A structure of neural network suitable for clustering and deinterleaving radar pulses is proposed. The proposed structure consists of two networks, one for intrinsic features of pluses and the other for PRIs (pulse repetition intervals). The unsupervised learning method which adjusts the number of nodes for clusters adaptively is adopted for these two networks to learn patterns. These two networks are connected by a set of links. According to the weights of these links, the clusters categorized by the network for features can be refined further by merging or partitioning. The main defect of the unsupervised network with an adaptive number of nodes for clusters is that the result of classification closely depends on the learning sequence of patterns. This defect can be improved by the proposed refinement algorithm. In addition to the proposed structure and learning algorithms, simulation results have also been discussed.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Hsuen-Chyun SHYU, Chin-Chi CHANG, Yueh-Jyun LEE, Ching-Hai LEE, "Radar Signal Clustering and Deinterleaving by a Neural Network" in IEICE TRANSACTIONS on Fundamentals,
vol. E80-A, no. 5, pp. 903-911, May 1997, doi: .
Abstract: A structure of neural network suitable for clustering and deinterleaving radar pulses is proposed. The proposed structure consists of two networks, one for intrinsic features of pluses and the other for PRIs (pulse repetition intervals). The unsupervised learning method which adjusts the number of nodes for clusters adaptively is adopted for these two networks to learn patterns. These two networks are connected by a set of links. According to the weights of these links, the clusters categorized by the network for features can be refined further by merging or partitioning. The main defect of the unsupervised network with an adaptive number of nodes for clusters is that the result of classification closely depends on the learning sequence of patterns. This defect can be improved by the proposed refinement algorithm. In addition to the proposed structure and learning algorithms, simulation results have also been discussed.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e80-a_5_903/_p
Copy
@ARTICLE{e80-a_5_903,
author={Hsuen-Chyun SHYU, Chin-Chi CHANG, Yueh-Jyun LEE, Ching-Hai LEE, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Radar Signal Clustering and Deinterleaving by a Neural Network},
year={1997},
volume={E80-A},
number={5},
pages={903-911},
abstract={A structure of neural network suitable for clustering and deinterleaving radar pulses is proposed. The proposed structure consists of two networks, one for intrinsic features of pluses and the other for PRIs (pulse repetition intervals). The unsupervised learning method which adjusts the number of nodes for clusters adaptively is adopted for these two networks to learn patterns. These two networks are connected by a set of links. According to the weights of these links, the clusters categorized by the network for features can be refined further by merging or partitioning. The main defect of the unsupervised network with an adaptive number of nodes for clusters is that the result of classification closely depends on the learning sequence of patterns. This defect can be improved by the proposed refinement algorithm. In addition to the proposed structure and learning algorithms, simulation results have also been discussed.},
keywords={},
doi={},
ISSN={},
month={May},}
Copy
TY - JOUR
TI - Radar Signal Clustering and Deinterleaving by a Neural Network
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 903
EP - 911
AU - Hsuen-Chyun SHYU
AU - Chin-Chi CHANG
AU - Yueh-Jyun LEE
AU - Ching-Hai LEE
PY - 1997
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E80-A
IS - 5
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - May 1997
AB - A structure of neural network suitable for clustering and deinterleaving radar pulses is proposed. The proposed structure consists of two networks, one for intrinsic features of pluses and the other for PRIs (pulse repetition intervals). The unsupervised learning method which adjusts the number of nodes for clusters adaptively is adopted for these two networks to learn patterns. These two networks are connected by a set of links. According to the weights of these links, the clusters categorized by the network for features can be refined further by merging or partitioning. The main defect of the unsupervised network with an adaptive number of nodes for clusters is that the result of classification closely depends on the learning sequence of patterns. This defect can be improved by the proposed refinement algorithm. In addition to the proposed structure and learning algorithms, simulation results have also been discussed.
ER -