Digital-Signal-Type Identification Using an Efficient Identifier. (3rd June 2007)

• Record Type: Journal Article
• Authors: Abrahamzadeh Abrahamzadeh, Ataollah Ataollah; Seyedin Seyedin, Seyed Alireza Seyed Alireza; Dehghan Dehghan, Mehdi Mehdi
• Other Names: Cetin Cetin Enis Ahmet Enis Ahmet Academic Editor.
• Is Part Of: EURASIP journal on advances in signal processing. Volume 2007(2007)
• Publication Date: 2007-06-03
• Subjects: Signal processing -- Periodicals; Traitement du signal; Signal processing; Periodicals; 621.3822
• DOI: 10.1155/2007/37690
• Languages: English
• ISSNs: 1687-6172

Abstract

Abstract : Automatic digital-signal-type identification plays an important role for various applications. This paper presents a highly efficient identifier (technique) that identifies a variety of digital signal types. In this technique, a selected number of the higher-order moments and the higher-order cumulants up to eighth are utilized as the effective features. A hierarchical support-vector-machine- (SVMs) based structure is proposed for multiclass classification. A genetic algorithm is proposed in order to improve the performance of the identifier. Genetic algorithm selects the suitable parameters of SVMs that are used in the structure of the classifier. Simulation results show that the proposed identifier has high performance for identification of the considered digital signal types even at very low SNRs.