• Journal of Korea Multimedia Society
• /
• v.20 no.10
• /
• pp.1637-1645
• /
• 2017

Target/Nontarget classification can be divided into the study of shape estimation of the target analysing reflected echo signal and of type classification of the target using acoustical features. In active sonar system, the feature vectors are extracted from the signal reflected from the target, and an classification algorithm is applied to determine whether the received signal is a target or not. However, received sonar signals can be distorted in the underwater environments, and the spatio-temporal characteristics of active sonar signals change according to the aspect of the target. In addition, it is very difficult to collect real sea-trial data for research. In this paper, target/non-target classification were performed using real sea-trial data. Feature vectors are extracted using MFCC(Mel-Frequency Cepstral Coefficients), filterbank energy in the Fourier spectrum and wavelet domain. For the performance verification, classification experiments were performed using backpropagation neural network classifiers.

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.10
• /
• pp.982-990
• /
• 2010

In a target tracking system using image information from a CCD (Charged Couple Device) or an IIR (Imaging Infra-red) sensor, occluded targets can result in track losses. If the target is occlued by background objects such as buildings or trees, probability of track existence will be reduced sharply and track will be terminated due to track maintenance algorithms. This paper proposes data association algorithm based on target existence for the robust tracking performance. we suggest the HPDA (Highest Probability Data Association) algorithm based on target existence and the tracking performance is compared with the established method based on target perceivability. Image tracking simulation that utilizes virtual 3D images and real IR images is employed to evaluate the robustness of the proposed tracking algorithm.

• Investigative Magnetic Resonance Imaging
• /
• v.25 no.1
• /
• pp.10-22
• /
• 2021

Purpose: To overcome the difficulty in building a large data set with a high-quality in medical imaging, a concept of 'blended-transfer learning' (BTL) using a combination of both source data and target data is proposed for the target task. Materials and Methods: Source and target tasks were defined as training of the source and target networks to reconstruct cardiac CINE images from undersampled data, respectively. In transfer learning (TL), the entire neural network (NN) or some parts of the NN after conducting a source task using an open data set was adopted in the target network as the initial network to improve the learning speed and the performance of the target task. Using BTL, an NN effectively learned the target data while preserving knowledge from the source data to the maximum extent possible. The ratio of the source data to the target data was reduced stepwise from 1 in the initial stage to 0 in the final stage. Results: NN that performed BTL showed an improved performance compared to those that performed TL or standalone learning (SL). Generalization of NN was also better achieved. The learning curve was evaluated using normalized mean square error (NMSE) of reconstructed images for both target data and source data. BTL reduced the learning time by 1.25 to 100 times and provided better image quality. Its NMSE was 3% to 8% lower than with SL. Conclusion: The NN that performed the proposed BTL showed the best performance in terms of learning speed and learning curve. It also showed the highest reconstructed-image quality with the lowest NMSE for the test data set. Thus, BTL is an effective way of learning for NNs in the medical-imaging domain where both quality and quantity of data are always limited.

• The Journal of the Acoustical Society of Korea
• /
• v.38 no.4
• /
• pp.415-426
• /
• 2019

In this paper, we discussed automatic target tracking algorithms for diver detection sonar that observes penetration forces of coastal military installations and major infrastructures. First of all, we analyzed sea trial data in diver detection sonar and composed automatic target tracking algorithms based on track existence probability as track quality measure in clutter environment. In particular, these are presented track management algorithms which include track initiation, confirmation, termination, merging and target tracking algorithms which include single target tracking IPDAF (Integrated Probabilistic Data Association Filter) and multitarget tracking LMIPDAF (Linear Multi-target Integrated Probabilistic Data Association Filter). And we analyzed performances of automatic target tracking algorithms using sea trial data and monte carlo simulation data.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.23 no.3
• /
• pp.204-212
• /
• 2020

For general target tracking works by receiving a set of measurements from sensor. However, if the SNR(Signal to Noise Ratio) is low due to small RCS(Radar Cross Section), caused by remote small targets, the target's information can be lost during signal processing. TBD(Track Before Detect) is an algorithm that performs target tracking without threshold for detection. That is, all sensor data is sent to the tracking system, which prevents the loss of the target's information by thresholding the signal intensity. On the other hand, using all sensor data inevitably leads to computational problems that can severely limit the application. In this paper, we propose an iterative Joint Integrated Probabilistic Data Association as a practical target tracking technique suitable for a low SNR multi-target environment with real time operation capability, and verify its performance through simulation studies.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.56 no.10
• /
• pp.1826-1835
• /
• 2007

In this paper, we present a new approach for automatic detection and tracking for multiple targets. We combine a highest probability data association(HPDA) algorithm for target detection with a particle filter for multiple target tracking. The proposed approach evaluates the probabilities of one-to-one assignments of measurement-to-track and the measurement with the highest probability is selected to be target- originated, and the measurement is used for probabilistic weight update of particle filtering. The performance of the proposed algorithm for target tracking in clutter is compared with the existing clustering algorithm and the sequential monte carlo method for probability hypothesis density(SMC PHD) algorithm for multi-target detection and tracking. Computer simulation studies demonstrate that the HPDA algorithm is robust in performing automatic detection and tracking for multiple targets even though the environment is hostile in terms of high clutter density and low target detection probability.

• Journal of the Korean Data and Information Science Society
• /
• v.14 no.2
• /
• pp.237-245
• /
• 2003

MDS(multi-dimensional scaling) for preference data is a graphical tool which usually figures out how consumers recognize, evaluate certain products. This article is mainly concerned with an optimal scaling for MDS when target configuration is available. Rotation of axis and SUR(seemingly unrelated regression) methods are employed to get a new configuration which is obtained as close to the target as we can. Methodologies developed here are also illustrated via a real data set.

• Journal of Information Technology Applications and Management
• /
• v.9 no.2
• /
• pp.1-16
• /
• 2002

Recently, neural network methods have been studied to find out more valuable information in data bases. But the supervised learning methods of neural networks have an overfitting problem, which leads to errors of target patterns. And the unsupervised learning methods can distort important information in the process of regularizing data. Thus they can't efficiently classify data, To solve the problems, this paper introduces a hybrid neural networks HACAB(Hybrid Algorithm combining a Competition learning model And BP Algorithm) combining a competition learning model and 8P algorithm. HACAB is designed for cases which there is no target patterns. HACAB makes target patterns by adopting a competition learning model and classifies input patterns using the target patterns by BP algorithm. HACAB is evaluated with random input patterns and Iris data In cases of no target patterns, HACAB can classify data more effectively than BP algorithm does.

• Journal of Institute of Control, Robotics and Systems
• /
• v.20 no.3
• /
• pp.313-322
• /
• 2014

This paper is to survey and put in perspective the working methods of multi-target tracking in clutter. This paper includes theories and practices for data association and related filter structures and is motivated by increasing interest in the area of target tracking, security, surveillance, and multi-sensor data fusion. It is hoped that it will be useful in view of taking into consideration a full understanding of existing techniques before using them in practice.

• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.550-553
• /
• 2005

To acquire radar target signature, various kinds of target are necessary. Measurement is one of the data acquiring method, but much time and high cost is required to get the target data from the real targets. Even if we can afford that, the targets we can access are very limited. To obtain target signatures avoiding these problems, we build the target CAD (Computer Aided Design) model for the calculation of target signatures. To speed up RCS calculation, we applied adaptive super-sampling and tested quite complex tank CAD model which is 1.4 hundred of thousands facet. We use calculated RCS data for ID range profile and 2D ISAR (Inverse Synthetic Aperture Radar) image formation. We adopted IFFT (Inverse Fast Fourier Transform) algorithm combined with polar formatting algorithm for the ISAR imaging. We could confirm the possibility of the construction of database from the images of CAD models for target classification applications.