• The Journal of Korean Orthopaedic Ultrasound Society
• /
• v.5 no.1
• /
• pp.9-14
• /
• 2012

Purpose: The purpose of the study was to evaluate the accuracy and clinical outcome of ultrasound-guided glenohumeral joint steroid injection on adhesive capsulitis. Materials and Methods: Patients who were diagnosed as adhesive capsulitis by MRI and physical examination and did not improve their symptom with physical therapy and NSAIDS treatment more than 6 months were included in the study. Patients who showed any other shoulder pathology or history if trauma were excluded from the study. 33 patients including 15 males and 18 females were enrolled in the study, the average age being 55.1 (age 42~72). Cocktail of steroid, lidocaine, saline and contrast medium injected inside shoulder glenohumeral joint using novel approach (which we called acromioclavicular approach) under ultrasound guidance. Clinical outcome was measured through passive range of motion and VAS scoring system. Results: Based on radiographic findings, cases were classified according to the leakage of contrast medium; perfect confinement of contrast-medium inside the capsule, partial leakage of the medium and contrast-medium found at outside the joint. Total 25 cases (76%) out of 33 cases showed perfect confinement of contrast-medium inside the glenohumeral joint. Partial leakage was observed in 6 cases (18%), and contrast medium was observed outside of the glenohumeral joint in 2 cases (6%). Perfect-confinement group showed $111^{\circ}$($80{\sim}140^{\circ}$) of forward flexion and $48^{\circ}$($0{\sim}90^{\circ}$) of external rotation before injection, and improved to $134^{\circ}$($90{\sim}150^{\circ}$) of forward flexion and $70^{\circ}$($30{\sim}90^{\circ}$) of external rotation after injection (p<0.01). Partial leakage showed $120^{\circ}$($90{\sim}150^{\circ}$) of forward flexion and $70^{\circ}$($10{\sim}90^{\circ}$) of external rotation before injection, and improved to $139^{\circ}$($135{\sim}140^{\circ}$) of forward flexion and $78^{\circ}$($50{\sim}90^{\circ}$) of external rotation after injection (p<0.01). VAS score improved from 7.1 (score 3~9) to 2.6 (score 0~5) (p<0.01) in perfect confinement group, from 7.5 (score 7~9) to 3.3 (score 2~4) (p<0.01) in partial leakage group. Two group showed no significant difference. Conclusion: Accuracy of Acromioclavicular approach was 94% which is better than any other methods published so far. Partial leakage of the injection material did not show inferior result compared to perfect injection.

• Journal of Navigation and Port Research
• /
• v.46 no.3
• /
• pp.280-288
• /
• 2022

This study examined the diagnostics of abnormalities and faults of equipment, whose rotational speed changes even during regular operation. The purpose of this study was to suggest a procedure that can properly apply machine learning to the time series data, comprising non-stationary characteristics as the rotational speed changes. Anomaly and fault diagnosis was performed using machine learning: k-Nearest Neighbor (k-NN), Support Vector Machine (SVM), and Random Forest. To compare the diagnostic accuracy, an autoencoder was used for anomaly detection and a convolution based Conv1D was additionally used for fault diagnosis. Feature vectors comprising statistical and frequency attributes were extracted, and normalization & dimensional reduction were applied to the extracted feature vectors. Changes in the diagnostic accuracy of machine learning according to feature selection, normalization, and dimensional reduction are explained. The hyperparameter optimization process and the layered structure are also described for each algorithm. Finally, results show that machine learning can accurately diagnose the failure of a variable-rotation machine under the appropriate feature treatment, although the convolution algorithms have been widely applied to the considered problem.

• Smart Structures and Systems
• /
• v.9 no.3
• /
• pp.273-286
• /
• 2012

As civil structures are exposed to various external loads, it is essential to assess the structural condition, especially the structural displacement, in every moment. Therefore, a visually servoed paired structured light system was proposed in the previous study. The proposed system is composed of two screens facing with each other, each with a camera, a screen, and one or two lasers controlled by a 2-DOF manipulator. The 6-DOF displacement can be calculated from the positions of three projected laser beams and the rotation angles of the manipulators. In the estimation process, one of well-known iterative methods such as Newton-Raphson or extended Kalman filter (EKF) was used for each measurement. Although the proposed system with the aforementioned algorithms estimates the displacement with high accuracy, it takes relatively long computation time. Therefore, an incremental displacement estimation (IDE) algorithm which updates the previously estimated displacement based on the difference between the previous and the current observed data is newly proposed. To validate the performance of the proposed algorithm, simulations and experiments are performed. The results show that the proposed algorithm significantly reduces the computation time with the same level of accuracy compared to the EKF with multiple iterations.

• Journal of Korea Multimedia Society
• /
• v.8 no.6
• /
• pp.768-775
• /
• 2005

For sign languages are main communication means among hearing-impaired people, there are communication difficulties between speaking-oriented people and sign-language-oriented people. Automated sign-language recognition may resolve these communication problems. In sign languages, finger spelling is used to spell names and words that are not listed in the dictionary. There have been research activities for gesture and posture recognition using glove-based devices. However, these devices are often expensive, cumbersome, and inadequate for recognizing elaborate finger spelling. Use of colored patches or gloves also cause uneasiness. In this paper, a vision-based finger spelling recognition system is introduced. In our method, captured hand region images were separated from the background using a skin detection algorithm assuming that there are no skin-colored objects in the background. Then, hand postures were recognized using a two-dimensional grid analysis method. Our recognition system is not sensitive to the size or the rotation of the input posture images. By optimizing the weights of the posture features using a genetic algorithm, our system achieved high accuracy that matches other systems using devices or colored gloves. We applied our posture recognition system for detecting Korean Sign Language, achieving better than $93\%$ accuracy.

• Smart Structures and Systems
• /
• v.18 no.4
• /
• pp.801-818
• /
• 2016

To estimate structural displacement, a visually servoed paired structured light system (ViSP) was proposed in previous studies. The ViSP is composed of two sides facing each other, each with one or two laser pointers, a 2-DOF manipulator, a camera, and a screen. By calculating the positions of the laser beams projected onto the screens and rotation angles of the manipulators, relative 6-DOF displacement between two sides can be estimated. Although the performance of the system has been verified through various simulations and experimental tests, it has a limitation that the accuracy of the displacement measurement depends on the alignment of the laser pointers. In deriving the kinematic equation of the ViSP, the laser pointers were assumed to be installed perfectly normal to the same side screen. In reality, however, this is very difficult to achieve due to installation errors. In other words, the pose of laser pointers should be calibrated carefully before measuring the displacement. To calibrate the initial pose of the laser pointers, a specially designed jig device is made and employed. Experimental tests have been performed to validate the performance of the proposed calibration method and the results show that the estimated displacement with the initial pose calibration increases the accuracy of the 6-DOF displacement estimation.

• Proceedings of the KIEE Conference
• /
• 2006.04a
• /
• pp.120-121
• /
• 2006

In this paper, We have designed a face recognition system based on the embedded Linux. This paper has an aim in embedded system to recognize the face more exactly. At first, the contrast of the face image is adjusted with lightening compensation method, the skin and lip color is founded based on YCbCr values from the compensated image. To take advantage of the method based on feature and appearance, these methods are applied to the eyes which has the most highly recognition rate of all the part of the human face. For eyes detecting, which is the most important component of the face recognition, we calculate the horizontal gradient of the face image and the maximum value. This part of the face is resized for fitting the eye image. The image, which is resized for fit to the eye image stored to be compared, is extracted to be the feature vectors using the continuous wavelet transform and these vectors are decided to be whether the same person or not with PNN, to miminize the error rate, the accuracy is analyzed due to the rotation or movement of the face. Also last part of this paper we represent many cases to prove the algorithm contains the feature vector extraction and accuracy of the comparison method.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.26 no.1
• /
• pp.15-22
• /
• 2002

This paper introduces a compensating system for machining error, which is resulted from chucking with separated jaws. In machining the chucked cylindrical workpiece, the deterioration of machining accuracy, such as out-of-roundness is inevitable due to the variation of the radial compliance of the chuck workpiece system which is caused by the position of jaws with respect to the direction of the applied force. To compensate the chucking compliance induced error, firstly roundness profile of workpiece due to chucking compliance after machining needs to be predicted. Then using this predicted profile, the compensated tool feed trajectory can be generated. And by synchronizing the cutting tool feed system with workpiece rotation, the chucking compliance induced error can be compensated. To satisfy the condition that the cutting tool feed system must provide high speed and high position accuracy, brushless linear DC motor is used. In this study, firstly through the force-deflection experiment in workpiece chucked lathe, the variation of radial compliance of chuck workpiece system is obtained. Secondly using the mathematical equation and cutting experiment result, the predicted profile of workpiece and its compensation tool trajectory are generated. Thirdly the configuration of compensation system using linear motor is introduced, and to improve the system performance, PID controller is designed. Finally the tracking performance of system is examined by experiment. Through the real cutting experiment, roundness is significantly improved.

• Nuclear Engineering and Technology
• /
• v.30 no.5
• /
• pp.452-461
• /
• 1998

The pin power distribution is determined by analyzing the rotational gamma scanning data for 36 element fuel bundle of HANARO. A fission monitor of Nb$^{95}$ is chosen by considering the criteria of the half-life, fission yield, emitting ${\gamma}$-ray energy and probability. The ${\gamma}$-ray spectra were measured in Korea Atomic Energy Research Institute(KAERI) by using a HPGe detector and by rotating the fuel bundle at steps of 10$^{\circ}$. The counting rates of Nb$^{95}$ 766 keV ${\gamma}$-rays are determined by analyzing the full absorption peak in the spectra. A 36$\times$36 response matrix is obtained from calculating the contribution of each rod at every scanning angle by assuming 2-dimensional and parallel beam approximations for the measuring geometry. In terms of the measured counting rates and the calculated response matrix, an inverse problem is set up for the unknown distribution of activity concentrations of pins. To select a suitable solving method, the performances of three direct methods and the iterative least-square method are tested by solving simulation examples. The final solution is obtained by using the iterative least-square method that shows a good stability. The influences of detection error, step size of rotation and the collimator width are discussed on the accuracy of the numerical solution. Hence an improvement in the accuracy of the solution is proposed by reducing the collimator width of the scanning arrangement.

• Journal of Power System Engineering
• /
• v.17 no.5
• /
• pp.121-127
• /
• 2013

In this paper, we propose a distance measurement system for automatic berthing control using a stereo camera mounted on a rotation control device, and a radial pattern target. Automatically controlling the position and attitude of a ship aims to prevent maritime accidents due to human error. Our goal is to measure the relative distance between a ship and an onshore or offshore target for berthing. Therefore, the distance should be continuously measured while tracking a fixed point on a target. To this end, we developed a stereo camerabased distance measurement system that satisfied these requirements. This paper describes the structure and principle of the measurement system. We validate the distance error for target incline due to the relative position and attitude between a camera and a target in miniature scale. In addition, the findings of an experiment in an outdoor environment demonstrate that the proposed measurement system has accuracy within 1 m at a range of 20-100 m which is the acceptable accuracy for automatic berthing.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.7
• /
• pp.1525-1530
• /
• 2014

In this research, we describe teaching based sweeping control for grinder robot has been proposed as a system which is suitable to work utilizing pressure sensitive alternative to human. Teaching method is used for grinder robots operations because of their position accuracy, path accuracy, and machining reaction force. A grinder robot for two-dimensional iron plate was developed on the basis of an force sensor based teaching method. An automatic-path-generation method and experimental results using specific points was adopted to reduce the number of teaching points and time. And also, in order to determine the proper machining conditions, various machining conditions such as grinder-wheel rotation speed and robot moving speed, were evaluated.