• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.1
• /
• pp.37-44
• /
• 2021

This study is implemented as a sensor-less position controller capable of multi-turn detection to replace the expensive absolute encoder used in the turret servo system. For sensor-less control, the position information of the rotor is essential. For this, a magnetic flux estimator was implemented from the mathematical model of IPMSM used in the turret servo system. The position of the rotor and the angular velocity of the rotor were obtained using the rotor magnetic flux calculated from the magnetic flux estimator. Using the zero-crossing technique, one pulse was generated for each rotation of the estimated rotor magnetic flux to measure the number of multi-turns. Simulation and experiment results confirmed the usefulness of the proposed method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.12
• /
• pp.4909-4926
• /
• 2020

Cyberattacks penetrate the server and perform various malicious acts such as stealing confidential information, destroying systems, and exposing personal information. To achieve this, attackers perform various malicious actions by infecting endpoints and accessing the internal network. However, the current countermeasures are only anti-viruses that operate in a signature or pattern manner, allowing initial unknown attacks. Endpoint Detection and Response (EDR) technology is focused on providing visibility, and strong countermeasures are lacking. If you fail to respond to the initial attack, it is difficult to respond additionally because malicious behavior like Advanced Persistent Threat (APT) attack does not occur immediately, but occurs over a long period of time. In this paper, we propose a technique that detects an unknown attack using an event log without prior knowledge, although the initial response failed with anti-virus. The proposed technology uses a combination of AutoEncoder and 1D CNN (1-Dimention Convolutional Neural Network) based on semi-supervised learning. The experiment trained a dataset collected over a month in a real-world commercial endpoint environment, and tested the data collected over the next month. As a result of the experiment, 37 unknown attacks were detected in the event log collected for one month in the actual commercial endpoint environment, and 26 of them were verified as malicious through VirusTotal (VT). In the future, it is expected that the proposed model will be applied to EDR technology to form a secure endpoint environment and reduce time and labor costs to effectively detect unknown attacks.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.624-629
• /
• 2022

에세이의 창의성을 자동으로 분류하는 기존의 주요 연구는 말뭉치에서 빈번하게 등장하지 않는 단어에 초점을 맞추어 기계학습을 수행한다. 그러나 이러한 연구는 에세이의 주제와 상관없이 단순히 참신한 단어가 많아 창의적으로 분류되는 문제점이 발생한다. 본 논문에서는 어텐션(Attention)과 역문서 빈도(Inverse Document Frequency; IDF)를 이용하여 에세이 내용 전달에 있어 중요하면서 참신한 단어에 높은 가중치를 두는 문맥 벡터를 구하고, 자기부호화기(AutoEncoder) 모델을 사용하여 문맥 벡터들로부터 창의적인 에세이와 창의적이지 않은 에세이의 특징 벡터를 추출한다. 그리고 시험 단계에서 새로운 에세이의 특징 벡터와 비교하여 그 에세이가 창의적인지 아닌지 분류하는 딥러닝 모델을 제안한다. 실험 결과에 따르면 제안 방안은 기존 방안에 비해 높은 정확도를 보인다. 구체적으로 제안 방안의 평균 정확도는 92%였고 기존의 주요 방안보다 9%의 정확도 향상을 보였다.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1996.04a
• /
• pp.641-645
• /
• 1996

Ball screws are used in the feeding system for transmission of driving force. The friction effect between bed and table, which can affect in accuracyin one dimension feeding and describe the dynamic feeding error, could be simplified as a specific model through experiments. The experiments for dynamic feeding errors were performed om tje NC lathe eith a ball screw. The errors in feeding were measured with respect to the variances of feed, spindle speed and motor current for feeding. A rotary encoder and a current sensor were installed with NC lathe.

• Korean Journal of Remote Sensing
• /
• v.39 no.3
• /
• pp.269-282
• /
• 2023

The purpose of this study was to construct land cover maps using a deep learning model and to select the optimal deep learning model for land cover classification by adjusting the dataset such as input image size and Stride application. Two types of deep learning models, the U-net model and the DeeplabV3+ model with an Encoder-Decoder network, were utilized. Also, the combination of the two deep learning models, which is an Ensemble model, was used in this study. The dataset utilized RapidEye satellite images as input images and the label images used Raster images based on the six categories of the land use of Intergovernmental Panel on Climate Change as true value. This study focused on the problem of the quality improvement of the dataset to enhance the accuracy of deep learning model and constructed twelve land cover maps using the combination of three deep learning models (U-net, DeeplabV3+, and Ensemble), two input image sizes (64 × 64 pixel and 256 × 256 pixel), and two Stride application rates (50% and 100%). The evaluation of the accuracy of the label images and the deep learning-based land cover maps showed that the U-net and DeeplabV3+ models had high accuracy, with overall accuracy values of approximately 87.9% and 89.8%, and kappa coefficients of over 72%. In addition, applying the Ensemble and Stride to the deep learning models resulted in a maximum increase of approximately 3% in accuracy and an improvement in the issue of boundary inconsistency, which is a problem associated with Semantic Segmentation based deep learning models.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.3
• /
• pp.23-31
• /
• 2010

The increasing demands on low-power, and low-complexity video encoder have been motivating extensive research activities on distributed video coding (DVC) in which the encoder compresses frames without utilizing inter-frame statistical correlation. In DVC encoder, contrary to the conventional video encoder, an error control code compresses the video frames by representing the frames in the form of syndrome bits. In the meantime, the DVC decoder generates side information which is modeled as a noisy version of the original video frames, and a decoder of the error-control code corrects the errors in the side information with the syndrome bits. The noisy observation, i.e., the side information can be understood as the output of a virtual channel corresponding to the orignal video frames, and the conditional probability of the virtual channel model is assumed to follow a Laplacian distribution. Thus, performance improvement of DVC systems depends on performances of the error-control code and the optimal reconstruction step in the DVC decoder. In turn, the performances of two constituent blocks are directly related to a better estimation of the parameter of the correlation channel. In this paper, we propose an algorithm to estimate the parameter of the correlation channel and also a low-complexity version of the proposed algorithm. In particular, the proposed algorithm minimizes squared-error of the Laplacian probability distribution and the empirical observations. Finally, we show that the conventional algorithm can be improved by adopting a confidential window. The proposed algorithm results in PSNR gain up to 1.8 dB and 1.1 dB on Mother and Foreman video sequences, respectively.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.1A
• /
• pp.93-98
• /
• 2004

Serial ATA interface Is inexpensive comparatively and performance is superior. So it is suitable technology in demand that now require data transmission and throughput of high speed. This paper describes a design and implementation of Serial ATA Link layer about error detection and 8b/10b encoder/decoder for DC balance in frequency 150MHz. The 8b/10b Encoder is partitioned into a 5b/6b plus a 3b/4b coder. The logical model of the block is described by using Verilog HDL at register transistor level and the verified HDL is synthesized using standard cell libraries. And it is fabricated with $0.35{\mu}m$ Standard CMOS Cell library and the chip size is about $1500{\mu}m\;*\;1500{\mu}m$. The function of this chip has been verified and tested using testboard with FPGA equipment and IDEC ATS2 test equipment. It is used to frequency of 100MHz in verification processes and supply voltage 3.3V. The result of testing is well on the system clock 100MHz. The designed and verified each blocks may be used IP in the field of high speed serial data communication.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.3
• /
• pp.129-138
• /
• 2014

This paper proposes a fast intra prediction method to reduce encoding time for the HEVC(high-efficiency video coding) encoder. The proposed fast Intra prediction method uses quadtree structure and SATD(Sum of Absolute Transformed Differences). In HEVC, a $8{\times}8$ SATD value using $8{\times}8$ hadamard transform is used to calculate a SATD value for $8{\times}8$ or larger blocks. The proposed method calculates the best SATD value by using each $8{\times}8$ SATD result in $16{\times}16$ or larger blocks. After that, the proposed method removes a candidate mode for RDO(Rate-Distortion Optimization) based on comparing SATD of the candidate mode and the best SATD. By removing candidate modes, the proposed method reduces the operation of RDO and reduces total encoding time. In $8{\times}8$ block, the proposed method uses additional $4{\times}4$ SATD to calculat the best SATD. The experimental results show that the proposed method achieved 5.08% reduction in encoding time compared to the HEVC test model 12.1 encoder with almost no loss in compression performance.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.1771-1776
• /
• 2003

In mobile robot navigation, one of the key problems is the pose estimation of the mobile robot. Although the odometry can be used to describe the motions of the mobile robots quite simple and accurately, the validities of the models are limited by a number of error sources contaminating the encoder outputs so that applying the conventional extended Kalman filter to these nominal model does not yield the satisfactory performance. As a remedy for this problem, we consider the uncertain nonlinear kinematic model of the mobile robot that contains the norm bounded uncertainties and also propose a new robust extended Kalman filter based on the Krein space approach. The proposed robust filter has the same recursive structure as the conventional extended Kalman filter and can hence be readily designed to effectively account for the uncertainties. The computer simulations will be given to verify the robustness against the parameter variation as well as the reliable performance of the proposed robust filter.

• ETRI Journal
• /
• v.43 no.6
• /
• pp.1038-1048
• /
• 2021

We propose an end-to-end neural coreference resolution for the Korean language that uses an attention mechanism to point to the same entity. Because Korean is a head-final language, we focused on a method that uses a pointer network based on the head. The key idea is to consider all nouns in the document as candidates based on the head-final characteristics of the Korean language and learn distributions over the referenced entity positions for each noun. Given the recent success of applications using bidirectional encoder representation from transformer (BERT) in natural language-processing tasks, we employed BERT in the proposed model to create word representations based on contextual information. The experimental results indicated that the proposed model achieved state-of-the-art performance in Korean language coreference resolution.