characteristics of each campaign type.

• Journal of Intelligence and Information Systems
• /
• v.27 no.4
• /
• pp.1-22
• /
• 2021

Aspect Based Sentiment Analysis (ABSA), which analyzes sentiment based on aspects that appear in the text, is drawing attention because it can be used in various business industries. ABSA is a study that analyzes sentiment by aspects for multiple aspects that a text has. It is being studied in various forms depending on the purpose, such as analyzing all targets or just aspects and sentiments. Here, the aspect refers to the property of a target, and the target refers to the text that causes the sentiment. For example, for restaurant reviews, you could set the aspect into food taste, food price, quality of service, mood of the restaurant, etc. Also, if there is a review that says, "The pasta was delicious, but the salad was not," the words "steak" and "salad," which are directly mentioned in the sentence, become the "target." So far, in ABSA, most studies have analyzed sentiment only based on aspects or targets. However, even with the same aspects or targets, sentiment analysis may be inaccurate. Instances would be when aspects or sentiment are divided or when sentiment exists without a target. For example, sentences like, "Pizza and the salad were good, but the steak was disappointing." Although the aspect of this sentence is limited to "food," conflicting sentiments coexist. In addition, in the case of sentences such as "Shrimp was delicious, but the price was extravagant," although the target here is "shrimp," there are opposite sentiments coexisting that are dependent on the aspect. Finally, in sentences like "The food arrived too late and is cold now." there is no target (NULL), but it transmits a negative sentiment toward the aspect "service." Like this, failure to consider both aspects and targets - when sentiment or aspect is divided or when sentiment exists without a target - creates a dual dependency problem. To address this problem, this research analyzes sentiment by considering both aspects and targets (Target-Aspect-Sentiment Detection, hereby TASD). This study detected the limitations of existing research in the field of TASD: local contexts are not fully captured, and the number of epochs and batch size dramatically lowers the F1-score. The current model excels in spotting overall context and relations between each word. However, it struggles with phrases in the local context and is relatively slow when learning. Therefore, this study tries to improve the model's performance. To achieve the objective of this research, we additionally used auxiliary loss in aspect-sentiment classification by constructing CNN(Convolutional Neural Network) layers parallel to existing models. If existing models have analyzed aspect-sentiment through BERT encoding, Pooler, and Linear layers, this research added CNN layer-adaptive average pooling to existing models, and learning was progressed by adding additional loss values for aspect-sentiment to existing loss. In other words, when learning, the auxiliary loss, computed through CNN layers, allowed the local context to be captured more fitted. After learning, the model is designed to do aspect-sentiment analysis through the existing method. To evaluate the performance of this model, two datasets, SemEval-2015 task 12 and SemEval-2016 task 5, were used and the f1-score increased compared to the existing models. When the batch was 8 and epoch was 5, the difference was largest between the F1-score of existing models and this study with 29 and 45, respectively. Even when batch and epoch were adjusted, the F1-scores were higher than the existing models. It can be said that even when the batch and epoch numbers were small, they can be learned effectively compared to the existing models. Therefore, it can be useful in situations where resources are limited. Through this study, aspect-based sentiments can be more accurately analyzed. Through various uses in business, such as development or establishing marketing strategies, both consumers and sellers will be able to make efficient decisions. In addition, it is believed that the model can be fully learned and utilized by small businesses, those that do not have much data, given that they use a pre-training model and recorded a relatively high F1-score even with limited resources.

• Journal of Chest Surgery
• /
• v.37 no.12
• /
• pp.992-998
• /
• 2004

Background: The decision of staging of esophageal cancer have great effect on the resectability of the lesion and estimation of the patient's prognosis. Today, CT is one of the most popular modality for staging of esophageal cancer. However, it has some limitations because of false-positive or false-negative findings on cancer staging. The purpose of this study was to analyze the efficacy of CT in preoperative staging of esophageal cancer. Material and Method: We retrospectively analysed the difference of staging of esophageal cancer between CT and histopathological findings for the 114 patients with histologically proven esophageal cancer who underwent operation at the department of thoracic and cardiovascular surgery, Chonnam national university hospital, between January 1999 and June 2003. We evaluated the efficacy of chest CT in the staging of esophageal cancer compared to postoperative histopathologic findings by calculating sensitivity, specificity, accuracy, and reproducibility of chest CT to detect abnormality. Result: The reproducibilities between chest CT and histopathologic findings were 0.32 (p<0.01) for primary tumor (T), 0.36 (p<0.01) for lymph node invasion (N), and 0.62 (p<0.01) for distant metastasis (M). The reproducibilities between chest CT and histopathologic findings for lymph node invasion (N) and distant metastasis (M) were superior to that of primary tumor (T). The accuracy of primary tumor (T) was 65.8% and 98.2% in group III and IV, which was significantly higher than that of group I and II (78.9% and 62.3%). In general, specificity of chest CT for TNM staging was superior to sensitivity. Conclusion: In conclusion, preoperative CT scanning can provide important information on lymph node invasion and metastasis of lesion than primary tumor invasion.

• Journal of Global Scholars of Marketing Science
• /
• v.19 no.4
• /
• pp.57-63
• /
• 2009

With an exponential increase in electronic commerce (e-commerce), marketers are attempting to gain a competitive advantage by emphasizing service quality and post interaction service aspects, which leads to customer satisfaction or behavioral consequence. Particularly for apparel, service quality is one of the key determinants in encouraging customer e-loyalty, and hence the success of apparel retailing in the context of electronic commerce. Therefore, this study explores e-service quality (E-SERVQUAL) factors and their unique effects on e-loyalty for apparel online shopping based on Parasuraman et al' s (2005) framework. Specific objectives of this study are to identify underlying dimension of E-SERVQUAL, and analyze a structural model for examining the effect of E-SERVQUAL on e-loyalty for online apparel shopping. For the theoretical framework of service quality in the context of online shopping, literatures on traditional and electronic service quality factors were comparatively reviewed, and two aspects of core and recovery services were identified. This study hypothesized that E-SERVQUAL has an effect on e-loyalty; customer satisfaction has a positive effect on e-service loyalty for apparel online shopping; and customer satisfaction mediates in the effect of E-SERVQUAL on e-loyalty for apparel online shopping. A self-administered questionnaire was developed based on literatures. A total of 252 usable questionnaires were obtained from online consumers who had purchase experience with online shopping for apparel products and reside in standard metropolitan areas, in the United States. Factor analysis (e.g., exploratory, confirmatory) was conducted to assess the validity and reliability and the structural equation model including measurement and structural models was estimated via LISREL 8.8 program. Findings showed that the E-SERVQUAL of shopping websites for apparel consisted of five factors: Compensation, Fulfillment, Efficiency, System Availability, and Responsiveness. This supports Parasuraman (2005)'s E-S-QUAL encompassing two aspects of core service (e.g., fulfillment, efficiency, system availability) and recovery related service (e.g., compensation, responsiveness) in the context of apparel shopping online. In the structural equation model, there are five exogenous latent variables for e-SERVQUAL factors; and two endogenous latent variables (e.g., customer satisfaction, e-loyalty). For the measurement model, the factor loadings for each respective construct were statistically significant and were greater than .60 and internal consistency reliabilities ranged from .85 to .88. In the estimated structural model of the e-SERVEQUAL factors, the system availability was found to have direct and positive effect on e-loyalty, whereas efficiency had a negative effect on e-loyalty for apparel online shopping. However, fulfillment was not a significant predictor for explaining consequences of E-SERVQUAL for apparel online shopping. This finding implies that perceived service quality of system available was likely to increase customer satisfaction for apparel online shopping. However, it was not supported that e-loyalty was determined by service quality, because service quality has an indirect effect on e-loyalty (i.e., repurchase intention) by mediating effect of value or satisfaction in the context of online shopping for apparel. In addition, both compensation and responsiveness were found to have a significant impact on customer satisfaction, which influenced e-loyalty for apparel online shopping. Thus, there was significant indirect effect of compensation and responsiveness on e-loyalty. This suggests that the recovery-specific service factors play an important role in maximizing customer satisfaction levels and then maintaining customer loyalty to the online shopping site for apparel. The findings have both managerial and research implications. Fashion marketers can establish long-term relationship with their customers based on continuously measuring customer perceptions for recovery-related service quality, such as quick responses to problem and returns, and compensation for customers' problem after their purchases. In order to maintain e-loyalty, recovery services play an important role in the first choice websites for consumers to purchase clothing. Given that online consumers may shop anywhere, a marketing strategy for improving competitive advantages is to provide better service quality, maximize satisfaction, and turn to creating customers' e-loyalty for apparel online shopping. From a researcher's perspective, there are some limitations of this research that should be considered when interpreting its findings. For future research, findings provide a basis for the further study of this important topic along both theoretical and empirical dimensions. Based on the findings, more comprehensive models for predicting E-SERVQUAL's consequences can be developed and tested. For global fashion marketing, this study can expand to a cross-cultural approach into e-service quality for apparel by including multinational samples.

• Korean Journal of Environment and Ecology
• /
• v.34 no.1
• /
• pp.9-17
• /
• 2020

Domestic cats (Felis catus) introduced to insular environments can be invasive predators that often threaten endemic species and cause biodiversity loss or local extinction on the island. This study was conducted from March to July 2018 to understand the population size, home range, and spatial use of cats introduced to Mara Islet (N 33° 07', E 126° 16') in Jeju Special Governing Province, the Republic of Korea. Observation records based on their natural marks revealed that there were 20 adult cats on Mara Islet. A capture-recapture method also estimated 20 adult individuals (95% confidence interval: 20-24 individuals). According to our telemetry study on ten adults deployed with GPS-based telemetry units, the home range size was 12.05±6.99 ha (95% KDE: kernel density estimation), and the core habitat size was 1.60±0.77 ha (50% KDE). There were no significant differences in the home range and core habitat sizes by sex. The home range of domestic cats overlapped with the human residential area, where they might secure easy foods. Five of ten tracked cats were active at potential breeding colonies for the Crested Murrlet (Synthliboramphus wumizusume), and six approached potential breeding areas of the Styan's Grasshopper Warbler (Locustella pleskei), suggesting the predation risk of the two endangered species by cats. This study provides novel information on the population size and home range of introduced cats on Mara Islet which is an important stopover site of migratory birds as well as a breeding habitat of the two endangered avian species. Reducing the potential negative impacts of the introduced cats on migratory birds and the endangered species on Mara Islet requires monitoring of the predation rate of birds by cats, the population trends of cats and endangered breeding birds as well as the effective cat population control and management.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.21 no.1
• /
• pp.1-10
• /
• 2016

Currently available surface seawater partial pressure carbon dioxide ($pCO_2$) data sets in the East Sea are not enough to quantify statistically the carbon dioxide flux through the air-sea interface. To complement the scarcity of the $pCO_2$ measurements, we construct a neural network (NN) model based on satellite data to map $pCO_2$ for the areas, which were not observed. The NN model is constructed for the Ulleung Basin, where $pCO_2$ data are best available, to map and estimate the variability of $pCO_2$ based on in situ $pCO_2$ for the years from 2003 to 2012, and the sea surface temperature (SST) and chlorophyll data from the MODIS (Moderate-resolution Imaging Spectroradiometer) sensor of the Aqua satellite along with geographic information. The NN model was trained to achieve higher than 95% of a correlation between in situ and predicted $pCO_2$ values. The RMSE (root mean square error) of the NN model output was $19.2{\mu}atm$ and much less than the variability of in situ $pCO_2$. The variability of $pCO_2$ with respect to SST and chlorophyll shows a strong negative correlation with SST than chlorophyll. As SST decreases the variability of $pCO_2$ increases. When SST is lower than $15^{\circ}C$, $pCO_2$ variability is clearly affected by both SST and chlorophyll. In contrast when SST is higher than $15^{\circ}C$, the variability of $pCO_2$ is less sensitive to changes in SST and chlorophyll. The mean rate of the annual $pCO_2$ increase estimated by the NN model output in the Ulleung Basin is $0.8{\mu}atm\;yr^{-1}$ from 2003 to 2014. As NN model can successfully map $pCO_2$ data for the whole study area with a higher resolution and less RMSE compared to the previous studies, the NN model can be a potentially useful tool for the understanding of the carbon cycle in the East Sea, where accessibility is limited by the international affairs.

• Journal of the Korean Geographical Society
• /
• v.30 no.2
• /
• pp.146-168
• /
• 1995

problems involved in defining and identifying it. However, data on ownership of business establishments may be useful and one of the best alternatives for this empirical research because of use of limited information about control This study examines the spatial patterns of external control in the Korean manufacturing activities between 1986 and 1992. Using the data on ownership iinkages of multilocational firms between 15 administrative areas, it was possible to construct a matrix of organizational control in terms of the number of establishments. The control matrix was disaggregated by three types of manufacturing industries according to the capital and labor requirements of production processes used in. On the basis of the disaggregated control matrix, a series of measures were calculated for investigating the magnitude and direction of control as well as the external dependency. In the past decades Korean industrialization development has risen at a rapid pace, deepening integration into the world economy, together with the continuing growth of the large industrial firms. The expanded scale of large firms led to a spatial separation of production from control, Increasing branch plants in the nation. But recent important changes have occurred in the spatial organization of production by technological development, increasing international competition, and changing local labor markets. These changes have forced firms to reorganize their production structures, resulting in changes of the organizational structures in certain industries and regions. In this context the empirical analysis revealed the following principal trends. In general term, the geography of corporate control in Korea is marked by a twofold pattern of concentration and dispersion. The dominance of Seoul as a major command and control center has been evident over the period, though its overall share of allexternally controlled establishments has decreased from 88% to 79%. And the substantial amount of external control from Seoul has concentrated to the Kyongki and Southeast regions which are well-developed industrial areas. But Seoul's corporate ownership links tend to streteh across the country to the less-developed regions, most of which have shown a significant increase of external dependency during the period 1986-1992. At the same time, a geographic dispersion of corporate control is taking place as Kyongki province and Pusan are developing as new increasingly important command and control reaions. Though these two resions contain a number of branch plants controlled from other locations, they may be increasingly attractive as a headquarters location with increasing locally owned establishments. The geographical patterns of external control observable in each of three types of manufacturing industries were examined in order to distinguish the changing spatial structures of organizational control with respect to the characteristics of the production processes. Labor intensive manufacturing with unskilled iabor experienced the strongest external pressure from foreign competition and a lack of low cost labor. The high pressure expected not only to disinte-grate the production process but also led to location of production facilities in areas of cheap labor. The linkages of control between Seoul and the less-developed regions have slightly increased, while the external dependency of the industrialized regions might be reduced from the tendency of organizational disintegration. Capita1 intensive manufacturing operates under high entry and exit barriers due to capital intensity. The need to increase scale economies ied to an even stronger economic and spatial oncentration of control. The strong geographical oncentration of control might be influenced by orporate and organizational scale economies rather than by locational advantages. Other sectors experience with respect to branch plants of multilocational firms. The policy implications of the increase of external dependency in less-developed regions may be negative because of the very share of unskilled workers and lack of autonomy in decision making. The strong growth of the national economy and a scarcity of labor in core areas have been important factors in this regional decentralization of industries to less-developed regions. But the rather gloomy prospects of the economic growth in the near future could prevent the further industrialization of less-developed areas. A major rethinking of regional policy would have to take place towards a need for a regional policy actively favoring indigenous establishments.

• Journal of the Korean earth science society
• /
• v.39 no.1
• /
• pp.53-66
• /
• 2018

The information of surface reflectance ($R_{sfc}$) is important for the heat balance and the environmental/climate monitoring. The $R_{sfc}$ sensitivity to error-induced variables for the Geostationary Environment Monitoring Spectrometer (GEMS) retrieval from geostationary-orbit satellite observations at 300-500 nm was investigated, utilizing polar-orbit satellite data of the MODerate resolution Imaging Spectroradiometer (MODIS) and Ozone Mapping Instrument (OMI), and the radiative transfer model (RTM) experiment. The variables in this study can be cloud, Rayleigh-scattering, aerosol, ozone and surface type. The cloud detection in high-resolution MODIS pixels ($1km{\times}1km$) was compared with that in GEMS-scale pixels ($8km{\times}7km$). The GEMS detection was consistent (~79%) with the MODIS result. However, the detection probability in partially-cloudy (${\leq}40%$) GEMS pixels decreased due to other effects (i.e., aerosol and surface type). The Rayleigh-scattering effect in RGB images was noticeable over ocean, based on the RTM calculation. The reflectance at top of atmosphere ($R_{toa}$) increased with aerosol amounts in case of $R_{sfc}$<0.2, but decreased in $R_{sfc}{\geq}0.2$. The $R_{sfc}$ errors due to the aerosol increased with wavelength in the UV, but were constant or slightly decreased in the visible. The ozone absorption was most sensitive at 328 nm in the UV region (328-354 nm). The $R_{sfc}$ error was +0.1 because of negative total ozone anomaly (-100 DU) under the condition of $R_{sfc}=0.15$. This study can be useful to estimate $R_{sfc}$ uncertainties in the GEMS retrieval.