• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.18 no.3
• /
• pp.61-69
• /
• 2018

In this paper, we propose a method for recognizing ground target using dual polarization channels in millimeter waveband air-to-surface radar. First, the Push-Broom target detection method is described and the received signal is modeled considering flight-path scenario of air-to-surface radar. The scattering centers were extracted using the RELAX algorithm, which is a time domain spectral estimation technique, and the feature vector of the target was generated. Based on this, a DB for 4 targets is constructed. As a result of the proposed method, it is confirmed that the target classification rates is improved by more than 15% than the single channel using the data of the dual polarization channel.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.11
• /
• pp.2505-2511
• /
• 2013

Many studies in detection and classification of the targets in the underwater environments have been conducted for military purposes, as well as for non-military purpose. Due to the complicated characteristics of underwater acoustic signal reflecting multipath environments and spatio-temporal varying characteristics, active sonar target classification technique has been considered as a difficult technique. And it has difficulties in collecting actual underwater data. In this paper, we synthesized active target echoes based on ray tracing algorithm using target model having 3-dimensional highlight distribution. Then, Fractional Fourier transform was applied to synthesized target echoes to extract feature vector. Recognition experiment was performed using neural network classifier.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.16 no.3 s.94
• /
• pp.335-343
• /
• 2005

In this paper, we propose a method to classify inverse synthetic aperture radar(ISAR) image from different target. The approach can provide efficient features for classification by the combined use of a polar mapping procedure and a well-designed classifier The resulting feature vectors are able to meet requirements that efficient features should have : invariance with respect to rotation and scale, small dimensionality, as well as highly discriminative information. Typical experimental examples of the proposed method are provided and discussed.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.29 no.9
• /
• pp.731-734
• /
• 2018

Many studies have been conducted on the accurate detection and identification of targets from ground clutter, in order to improve the accuracy rate of land guided weapons. Due to the variety and complicated characteristics of the ground clutter signal compared to the target, an active target identification technique is needed. In this paper, we propose a new algorithm to identify targets and divide them into different types by extracting the unique characteristics of the target through fractal dimension calculation with the characteristics of self-similarity. In the simulation using the algorithm, the probabilities of identifying the tank and truck were 100 % and 98.89 %, respectively, and the type of the target could be identified with a probability of 98 % or more.

• The Journal of the Acoustical Society of Korea
• /
• v.15 no.5
• /
• pp.118-124
• /
• 1996

Signal frequency lines generated from the acoustic targets are of particular importance for target detection and classification in passive sonar systems. The underwater noise consists of a mixture of ambient noise and radiated noise of targets. Detction of exact signal frequency lines depends on signal detection threshold and variation of ambient noise. In this paper, a detection method of signal frequency lines for acoustic targets using autoassociative memory (ASM) neural network, which is not sensitive to variation of signal detection threshold and ambient noise, is proposed. It is confirmed by simulation and application of real acoustic targets that the proposed method shows good performance for detection of signal frequency lines.

• The Journal of the Acoustical Society of Korea
• /
• v.19 no.8
• /
• pp.78-83
• /
• 2000

Passive sonar system is designed to classify the underwater targets by analyzing and comparing the various acoustic characteristics such as signal strength, bandwidth, number of tonals and relationship of tonals from the extracted tonals and frequency lines. First of all the precise detection and extraction of signal frequency lines is of particular importance for enhancing the reliability of target classification. But, the narrowband frequency lines which are the line formed in spectrogram by a tonal of constant frequency in each frame can be detected weakly or discontinuously because of the variation of signal strength and transmission loss in the sea. Also, it is very difficult to detect and extract precisely the signal frequency lines by the complexity of impulsive ambient noise and signal components. In this paper, the automatic detection and extraction method that can detect and extract the signal components of frequency tines precisely are proposed. The proposed method can be applied under the bad conditions with weak signal strength and high ambient noise. It is confirmed by the simulation using real underwater target data.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.9
• /
• pp.1545-1550
• /
• 2006

In this paper, we propose a method for applying the CLEAN algorithm to an minimum variance distortionless response(MVDR) to estimate the location of multiple targets distributed in the ocean. The CLEAN algorithm is easy to implement in a linear processor, yet not in a nonlinear processor. In the proposed method, the CSDM of a Dirty map is separated into the CSDM of a Clean beam and the CSDM of the Residual, then an individual ambiguity surface(AMS) is generated. As such, the CLEAN algorithm can be applied to an MVDR, a nonlinear processor. To solve the ill-conditioned problem related to the matrix inversiion by an MVDR when using the CLEAN algorithm, Singular value decomposition(SVD) is carried out, then the reciprocal of small eigenvalues is replaced with zero. Experimental results show that the proposed method improves the performance of an MVDR.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.18 no.8
• /
• pp.984-996
• /
• 2007

This paper presents techniques of 2-D scattering center extraction and 2-B ISAR(Inverse SAR) image formation for scattering wave which is scattered by a target. In general, 2-D IFFT is widely used to obtain 2-D scattering center and ISAR image of targets. But, this method has drawbacks, that is poor in a resolution aspect. To overcome these shortcomings with the FT(Fourier Transform)-based method, various techniques of high resolution signal processing were developed. In this paper, algorithms of 2-D scattering center extraction and ISAR image formation such as 2-D MEMP(Matrix Enhancement and Matrix Pencil), 2-D ESPRIT(Estimation of Signal Parameter via Rotational Invariance Techniques) are described. In order to show the performances of each algorithm, we use scattering wave of the ideal point scatterers and F-18 aircraft to estimate 2-D scattering center and abtain 2-D ISAR image.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1993.06a
• /
• pp.222-225
• /
• 1993

일반적임 빔 형성기는 표적의 방위탐지가 가능하지만, 구조적인 특성상 대칭적인 빔을 형성하므로 표적의 좌/우 방위 구분이 불가능하기 때문에 표적의 정확한 방위를 탐지하고자 할 때 좌/우 구분이 가능한 빔 형성기가 필수적이다. 좌/우 분리 빔 형성 기법으로는 카디오이드(Cardioid) 빔 형성기법을 일반적인 빔 형성기에 적용시키는 방법이 최적으로 알려져 왔다. 그러나 좌/우 분리 빔을 형성하기 위해서는 많은 연산량과 하드웨어 설계에 대한 고려가 있어야한다. 본 논문에서는 좌/우 분리 빔 형성을 위하여 주파수 빔 형성기법과 카디오이드 빔 형성기법을 합성하여 적용하였다. 주파수 빔 형성 기법은 짧은 수행시간 동안에 표적의 정보추출을 위하여 고려되었으며, 카디오이드 빔 형성기법은 3개의 센서를 이용하여 센서의 기울기를 보상하여 수행하는 기법을 적용하였다. 또한 방향성 있는 시뮬레이션 신호를 생성하여 좌/우 분리 빔 형성 시뮬레이션을 수행하였다.

• Korean Journal of Cognitive Science
• /
• v.28 no.4
• /
• pp.299-314
• /
• 2017

Predicting compound-protein interactions in-silico is significant for the drug discovery. In this paper, we propose an scalable machine learning model to predict compound-protein interaction. The key idea of this scalable machine learning model is the architecture of pairwise neural network model and feature embedding method from the raw data, especially for protein. This method automatically extracts the features without additional knowledge of compound and protein. Also, the pairwise architecture elevate the expressiveness and compact dimension of feature by preventing biased learning from occurring due to the dimension and type of features. Through the 5-fold cross validation results on large scale database show that pairwise neural network improves the performance of predicting compound-protein interaction compared to previous prediction models.