• International Journal of Computer Science & Network Security
• /
• v.23 no.11
• /
• pp.21-31
• /
• 2023

In this paper, we focused on the problem of evaluating multi-class classification accuracy and simulation of multiple classifier performance metrics. Multi-class classifiers for sentiment analysis involved many challenges, whereas previous research narrowed to the binary classification model since it provides higher accuracy when dealing with text data. Thus, we take inspiration from the non-linear Support Vector Machine to modify the algorithm by embedding dynamic hyperplanes representing multiple class labels. Then we analyzed the performance of multi-class classifiers using macro-accuracy, micro-accuracy and several other metrics to justify the significance of our algorithm enhancement. Furthermore, we hybridized Enhanced Convolution Neural Network (ECNN) with Dynamic Support Vector Machine (DSVM) to demonstrate the effectiveness and efficiency of the classifier towards multi-class text data. We performed experiments on three hybrid classifiers, which are ECNN with Binary SVM (ECNN-BSVM), and ECNN with linear Multi-Class SVM (ECNN-MCSVM) and our proposed algorithm (ECNNDSVM). Comparative experiments of hybrid algorithms yielded 85.12 % for single metric accuracy; 86.95 % for multiple metrics on average. As for our modified algorithm of the ECNN-DSVM classifier, we reached 98.29 % micro-accuracy results with an f-score value of 98 % at most. For the future direction of this research, we are aiming for hyperplane optimization analysis.

• Asian-Australasian Journal of Animal Sciences
• /
• v.30 no.6
• /
• pp.765-772
• /
• 2017

Objective: This study examines the genetic factors influencing the phenotypes (four economic traits:oleic acid [C18:1], monounsaturated fatty acids, carcass weight, and marbling score) of Hanwoo. Methods: To enhance the accuracy of the genetic analysis, the study proposes a new statistical model that excludes environmental factors. A statistically adjusted, analysis of covariance model of environmental and genetic factors was developed, and estimated environmental effects (covariate effects of age and effects of calving farms) were excluded from the model. Results: The accuracy was compared before and after adjustment. The accuracy of the best single nucleotide polymorphism (SNP) in C18:1 increased from 60.16% to 74.26%, and that of the two-factor interaction increased from 58.69% to 87.19%. Also, superior SNPs and SNP interactions were identified using the multifactor dimensionality reduction method in Table 1 to 4. Finally, high- and low-risk genotypes were compared based on their mean scores for each trait. Conclusion: The proposed method significantly improved the analysis accuracy and identified superior gene-gene interactions and genotypes for each of the four economic traits of Hanwoo.

• Journal of the Korean Society for Precision Engineering
• /
• v.19 no.6
• /
• pp.62-69
• /
• 2002

For improving the motion accuracy of hydrostatic table, corrective machining algorithm is proposed in this paper. The algorithm consists of three main processes. reverse analysis is performed firstly to estimate rail profile from measured linear and angular motion error, in the algorithm. For the next step, corrective machining information is decided as referring to the estimating rail profile. Finally, motion errors on correctively machined rail are analized by using motion error analysis method proposed in the previous paper. These processes can be iterated until the analized motion errors are satisfied with target accuracy. In order to verify the validity of the algorithm theoretically, motion errors by the estimated rail, after corrective machining, are compared with motion errors by true rail assumed as the measured value. Estimated motion errors show good agreement with assumed values, and it is confirmed that the algorithm is effective to acquire the corrective machining information to improve the accuracy of hydrostatic table.

• Journal of the Korean Society for Precision Engineering
• /
• v.28 no.3
• /
• pp.259-264
• /
• 2011

Authors are carrying out a national project which develops an accuracy simulation technology of mechanical machines to predict the stiffness and accuracy of machine components or entire machine in the design stage. Analysis methods in this technology are generalized to achieve the wide applicability and to be utilized as a web based platform type. In this paper, outline of the project such as concept, aim and configuration is introduced. Contents of the research are also introduced, which are composed of four main research fields; structural dynamics, linear motion analysis, rotary motion analysis and control and vibration analysis. Finally, a future plan is presented which is made up with three stages for the advance toward an ultimate manufacturing tools.

• International Journal of Precision Engineering and Manufacturing
• /
• v.5 no.2
• /
• pp.60-67
• /
• 2004

For improving the motion accuracy of hydrostatic tables, a corrective machining algorithm is proposed in this paper. The algorithm consists of three main processes. The reverse analysis is performed firstly to estimate the rail profile from the measured linear and angular motion error, in the algorithm. For the next step, the corrective machining information is obtained based upon the estimated rail pronto. Finally, the motion errors on the correctively machined rail are analyzed by using the motion error analysis method. These processes are iterated until the analyzed motion errors are satisfactory within the target accuracy. In order to verify the validity of the algorithm theoretically, the motion errors calculated by the estimated rail after the corrective machining process, are compared with those by the true rail which is previously assumed as the initially measured value. The motion errors calculated using the estimated rail show good agreement with the assumed values, and it is shown that the algorithm is effective in acquiring the corrective machining information to improve the accuracy of hydrostatic tables.

• Near Infrared Analysis
• /
• v.1 no.2
• /
• pp.41-44
• /
• 2000

The objectives of this study are to discriminate the geographical origin and cultivation years of ginseng based on the near-infrared(NIR) reflectance spectroscopic analysis. Korea and China ginseng samples were prepared for discrimination of geographical origin. 4, 5 and 6 years-old ginseng samples from Korea were prepared for discrimination of cultivation years. Used spectrometer were InfraAlyzer 500, InfraAlyzer 400 and Fiber optic. Sample type of ginseng was 3, whole ginseng radix, slide section and powder type. The accuracy was affected by sample types and instruments. The accuracy for discrimination geographical origin was 97% in calibration model using IA 500 and ginseng powder. For discrimination of cultivation years, the model with slide selection using IA500 were relative accurate. The accuracy was 96.7% for 4-year, 91.3% for 5-year and 89.3% for 6-year old ginseng. The study shows that NIR spectroscopic analysis can be used to discriminate the geographical origin and cultivation years of ginseng with acceptable accuracy.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.13 no.1
• /
• pp.95-106
• /
• 1995

The purpose of this study is to analyse the accuracy of non-metric photos by close-range photogrammetry. Close-range photogrammetry using non-metric photos is 'economical and convenient to handle, but it is insufficient of study on accuracy. To execute this study, first, the terrain model was made and then taken photographs of this model with metric and non-metric cameras. The Bundle adjustment and the Direct linear transformation methods are used for the analysis close-range photogrammetry. The results of the analysis showed that the Bundle adjustment method is a appropriate method for the analysis of the non-netric photo. Therefore, we concluded that the accuracy of the non-metric photo by close-range photogrammetry is applicability for the photogrammetry.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.267-269
• /
• 2019

There are many recommendation systems offer an effort to get better preciseness the information to the users. In order to further improve more accuracy, the social network analysis method which is used to analyze data to community detection in social networks was introduced in the recommendation system and the result shows this method is improving more accuracy. In this paper, we propose a movie recommendation system using social network analysis and normalized discounted cumulative gain with the best accuracy. To estimate the performance, the collaborative filtering using the k nearest neighbor method, the social network analysis with collaborative filtering method and the proposed method are used to evaluate the MovieLens data. The performance outputs show that the proposed method get better the accuracy of the movie recommendation system than any other methods used in this experiment.

• Journal of the Korean Society of Industry Convergence
• /
• v.26 no.1
• /
• pp.121-131
• /
• 2023

Although the utilization of drone photogrammetry that can generate spatial information using ultra-high-resolution images is increasing in the civil engineering and construction fields, analysis of areas that can be used is insufficient. Therefore, this study attempted to determine how far drone photogrammetry can be used in the civil engineering and construction fields by applying a detailed analysis method. The status map and cross-sectional map were actually vectorized using drone photogrammetry outcomes, compared and analyzed with the results acquired in the field, and the qualitative aspects of traffic safety facilities were analyzed to determine their usability. As a result, the accuracy of the plane position using drone photogrammetry was reliable, but the height accuracy was difficult to trust. Accordingly, although there is a possibility of preparing a status map, the use of it in areas requiring high accuracy such as cross-sectional plans was limited, and it is believed that it can be used in the construction management field where qualitative analysis is conducted.

• Earthquakes and Structures
• /
• v.26 no.2
• /
• pp.117-130
• /
• 2024

Probabilistic model of seismic demand is the main tool used for seismic demand estimation, which is a fundamental component of the new performance-based design method. This model seeks to mathematically relate the seismic demand parameter and the ground motion intensity measure. This study is intended to use Bayesian analysis to evaluate the accuracy of the seismic demand estimation of Steel moment resisting frames (SMRFs) through a completely Bayesian method in statistical calculations. In this study, two types of intensity measures (earthquake intensity-related indices such as magnitude and distance and intensity indices related to ground motion and spectral response including peak ground acceleration (PGA) and spectral acceleration (SA)) have been used to form the models. In addition, an extensive database consisting of sixty accelerograms was used for time-series analysis, and the target structures included five SMRFs of three, six, nine, twelve and fifteen stories. The results of this study showed that for low-rise frames, first mode spectral acceleration index is sufficient to accurately estimate demand. However, for high-rise frames, two parameters should be used to increase the accuracy. In addition, adding the product of the square of earthquake magnitude multiplied by distance to the model can significantly increase the accuracy of seismic demand estimation.