• ETRI Journal
• /
• v.41 no.6
• /
• 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.

• IE interfaces
• /
• v.11 no.2
• /
• 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
• /
• v.12 no.1
• /
• 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
• /
• v.30 no.2
• /
• 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.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.16 no.7
• /
• pp.1322-1331
• /
• 1992

The conventional neural networks are built without considering the underlying structure of the problems. Hence, they usually contain redundant weights and require excessive training time. A novel neural network structure is proposed for symmetric problems, which alleviate some of the aforementioned drawback of the conventional neural networks. This concept is expanded to that of the constrained neural network which may be applied to general structured problems. Because these neural networks can not be trained by the conventional training algorithm, which destroys the weight structure of the neural networks, a proper training algorithm is suggested. The illustrative examples are shown to demonstrate the applicability of the proposed idea.

• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.9
• /
• 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.

• The KIPS Transactions:PartC
• /
• v.9C no.3
• /
• pp.375-384
• /
• 2002

In the current Internet, the QoS of interactive applications is hardly guaranteed because of variable bandwidth, packet loss and delay. Moreover, VoIP which is becoming an important part of the information infra-structure in these days, is susceptible to network packet loss and end-to-end delay. Therefore, it needs error control mechanisms in network level or application level. The FEC-based error control mechanisms are used for interactive audio application such as VoIP. The FEC sends a main information along with redundant information to recover the lost packets and adjusts redundant information depending on network conditions to reduce the bandwidth overhead. However, because most of the error control mechanisms do not consider end-to-end delay but packet loss rate, their performances are poor. In this paper, we propose a new error control algorithm, SCCRP, considering packet loss rate as well as end-to-end delay. Through experiments, we confirm that the SCCRP has a lower packet loss rate and a lower end-to-end delay after reconstruction.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.47 no.2
• /
• pp.153-160
• /
• 2019

Electro-mechanical actuator system for aircraft has advantages in compactness and its lightweight, compared to the hydraulic actuator system. Hinge line actuator has low air resistance and is suitable for special purpose such as stealth. This paper describes design contents of 10,000 lbf-in class dual redundant hinge line electro-mechanical actuator system for performance test. The control structure was designed to minimize impact of torque fighting. A mathematical model is proposed to analyze and validate the performances of actuator by comparison with experiment results.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.1
• /
• 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.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.17 no.1
• /
• pp.11-20
• /
• 2007

A fast Montgomery multiplication occupies important to the design of RSA cryptosystem. Montgomery multiplication consists of two addition, which calculates using CSA or RBA. In terms of CSA, the multiplier is implemented using 4-2 CSA o. 5-2 CSA. In terms of RBA, the multiplier is designed based on redundant binary system. In [1], A new redundant binary adder that performs the addition between two binary signed-digit numbers and apply to Montgomery multiplier was proposed. In this paper, we reconstruct the logic structure of the RBA in [1] for reducing time and space complexity. Especially, the proposed RB multiplier has no coupler like the RBA in [1]. And the proposed RB multiplier is suited to binary exponentiation as modified input and output forms. We simulate to the proposed NRBA using gates provided from SAMSUNG STD130 $0.18{\mu}m$ 1.8V CMOS Standard Cell Library. The result is smaller by 18.5%, 6.3% and faster by 25.24%, 14% than 4-2 CSA, existing RBA, respectively. And Especially, the result is smaller by 44.3% and faster by 2.8% than the RBA in [1].