Please use this identifier to cite or link to this item: http://nopr.niscair.res.in/handle/123456789/45308
Title: Fusion of the Targets of AIS and Radar Based on a Stacked Auto-Encoder
Authors: Xiufeng, Cao
Shu, Gao
Zilong, Jiang
Liangchen, Chen
Yan, Wang
Keywords: Track association;Track Fusion;SAE;BP;Soft max
Issue Date: Nov-2018
Publisher: NISCAIR-CSIR, India
Abstract: Automatic identification system(AIS) and radar have its own advantages and disadvantages and employ track association and fusion to complement each other. This study proposes a new model of target track association and fusion based on deep learning to overcome the drawbacks of AIS and radar target traces. First, the features of fusion data are selected; then, the standard deviation is employed to normalize the pre-selected data. Next, an algorithm and regression are added to the top layer of the stacked auto-encoder(SAE), and a back propagation (BP) algorithm is used to adjust the weights and thresholds of the cost function for track association. Finally, rule items are added to the softmax regression to conduct track fusion. Experimental results demonstrate that the proposed model improves the accuracy of AIS and radar tracking.
Page(s): 2186-2197
URI: http://nopr.niscair.res.in/handle/123456789/45308
ISSN: 0975-1033 (Online); 0379-5136 (Print)
Appears in Collections:IJMS Vol.47(11) [November 2018]

Files in This Item:
File Description SizeFormat 
IJMS 47(11) 2186-2197.pdf881.37 kBAdobe PDFView/Open


Items in NOPR are protected by copyright, with all rights reserved, unless otherwise indicated.