• Journal of Multimedia Information System
• /
• 제6권2호
• /
• pp.75-80
• /
• 2019

In machine learning, the performance of the system depends upon the nature of input data. The efficiency of the system improves when the behavior of the input data changes from un-normalized to normalized form. This paper experimentally demonstrated the performance of KNN, SVM, LDA and NB on Alzheimer's dataset. The dataset undertaken for the study consisted of 3 classes, i.e. Demented, Converted and Non-Demented. Analysis shows that LDA and NB gave an accuracy of 89.83% and 88.19% respectively in both the cases whereas the accuracy of KNN and SVM improved from 46.87% to 82.80% and 53.40% to 88.75% respectively when input data changed from un-normalized to normalized state. From the above results it was observed that KNN and SVM show significant improvement in classification accuracy on normalized data as compared to un-normalized data, whereas LDA and NB reflect no such change in their performance.

• Korean Journal of Geomatics
• /
• 제2권2호
• /
• pp.99-105
• /
• 2002

The accuracy of the Digital Photologging System, designed for the construction of the road Facility Database, highly depends on the positions and attitudes of the cameras from GPS/INS integration. In this paper, the development of a loosely coupled GPS/INS is presented. The performance of the system is verified through a simulation as well as a real test data processing. Since the IMU used in this study shows large systematic errors, the possible accuracy of the positions and attitudes of this low-performance IMU when combined with precise GPS positions are assigned. Currently, the integrated system shows the positional accuracy better than 5cm in real data processing. Although the accuracy of attitude based on real test could not be assigned at this time, it is expected that better than 0.5 degrees and 1.8 degrees for horizontal and down component are achievable according to the simulation result.

• 대한기계학회논문집A
• /
• 제30권5호
• /
• pp.609-614
• /
• 2006

Recently linear motor has been used mainly for high speed feeding performance of machine tools. The advantages of linear motor are not only high speed but high accuracy, because it is not required the coupling and ballscrew for converting rotary to liner motion. Before applying in different moving system, the dynamometer is necessary to test the performance. In Korea, the linear motor is producing in a couple of company However, the liner motor dynamometer is not commercialized yet, like as rotary motor dynamometer. In this paper, a linear motor dynamometer is designed and manufactured using a MR damper. The dynamometer system developed in this study could be used for testing the positioning accuracy fur different loading conditions, traction forces, dynamic performance and so on.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2017년도 춘계학술발표대회
• /
• pp.787-790
• /
• 2017

Data quality is the main issue in the classification problems; generally, the presence of noisy instances in the training dataset will not lead to robust classification performance. Such instances may cause the generated decision tree to suffer from over-fitting and its accuracy may decrease. Decision trees are useful, efficient, and commonly used for solving various real world classification problems in data mining. In this paper, we introduce a preprocessing technique to improve the classification accuracy rates of the C4.5 decision tree algorithm. In the proposed preprocessing method, we applied the naive Bayes classifier to remove the noisy instances from the training dataset. We applied our proposed method to a real e-commerce sales dataset to test the performance of the proposed algorithm against the existing C4.5 decision tree classifier. As the experimental results, the proposed method improved the classification accuracy by 8.5% and 14.32% using training dataset and 10-fold crossvalidation, respectively.

• Journal of Positioning, Navigation, and Timing
• /
• 제6권2호
• /
• pp.53-57
• /
• 2017

eLoran refers to a terrestrial navigation system using high-power low-frequency signals. Thus, it can be regarded as a positioning, navigation and timing (PNT) system to back up a global navigation satellite system (GNSS) or an alternative to GNSS. South Korea is vulnerable to interference such as GNSS jamming in particular. Therefore, South Korea has made an effort to develop an independent navigation system through eLoran system. More particularly, an eLoran testbed has been developed to be used in the northwest sea area and research on applicability of eLoran in South Korea has been underway. The present study analyzes expected performance of eLoran according to locations of newly built eLoran transmitting stations as part of the eLoran testbed research. The performance of eLoran is analyzed in terms of horizontal position accuracy, and horizontal dilution of precision (HDOP) information was used since it affects accuracy significantly. The target service areas of the eLoran testbed are Incheon and Pyeongtaek Ports, and the required target performance is positioning accuracy of 20 m position within 30 km coverage of the target service area.

• 한국임상수의학회지
• /
• 제32권4호
• /
• pp.319-323
• /
• 2015

The performance of diagnostic test accuracy is usually summarized by a variety of statistics such as sensitivity, specificity, predictive value, likelihood ratio, and kappa. These indices are most commonly presented when evaluations of competing diagnostic tests are reported, and it is of utmost importance to compare the accuracies of diagnostic tests to decide on the best available test for certain medical disorder. However, it is important to emphasize that specific point values of these indices are merely estimates. If parameter estimates are reported without a measure of uncertainty (precision), knowledgeable readers cannot know the range within which the true values of the indices are likely to lie. Therefore, when evaluations of diagnostic accuracy are reported the precision of estimates should be stated in parallel. To reflect the precision of any estimate of a diagnostic performance characteristic or of the difference between performance characteristics, the computation of confidential interval (CI), an indicator of precision, is widely used in medical literatures in that CIs are more informative to interpret test results than the simple point estimates. The majority of peer-reviewed journals usually require CIs to be specified for descriptive estimates, whereas domestic veterinary journals seem less vigilant on this issues. This paper describes how to calculate the indices and associated CIs using practical examples when assessing diagnostic test performance.

• 대한인간공학회지
• /
• 제36권3호
• /
• pp.255-265
• /
• 2017

Objective: This study aims to survey visual search performance models to assess and predict individual's visual tasks in everyday life and industrial sites. Background: Visual search is one of the most frequently performed and critical activities in everyday life and works. Visual search performance models are needed when designing or assessing the visual tasks. Method: This study was mainly based on survey of literatures related to ergonomics relevant journals and web surfing. In the survey, the keywords of visual search, visual search performance, visual search model, etc. were used. Results: On the basis of the purposes, developing methods and results of the models, this study categorized visual search performance models into six groups: probability-based models, SATO models, visual lobe-based models, computer vision models, neutral network-based models and detection time models. Major models by the categories were presented with their advantages and disadvantages. More models adopted the accuracy among two factors of accuracy and speed characterizing visual tasks as dependent variables. Conclusion: This study reviewed and summarized various visual search performance models. Application: The results would be used as a reference or tool when assessing the visual tasks.

• 대한의용생체공학회:의공학회지
• /
• 제42권4호
• /
• pp.167-174
• /
• 2021

The purpose of this study is to classify TIFF images, PNG images, and JPEG images using deep learning, and to compare the accuracy by verifying the classification performance. The TIFF, PNG, and JPEG images converted from chest X-ray DICOM images were applied to five deep neural network models performed in image recognition and classification to compare classification performance. The data consisted of a total of 4,000 X-ray images, which were converted from DICOM images into 16-bit TIFF images and 8-bit PNG and JPEG images. The learning models are CNN models - VGG16, ResNet50, InceptionV3, DenseNet121, and EfficientNetB0. The accuracy of the five convolutional neural network models of TIFF images is 99.86%, 99.86%, 99.99%, 100%, and 99.89%. The accuracy of PNG images is 99.88%, 100%, 99.97%, 99.87%, and 100%. The accuracy of JPEG images is 100%, 100%, 99.96%, 99.89%, and 100%. Validation of classification performance using test data showed 100% in accuracy, precision, recall and F1 score. Our classification results show that when DICOM images are converted to TIFF, PNG, and JPEG images and learned through preprocessing, the learning works well in all formats. In medical imaging research using deep learning, the classification performance is not affected by converting DICOM images into any format.

• The Journal of Asian Finance, Economics and Business
• /
• 제6권4호
• /
• pp.91-98
• /
• 2019

Dividend policy is an important business decision and is considered a channel to communicate a firm's performance to shareholders. Given the empirical findings that earnings quality significantly affects financial analysts' forecasting activities, it is predicted that higher earnings quality would positively influence forecast accuracy. Specifically, it is expected that financial analysts would forecast dividends more accurately for firms with higher earning quality. Unlike the research on financial analysts' earnings forecasts was heavily conducted, there is little study about financial analysts' dividend forecasts. This paper examines the effect of earnings quality on financial analysts' dividend forecast accuracy. We use a sample of South Korean firms for the period of 2011-2015 for multivariate regression. Earnings quality is measured by accruals quality and performance-adjusted discretionary accruals followed by prior studies. We first compare the accuracy between dividend forecasts and earnings forecasts using t-test and Wilcoxon singed-rank test. It is confirmed that financial analysts' dividend forecasts are more accurate than earnings forecasts in Korea. We find that financial analysts' dividend forecasts are more accurate for firms with higher earnings quality. We also find that the result is still valid after controlling for the accuracy of financial analysts' earnings forecasts. This confirms that earnings quality positively affects financial analysts' dividend forecasts.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1998년도 하계종합학술대회논문집
• /
• pp.635-638
• /
• 1998

This paper proposes a simple method to measure system's performance in target tracking problems. Essentially employing the Cramer-Rao lower bound (CRLB) on trakcing accuracy, an algorithm of predicting system's performance under various scenarios is developed. The input data is a collection of measurements over time fromsensors embedded in gaussian noise. The target of interest may not maneuver over the processing time interval while the own ship observing platform may maneuver in an arbitrary fashion. Th eproposed approach is demonstrated and discussed through simulation results.