• Journal of Periodontal and Implant Science
• /
• v.52 no.3
• /
• pp.220-229
• /
• 2022

Purpose: The aim of this study was to evaluate and compare the accuracy performance of dental professionals in the classification of different types of dental implant systems (DISs) using panoramic radiographic images with and without the assistance of a deep learning (DL) algorithm. Methods: Using a self-reported questionnaire, the classification accuracy of dental professionals (including 5 board-certified periodontists, 8 periodontology residents, and 31 dentists not specialized in implantology working at 3 dental hospitals) with and without the assistance of an automated DL algorithm were determined and compared. The accuracy, sensitivity, specificity, confusion matrix, receiver operating characteristic (ROC) curves, and area under the ROC curves were calculated to evaluate the classification performance of the DL algorithm and dental professionals. Results: Using the DL algorithm led to a statistically significant improvement in the average classification accuracy of DISs (mean accuracy: 78.88%) compared to that without the assistance of the DL algorithm (mean accuracy: 63.13%, P<0.05). In particular, when assisted by the DL algorithm, board-certified periodontists (mean accuracy: 88.56%) showed higher average accuracy than did the DL algorithm, and dentists not specialized in implantology (mean accuracy: 77.83%) showed the largest improvement, reaching an average accuracy similar to that of the algorithm (mean accuracy: 80.56%). Conclusions: The automated DL algorithm classified DISs with accuracy and performance comparable to those of board-certified periodontists, and it may be useful for dental professionals for the classification of various types of DISs encountered in clinical practice.

• Journal of Biomedical Engineering Research
• /
• v.30 no.5
• /
• pp.428-437
• /
• 2009

The Performance research about EEG-BCI algorithm in BCI-naive subjects is very important for evaluating the applicability to the public. We analyzed the result of the performance evaluation experiment about the EEG-BCI algorithm in BCI-naive subjects on three different aspects. The EEG-BCI algorithm used in this paper is composed of the common spatial pattern(CSP) and the least square linear classifier. CSP is used for obtaining the characteristic of event related desynchronization, and the least square linear classifier classifies the motor imagery EEG data of the left hand or right hand. The performance evaluation experiments about EEG-BCI algorithm is conducted for 40 men and women whose age are 23.87${\pm}$2.47. The performance evaluation about EEG-BCI algorithm in BCI-naive subjects is analyzed in terms of the accuracy, the relation between the information transfer rate and the accuracy, and the performance changes when the different types of cue were used in the training session and testing session. On the result of experiment, BCI-naive group has about 20% subjects whose accuracy exceed 0.7. And this results of the accuracy were not effected significantly by the types of cue. The Information transfer rate is in the inverse proportion to the accuracy. And the accuracy shows the severe deterioration when the motor imagery is less then 2 seconds.

• International journal of advanced smart convergence
• /
• v.13 no.2
• /
• pp.80-87
• /
• 2024

This paper focuses on improving accuracy in constrained computing settings by employing the ReLU (Rectified Linear Unit) activation function. The research conducted involves modifying parameters of the ReLU function and comparing performance in terms of accuracy and computational time. This paper specifically focuses on optimizing ReLU in the context of a Multilayer Perceptron (MLP) by determining the ideal values for features such as the dimensions of the linear layers and the learning rate (Ir). In order to optimize performance, the paper experiments with adjusting parameters like the size dimensions of linear layers and Ir values to induce the best performance outcomes. The experimental results show that using ReLU alone yielded the highest accuracy of 96.7% when the dimension sizes were 30 - 10 and the Ir value was 1. When combining ReLU with the Adam optimizer, the optimal model configuration had dimension sizes of 60 - 40 - 10, and an Ir value of 0.001, which resulted in the highest accuracy of 97.07%.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.10 no.5
• /
• pp.26-30
• /
• 2011

Currently, many researches are carried out about tilting index table, which is one of the main component of 5-axis machine tool. The performance of the tilting index table is associated the rotational accuracy which is very important factor for high precision machining because it have an effect on machining error. In this paper, a tilting index table is developed, and the rotational accuracy of the tilting index table using a laser measurement equipment is measured. In addition, a correction value is obtained from the measured value through compensation, and the correction value is used to improve the accuracy of the table. Comparative analysis is carried out for the accuracy of the table before and after compensation. This paper can be used by a reference for performance and reliability advancement of tilting index table.

• Journal of Positioning, Navigation, and Timing
• /
• v.7 no.1
• /
• pp.15-24
• /
• 2018

This study analyzed positioning accuracy of the multi-differential global navigation satellite system (DGNSS) algorithm that integrated GPS, GLONASS, and BDS. Prior to the analysis, four sites of which satellite observation environment was different were selected, and satellite observation environments for each site were analyzed. The analysis results of the algorithm performance at each of the survey points showed that high positioning performance was obtained by using DGPS only without integration of satellite navigation systems in the open sky environment but the positioning performance of multi-DGNSS became higher as the satellite observation environments degraded. The comparison results of improved positioning performance of the multi-DGNSS at the poor reception environment compared to differential global positioning system (DGPS) positioning results showed that horizontal accuracy was improved by 78% and vertical accuracy was improved by 65% approximately.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.9 no.3
• /
• pp.1-7
• /
• 2010

The aim of this research is to evaluate movement and path characteristics of developed heavy duty handling robot using laser tracker(API T3) according to the ISO 9283 robot performance evaluation criteria. As carry out 3D modeling and simulation using CATIA, a test cube was set up to select moving and measuring range of robot. Performance test for pose and distance accuracy, path and path velocity accuracy under payload zero and 440kgf was accomplished. The resulted output data show the reliability of the developed robot.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.10 no.5
• /
• pp.77-82
• /
• 2010

The tracking performance of the big tracking antenna system using Radio Frequency is very important for the tracking and position measuring for the flight vehicle, but the precise measuring of the tracking performance is not easy, especially for the big antenna system such as ground telemetry antenna or tracking radar in space application because it's characteristics could be different in accordance with the antenna direction. In this paper, the error factors impacting on the tracking performance (pointing accuracy and tracking accuracy) and the ranges of each factor are reviewed, and the simple and efficient method to measure the tracking performance is introduced which using low earth orbit as the signal source. Finally, the measurement results for the telemetry ground antenna in NARO Space Center are reviewed.

• Journal of Positioning, Navigation, and Timing
• /
• v.4 no.2
• /
• pp.79-85
• /
• 2015

Existing Differential GPS (DGPS) pseudorange correction (PRC) generation techniques based on a virtual reference station cannot effectively assign a weighting factor if the baseline distance between a user and a reference station is not long enough. In this study, a virtual reference station DGPS PRC generation technique was developed based on an enhanced inverse distance weighting method using an exponential function that can maximize a small baseline distance difference due to the dense arrangement of DGPS reference stations in South Korea, and its positioning performance was validated. For the performance verification, the performance of the model developed in this study (EIDW) was compared with those of typical inverse distance weighting (IDW), first- and second-order multiple linear regression analyses (Planar 1 and 2), the model of Abousalem (1996) (Ab_EXP), and the model of Kim (2013) (Kim_EXP). The model developed in the present study had a horizontal accuracy of 53 cm, and the positioning based on the second-order multiple linear regression analysis that showed the highest positioning accuracy among the existing models had a horizontal accuracy of 51 cm, indicating that they have similar levels of performance. Also, when positioning was performed using five reference stations, the horizontal accuracy of the developed model improved by 8 ~ 42% compared to those of the existing models. In particular, the bias was improved by up to 27 cm.

• Journal of Astronomy and Space Sciences
• /
• v.35 no.1
• /
• pp.39-46
• /
• 2018

In this study, the performance of ranging techniques for the Korea Pathfinder Lunar Orbiter (KPLO) space communication system is investigated. KPLO is the first lunar mission of Korea, and pseudo-noise (PN) ranging will be used to support the mission along with sequential ranging. We compared the performance of both ranging techniques using the criteria of accuracy, acquisition probability, and measurement time. First, we investigated the end-to-end accuracy error of a ranging technique incorporating all sources of errors such as from ground stations and the spacecraft communication system. This study demonstrates that increasing the clock frequency of the ranging system is not required when the dominant factor of accuracy error is independent of the thermal noise of the ranging technique being used in the system. Based on the understanding of ranging accuracy, the measurement time of PN and sequential ranging are further investigated and compared, while both techniques satisfied the accuracy and acquisition requirements. We demonstrated that PN ranging performed better than sequential ranging in the signal-to-noise ratio (SNR) regime where KPLO will be operating, and we found that the T2B (weighted-voting balanced Tausworthe, voting v = 2) code is the best choice among the PN codes available for the KPLO mission.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.6
• /
• pp.1955-1960
• /
• 2010

A performance of CNC 3-axis pipe profile-cutting machine we developed was evaluated by measuring and verifying a positioning accuracy of its feeding unit and a cutting shape accuracy of pipe workpiece. The positioning accuracy was verified by comparing moving distance actuated by PLC motion controller with actual one measured by a laser interferometer. The cutting shape accuracy was also verified by comparing a cutting shape obtained through scanning and 3D modeling the pipe workpiece with that through CL data.