• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.12
• /
• pp.3364-3382
• /
• 2023

Remote sensing image segmentation plays an important role in realizing intelligent city construction. The current mainstream segmentation networks effectively improve the segmentation effect of remote sensing images by deeply mining the rich texture and semantic features of images. But there are still some problems such as rough results of small target region segmentation and poor edge contour segmentation. To overcome these three challenges, we propose an improved semantic segmentation model, referred to as MRU-Net, which adopts the U-Net architecture as its backbone. Firstly, the convolutional layer is replaced by BasicBlock structure in U-Net network to extract features, then the activation function is replaced to reduce the computational load of model in the network. Secondly, a hybrid multi-scale recognition module is added in the encoder to improve the accuracy of image segmentation of small targets and edge parts. Finally, test on Massachusetts Buildings Dataset and WHU Dataset the experimental results show that compared with the original network the ACC, mIoU and F1 value are improved, and the imposed network shows good robustness and portability in different datasets.

• Journal of the Korea Computer Industry Society
• /
• v.3 no.1
• /
• pp.57-66
• /
• 2002

In this study, Multi-Values Logic processor was designed using the basic circuit of the electric current mode CMOS. First of all, binary FFT(Fast Fourier Transform) was extended and high-speed Multi-Valued Logic processor was constructed using a multi-valued logic circuit. Compared with the existing two-valued FFT, the FFT operation can reduce the number of transistors significantly and show the simplicity of the circuit. Moreover, for the construction of amount was used inside the FFT circuit with the set of redundant numbers like ［0,1,2,3］. As a result, the defects in lines were reduced and it turned out to be effective in the aspect of normality an regularity when it was used designing VLSI(Very Large Scale Integration). To multiply FFT, the time and size of the operation was used as LUT(Look Up Table) Finally, for the compatibility with the binary system, multiple-valued hybrid-type FFT processor was proposed and designed using binary-four valued encoder, four-binary valued decoder, and the electric current mode CMOS circuit.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2001.10a
• /
• pp.286-290
• /
• 2001

This paper presents a full-digital low-level controller for a robotic material transfer system which has been developed for a computer-integrated manufacturing model plant. Compared to conventional analog or hybrid type controllers in current industrial environments, this controller system has some advantages such as strong noise-immunity, easy control algorithm implementation, etc The servo-controller consists of two modules, a position controller and a DC servo motor driver. The position controller operates position feedback routines by receiving position encoder data and sending control outputs to the driver. The position controller is implemented in a full-digital way using a recently introduced microcontroller. The DC servomotor driver controls speeds and torques. The driver consists of a micro-controller and insulated-gate-bipolar-transistors (IGBT). The micro-controller provides control signals, and the IGBT's amplifies the control signals and sends them to the motor.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.33 no.9
• /
• pp.327-339
• /
• 1984

In this paper we present how to design the software-based speed and position controller of a DC servo drive system for an educational robot. The controller designed by fully digital scheme consists of a CPU, drive unit, encoder pulse coding unit, speed and position detector. The control algirithm of the controller is a hybrid one such that speed control and position control are switched at some instant to get more accuracy. The experimental resusts of the proposed DC servo-controller show good performances for the position and speed control of the proposed educational robot system.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2006.05a
• /
• pp.143-146
• /
• 2006

In this paper, a hybrid sensor is proposed that has two capabilities: The first is to sense longitudinal of flexural elastic waves selectively which are transmitted along the targe shaft, the second to measure the rotating speed of the shaft. All measurement are made in a noncontact manner since this sensor uses magnetostriction as its measuring principles. Furthermore, the switching between these two sensing capabilities are accomplished by a very simple mechanical operation. To verify the capabilities of the Proposed sensor, an Prototype sensor are fabricated and the experiments are made. The result shows this sensor can embody two sensing capabilities in one sensor configuration.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2002.11a
• /
• pp.105-109
• /
• 2002

The main ideas of hybrid video coding methods are to reduce the spatial and temporal redundancy for efficient data compression. If compressed video stream is transmitted through the error-prone channel, bitstream can be critically damaged and the spatio-temporal error propagates through successive frames at the decoder because of drift noise in the references between encoder and decoder. In this paper, I propose the lagrangian multiplier selection method in the error-prone environment. Finally, it is shown that the performance comparisons of the R-D optimized mode decision are made against the conventional method and simulation results are given in the following.

• Proceedings of the KIEE Conference
• /
• 2005.07b
• /
• pp.1129-1131
• /
• 2005

본 논문은 저가형 고정도 아날로그 디지털 혼합형 엔코더에서 센서 취부 오차에 의해 발생하는 정지 2축 좌표상의 두 아날로그신호의 크기, 위상오차 문제 보상에 관한 연구이다. 기존의 혼합형 엔코더에서 문제시되고 있는 두 아날로그 위치정보 신호의 크기문제는 상대 크기에 대하여 정규화 함으로써 해결하였으며, 센서 취부시 발생하는 위치오차문제는 정지 2축 좌표축을 센서의 위치 오차분을 보상할 수 있도록 회전함으로써 보상할 수 있었다. 또한 제안된 새로운 방식의 위치 검출기법을 DSP의 QEP기능과 A/D변환기를 사용한 실험을 통하여 그 타당성을 검증하였다.

• ETRI Journal
• /
• v.46 no.1
• /
• pp.137-153
• /
• 2024

This study introduces a new approach in Korean morphological analysis combining dictionary-based techniques with Transformer-based deep learning models. The key innovation is the use of a BERT-based reranking system, significantly enhancing the accuracy of traditional morphological analysis. The method generates multiple suboptimal paths, then employs BERT models for reranking, leveraging their advanced language comprehension. Results show remarkable performance improvements, with the first-stage reranking achieving over 20% improvement in error reduction rate compared with existing models. The second stage, using another BERT variant, further increases this improvement to over 30%. This indicates a significant leap in accuracy, validating the effectiveness of merging dictionary-based analysis with contemporary deep learning. The study suggests future exploration in refined integrations of dictionary and deep learning methods as well as using probabilistic models for enhanced morphological analysis. This hybrid approach sets a new benchmark in the field and offers insights for similar challenges in language processing applications.

• Journal of Information Processing Systems
• /
• v.20 no.4
• /
• pp.458-476
• /
• 2024

To address the issue of class imbalance in network traffic data, which affects the network intrusion detection performance, a combined framework using transformers is proposed. First, Tomek Links, SMOTE, and WGAN are used to preprocess the data to solve the class-imbalance problem. Second, the transformer is used to encode traffic data to extract the correlation between network traffic. Finally, a hybrid deep learning network model combining a bidirectional gated current unit and deep neural network is proposed, which is used to extract long-dependence features. A DNN is used to extract deep level features, and softmax is used to complete classification. Experiments were conducted on the NSLKDD, UNSWNB15, and CICIDS2017 datasets, and the detection accuracy rates of the proposed model were 99.72%, 84.86%, and 99.89% on three datasets, respectively. Compared with other relatively new deep-learning network models, it effectively improved the intrusion detection performance, thereby improving the communication security of network data.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.11
• /
• pp.501-512
• /
• 2021

Recently, a breakthrough has been made in the NLP area by Transformer techniques based on encoder-decoder. However, this only can be used in mainstream languages where millions of dataset are well-equipped, such as English and Chinese, and there is a limitation that it cannot be used in non-mainstream languages where dataset are not established. In addition, there is a deflection problem that focuses on the beginning of the document in mechanical summarization. Therefore, these methods are not suitable for documents with flows such as fairy tales and novels. In this paper, we propose a hybrid summarization method that does not require a dataset and improves the deflection problem using GAN with two adaptive discriminators. We evaluate our model on the CNN/Daily Mail dataset to verify an objective validity. Also, we proved that the model has valid performance in Korean, one of the non-mainstream languages.