• Journal of information and communication convergence engineering
• /
• v.21 no.3
• /
• pp.198-207
• /
• 2023

Responding to changes in artificial intelligence models and the data environment is crucial for increasing data-learning accuracy and inference stability of industrial applications. A learning model that is overfitted to specific training data leads to poor learning performance and a deterioration in flexibility. Therefore, an early stopping technique is used to stop learning at an appropriate time. However, this technique does not consider the homogeneity and independence of the data collected by heterogeneous nodes in a differential network environment, thus resulting in low learning accuracy and degradation of system performance. In this study, the generalization performance of neural networks is maximized, whereas the effect of the homogeneity of datasets is minimized by achieving an accuracy of 99.7%. This corresponds to a decrease in delay time by a factor of 2.33 and improvement in performance by a factor of 2.5 compared with the conventional method.

• Journal of the Semiconductor & Display Technology
• /
• v.21 no.3
• /
• pp.63-68
• /
• 2022

In this study, we produced defect detection models using parallel convolution neural networks. If convolution neural networks are constructed parallel type, the model's detection accuracy will increase and detection time will decrease. We produced parallel-type defect detection models using 4 types of convolutional algorithms. The performance of models was evaluated using evaluation indicators. The model's performance is detection accuracy and detection time. We compared the performance of each parallel model. The detection accuracy of the model using AlexNet is 97 % and the detection time is 0.3 seconds. We confirmed that when AlexNet algorithm is constructed parallel type, the model has the highest performance.

• Journal of the Korean Professional Engineers Association
• /
• v.22 no.3
• /
• pp.5-13
• /
• 1989

A major problem of stopwatch time study is how to do for the accurate and consistent performance rating, which is one of the critical variables to determine the accuracy of work measurement and should be still dependent upon time observer's judgement. Therefore the time observer's ability for the performance rating is very important, and must be improved by correct training method and procedure. This paper developed a new benchmark and benchmark-observation method for the effective performance rating training of assembling and machining operations. The trainees' ability in the accuracy and consistency of the performance rating ,improved significantly after being trained by subject method. The percentage improvement in rating accuracy and consistency values was 34.7% and 49% respectively. In addition, benchmark-practice method for the performance rating training is not significant, so it is proofed that the skill of a certain operation is not important for the improvement of the rating ability.

• Journal of Institute of Control, Robotics and Systems
• /
• v.20 no.5
• /
• pp.578-583
• /
• 2014

Optical pick-up is a core component for data read/write operations in optical disc drives, and an optical pick-up performance evaluator is an instrument used to analyze the overall performance of an optical pick-up. Due to inevitable errors in an analog measurement circuit, resultant evaluation data is not guaranteed to be accurate. In this paper, a calibration method for an optical pick-up performance evaluator is proposed to ensure evaluation accuracy. Measured data is corrected by a 1st order correction function, and a calibration process based on least-square method is utilized to obtain correction coefficients of the correction function. The proposed calibration method is applied to experiments, and enhanced accuracy is presented with resultant evaluation data.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.434-434
• /
• 2000

It is the main problem to measure the position and orientation of a robot end effector for the calibration of robots. The calibration methods can be used as a tool to improve the accuracy of robots without change of the arm or control architecture of robots. But such calibration methods require the accurate measurements. Dynamic measurement of position and orientation Provides a solution of this problem and improves dynamic accuracy by dynamic calibration o( robots. This paper describes the development o( the laser tracking system capable of determining the static and dynamic performance of industrial robots. The structure and system components are presented and basic experimental results are included to demonstrate the instrument performance. The system can be applied to the remote controlled mobile robots as weil as the calibration of robots.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.8
• /
• pp.305-314
• /
• 2017

Clustering is a method that collects data objects into groups based on their similary. Performance of the state-of-the-art clustering methods is different according to the data characteristics. There have been numerous studies that performed experiments to compare the accuracy of the state-of-the-art clustering methods by applying various kinds of datasets. A common problem of these studies is that they only consider clustering algorithms that yield the most accurate results for a particular dataset. They do not consider what factors affect the execution time of each clustering method and how they are affected. Nevertheless, execution time is an important factor in clustering performance if there is no significant difference in accuracy. In order to solve the problems of the existing research, through a series of experiments using various types of datasets, we compare the accuracy of four representative clustering methods. In addition, we perform practical clustering performance comparisons by deriving time complexity and identifying factors that influences to its performance.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2000.10a
• /
• pp.75-80
• /
• 2000

Evaluation method of seismic performance has mainly used elastic spectrum analysis. This method has simplicity of analysis but deficiency of accuracy. And evaluation method of seismic performance using inelastic dynamic analysis reflects accurately inelasticity of material but hardly reflects site effects. This study suggested evaluation scheme of seismic performance for bridge structure using capacity spectrum method applied inelastic static analysis and standard design response spectrum of Korea Standard Specification for Highway Bridge. Two results, capacity spectrum method and inelastic dynamic analysis method, are very similar. As a result, this study appropriately supply both simplicity of analysis and accuracy of result.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2000.04a
• /
• pp.624-628
• /
• 2000

The performance of machine tools is qualified by many test procedures given by the national/international standards or respected organisations. Among them, test regarding circular-interpolation accuracy is getting to be one of the important acceptance tests at the production level. Machine tool systems are composed of many mechanical and electronical sub-systems so that it is not easy to improve dynamic performance by examining only one particular part. Instead, overall systematic approach encompassing all the contributing elements is necessary to achieve good results. In this study, measures taken in circular accuracy improvements will be explained case by case.

• Journal of radiological science and technology
• /
• v.45 no.2
• /
• pp.127-134
• /
• 2022

In order to overcome the image quality limitations of the conventional C-arm, a flat panel detector (FPD) is used to enhance spatial resolution, detective quantum efficiency, frame rate, and dynamic range. Three-dimensional (3D) visualized information can be obtained from C-arm computed tomography (CT) equipped with an FPD, which can reduce patient discomfort and provide various medical information to health care providers by conducting procedures in the interventional procedure room without moving the patient to the CT scan room. Unlike a conventional C-arm device, a C-arm CT requires different basic safety and essential performance evaluation criteria; therefore, in this study, basic safety and essential performance evaluation criteria to protect patients, medical staff, and radiologists were derived based on International Electrotechnical Commission (IEC) standards, the Ministry of Food and Drug Safety (MFDS) standards in Korea, and the rules on the installation and operation of special medical equipment in Korea. As a result of the study, six basic safety evaluation criteria related to electrical and mechanical radiation safety (leakage current, collision protection, emergency stopping device, overheating, recovery management, and ingress of water or particulate matter into medical electrical (ME) equipment and ME systems: footswitches) and 14 essential performance evaluation criteria (accuracy of tube voltage, accuracy of tube current, accuracy of loading time, accuracy of current time product, reproducibility of radiation output, linearity and consistency in radiography, half layer value in X-ray equipment, focal size and collimator, relationship between X-ray field and image reception area, consistency of light irradiation versus X-ray irradiation, performance of the mechanical device, focal spot to skin distance accuracy, image quality evaluation, and technical characteristic of cone-beam computed tomography) were selected for a total of 20 criteria.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2000.04a
• /
• pp.291-296
• /
• 2000

Liner DC motors are widely used for servo-actuator, which would be applied for semiconductor equipments and precise machining systems. we have been developed linear DC motor with high speed, acceleration and position accuracy. From performance test, the position accuracy. From performance test, the position and repeatability accuracy were able to be controlled with 10 ${\mu}{\textrm}{m}$ and $\pm$1 ${\mu}{\textrm}{m}$, respectively. The highest acceleration and speed were obtained 3 G and 2m/sec, respectively. Static thrust force was 270N, and then error was 25%.