• ETRI Journal
• /
• 제41권6호
• /
• pp.750-759
• /
• 2019

Presently, the extraction of hand-crafted features is still the dominant method in radar emitter recognition. To solve the complicated problems of selection and updation of empirical features, we present a novel automatic feature extraction structure based on deep learning. In particular, a convolutional neural network (CNN) is adopted to extract high-level abstract representations from the time-frequency images of emitter signals. Thus, the redundant process of designing discriminative features can be avoided. Furthermore, to address the performance degradation of a single platform, we propose the construction of an ensemble learning-based architecture for multi-platform fusion recognition. Experimental results indicate that the proposed algorithms are feasible and effective, and they outperform other typical feature extraction and fusion recognition methods in terms of accuracy. Moreover, the proposed structure could be extended to other prevalent ensemble learning alternatives.

• 산업공학
• /
• 제11권2호
• /
• pp.149-157
• /
• 1998

In this paper, various techniques considering the characteristics of computer memory management are suggested, which can be used in the implementation of simplex method. First, reduction technique of indirect addressing, redundant references of memory, and scatter/gather technique are implemented, and the effectiveness of the techniques is shown. Loop-unrolling technique, which exploits the arithmetic operation mechanism of computer, is also implemented. Second, a subroutine frequently called is written in low-level language, and the effectiveness is proved by experimental results. Third, row-column linked list and Gustavson's data structure are compared as the data structure for the large sparse matrix in LU form. Last, buffering technique and memory-mapped file which can be used in reading large data file are implemented and the effectiveness is shown.

• Coupled systems mechanics
• /
• 제12권1호
• /
• pp.69-81
• /
• 2023

This paper considers a delamination analysis of a statically undetermined inhomogeneous beam structure of rectangular section with viscoelastic behavior under torsion. The beam is built in at its two ends. The beam has two longitudinal inhomogeneous layers with a delamination crack between them. A notch is made in the upper crack arm. The external torsion moment applied on the beam is a function of time. Under these conditions, the beam has one degree of indeterminacy. In order to derive the strain energy release rate, first, the static indeterminacy is resolved. Then the strain energy release rate is obtained by analyzing the balance of the energy with considering the viscoelastic behavior. The strain energy release rate is found also by analyzing the compliance of the beam for checkup. Solution of the strain energy release rate in a beam without a notch in the upper crack arm is derived too. In this case, the beam has two degrees of static indeterminacy (the torsion moment in the upper crack arm is treated as an additional internal redundant unknown). A parametric investigation of the strain energy release rate is carried-out.

• Journal of the Korean Statistical Society
• /
• 제30권2호
• /
• pp.179-192
• /
• 2001

When a statistical model has a hierarchical structure such as multilayer perceptrons in neural networks or Gaussian mixture density representation, the model includes distribution with unidentifiable parameters when the structure becomes redundant. Since the exact structure is unknown, we need to carry out statistical estimation or learning of parameters in such a model. From the geometrical point of view, distributions specified by unidentifiable parameters become a singular point in the parameter space. The problem has been remarked in many statistical models, and strange behaviors of the likelihood ratio statistics, when the null hypothesis is at a singular point, have been analyzed so far. The present paper studies asymptotic behaviors of the maximum likelihood estimator and the Bayesian predictive estimator, by using a simple cone model, and show that they are completely different from regular statistical models where the Cramer-Rao paradigm holds. At singularities, the Fisher information metric degenerates, implying that the cramer-Rao paradigm does no more hold, and that he classical model selection theory such as AIC and MDL cannot be applied. This paper is a first step to establish a new theory for analyzing the accuracy of estimation or learning at around singularities.

• 대한기계학회논문집
• /
• 제16권7호
• /
• pp.1322-1331
• /
• 1992

본 연구에서는 Fig.3과 같은 다층 퍼셉트론을 사용하기로 한다. 그리고 위 에서 언급한 세가지점에서 다층퍼셉트론을 다시 살펴보아 해결하고자 하는 문제에 맞 도록 다층퍼셉트론을 개선시켜 보기로 한다. 따라서 본 연구의 목적은 제한조건을 갖는 문제를 풀기위한 새로운 형태의 다층퍼셉트론 설계 및 이에 적합한 학습규칙을 적용하여 보다 간단한 구조와 빠른 학습시간을 갖는 신경망을 구성하는데 있다.

• 제어로봇시스템학회논문지
• /
• 제19권9호
• /
• pp.797-804
• /
• 2013

In this paper, a study of a new hovering six dof underwater robot with redundant horizontal thrusters, titled HAUV (hovering AUV), is presented. The results of study on the structure design, deployment of thrusters, and development of the developed control system of the AUV was presented. For the HAUV structure, a structure design and an analysis of the thrusting system was performed. For navigation, a sensor fusion board which can proceed various sensor signals to identify correct positions and speeds was developed and a total control system including EKF (Extended Kalman Filter) was designed. Rolling, pitching and depth control tests of the HAUV have been performed, and relatively small angle error and depth tracking error results were shown.

• 정보처리학회논문지C
• /
• 제9C권3호
• /
• pp.375-384
• /
• 2002

현재의 인터넷은 가변적인 대역폭과 패킷손실 그리고 지연으로 인하여 대화식 응용의 QoS 보장이 어렵다. 특히 최근에 정보의 기반구조로 중요성이 강조되고 있는 VOIP는 패킷손실률과 종점간지연이 클 때 통화품질이 크게 떨어지므로 네트웍 수준에서나 응용 수준에서 에러제어 기법이 요구된다. 인터넷 전화와 같은 대화식 응용을 위한 응용 수준의 에러 제어 기법으로 FEC(Forward Error Correction)가 가장 많이 사용되고 있는데, 이 기법은 주정보와 더불어 부가정보를 전송함으로서 패킷손실을 복구하는 방법으로 네트웍의 상태에 따라 적응적으로 부가정보의 양을 조절한다. 그러나 기존의 알고리즘들은 패킷손실률만을 고려하여 부가정보를 조절하였으며 부가 정보를 증가시킬 때 수반되는 종점간지연을 간과함으로써 통화품질을 떨어뜨리는 단점이 있다. 본 논문에서는 패킷손실률뿐만 아니라 종점간지연을 고려하는 FEC기반 에러제어 기법인 SCCRP (Selecting a Codec Combination using Reward and Penalty)를 제안한다. 실험 결과, SCCRP는 다른 알고리즘들에 비해 복구 후 패킷손실률은 물론 복구 후 종점간지연을 낮게 유지하였다.

• 한국항공우주학회지
• /
• 제47권2호
• /
• pp.153-160
• /
• 2019

항공기용 전기식 구동장치는 유압식 구동장치에 비해 소형/경량화에 유리하고, 힌지라인 형태의 구동장치는 공기저항이 작고 스텔스 등의 특수 목적에 적합한 특징을 가지고 있다. 본 논문에서는 10,000 lbf-in급 힌지라인 이중화 전기식 구동장치의 동작성능시험을 위한 시스템 설계 내용을 기술하였다. 영구자석전동기의 자속 기준 제어와 이중화 구동기의 torque fighting을 고려한 제어기를 설계하고, 구동장치 시스템 모델을 수립하여 성능 시뮬레이션을 수행하였다. 성능시험을 수행하여 시뮬레이션 결과와 비교하였으며 목표성능 만족여부를 확인하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권1호
• /
• pp.170-191
• /
• 2024

The transmission of confidential data using cover media is called steganography. The three requirements of any effective steganography system are high embedding capacity, security, and imperceptibility. The text file's structure, which makes syntax and grammar more visually obvious than in other media, contributes to its poor imperceptibility. Text steganography is regarded as the most challenging carrier to hide secret data because of its insufficient redundant data compared to other digital objects. Unicode characters, especially non-printing or invisible, are employed for hiding data by mapping a specific amount of secret data bits in each character and inserting the character into cover text spaces. These characters are known with limited spaces to embed secret data. Current studies that used Unicode characters in text steganography focused on increasing the data hiding capacity with insufficient redundant data in a text file. A sequential embedding pattern is often selected and included in all available positions in the cover text. This embedding pattern negatively affects the text steganography system's imperceptibility and security. Thus, this study attempts to solve these limitations using the Part-of-speech (POS) tagging technique combined with the randomization concept in data hiding. Combining these two techniques allows inserting the Unicode characters in randomized patterns with specific positions in the cover text to increase data hiding capacity with minimum effects on imperceptibility and security. Format-preserving encryption (FPE) is also used to encrypt a secret message without changing its size before the embedding processes. By comparing the proposed technique to already existing ones, the results demonstrate that it fulfils the cover file's capacity, imperceptibility, and security requirements.

• 정보보호학회논문지
• /
• 제17권1호
• /
• pp.11-20
• /
• 2007

몽고메리 곱셈 방법을 이용한 고속 연산은 RSA 암호 시스템의 설계에 중요한 부분을 차지한다. 몽고메리 곱셈은 두번의 덧셈 연산으로 구성되며 CSA를 이용한 방법과 RBA를 이용한 방법이 있다. CSA의 경우 4-2 CSA 또는 5-2 CSA를 이용하여 구현하며, RBA의 경우 기존 이진 방법과 달리 잉여 이진체계를 이용한다는 특징을 가진다. [1] 에서는 기존의 RBA와 다른 새로운 이진 체계와 하드웨어 구조를 제안하고 몽고메리 곱셈에 적용하였다. 본 논문에서는 [1] 에서 제안한 RBA의 로직 구조를 재구성하여 시간 복잡도 뿐만 아니라 결합기가 필요하지 않도록 구성하여 공간 복잡도를 크게 줄였다. 또한 입 출력 값을 변형시켜 지수승 연산에 적합하도록 설계하였다. 그 결과 제안하는 RBA는 삼성 STD130 $0.18{\mu}m$ 1.8V 표준 셀 라이브러리에서 지원하는 게이트들을 사용하여 설계하는 환경에서, 기존의 4-2 CSA 보다 공간과 시간 복잡도를 각각 18.5%와 25.24%를, 기존의 RBA 보다 6.3%와 14%를 감소시킨다. 또한 [1] 의 RBA와 비교시 44.3%, 2.8%의 감소된 복잡도를 갖는다.