• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2003.06a
• /
• pp.378-381
• /
• 2003

Efficient development of method on a performance evaluation for machine tools has been regarded as the most important work for accuracy and quality enhancement to every user and manufacturer. A evaluation method of accuracy for machine tools has been studied recently according to the rapid increase of interest in precision machine tools. To this point of view, the circular interpolation test of machine tools is recognized as the most useful method to distinguish a dynamic accuracy of NC machine tools by ISO and ANSI/ASME, etc. In this paper, we have studied and developed the form measurement system with grid encoder to analyse the final accuracy of NC machine tools. we have analyzed the servo system error and geometric error of NC machine tools through measuring a dynamic error signal by this system. and then we verified the experimental result and enhanced the reliability by means of comparing the characteristics of the developed system with the kinematic ball-bar system.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.12
• /
• pp.419-430
• /
• 2020

This paper investigated methods to improve the forecasting accuracy of the electricity consumption prediction model. Currently, the demand for electricity has continuously been rising more than ever. Since the industrial sector uses more electricity than any other sectors, the importance of a more precise forecasting model for manufacturing sites has been highlighted to lower the excess energy production. We propose a double encoder-decoder model, which uses two separate encoders and one decoder, in order to adapt both long-term and short-term data for better forecasts. We evaluated our proposed model on our electricity power consumption dataset, which was collected in a manufacturing site of Sehong from January 1st, 2019 to June 30th, 2019 with 1 minute time interval. From the experiment, the double encoder-decoder model marked about 10% reduction in mean absolute error percentage compared to a conventional encoder-decoder model. This result indicates that the proposed model forecasts electricity consumption more accurately on manufacturing sites compared to an encoder-decoder model.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.29 no.2 s.233
• /
• pp.311-317
• /
• 2005

NC controller parameters 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. Ultimately, it results in tool positioning accuracy changing. The loading torque in servo motor also influences on the positioning accuracy. This study focus on a measuring and analysing method for verifying the angular positioning accuracy of NC servo motor. We used a high resolution A/D converter for acquiring analogue signal of rotary encoder in servo motor. Generating tool path by the combination of axial movements (X,Y,Z) is compared with the encoder signals with the servo motor torque. The current variation signal is also read from the servo motor power using a hall sensor and converted to the motor torque. The method of analysing proposed in this study will be used for determining the gains (tuning) of parameter in NC controller, when the controller is set up at a machine initially or the controller condition is changed during the work.

• Journal of Forest and Environmental Science
• /
• v.40 no.1
• /
• pp.15-23
• /
• 2024

This research aimed to assess the possibility of detecting forest degradation using time-series satellite imagery and three different deep learning-based change detection techniques. The dataset used for the deep learning models was composed of two sets, one based on surface reflectance (SR) spectral information from satellite imagery, combined with Texture Information (GLCM; Gray-Level Co-occurrence Matrix) and terrain information. The deep learning models employed for land cover change detection included image differencing using the Unet semantic segmentation model, multi-encoder Unet model, and multi-encoder Unet++ model. The study found that there was no significant difference in accuracy between the deep learning models for forest degradation detection. Both training and validation accuracies were approx-imately 89% and 92%, respectively. Among the three deep learning models, the multi-encoder Unet model showed the most efficient analysis time and comparable accuracy. Moreover, models that incorporated both texture and gradient information in addition to spectral information were found to have a higher classification accuracy compared to models that used only spectral information. Overall, the accuracy of forest degradation extraction was outstanding, achieving 98%.

• Journal of Internet Computing and Services
• /
• v.22 no.2
• /
• pp.1-9
• /
• 2021

Traditionally, most malicious codes have been analyzed using feature information extracted by domain experts. However, this feature-based analysis method depends on the analyst's capabilities and has limitations in detecting variant malicious codes that have modified existing malicious codes. In this study, we propose a ResNet-Variational AutoEncder-based variant malware classification method that can classify a family of variant malware without domain expert intervention. The Variational AutoEncoder network has the characteristics of creating new data within a normal distribution and understanding the characteristics of the data well in the learning process of training data provided as input values. In this study, important features of malicious code could be extracted by extracting latent variables in the learning process of Variational AutoEncoder. In addition, transfer learning was performed to better learn the characteristics of the training data and increase the efficiency of learning. The learning parameters of the ResNet-152 model pre-trained with the ImageNet Dataset were transferred to the learning parameters of the Encoder Network. The ResNet-Variational AutoEncoder that performed transfer learning showed higher performance than the existing Variational AutoEncoder and provided learning efficiency. Meanwhile, an ensemble model, Stacking Classifier, was used as a method for classifying variant malicious codes. As a result of learning the Stacking Classifier based on the characteristic data of the variant malware extracted by the Encoder Network of the ResNet-VAE model, an accuracy of 98.66% and an F1-Score of 98.68 were obtained.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2006.10a
• /
• pp.103-104
• /
• 2006

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.9
• /
• pp.21-27
• /
• 2019

In this paper, we propose a deep auto-encoder-based pipe leak detection (PLD) technique from time-series acoustic data collected by microphone sensor nodes. The key idea of the proposed technique is to learn representative features of the leak-free state using leak-free time-series acoustic data and the deep auto-encoder. The proposed technique can be used to create a PLD model that detects leaks in the pipeline in an unsupervised learning manner. This means that we only use leak-free data without labeling while training the deep auto-encoder. In addition, when compared to the previous supervised learning-based PLD method that uses image features, this technique does not require complex preprocessing of time-series acoustic data owing to the unsupervised feature extraction scheme. The experimental results show that the proposed PLD method using the deep auto-encoder can provide reliable PLD accuracy even considering unsupervised learning-based feature extraction.

• Journal of Information Processing Systems
• /
• v.20 no.1
• /
• pp.13-23
• /
• 2024

Music brings pleasure and relaxation to people. Therefore, it is necessary to classify musical genres based on scenes. Identifying favorite musical genres from massive music data is a time-consuming and laborious task. Recent studies have suggested that machine learning algorithms are effective in distinguishing between various musical genres. However, meeting the actual requirements in terms of accuracy or timeliness is challenging. In this study, a hybrid machine learning model that combines a deep residual auto-encoder (DRAE) and support vector machine (SVM) for musical genre recognition was proposed. Eight manually extracted features from the Mel-frequency cepstral coefficients (MFCC) were employed in the preprocessing stage as the hybrid music data source. During the training stage, DRAE was employed to extract feature maps, which were then used as input for the SVM classifier. The experimental results indicated that this method achieved a 91.54% F1-score and 91.58% top-1 accuracy, outperforming existing approaches. This novel approach leverages deep architecture and conventional machine learning algorithms and provides a new horizon for musical genre classification tasks.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.9 no.1
• /
• pp.1-10
• /
• 1984

The time division multiplexing PCM encoder which is constructed for an airborne telemetering system is investigated. Selected by program switch, the PCM encoder has 0~64 words/framd($\pm$5V full scale) of allowable analog input channels, 0~30bits(5V$\pm$1V or 0V$\pm$1V dc) of discrete channels, 70 and 140K bits/sec of bit rate and 8~12bits/word of resolution. And filtered output PCM code is NRZ-L and Bi-S through the 5 pole Bessel LPF(f=100kHz), and the maximum accuracy of PCM encoder is $\pm$0.2% of its full scale.

• KIEE International Transaction on Electrical Machinery and Energy Conversion Systems
• /
• v.11B no.4
• /
• pp.185-192
• /
• 2001

In SRM drive, the ON·OFF angles of each phase switch should be accurately controlled in order to control the torque and speed stably. The accuracy of the switching angles is dependent upon the resolution of the encoder and the sampling period of the microprocessor, that are used to provide the information of the rotor position and to control the SRM power circuit, respectively. However, as the speed increases, the amount of the switching angle deviation from the preset values is also increased. Therefore, the low cost encoder suitable for the practical and stable SRM drive is proposed and the control algorithm to provide the switching signals using the simple digital logic circuit is also presented in this paper, As a result, a stable high speed SRM drive can be achieved by the high resolution switching angle control and it is verified from the experiments that the proposed encoder the logic controller can be a powerful candidate for the practical low cost SRM drive.