A Novel Classifier Design Algorithm Based on Gray Relation Theory

作者：Hui, Han; Jingchao, Li; Xiang, Chen; Yulong, Ying

来源：Recent Patents on Engineering, 2019, 13(4): 442-447.

DOI：10.2174/1872212112666180828125338

<jats:sec>
<jats:title>Background:</jats:title>
<jats:p>With the technical development of counter-reconnaissance and antijamming,
communication system becomes more and more complex, and therefore, the recognition
of communication signal becomes a challenging task according to recent patents. In order to achieve
successful recognition and classification of radiation source signal under variant SNR environment,
the design and selection of classifier are one of the key points.</jats:p>
</jats:sec>
<jats:sec>
<jats:title>Methods:</jats:title>
<jats:p>Gray relation theory can solve the learning problem with a small number of samples and
its algorithm is simple and can solve the issue of generality versus accuracy, which is very suitable
for dealing with fuzzy mathematical problems. However, the selection of distinguishing coefficient
has a direct effect on the recognition results by gray relation classifier. For conventional gray relation
classifier, the distinguishing coefficient is usually set as a fixed value of 0.5, and for different
types of signals, its recognition rate varies. Aiming at this issue, an improved adaptive gray relation
classifier algorithm is proposed in the paper.</jats:p>
</jats:sec>
<jats:sec>
<jats:title>Results:</jats:title>
<jats:p>The simulation results show that the recognition rate can still reach more than 87% even at
the SNR of 10dB.</jats:p>
</jats:sec>
<jats:sec>
<jats:title>Conclusion:</jats:title>
<jats:p>The proposed methods can improve the anti-jamming capability of the classifier, which
can be widely used in the fields of electronic reconnaissance, fault diagnosis and image processing.</jats:p>
</jats:sec>

• 出版日期2019-12-27
• 单位上海大学