Browsing by Author "Ibrahim Elimam Abdalla, Abubakr Elsidig Mirghani El Hussien"

Now showing 1 - 3 of 3

Blind Source Separation Technique via Parallel Computing
(2006-05) Ibrahim Elimam Abdalla, Abubakr Elsidig Mirghani El Hussien; Othman Khalif
Blind source separation is one of the more challenging problems in signal processing where mixture of sources, sounds or any type of signals are to be separated and located without any prior information about these sources and the way they have been mixed, hence the name blind. Many methods and algorithms have been developed to tackle this problem, they are mostly complicated and computational expensive. The main aim of this paper is to study and compare these techniques that are currently used in source separation, highlighting their advantages and weaknesses. A parallel computing approach is introduced as an efficient way to enhance the current techniques of blind source separation. The benefits of the proposed technique are discussed.
Investigation of the Impact of Bad Learning on Blind Source Separation
(2007-03) Ibrahim Elimam Abdalla, Abubakr Elsidig Mirghani El Hussien; Othman Khalifa, Aisha Hassan Abdalla
Blind source separation is one of the more challenging problems in signal processing where mixture of sources, sounds or any type of signals are to be separated and located without any prior information about these sources and the way they have been mixed. Any blind source separation algorithm consists of a contrast or cost function plus an adaptation or learning rule which is used to minimize or maximize the cost function so as to perform separation. This typically used in human being brains to distinguish between the different voices and scenes. Here we introduce an approach that explains some strange natural phenomena and relate their occurrence to what is called bad learning in the process of blind source separation.
Parallel Algorithm for Blind Source Separation
(2008) Ibrahim Elimam Abdalla, Abubakr Elsidig Mirghani El Hussien; Aisha Hassan Abdalla
In Blind Source Separation a mixture of sources, sounds or any type of signals are to be separated without any prior information about these sources and the way they have been mixed. Most of the methods and algorithms that have been developed to tackle this problem are computationally expensive. Specially those dealing with Convolutive Blind Source Separation. Here, a new parallel, computationally none expensive Convolutive Blind Source Separation algorithm is presented and evaluated. Then parallelization of an already existing Blind Source separation algorithm is also presented and tested.