• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.4
• /
• pp.144-159
• /
• 2014

Techniques for making a single panoramic image using multiple pictures are widely studied in many areas such as computer vision, computer graphics, etc. The panorama image can be applied to various fields like virtual reality, robot vision areas which require wide-angled shots as an useful way to overcome the limitations such as picture-angle, resolutions, and internal informations of an image taken from a single camera. It is so much meaningful in a point that a panoramic image usually provides better immersion feeling than a plain image. Although there are many ways to build a panoramic image, most of them are using the way of extracting feature points and matching points of each images for making a single panoramic image. In addition, those methods use the RANSAC(RANdom SAmple Consensus) algorithm with matching points and the Homography matrix to transform the image. The SURF(Speeded Up Robust Features) algorithm which is used in this paper to extract featuring points uses an image's black and white informations and local spatial informations. The SURF is widely being used since it is very much robust at detecting image's size, view-point changes, and additionally, faster than the SIFT(Scale Invariant Features Transform) algorithm. The SURF has a shortcoming of making an error which results in decreasing the RANSAC algorithm's performance speed when extracting image's feature points. As a result, this may increase the CPU usage occupation rate. The error of detecting matching points may role as a critical reason for disqualifying panoramic image's accuracy and lucidity. In this paper, in order to minimize errors of extracting matching points, we used $3{\times}3$ region's RGB pixel values around the matching points' coordinates to perform intermediate filtering process for removing wrong matching points. We have also presented analysis and evaluation results relating to enhanced working speed for producing a panorama image, CPU usage rate, extracted matching points' decreasing rate and accuracy.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.3 no.1
• /
• pp.5-15
• /
• 2001

For estimating paddy field area with Landsat TM images, two dates, May 31, 1991 (transplanting stage) and August 19, 1991 (heading stage) were selected by the data analysis of digital numbers considering rice cropping calendar. Four different estimating methods (1) rule-based classification method, (2) supervised classification(maximum likelihood), (3) unsupervised classification (ISODATA, No. of class:15), (4) unsupervised classification (ISODATA, No. of class:20) were examined. Paddy field area was estimated to 7291.19 ha by non-classification method. In comparison with topographical map (1:25,000), accuracy far paddy field area was 92%. A new image stacked by 10 layers, Landsat TM band 3,4,5, RVI, and wetness in May 31,1991 and August 19,1991 was made to estimate paddy field area by both supervised and unsupervised classification method. Paddy field was classified to 9100.98 ha by supervised classification. Error matrix showed 97.2% overall accuracy far training samples. Accuracy compared with topographical map was 95%. Unsupervised classifications by ISODATA using principal axis. Paddy field area by two different classification number of criteria were 6663.60 ha and 5704.56 ha and accuracy compared with topographical map was 87% and 82%. Irrespective of the estimating methods, paddy fields were discriminated very well by using two-date Landsat TM images in May 31,1991 (transplanting stage) and August 19,1991 (heading stage). Among estimation methods, rule-based classification method was the easiest to analyze and fast to process.

• Journal of Intelligence and Information Systems
• /
• v.21 no.2
• /
• pp.1-18
• /
• 2015

Collaborative filtering(CF) algorithm has been popularly used for recommender systems in both academic and practical applications. A general CF system compares users based on how similar they are, and creates recommendation results with the items favored by other people with similar tastes. Thus, it is very important for CF to measure the similarities between users because the recommendation quality depends on it. In most cases, users' explicit numeric ratings of items(i.e. quantitative information) have only been used to calculate the similarities between users in CF. However, several studies indicated that qualitative information such as user's reviews on the items may contribute to measure these similarities more accurately. Considering that a lot of people are likely to share their honest opinion on the items they purchased recently due to the advent of the Web 2.0, user's reviews can be regarded as the informative source for identifying user's preference with accuracy. Under this background, this study proposes a new hybrid recommender system that combines with users' review mining. Our proposed system is based on conventional memory-based CF, but it is designed to use both user's numeric ratings and his/her text reviews on the items when calculating similarities between users. In specific, our system creates not only user-item rating matrix, but also user-item review term matrix. Then, it calculates rating similarity and review similarity from each matrix, and calculates the final user-to-user similarity based on these two similarities(i.e. rating and review similarities). As the methods for calculating review similarity between users, we proposed two alternatives - one is to use the frequency of the commonly used terms, and the other one is to use the sum of the importance weights of the commonly used terms in users' review. In the case of the importance weights of terms, we proposed the use of average TF-IDF(Term Frequency - Inverse Document Frequency) weights. To validate the applicability of the proposed system, we applied it to the implementation of a recommender system for smartphone applications (hereafter, app). At present, over a million apps are offered in each app stores operated by Google and Apple. Due to this information overload, users have difficulty in selecting proper apps that they really want. Furthermore, app store operators like Google and Apple have cumulated huge amount of users' reviews on apps until now. Thus, we chose smartphone app stores as the application domain of our system. In order to collect the experimental data set, we built and operated a Web-based data collection system for about two weeks. As a result, we could obtain 1,246 valid responses(ratings and reviews) from 78 users. The experimental system was implemented using Microsoft Visual Basic for Applications(VBA) and SAS Text Miner. And, to avoid distortion due to human intervention, we did not adopt any refining works by human during the user's review mining process. To examine the effectiveness of the proposed system, we compared its performance to the performance of conventional CF system. The performances of recommender systems were evaluated by using average MAE(mean absolute error). The experimental results showed that our proposed system(MAE = 0.7867 ~ 0.7881) slightly outperformed a conventional CF system(MAE = 0.7939). Also, they showed that the calculation of review similarity between users based on the TF-IDF weights(MAE = 0.7867) leaded to better recommendation accuracy than the calculation based on the frequency of the commonly used terms in reviews(MAE = 0.7881). The results from paired samples t-test presented that our proposed system with review similarity calculation using the frequency of the commonly used terms outperformed conventional CF system with 10% statistical significance level. Our study sheds a light on the application of users' review information for facilitating electronic commerce by recommending proper items to users.

• 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.

• Journal of the Korean earth science society
• /
• v.37 no.7
• /
• pp.420-433
• /
• 2016

The purpose of this study is to improve the calibration matrixes of 2-D and 3-D convective rainfall rates (CRR) using the brightness temperature of the infrared $10.8{\mu}m$ channel (IR), the difference of brightness temperatures between infrared $10.8{\mu}m$ and vapor $6.7{\mu}m$ channels (IR-WV), and the normalized reflectance of the visible channel (VIS) from the COMS satellite and rainfall rate from the weather radar for the period of 75 rainy days from April 22, 2011 to October 22, 2011 in Korea. Especially, the rainfall rate data of the weather radar are used to validate the new 2-D and 3-DCRR calibration matrixes suitable for the Korean peninsula for the period of 24 rainy days in 2011. The 2D and 3D calibration matrixes provide the basic and maximum CRR values ($mm\;h^{-1}$) by multiplying the rain probability matrix, which is calculated by using the number of rainy and no-rainy pixels with associated 2-D (IR, IR-WV) and 3-D (IR, IR-WV, VIS) matrixes, by the mean and maximum rainfall rate matrixes, respectively, which is calculated by dividing the accumulated rainfall rate by the number of rainy pixels and by the product of the maximum rain rate for the calibration period by the number of rain occurrences. Finally, new 2-D and 3-D CRR calibration matrixes are obtained experimentally from the regression analysis of both basic and maximum rainfall rate matrixes. As a result, an area of rainfall rate more than 10 mm/h is magnified in the new ones as well as CRR is shown in lower class ranges in matrixes between IR brightness temperature and IR-WV brightness temperature difference than the existing ones. Accuracy and categorical statistics are computed for the data of CRR events occurred during the given period. The mean error (ME), mean absolute error (MAE), and root mean squire error (RMSE) in new 2-D and 3-D CRR calibrations led to smaller than in the existing ones, where false alarm ratio had decreased, probability of detection had increased a bit, and critical success index scores had improved. To take into account the strong rainfall rate in the weather events such as thunderstorms and typhoon, a moisture correction factor is corrected. This factor is defined as the product of the total precipitable waterby the relative humidity (PW RH), a mean value between surface and 500 hPa level, obtained from a numerical model or the COMS retrieval data. In this study, when the IR cloud top brightness temperature is lower than 210 K and the relative humidity is greater than 40%, the moisture correction factor is empirically scaled from 1.0 to 2.0 basing on PW RH values. Consequently, in applying to this factor in new 2D and 2D CRR calibrations, the ME, MAE, and RMSE are smaller than the new ones.

• Journal of Korea Water Resources Association
• /
• v.47 no.4
• /
• pp.371-384
• /
• 2014

This study developed a new algorithm of extreme rainfall extraction based on the Communication, Ocean and Meteorological Satellite (COMS) and the Tropical Rainfall Measurement Mission (TRMM) Satellite image data and evaluated its applicability for the heavy rainfall event in July-2011 in Seoul, South Korea. The power-series-regression-based Z-R relationship was employed for taking into account for empirical relationships between TRMM/PR, TRMM/VIRS, COMS, and Automatic Weather System(AWS) at each elevation. The estimated Z-R relationship ($Z=303R^{0.72}$) agreed well with observation from AWS (correlation coefficient=0.57). The estimated 10-minute rainfall intensities from the COMS satellite using the Z-R relationship generated underestimated rainfall intensities. For a small rainfall event the Z-R relationship tended to overestimated rainfall intensities. However, the overall patterns of estimated rainfall were very comparable with the observed data. The correlation coefficients and the Root Mean Square Error (RMSE) of 10-minute rainfall series from COMS and AWS gave 0.517, and 3.146, respectively. In addition, the averaged error value of the spatial correlation matrix ranged from -0.530 to -0.228, indicating negative correlation. To reduce the error by extreme rainfall estimation using satellite datasets it is required to take into more extreme factors and improve the algorithm through further study. This study showed the potential utility of multi-geostationary satellite data for building up sub-daily rainfall and establishing the real-time flood alert system in ungauged watersheds.

• Radiation Oncology Journal
• /
• v.14 no.1
• /
• pp.69-76
• /
• 1996

Purpose : The aim of this study is to investigate the random and systematic errors and tumor movement using electronic portal imaging device in lung cancer patients for the adequate margin in the treatment planning of 3-dimensional conformal therapy. Material and Methods : The electronic portal imaging device is matrix ion chamber type(Portal Vision, Varian). Ten patients of lung cancer treated with chest irradiation were selected for this study. Patients were treated in the supine position without immobilization device. All treatments were delivered by an 10 MV linear accelerator that had the portal imaging system mounted to its ganrty. AP or PA field Portal images were only analyzed. Radiation therapy field included the tumor, mediastinum and supraclavicular lymph nodes. A total of 103 portal images were analyzed for set-up deviation and 10 multiple images were analyzed for tumor movement because of respiration and cardiac motion. Result : The average values of setup displacements in the x, y direction was 1.41 mm, 1 78 mm, respectively. The standard deviation of systematic component was 4.63 mm, 4.11 mm along the x, y axis, respectively while the random component was 4.17 mm in the x direction and 3.31 mm in the y direction. The average displacement from respiratory movement was 12.2 mm with a standard deviation of 4.03 mm. Conclusion : The overall set-up displacement includes both random and systematic component and respiratory movement. About 10 mm, 25 mm margins along x, y axis which considered the set-up displacement and tumor movement were required for initial 3-dimensional conformal treatment planning in the lung cancer patients and portal images should be made and analyzed during first week of treatment, individually.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.219-239
• /
• 2019

As the importance of providing customized services to individuals becomes important, researches on personalized recommendation systems are constantly being carried out. Collaborative filtering is one of the most popular systems in academia and industry. However, there exists limitation in a sense that recommendations were mostly based on quantitative information such as users' ratings, which made the accuracy be lowered. To solve these problems, many studies have been actively attempted to improve the performance of the recommendation system by using other information besides the quantitative information. Good examples are the usages of the sentiment analysis on customer review text data. Nevertheless, the existing research has not directly combined the results of the sentiment analysis and quantitative rating scores in the recommendation system. Therefore, this study aims to reflect the sentiments shown in the reviews into the rating scores. In other words, we propose a new algorithm that can directly convert the user 's own review into the empirically quantitative information and reflect it directly to the recommendation system. To do this, we needed to quantify users' reviews, which were originally qualitative information. In this study, sentiment score was calculated through sentiment analysis technique of text mining. The data was targeted for movie review. Based on the data, a domain specific sentiment dictionary is constructed for the movie reviews. Regression analysis was used as a method to construct sentiment dictionary. Each positive / negative dictionary was constructed using Lasso regression, Ridge regression, and ElasticNet methods. Based on this constructed sentiment dictionary, the accuracy was verified through confusion matrix. The accuracy of the Lasso based dictionary was 70%, the accuracy of the Ridge based dictionary was 79%, and that of the ElasticNet (${\alpha}=0.3$) was 83%. Therefore, in this study, the sentiment score of the review is calculated based on the dictionary of the ElasticNet method. It was combined with a rating to create a new rating. In this paper, we show that the collaborative filtering that reflects sentiment scores of user review is superior to the traditional method that only considers the existing rating. In order to show that the proposed algorithm is based on memory-based user collaboration filtering, item-based collaborative filtering and model based matrix factorization SVD, and SVD ++. Based on the above algorithm, the mean absolute error (MAE) and the root mean square error (RMSE) are calculated to evaluate the recommendation system with a score that combines sentiment scores with a system that only considers scores. When the evaluation index was MAE, it was improved by 0.059 for UBCF, 0.0862 for IBCF, 0.1012 for SVD and 0.188 for SVD ++. When the evaluation index is RMSE, UBCF is 0.0431, IBCF is 0.0882, SVD is 0.1103, and SVD ++ is 0.1756. As a result, it can be seen that the prediction performance of the evaluation point reflecting the sentiment score proposed in this paper is superior to that of the conventional evaluation method. In other words, in this paper, it is confirmed that the collaborative filtering that reflects the sentiment score of the user review shows superior accuracy as compared with the conventional type of collaborative filtering that only considers the quantitative score. We then attempted paired t-test validation to ensure that the proposed model was a better approach and concluded that the proposed model is better. In this study, to overcome limitations of previous researches that judge user's sentiment only by quantitative rating score, the review was numerically calculated and a user's opinion was more refined and considered into the recommendation system to improve the accuracy. The findings of this study have managerial implications to recommendation system developers who need to consider both quantitative information and qualitative information it is expect. The way of constructing the combined system in this paper might be directly used by the developers.

• Journal of Korean Society of Occupational and Environmental Hygiene
• /
• v.11 no.2
• /
• pp.161-168
• /
• 2001

The types of exposure data needed in an industry-based study depend on the diseases of interest and the study design to be used. The best situation occurs when we have quantified personal exposure estimates for the agents of interest, the least informative case occurs when we have only knowledge of the fact of employment in a plant, industry, or trade where exposure probability is high. Exposure information for most industry-based studies falls somewhere between these tow extremes. Job exposure matrices(JEM) are designed to link information on occupation with information on exposure to specific workplace hazards. Some forms of systematic error of bias may be less likely to occur in studies that utilize job-exposure matrices to indirectly infer exposures from job titles than in studies that assess exposures by asking subjects about their past exposure. JEM can be used effectively in industry-based studies for historic cohort studies, case-control study to assist with the retrospective assessment of occupational exposures among workers whose individual exposure histories are unavailable. JEM generally consist of a computerized database that links information about job categories and likely exposures. These two major axes may be stratified by calendar time. This article reviews the design of JEM in support of industry-based studies. Specific matrices may find broader applicability along with the increasing availability of detailed hygienic data.

• Journal of Korean Society of Forest Science
• /
• v.105 no.4
• /
• pp.429-434
• /
• 2016

Slope failures in forest roads often result in social and economic loss as well as environmental damage. This study was carried out to assess susceptibility of slope failures of forest roads in Hongcheon-gun, Gangwon-do where many slope failures occurred after heavy rainfall in 2013 using GIS and logistic regression analysis. The results showed that sandy soil (6.616) in soil texture type had the highest susceptibility to slope failures while medium class (-3.282) in tree diameter showed the lowest susceptibility. A error matrix for both slope failure and non-slope failure area was made and a model was developed showing a classification accuracy of 74.6%. Non-slope failures area in the forest roads were classified mostly in the range of >0.7 which was higher values than the classification criteria (0.5) used by the logistic regression model. It is suggested that considering forest environment and site factors related to forest road failures would improve the accuracy in predicting susceptibility of slope failures.