• Journal of Intelligence and Information Systems
• /
• v.18 no.1
• /
• pp.1-21
• /
• 2012

In recent years, mobile phone has experienced an extremely fast evolution. It is equipped with high-quality color displays, high resolution cameras, and real-time accelerated 3D graphics. In addition, some other features are includes GPS sensor and Digital Compass, etc. This evolution advent significantly helps the application developers to use the power of smart-phones, to create a rich environment that offers a wide range of services and exciting possibilities. To date mobile AR in outdoor research there are many popular location-based AR services, such Layar and Wikitude. These systems have big limitation the AR contents hardly overlaid on the real target. Another research is context-based AR services using image recognition and tracking. The AR contents are precisely overlaid on the real target. But the real-time performance is restricted by the retrieval time and hardly implement in large scale area. In our work, we exploit to combine advantages of location-based AR with context-based AR. The system can easily find out surrounding landmarks first and then do the recognition and tracking with them. The proposed system mainly consists of two major parts-landmark browsing module and annotation module. In landmark browsing module, user can view an augmented virtual information (information media), such as text, picture and video on their smart-phone viewfinder, when they pointing out their smart-phone to a certain building or landmark. For this, landmark recognition technique is applied in this work. SURF point-based features are used in the matching process due to their robustness. To ensure the image retrieval and matching processes is fast enough for real time tracking, we exploit the contextual device (GPS and digital compass) information. This is necessary to select the nearest and pointed orientation landmarks from the database. The queried image is only matched with this selected data. Therefore, the speed for matching will be significantly increased. Secondly is the annotation module. Instead of viewing only the augmented information media, user can create virtual annotation based on linked data. Having to know a full knowledge about the landmark, are not necessary required. They can simply look for the appropriate topic by searching it with a keyword in linked data. With this, it helps the system to find out target URI in order to generate correct AR contents. On the other hand, in order to recognize target landmarks, images of selected building or landmark are captured from different angle and distance. This procedure looks like a similar processing of building a connection between the real building and the virtual information existed in the Linked Open Data. In our experiments, search range in the database is reduced by clustering images into groups according to their coordinates. A Grid-base clustering method and user location information are used to restrict the retrieval range. Comparing the existed research using cluster and GPS information the retrieval time is around 70~80ms. Experiment results show our approach the retrieval time reduces to around 18~20ms in average. Therefore the totally processing time is reduced from 490~540ms to 438~480ms. The performance improvement will be more obvious when the database growing. It demonstrates the proposed system is efficient and robust in many cases.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.109-125
• /
• 2019

As interest on intelligent search engines increases, various studies have been conducted to extract and utilize the features related to products intelligencely. In particular, when users search for goods in e-commerce search engines, the 'color' of a product is an important feature that describes the product. Therefore, it is necessary to deal with the synonyms of color terms in order to produce accurate results to user's color-related queries. Previous studies have suggested dictionary-based approach to process synonyms for color features. However, the dictionary-based approach has a limitation that it cannot handle unregistered color-related terms in user queries. In order to overcome the limitation of the conventional methods, this research proposes a model which extracts RGB values from an internet search engine in real time, and outputs similar color names based on designated color information. At first, a color term dictionary was constructed which includes color names and R, G, B values of each color from Korean color standard digital palette program and the Wikipedia color list for the basic color search. The dictionary has been made more robust by adding 138 color names converted from English color names to foreign words in Korean, and with corresponding RGB values. Therefore, the fininal color dictionary includes a total of 671 color names and corresponding RGB values. The method proposed in this research starts by searching for a specific color which a user searched for. Then, the presence of the searched color in the built-in color dictionary is checked. If there exists the color in the dictionary, the RGB values of the color in the dictioanry are used as reference values of the retrieved color. If the searched color does not exist in the dictionary, the top-5 Google image search results of the searched color are crawled and average RGB values are extracted in certain middle area of each image. To extract the RGB values in images, a variety of different ways was attempted since there are limits to simply obtain the average of the RGB values of the center area of images. As a result, clustering RGB values in image's certain area and making average value of the cluster with the highest density as the reference values showed the best performance. Based on the reference RGB values of the searched color, the RGB values of all the colors in the color dictionary constructed aforetime are compared. Then a color list is created with colors within the range of ${\pm}50$ for each R value, G value, and B value. Finally, using the Euclidean distance between the above results and the reference RGB values of the searched color, the color with the highest similarity from up to five colors becomes the final outcome. In order to evaluate the usefulness of the proposed method, we performed an experiment. In the experiment, 300 color names and corresponding color RGB values by the questionnaires were obtained. They are used to compare the RGB values obtained from four different methods including the proposed method. The average euclidean distance of CIE-Lab using our method was about 13.85, which showed a relatively low distance compared to 3088 for the case using synonym dictionary only and 30.38 for the case using the dictionary with Korean synonym website WordNet. The case which didn't use clustering method of the proposed method showed 13.88 of average euclidean distance, which implies the DBSCAN clustering of the proposed method can reduce the Euclidean distance. This research suggests a new color synonym processing method based on RGB values that combines the dictionary method with the real time synonym processing method for new color names. This method enables to get rid of the limit of the dictionary-based approach which is a conventional synonym processing method. This research can contribute to improve the intelligence of e-commerce search systems especially on the color searching feature.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.57-73
• /
• 2021

Maintenance and prevention of failure through anomaly detection of ICT infrastructure is becoming important. System monitoring data is multidimensional time series data. When we deal with multidimensional time series data, we have difficulty in considering both characteristics of multidimensional data and characteristics of time series data. When dealing with multidimensional data, correlation between variables should be considered. Existing methods such as probability and linear base, distance base, etc. are degraded due to limitations called the curse of dimensions. In addition, time series data is preprocessed by applying sliding window technique and time series decomposition for self-correlation analysis. These techniques are the cause of increasing the dimension of data, so it is necessary to supplement them. The anomaly detection field is an old research field, and statistical methods and regression analysis were used in the early days. Currently, there are active studies to apply machine learning and artificial neural network technology to this field. Statistically based methods are difficult to apply when data is non-homogeneous, and do not detect local outliers well. The regression analysis method compares the predictive value and the actual value after learning the regression formula based on the parametric statistics and it detects abnormality. Anomaly detection using regression analysis has the disadvantage that the performance is lowered when the model is not solid and the noise or outliers of the data are included. There is a restriction that learning data with noise or outliers should be used. The autoencoder using artificial neural networks is learned to output as similar as possible to input data. It has many advantages compared to existing probability and linear model, cluster analysis, and map learning. It can be applied to data that does not satisfy probability distribution or linear assumption. In addition, it is possible to learn non-mapping without label data for teaching. However, there is a limitation of local outlier identification of multidimensional data in anomaly detection, and there is a problem that the dimension of data is greatly increased due to the characteristics of time series data. In this study, we propose a CMAE (Conditional Multimodal Autoencoder) that enhances the performance of anomaly detection by considering local outliers and time series characteristics. First, we applied Multimodal Autoencoder (MAE) to improve the limitations of local outlier identification of multidimensional data. Multimodals are commonly used to learn different types of inputs, such as voice and image. The different modal shares the bottleneck effect of Autoencoder and it learns correlation. In addition, CAE (Conditional Autoencoder) was used to learn the characteristics of time series data effectively without increasing the dimension of data. In general, conditional input mainly uses category variables, but in this study, time was used as a condition to learn periodicity. The CMAE model proposed in this paper was verified by comparing with the Unimodal Autoencoder (UAE) and Multi-modal Autoencoder (MAE). The restoration performance of Autoencoder for 41 variables was confirmed in the proposed model and the comparison model. The restoration performance is different by variables, and the restoration is normally well operated because the loss value is small for Memory, Disk, and Network modals in all three Autoencoder models. The process modal did not show a significant difference in all three models, and the CPU modal showed excellent performance in CMAE. ROC curve was prepared for the evaluation of anomaly detection performance in the proposed model and the comparison model, and AUC, accuracy, precision, recall, and F1-score were compared. In all indicators, the performance was shown in the order of CMAE, MAE, and AE. Especially, the reproduction rate was 0.9828 for CMAE, which can be confirmed to detect almost most of the abnormalities. The accuracy of the model was also improved and 87.12%, and the F1-score was 0.8883, which is considered to be suitable for anomaly detection. In practical aspect, the proposed model has an additional advantage in addition to performance improvement. The use of techniques such as time series decomposition and sliding windows has the disadvantage of managing unnecessary procedures; and their dimensional increase can cause a decrease in the computational speed in inference.The proposed model has characteristics that are easy to apply to practical tasks such as inference speed and model management.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.45-68
• /
• 2022

The central and local governments of the Republic of Korea provided information necessary for disaster response through wireless emergency alerts (WEAs) in order to overcome the pandemic situation in which COVID-19 rapidly spreads. Among all channels for delivering disaster information, wireless emergency alert is the most efficient, and since it adopts the CBS(Cell Broadcast Service) method that broadcasts directly to the mobile phone, it has the advantage of being able to easily access disaster information through the mobile phone without the effort of searching. In this study, the characteristics of wireless emergency alerts sent to Seoul during the past year and one month (January 2020 to January 2021) were derived through various text mining methodologies, and various types of information contained in wireless emergency alerts were analyzed. In addition, it was confirmed through the population mobility by age in the districts of Seoul that what kind of influence it had on the movement behavior of people. After going through the process of classifying key words and information included in each character, text analysis was performed so that individual sent characters can be used as an analysis unit by applying a document cluster analysis technique based on the included words. The number of WEAs sent to the Seoul has grown dramatically since the spread of Covid-19. In January 2020, only 10 WEAs were sent to the Seoul, but the number of the WEAs increased 5 times in March, and 7.7 times over the previous months. Since the basic, regional local government were authorized to send wireless emergency alerts independently, the sending behavior of related to wireless emergency alerts are different for each local government. Although most of the basic local governments increased the transmission of WEAs as the number of confirmed cases of Covid-19 increases, the trend of the increase in WEAs according to the increase in the number of confirmed cases of Covid-19 was different by region. By using structured econometric model, the effect of disaster information included in wireless emergency alerts on population mobility was measured by dividing it into baseline effect and accumulating effect. Six types of disaster information, including date, order, online URL, symptom, location, normative guidance, were identified in WEAs and analyzed through econometric modelling. It was confirmed that the types of information that significantly change population mobility by age are different. Population mobility of people in their 60s and 70s decreased when wireless emergency alerts included information related to date and order. As date and order information is appeared in WEAs when they intend to give information about Covid-19 confirmed cases, these results show that the population mobility of higher ages decreased as they reacted to the messages reporting of confirmed cases of Covid-19. Online information (URL) decreased the population mobility of in their 20s, and information related to symptoms reduced the population mobility of people in their 30s. On the other hand, it was confirmed that normative words that including the meaning of encouraging compliance with quarantine policies did not cause significant changes in the population mobility of all ages. This means that only meaningful information which is useful for disaster response should be included in the wireless emergency alerts. Repeated sending of wireless emergency alerts reduces the magnitude of the impact of disaster information on population mobility. It proves indirectly that under the prolonged pandemic, people started to feel tired of getting repetitive WEAs with similar content and started to react less. In order to effectively use WEAs for quarantine and overcoming disaster situations, it is necessary to reduce the fatigue of the people who receive WEA by sending them only in necessary situations, and to raise awareness of WEAs.

• Journal of Global Scholars of Marketing Science
• /
• v.20 no.1
• /
• pp.59-69
• /
• 2010

Green or an environmental consciousness has been a major issue for businesses and government offices, as well as consumers, worldwide. In response to this movement, the Korean government announced, in the early 2000s, the era of "Green Growth" as a way to encourage green-related business activities. The Korean fashion industry, in various levels of involvement, presents diverse eco-friendly products as a part of the green movement. These apparel products include organic products and recycled clothing. For these companies to be successful, they need information about who are the consumers who consider green issues (e.g., environmental sustainability) as part of their personal values when making a decision for product purchase, use, and disposal. These consumers can be considered as eco-sumers. Previous studies have examined consumers' purchase intention for or with eco-friendly products. In addition, studies have examined influential factors used to identify the eco-sumers or green consumers. However, limited attention was paid to eco-sumers' disposal or recycling behavior of clothes in comparison with their green product purchases. Clothing disposal behaviors are ways that consumer can get rid of unused clothing and in clue temporarily lending the item or permanently eliminating the item by "handing down" (e.g., giving it to a younger sibling), donating, exchanging, selling, or simply throwing it away. Accordingly, examining purchasing behaviors of eco-friendly fashion items in conjunction with clothing disposal behaviors should improve understanding of a consumer's clothing consumption behavior from the environmental perspective. The purpose of this exploratory study is to provide descriptive information about Korean eco-sumers who have ecologically-favorable lifestyles and behaviors when buying and disposing of clothes. The objectives of this study are to (a) categorize Koreans on the basis of clothing disposal behaviors; (b) investigate the differences in demographics, lifestyles, and clothing consumption values among segments; and (c) compare the purchase intention of eco-friendly fashion items and influential factors among segments. A self-administered questionnaire was developed based on previous studies. The questionnaire included 10 items of clothing disposal behavior, 22 items of LOHAS (Lifestyles of Health and Sustainability) characteristics, and 19 items of consumption values, measured by five-point Likert-type scales. In addition, the purchase intention of two eco-friendly fashion items and 11 attributes of each item were measured by seven-point Likert type scales. Two polyester fleece pullovers, made from fabric created from recycled bottles with the PET identification code, were selected from one Korean brand and one US imported brand among outdoor sportswear brands. A brief description of each product with a color picture was provided in the survey. Demographic variables (i.e., gender, age, marital status, education level, income, occupation) were also included. The data were collected through a professional web survey agency during May 2009. A total of 600 final usable questionnaires were analyzed. The age of respondents ranged from 20 to 49 years old with a mean age of 34 years. Fifty percent of the respondents were males and about 58% were married, and 62% reported having earned university degrees. Principal components factor analysis with varimax rotation was used to identify the underlying dimensions of the clothing disposal behavior scale, and three factors were generated (i.e., reselling behavior, donating behavior, non-recycling behavior). To categorize the respondents on the basis of clothing disposal behaviors, k-mean cluster analysis was used, and three segments were obtained. These consumer segments were labeled as 'Resale Group', 'Donation Group', and 'Non-Recycling Group.' The classification results indicated approximately 98 percent of the original cases were correctly classified. With respect to demographic characteristics among the three segments, significant differences were found in gender, marital status, occupation, and age. LOHAS characteristics were reduced into the following five factors: self-satisfaction, family orientation, health concern, environmental concern, and voluntary service. Significant differences were found in the LOHAS factors among the three clusters. Resale Group and Donation Group showed a similar predisposition to LOHAS issues while the Non-Recycling Group presented the lowest mean scores on the LOHAS factors compared to the other segments. The Resale and Donation Groups described themselves as enjoying or being satisfied with their lives and spending spare-time with family. In addition, these two groups cared about health and organic foods, and tried to conserve energy and resources. Principal components factor analysis generated clothing consumption values into the following three factors: personal values, social value, and practical value. The ANOVA test with the factors showed differences primarily between the Resale Group and the other two groups. The Resale Group was more concerned about personal value and social value than the other segments. In contrast, the Non-Recycling Group presented the higher level of social value than did Donation Group. In a comparison of the intention to purchase eco-friendly products, the Resale Group showed the highest mean score on intent to purchase Product A. On the other hand, the Donation Group presented the highest intention to purchase for Product B among segments. In addition, the mean scores indicated that the Korean product (Product B) was more preferable for purchase than the U.S. product (Product A). Stepwise regression analysis was used to identify the influence of product attributes on the purchase intention of eco product. With respect to Product A, design, price and contribution to environmental preservation were significant to predict purchase intention for the Resale Group, while price and compatibility with my image factors were significant for the Donation Group. For the Non-Recycling Group, design, price compatibility with the factors of my image, participation to eco campaign, and contribution to environmental preservation were significant. Price appropriateness was significant for each of the three clusters. With respect to Product B, design, price and compatibility with my image factors were important, but different attributes were associated significantly with purchase intention for each of the three groups. The influence of LOHAS characteristics and clothing consumption values on intention to purchase Products A and B were also examined. The LOHAS factor of health concern and the personal value factor were significant in the relationships with the purchase intention; however, the explanatory powers were low in the three segments. Findings showed that each group as classified by clothing disposal behaviors showed differences in the attributes of a product, personal values, and the LOHAS characteristics that influenced their purchase intention of eco-friendly products. Findings would enable organizations to understand eco-friendly behavior and to design appropriate strategic decisions to appeal eco-sumers.