Signal Identification using a new high efficient technique
Year
: 2005
Abstract: Abstract: Automatic signal type identification (ASTI) is an important topic for both the
civilian and military domains. Most of the proposed identifiers can only recognize a few
types of digital signal and usually need high levels of SNRs. This paper presents a new high
efficient technique that includes a variety of digital signal types. In this technique, a
combination of higher order moments and higher order cumulants (up to eighth) are
proposed as the effective features. A hierarchical support vector machine based structure is
proposed as the classifier. In order to improve the performance of identifier, a genetic
algorithm is used for parameters selection of the classifier. Simulation results show that the
proposed technique is able to identify the different types of digital signal (e.g. QAM128,
ASK8, and V29) with high accuracy even at low SNRs.
civilian and military domains. Most of the proposed identifiers can only recognize a few
types of digital signal and usually need high levels of SNRs. This paper presents a new high
efficient technique that includes a variety of digital signal types. In this technique, a
combination of higher order moments and higher order cumulants (up to eighth) are
proposed as the effective features. A hierarchical support vector machine based structure is
proposed as the classifier. In order to improve the performance of identifier, a genetic
algorithm is used for parameters selection of the classifier. Simulation results show that the
proposed technique is able to identify the different types of digital signal (e.g. QAM128,
ASK8, and V29) with high accuracy even at low SNRs.
Keyword(s): Statistical pattern recognition,Signal identification,Support vector machine,
Higher order moments,Higher order cumulants
Collections
:
-
Statistics
Signal Identification using a new high efficient technique
Show full item record
| contributor author | سیدعلی رضا سیدین | en |
| contributor author | Seyed Alireza Seyedin | fa |
| date accessioned | 2020-06-06T13:28:22Z | |
| date available | 2020-06-06T13:28:22Z | |
| date issued | 2005 | |
| identifier uri | https://libsearch.um.ac.ir:443/fum/handle/fum/3356268?locale-attribute=en | |
| description abstract | Abstract: Automatic signal type identification (ASTI) is an important topic for both the civilian and military domains. Most of the proposed identifiers can only recognize a few types of digital signal and usually need high levels of SNRs. This paper presents a new high efficient technique that includes a variety of digital signal types. In this technique, a combination of higher order moments and higher order cumulants (up to eighth) are proposed as the effective features. A hierarchical support vector machine based structure is proposed as the classifier. In order to improve the performance of identifier, a genetic algorithm is used for parameters selection of the classifier. Simulation results show that the proposed technique is able to identify the different types of digital signal (e.g. QAM128, ASK8, and V29) with high accuracy even at low SNRs. | en |
| language | English | |
| title | Signal Identification using a new high efficient technique | en |
| type | Journal Paper | |
| contenttype | External Fulltext | |
| subject keywords | Statistical pattern recognition | en |
| subject keywords | Signal identification | en |
| subject keywords | Support vector machine | en |
| subject keywords | Higher order moments | en |
| subject keywords | Higher order cumulants | en |
| journal title | Iranian Journal of Electrical and Electronic Engineering | fa |
| pages | 29-36 | |
| journal volume | 1 | |
| journal issue | 4 | |
| identifier link | https://profdoc.um.ac.ir/paper-abstract-1004585.html | |
| identifier articleid | 1004585 |