• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2012.05a
• /
• pp.585-586
• /
• 2012

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2000.11a
• /
• pp.211-214
• /
• 2000

An error analysis is very important for a precision machine tool to estimate its performance. This study proposes a new parallel device, a cubic parallel manipulator. Errors of the proposed cubic parallel manipulator include universal joint errors, errors occurring due to changes in the fore directions in the links, and actuation errors. An error analysis is performed for the manipulator platform moving at uniform velocity. The analysis shows how the position and orientation of the platform influences the directional link forces that change the errors in the manipulator. The analysis shows that the method can be used in predicting the accuracy of parallel devices.

• Journal of the Korean Society for Precision Engineering
• /
• v.18 no.6
• /
• pp.87-92
• /
• 2001

An error analysis is very important for a precision machine to estimate its performances. This study proposes a new parallel device, cubic parallel manipulator. Errors of the proposed cubic parallel manipulator include upper and down universal joint errors, due to the directional changes in the forces in the links, and actuation errors. An error analysis is presented based on an error model formed through the relation between the universal joint errors of the cubic parallel manipulator and the end effector accuracy. The analysis shows that the method can be used in predicting the accuracy of other cubic parallel devices.

• International Journal of Precision Engineering and Manufacturing
• /
• v.2 no.4
• /
• pp.75-80
• /
• 2001

An error analysis is very important to estimate performance of a precision machine. This study proposes an error analysis for a new parallel device, a cubic parallel device. The cubic parallel manipulator has error sources including upper and lower universal joint errors due to the directional changes in the link and actuation errors. The maximum errors of the end effector are affected by the axial direction changes of each links and the clearances of the universal joints when the parallel manipulator is moving along a path. It is found that the changes of errors mostly occur at the positions where the directions of exerting link forces shift. The error analysis is based on an error model formed from the relation between the universal point errors and the end-effector accuracy. The analysis method can be also used in predicting the accuracy of other parallel devices.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.12
• /
• pp.1-9
• /
• 2020

As pet dogs rapidly increase in number, abandoned and lost dogs are also increasing in number. In Korea, animal registration has been in force since 2014, but the registration rate is not high owing to safety and effectiveness issues. Biometrics is attracting attention as an alternative. In order to increase the recognition rate from biometrics, it is necessary to collect biometric images in the same form as much as possible-from the face. This paper proposes a method to determine whether a dog is facing front or not in a real-time video. The proposed method detects the dog's eyes and nose using deep learning, and extracts five types of directional face information through the relative size and position of the detected face. Then, a machine learning classifier determines whether the dog is facing front or not. We used 2,000 dog images for learning, verification, and testing. YOLOv3 and YOLOv4 were used to detect the eyes and nose, and Multi-layer Perceptron (MLP), Random Forest (RF), and the Support Vector Machine (SVM) were used as classifiers. When YOLOv4 and the RF classifier were used with all five types of the proposed face orientation information, the face recognition rate was best, at 95.25%, and we found that real-time processing is possible.