• Proceedings of the KSRS Conference
• /
• 1998.09a
• /
• pp.213-217
• /
• 1998

This study overviews existing evaluation methods of classification accuracy using confusion matrix proposed by Cohen in 1960's, and proposes ISDd(Index of Spatial Distribution by distance) and ISDs(Index of Spatial Distribution by scatteredness) for the evaluation of spatial distribution of satellite image classification errors, which has not been tried yet. Index of spatial distribution offers the basis of decision on adoption/rejection of classification results at sub-image level by evaluation of distribution, such as status of local aggregation of misclassified pixels. So, users can understand the spatial distribution of misclassified pixels and, can have the basis of judgement of suitability and reliability of classification results.

• 연구논문집
• /
• s.33
• /
• pp.89-97
• /
• 2003

A barrel cam is used as a very important part of an index drive unit. The index drive unit must have an intermittent-rotational motion. The barrel typed cam and roller gear mechanism has the advantages of high reliability to perform a prescribed motion of a follower. This paper proposes a new method for the shape design of the barrel cam and also a CAD program is developed by using the proposed method. As defined in this paper, the relative velocity method for the shape design calculates the relative velocity of the follower versus cam at a center of roller, and then detemines a contact point by using the geometric relationships and the kinematic constraints, where the direction of the relative velocity must be parallel to a common tangential line at the contact point of two independent bodies, i.e. the cam and the follower. Then, the shape of the cam is defined by the coordinate transformation of the trace of the contact points. This paper presents shape design of the barrel cam in order to prove the accuracy of the proposed methods

• Journal of Intelligence and Information Systems
• /
• v.1 no.2
• /
• pp.103-121
• /
• 1995

This study proposes a artificial neural network method to predict the time to buy and sell the stocks listed on the Korea Composite Stock Price Index(KOSPI). Four types (NN1, NN2, NN3, NN4) of independent networks were developed to predict KOSPIs up/down direction after four weeks. These networks have a difference only in the length of learning period. NN5 - arithmetic average of four networks outputs - shows an higher accuracy than other network types and Multiple Linear Regression (MLR), and buying and selling simulation using systems outputs produces higher reture than buy-and-hold strategy.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.144-144
• /
• 2022

Identifying waterbody from remote sensing images, namely water detection, helps understand continuous redistribution of terrestrial water storage and accompanying hydrological processes. It also allows us to estimate available surface water resources and help effective water management. For this problem, NDWI (Normalized Difference Water Index) and MNDWI (Modified Normalized Difference Water Index) are widely used. Although remote sensing indexes can highlight remote sensing image in the water, the noise and the spatial information of the remote sensing image are difficult to be considered, so the accuracy is difficult to be compared with the visual interpretation (the most accurate method, but it requires a lot of labor, which makes it difficult to apply). In this study, we attempt to improve existing NDWI and MNDWI to better water detection. We establish waterbody database of South Korea first and then used it for assessing waterbody indices.

• Journal of Information Management
• /
• v.41 no.2
• /
• pp.161-181
• /
• 2010

The purpose of this study is to investigate citation behavior in internet news to research papers of 10 domestic economic institutes and to suggest institutes' impact quantitatively with h-index and various modified indices. Content analysis of 878 news articles that collected from NAVER news site was performed. First, as citing behavior, cited numbers of research papers, preferred news media, speed, source entry accuracy, centrality, subject section, and length by the institutes were examined. Next, impact indices for institutes were calculated by cited numbers using h-index, g-index, $h_s$-index, and $g_s$-index, and the ranking of 10 research institutes were determined by each impact indices. As a result, institutes belonged to upper ranks showed little variation among the different indices. On the other hand, institutes belonged to middle and lower ranks showed variations in impact indices and experts' survey.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.1
• /
• pp.489-493
• /
• 2024

Happiness index is a measurement system for understanding collective happiness. As values change, studies have been proposed to add the value of behavior to the happiness index. However, there is a lack of studies analyze the relationship using individual emotions. Using a deep learning model, we predicted happiness index using social variables and individual emotional index. First, we collected social and emotional variables from January 2005 to December 2020. Second, we preprocessed the data and identified significant variables. Finally, we trained deep learning-based regression model. Our proposed model was evaluated using 5-fold cross validation. The proposed model showed 90.86% accuracy on test sets. Our model will be expected to analyze the significant factors of country-specific happiness index.

• Journal of Biomedical Engineering Research
• /
• v.33 no.1
• /
• pp.8-14
• /
• 2012

The purpose of this study was to evaluate how much effect to accuracy when measuring abdominal fat by Computed Tomography (CT) under different respiration movements. The study volunteer composed of 66 normal adults ($50.4{\pm}11.2$ years, 33 males, 33 females). We measured their obesity by using Broca index, body mass index (BMI) and CT and have investigated the correlation. The CT scanning for the obesity measurement have done in two ways, one was done in stopping breath after exhaling and the other was holding a breath after inhaling. The results showed no statistically significant difference among the three measuring techniques. And, the error in two ways of inhaling and exhaling was showed 24.2% of volunteers. The two ways of respiration movements made different result in visceral fat area (P = 0.044), subcutaneous fat area (P = 0.636) and abdominal obesity value (P = 0.012). This study demonstrates that the two ways of respiration movements when scanning CT makes change in accuracy in visceral fat area, and in abdominal obesity quantitative measure. Therefore, our study suggests that CT should take twice in two ways while a patient stops breath after exhaling and holds a breath after inhaling when measuring abdominal obesity using CT equipments.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.58 no.6
• /
• pp.1078-1086
• /
• 2009

This paper presents a Fourier based algorithm for estimating the parameters of the low frequency oscillating modes. The proposed methods estimates various parameters(frequency, damping factor, mode magnitude, phase) by fitting Fourier spectrum and phase with a damped exponential cosine function. Dominant frequency is selected by taking frequency corresponding to the peak spectrum, and damping factor is estimated using the left/right spectra of Fourier spectrum. In addition, mode magnitude is calculated by the normalized peak spectrum, and phase is estimated from spectrum phase. Also, we introduce an accuracy index in order to determine the accuracy of the estimated parameters, and the index is calculated using the deviations of the peak spectrum and the left/right spectra. The parameter estimation methods proposed in this paper include very simple arithmetical processes, so the algorithms are simple and the calculation speed is very fast. The proposed methods are applied to test functions with two dominant modes. The results show that the proposed methods are highly applicable to low frequency parameter estimation.

• Proceedings of the Korean Society of Crop Science Conference
• /
• 2017.06a
• /
• pp.46-46
• /
• 2017

We developed a rice simulation model for remote-sensing (SIMRIW-RS, Homma et al., 2007) to evaluate rice production and management on a regional scale. Here, we reports its application trial to estimate rice production in farmers' fields in Sendai, Japan. The remote-sensing data for the application was periodically obtained by multispectral camera (RGB + NIR and RedEdge) attached with unmanned air vehicle (UAV). The airborne images was 8 cm in resolution which was attained by the flight at an altitude of 115 m. The remote-sensing data was relatively corresponded with leaf area index (LAI) of rice and its spatial and temporal variation, although the correspondences had some errors due to locational inaccuracy. Calibration of the simulation model depended on the first two remote-sensing data (obtained around one month after transplanting and panicle initiation) well predicted rice growth evaluated by the third remote-sensing data. The parameters obtained through the calibration may reflect soil fertility, and will be utilized for nutritional management. Although estimation accuracy has still needed to be improved, the rice yield was also well estimated. These results recommended further data accumulation and more accurate locational identification to improve the estimation accuracy.

• Perspectives in Nursing Science
• /
• v.9 no.1
• /
• pp.24-35
• /
• 2012

Purpose: This research was performed to investigate Korean adolescents' body weight perception, appropriate weight change efforts, and factors that influencing these efforts. Methods: The data were obtained from 68,136 adolescents, aged 12~18 years from the 2007 Third Korean Youth' Risk Behavior Web-based Survey. Descriptive statistical analysis and odds ratio were calculated by logistic regression. Results: The distribution of the body mass index differed in boys and girls. The accuracy of body weight perception was shown in the order of the underweight (91.6%), overweigh t (73.3%), normal weight (55.4%), obesity (41.3%) groups. Adolescents with high perceived economic status tended to have a high prevalence of accuracy of body weight perception. The distribution of appropriate weight change efforts according to the actual body mass index showed that girls were trying to lose weight more than boys. The results of a logistic regression analysis regarding appropriate weight change efforts showed differences according to gender, perceived economic status, mother's educational level, and family affluence scale. Conclusion: Appropriate body weight perception and change management plans are needed for Korean adolescents. In addition, active weight change programs have to be established in the adolescents' living environments, such as schools.