• Journal of the Korean Society for Precision Engineering
• /
• v.18 no.7
• /
• pp.98-105
• /
• 2001

The machining accuracy is affected by geometric, volumetric errors of the machine tools. To improve the product quality, we need to enhance the machining accuracy of the machine tools. To this point of view, measurement and inspection of finished part as error analysis of machine tools ahas been studied for last several decades. This paper suggests the enhancement method of machining accuracy for precision machining of high quality metal reflection mirror or optics lens, etc. In this paper, we study 1) the compensation of linear pitch error with NC controller compensation function using laser interferometer measurement, 2) the method for enhancing the accuracy of NC milling machining by modeling and compensation of volumetric error, 3) the spherical surface manufacturing by modeling and compensation of volumetric error of the machine tool, 4) the system development of OMM without detaching work piece from a bed of machine tool after working, 5) the generation of the finished part profile by OMM. Furthermore, the output of OMM is compared with that of CMM, and verified the feasibility of the measurement system.

• Journal of Radiation Protection and Research
• /
• v.46 no.4
• /
• pp.204-212
• /
• 2021

Background: Identification of radioisotopes for plastic scintillation detectors is challenging because their spectra have poor energy resolutions and lack photo peaks. To overcome this weakness, many researchers have conducted radioisotope identification studies using machine learning algorithms; however, the effect of data normalization on radioisotope identification has not been addressed yet. Furthermore, studies on machine learning-based radioisotope identifiers for plastic scintillation detectors are limited. Materials and Methods: In this study, machine learning-based radioisotope identifiers were implemented, and their performances according to data normalization methods were compared. Eight classes of radioisotopes consisting of combinations of ²²Na, ⁶⁰Co, and ¹³⁷Cs, and the background, were defined. The training set was generated by the random sampling technique based on probabilistic density functions acquired by experiments and simulations, and test set was acquired by experiments. Support vector machine (SVM), artificial neural network (ANN), and convolutional neural network (CNN) were implemented as radioisotope identifiers with six data normalization methods, and trained using the generated training set. Results and Discussion: The implemented identifiers were evaluated by test sets acquired by experiments with and without gain shifts to confirm the robustness of the identifiers against the gain shift effect. Among the three machine learning-based radioisotope identifiers, prediction accuracy followed the order SVM > ANN > CNN, while the training time followed the order SVM > ANN > CNN. Conclusion: The prediction accuracy for the combined test sets was highest with the SVM. The CNN exhibited a minimum variation in prediction accuracy for each class, even though it had the lowest prediction accuracy for the combined test sets among three identifiers. The SVM exhibited the highest prediction accuracy for the combined test sets, and its training time was the shortest among three identifiers.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 1998.03a
• /
• pp.143-147
• /
• 1998

As the accuracy of manufactured goods needed high-accuracy processing has made the efficiency of NC and measurment technology develop, the innovation of machine tools has influence the development of the semi-conductor and optical technology. We can mention that a traction role of the acceleration for the development like that depends on the development of the measurement technics - Stylus instrument method, STM, SEM, Laser interferometer method - which are used for measuring the movement accuracy of machine tools. The movement error factors in movement accuracy are expressed as yaw, roll, and pitch etc. Machining center has 21 movement error factors including of 3 axies joint errors because that has 3 axies and has been measured as the standard of the unloaded condition until now inspite of getting static, dynamic, and servo-gain errors in the case of expending the error range. Therefore, this study tries to measure position accuracy according to loading on the X-Y table of the machining center.

• IE interfaces
• /
• v.11 no.1
• /
• pp.199-205
• /
• 1998

This paper describes the development of on-the-machine measuring(OMM) system which can directly measure the two and three dimensional machined accuracy using a scanning probe in milling machine. Two algorithms, NC program based continuous path(CP) measurement and CAD data assisted point to point(PTP) measurement, are developed for three dimensional measurements, with consideration of the characteristics of the scanning probe. The algorithms are used to develop an auto measuring system. The delveloped system is compared with the CMM (Coordinate Measuring Machine) in terms of accuracy and repeatability. The OMM system is expected to realize measurement time reduction and hence result in high productivity.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2005.05a
• /
• pp.209-215
• /
• 2005

The dimensions and forms of precise machined parts are different to kinds of machine. It will be variant according to machine wear, tool form, cutting method and cutting condition at the same machine. At that time, the most important things are controlled and measured by appropriate measuring instruments. This paper aims to contribute to improving measurement accuracy through evaluation and consideration about various roundness in the machining company.

• ETRI Journal
• /
• v.46 no.3
• /
• pp.538-549
• /
• 2024

A conventional codec aims to increase the compression efficiency for transmission and storage while maintaining video quality. However, as the number of platforms using machine vision rapidly increases, a codec that increases the compression efficiency and maintains the accuracy of machine vision tasks must be devised. Hence, the Moving Picture Experts Group created a standardization process for video coding for machines (VCM) to reduce bitrates while maintaining the accuracy of machine vision tasks. In particular, in-loop filters have been developed for improving the subjective quality and machine vision task accuracy. However, the high computational complexity of in-loop filters limits the development of a high-performance VCM architecture. We analyze the effect of an in-loop filter on the VCM performance and propose a suboptimal VCM method based on the selective activation of in-loop filters. The proposed method reduces the computation time for video coding by approximately 5% when using the enhanced compression model and 2% when employing a Versatile Video Coding test model while maintaining the machine vision accuracy and compression efficiency of the VCM architecture.

• Journal of the Korean Society for Precision Engineering
• /
• v.33 no.8
• /
• pp.683-689
• /
• 2016

Servo mismatch, which affects positioning accuracy of multi-axis machine tools, is usually estimated via the circular test. However, due to mechanical restrictions in measuring instruments, the circular test using a double ball-bar is difficult to apply in miniaturized or super-large sized machine tools. Laser trackers are widely used to measure the form accuracy of parts and the positioning accuracy of driving systems. In this paper, a technique for the servo mismatch estimation of multi-axis machine tools is proposed via the circular test using a laser tracker. To verify the proposed technique, experiments using a double ball-bar and laser tracker are conducted in a 3-axis machine tool. The difference in the evaluation results is 0.05 msec. The servo mismatch for the miniaturized machine tool is also evaluated using the proposed technique.

• International Journal of Computer Science & Network Security
• /
• v.23 no.7
• /
• pp.202-209
• /
• 2023

Android malware is now on the rise, because of the rising interest in the Android operating system. Machine learning models may be used to classify unknown Android malware utilizing characteristics gathered from the dynamic and static analysis of an Android applications. Anti-virus software simply searches for the signs of the virus instance in a specific programme to detect it while scanning. Anti-virus software that competes with it keeps these in large databases and examines each file for all existing virus and malware signatures. The proposed model aims to provide a machine learning method that depend on the malware detection method for Android inability to detect malware apps and improve phone users' security and privacy. This system tracks numerous permission-based characteristics and events collected from Android apps and analyses them using a classifier model to determine whether the program is good ware or malware. This method used the machine learning techniques KNN-SVM, DBN, and GRU in which help to find the accuracy which gives the different values like KNN gives 87.20 percents accuracy, SVM gives 91.40 accuracy, Naive Bayes gives 85.10 and DBN-GRU Gives 97.90. Furthermore, in this paper, we simply employ standard machine learning techniques; but, in future work, we will attempt to improve those machine learning algorithms in order to develop a better detection algorithm.

• Journal of Internet Computing and Services
• /
• v.21 no.4
• /
• pp.127-135
• /
• 2020

The purpose of this study is to develop a human activity recognition (HAR) system, which distinguishes 13 activities, including five activities commonly dealt with in conventional HAR researches and eight activities from the Eastern-Asian culture. The eight special activities include floor-sitting/standing, chair-sitting/standing, floor-lying/up, and bed-lying/up. We used a 3-axis accelerometer sensor on the wrist for data collection and designed a machine learning model for the activity classification. Data clustering through preprocessing and feature extraction/reduction is performed. We then tested six machine learning algorithms for recognition accuracy comparison. As a result, we have achieved an average accuracy of 99.7% for the 13 activities. This result is far better than the average accuracy of current HAR researches based on a smartwatch (89.4%). The superiority of the HAR system developed in this study is proven because we have achieved 98.7% accuracy with publically available 'pamap2' dataset of 12 activities, whose conventionally met the best accuracy is 96.6%.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.29 no.5 s.236
• /
• pp.770-776
• /
• 2005

The gains fur NC controller parameter are fixed when the controller is combined with a machine. However, the characteristics of controller could be changed as it has being used by the machine or other environmental conditions. Those result in that the tool positioning accuracy is influenced. The loading torque in servo motor influences on the tool positioning accuracy and it is controlled by the parameter gains. It is required to analyze the torque variation with angular positioning accuracy of the servo motor. This study focus on a measuring method and device for verifying angular positioning accuracy of NC servo motor. We used a high resolution An converter for acquiring analogue signal of rotary encoder in servo motor. The positional accuracy for a nominal tool path, which is generated by the combination of axial movements (X,Y,Z), is analyzed with the servo motor torque. The current variation signal is acquired at the power line using a hall sensor and converted to the loading torque of servo motor. The method of measurement and analysis proposed in this study will be used for determining the gains of parameter in NC controller. This gain tuning is also necessary when the controller is set up at a machine.