Jalil Taghia

Publications (3)0 Total impact

• Source

  Available from: wseas.us

  Chapter: A new algorithm in blind source separation for high-dimensional data sets such as MEG data

  Jalil Taghia, M. A. Doostari, Jalal Taghia
  [show abstract] [hide abstract]
  ABSTRACT: BSS is one of the well-known methods of signal processing. This method is based on recovering of original sources from observed mixtures without any further information about mixing system and original sources. In many applications, mixtures are combination of non-Gaussian and time-correlated components. MCOMBI algorithm is known as a method for separation of these kinds of sources. The performance and accuracy of this algorithm are noticeable but the high computational cost is one of the most significant limitations of MCOMBI algorithm, especially for high-dimensional data sets like high-density electroencephalographic (EEG) or magnetoencephalographic (MEG) recordings. In this chapter, we propose a new algorithm which uses combination of WASOBI and EFICA algorithms. In addition we use clustering method to decrease computational cost. In contrast with MCOMBI algorithm, the proposed algorithm decreases run time of separation and it has high accuracy close to MCOMBI algorithm. Thus, this algorithm is suitable for real high-dimensional data sets. In this chapter we use our algorithm for separation of artifacts in real MEG data. KeywordsStatistical signal analysis–biomedical signal processing–blind source separation–independent component analysis–Non-Gaussianity–time-correlation–MEG data
  12/2008: pages 237-248;
• Conference Proceeding: An Image Watermarking Method Based on Bidimensional Empirical Mode Decomposition

  Jalil Taghia, Mohammad Ali Doostari, Jalal Taghia
  [show abstract] [hide abstract]
  ABSTRACT: In this paper, we propose a blind image watermarking scheme based on bidimensional empirical mode decomposition (BEMD). BEMD is a possible 2D extension of empirical mode decomposition (EMD). We employ BEMD in watermark embedding and watermark extraction. In watermark embedding scheme at first, the original image is divided into K sub-images then in order to obtain a set of 2D-IMFs BEMD is applied to each sub-image and watermark. For watermark embedding each 2D-IMF, which is extracted from watermark, is placed instead of one of the 2D-IMFs which are extracted from each sub-image in a special procedure. On the other hand the proposed method in watermark extraction is based on BEMD and clustering method with metric, local linear structure and affine symmetry to extract watermark blindly. We perform two classes of tests in our experiments: First, we measure imperceptibility of watermark and then we examine the performance against different kinds of attacks.
  Image and Signal Processing, 2008. CISP '08. Congress on; 06/2008
• Conference Proceeding: One-Channel Audio Source Separation of Convolutive Mixture.

  Jalal Taghia, Jalil Taghia
  Advances in Computer and Information Sciences and Engineering, Proceedings of the 2007 International Conference on Systems, Computing Sciences and Software Engineering (SCSS), part of the International Joint Conferences on Computer, Information, and Systems Sciences, and Engineering (CISSE 2007), Bridgeport, CT, USA, December 3-12, 2007; 01/2007