• Journal of the Korea Society of Computer and Information
• /
• v.24 no.1
• /
• pp.9-23
• /
• 2019

In this paper, we propose a layer structure of a pest image classifier model using CNN (Convolutional Neural Network) and background removal image processing algorithm for improving classification accuracy in order to build a smart monitoring system for pine wilt pest control. In this study, we have constructed and trained a CNN classifier model by collecting image data of pine wilt pest mediators, and experimented to verify the classification accuracy of the model and the effect of the proposed classification algorithm. Experimental results showed that the proposed method successfully detected and preprocessed the region of the object accurately for all the test images, resulting in showing classification accuracy of about 98.91%. This study shows that the layer structure of the proposed CNN classifier model classified the targeted pest image effectively in various environments. In the field test using the Smart Trap for capturing the pine wilt pest mediators, the proposed classification algorithm is effective in the real environment, showing a classification accuracy of 88.25%, which is improved by about 8.12% according to whether the image cropping preprocessing is performed. Ultimately, we will proceed with procedures to apply the techniques and verify the functionality to field tests on various sites.

• Journal of Information Processing Systems
• /
• v.19 no.6
• /
• pp.745-755
• /
• 2023

The wire rope is an indispensable production machinery in coal mines. It is the main force-bearing equipment of the underground traction system. Accurate detection of wire rope defects and positions exerts an exceedingly crucial role in safe production. The existing defect detection solutions exhibit some deficiencies pertaining to the flexibility, accuracy and real-time performance of wire rope defect detection. To solve the aforementioned problems, this study utilizes the camera to sample the wire rope before the well entry, and proposes an object based on YOLOv5. The surface small-defect detection model realizes the accurate detection of small defects outside the wire rope. The transfer learning method is also introduced to enhance the model accuracy of small sample training. Herein, the enhanced YOLOv5 algorithm effectively enhances the accuracy of target detection and solves the defect detection problem of wire rope utilized in mine, and somewhat avoids accidents occasioned by wire rope damage. After a large number of experiments, it is revealed that in the task of wire rope defect detection, the average correctness rate and the average accuracy rate of the model are significantly enhanced with those before the modification, and that the detection speed can be maintained at a real-time level.

• Physical Therapy Korea
• /
• v.12 no.3
• /
• pp.39-45
• /
• 2005

Tracking is an experimental paradigm that can be used to study information processing in continuous movements involving accurate, ongoing control of motor performance. The purpose of this study was to identify the effects of knee tracking performance. Six patients with hemiplegia and six age-matched controls participated in the study. The tracking test was administrated. It was composed with regular ranges of $0^{\circ}C$ to $40^{\circ}C$ and randomized range .2 to .4 Hz. Using the Mann-Whitney U test, a comparison was made between subjects who had suffered from stroke and subjects who were well coordinated. The Wilcoxon Matched Pairs Signed Ranks Test was used to compare and analyze the paretic and nonparetic sides of the stroke patients. The results of study were as follows: accuracy index of the tracking test was significantly higher on the control side than paretic and nonparetic sides. Accuracy index scores were significantly higher for nonparetic sides with stroke compared with paretic sides with stroke. This study shows tracking is impaired in paretic and nonparetic knee of subjects with stroke.

• English Language & Literature Teaching
• /
• v.11 no.1
• /
• pp.1-15
• /
• 2005

The purpose of this study was to investigate whether or not the use of the Korean alphabet increased the accuracy of English sentences Korean university students produced in dictation. The students were divided into three categories, beginning, intermediate, and advanced, based on the listening comprehension scores of a practice TOEIC test. The total population of 120 students were divided into two groups, control and experiment. In the first testing, the experiment group transcribed the English utterances on a practice TOEIC tape into phonological writing in Korean and then later changed the Korean writing into English words and sentences. In the second testing, the control group became the experiment group and used the Korean alphabet in transcribing the English sounds. Statistically significant differences were found in the improvement of accuracy in dictation when the Korean alphabet was used, especially for the beginning and intermediate students. By using the Korean alphabet as the phonological representation of the sounds, the students in the experiment group produced more accurate English words than the control group who went directly from the English utterances to writing in English. Statistically significant results were not produced for the advanced students. The significance of the present study relates to the need to add to the paucity of available data on the use of the Korean alphabet in teaching listening comprehension.

• Journal of Korea Multimedia Society
• /
• v.20 no.6
• /
• pp.927-934
• /
• 2017

As the technology of drone develops, the use of drone is increasing, In addition, the types of sensors that are inside of smart phones are becoming various and the accuracy is enhancing day by day. Various of researches are being progressed. Therefore, we need to control drone by using smart phone's sensors. In this paper, we propose the most suitable machine learning model that matches the gyro sensor data with drone's moving. First, we classified drone by it's moving of the gyro sensor value of 4 and 8 degree of freedom. After that, we made it to study machine learning. For the method of machine learning, we applied the One-Rule, Neural Network, Decision Tree, and Navie Bayesian. According to the result of experiment that we designated the value from gyro sensor as the attribute, we had the 97.3 percent of highest accuracy that came out from Naive Bayesian method using 2 attributes in 4 degree of freedom. On and the same, in 8 degree of freedom, Naive Bayesian method using 2 attributes showed the highest accuracy of 93.1 percent.

• Journal of Environmental Health Sciences
• /
• v.37 no.1
• /
• pp.57-63
• /
• 2011

Crocidolite quality control (QC) sampling created by the wet generation method has been validated by validation tests such as the accuracy, precision, and storage tests. For this study we designed and developed a manufacturing apparatus and standard operating procedure for making these QC samples. The most important step in the procedure of making QC samples was the stage eliminating static electricity in asbestos fibers. This static electricity hampers the fibers clog functioning. In accuracy and precision tests by phase contrast microscopy analysis, the difference between the reference values and the studied values was at maximum 17.8%. This satisfies the AIHA proficiency analytical test criteria for asbestos. We could confirm the nearly even distribution of crocidolite fibers on the membrane filter. Also, there was no loss of fibers in the storage test after the one month.

• International Journal of Aeronautical and Space Sciences
• /
• v.1 no.2
• /
• pp.43-49
• /
• 2000

The Global Positioning System (GPS) is becoming more attractive navigation means for LEO (Low Earth Orbit) spacecraft due to the data accuracy and convenience for utilization. The anomalies such as serious variations of Dilution-Of-Precision (DOP), loss of infrequent 3-dimensional position fix, and deterioration of instantaneous accuracy of position and velocity data could be observed, which have not been appeared during the ground testing. It may cause lots of difficulty for the processing of the orbit control algorithm using the GPS data. In this paper, the characteristics of the GPS data were analyzed according to the configuration of GPS receiver such as position fix algorithm and mask angle using GPS navigation data obtained from the first Korea Multi-Purpose Satellite (KOMPSAT). The problem in orbit tracking using GPS data, including the infrequent deterioration of the accuracy, and an efficient algorithm for its countermeasures has also been introduced. The reliability and efficiency of the modified algorithm were verified by analyzing the effect of the results between algorithm simulation using KOMPSAT flight data and ground simulator.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.30 no.10 s.253
• /
• pp.1209-1218
• /
• 2006

Precision servomechanisms are widely used in machine tool, semiconductor and flat panel display industries. It is important to improve contouring accuracy in high-precision servomechanisms. In order to improve the contouring accuracy, cross-coupled control systems have been proposed. However, it is very difficult to select the controller parameters because cross-coupled control systems are multivariable, nonlinear and time-varying systems. In this paper, in order to improve contouring accuracy of a biaxial servomechanism, a cross-coupled controller is adopted and an optimal tuning procedure based on an integrated design concept is proposed. Strict mathematical modeling and identification process of a servomechanism are performed. An optimal tuning problem is formulated as a nonlinear constrained optimization problem including the relevant controller parameters of the servomechanism. The objective of the optimal tuning procedure is to minimize both the contour error and the settling time while satisfying constraints such as the relative stability and maximum overshoot conditions, etc. The effectiveness of the proposed optimal tuning procedure is verified through experiments.

• Journal of Navigation and Port Research
• /
• v.35 no.2
• /
• pp.121-130
• /
• 2011

The localization of vehicle is an important part of an unmanned vehicle control problem. Pseudolite ultrasonic system(PUS) is the method to find an absolute position with a high accuracy by using ultrasonic sensor. And Gyro is the inertial sensor to measure yaw angle of vehicle. PUS can be able to estimate the position of mobile robot precisely, in which errors are not accumulated. And Gyro is a more faster measure method than PUS. In this paper, we suggest a more accuracy method of calculating PUS which is numerical analysis approach named Newtonian method. And also propose the fusion method to increase the accuracy of estimated angle on moving vehicle by using PUS and Gyro integrated system by Kalman filtering. To control the 4WS unmanned vehicle, the trajectory following algorithm is suggested. And the new concept arbitration of goal controller is suggested. This method considers the desirability function of vehicle state. Finally, the performances of Newtonian method and designed controller were verified from the experimental results with the 4WS vehicle scaled 1/10.

• Journal of radiological science and technology
• /
• v.43 no.6
• /
• pp.461-467
• /
• 2020

In the field of nuclear medicine, errors are sometimes generated because the assessment of the uniformity of gamma cameras relies on the naked eye of the evaluator. To minimize these errors, we created an artificial intelligence model based on CNN algorithm and wanted to assess its usefulness. We produced 20,000 normal images and partial cold region images using Python, and conducted artificial intelligence training with Resnet18 models. The training results showed that accuracy, specificity and sensitivity were 95.01%, 92.30%, and 97.73%, respectively. According to the results of the evaluation of the confusion matrix of artificial intelligence and expert groups, artificial intelligence was accuracy, specificity and sensitivity of 94.00%, 91.50%, and 96.80%, respectively, and expert groups was accuracy, specificity and sensitivity of 69.00%, 64.00%, and 74.00%, respectively. The results showed that artificial intelligence was better than expert groups. In addition, by checking together with the radiological technologist and AI, errors that may occur during the quality control process can be reduced, providing a better examination environment for patients, providing convenience to radiologists, and improving work efficiency.