WSEAS CONFERENCES. WSEAS, Unifying the Science

Main Page of the Journal                                                              Main Page of the WSEAS

Sept. 2006, October 2006, Nov. 2006, Dec.2006, Jan. 2007

Issue 9, Volume 3, September 2006
Print ISSN: 1109-9518
E-ISSN: 2224-2902







Title of the Paper: Non thermal effects of the electromagnetic waves on DNA: Study on E. coli


Authors: Fatima Jebai, Mohamad Ezzedine, Manal Khalife, Nissrine Daou and Riad Hamamieh

Abstract: -E. coli strain TB1 are used to determine the effects of microwaves (MW) of frequency 900 MHz and an intensity of field exposure 6 V/m at ambient temperature. Our experiment was preformed by studying the effect of MW on DNA. We transformed unexposed bacteria with exposed pUC18 plasmid. We did not find any variation in the transformation ratio (100 transformants/μg DNA). We did not find any variation in the number of blue colonies (100% blue colonies). Analysis of exposed DNA with quantitative PCR technique was realized to determine the quantity of broken DNA strands after MW exposure. By comparison between exposed and control DNA no difference was observed. Electrophoresis and spectroscopic analysis of exposed DNA did not reveal any hyperchrome effect. In order to confirm our results we sequenced exposed pUC18 plasmid but again no alteration of the DNA on the molecular level was observed.

Keywords: Microwaves, Elecromagnetic, Mobile, DNA, Mutation, HSP

Title of the Paper: A New Methodology for Segmentation of Functional Magnetic Resonance Imaging Using Functional Echo State Neural Network


Authors: Ravichandran C G and Ravindran G

Abstract: In this paper a new intelligent segmentation of functional magnetic resonance imaging (fMRI) has been implemented using echo state neural network (ESNN). fMRI is a non-invasive method which can be used to indirectly localize neuronal activations in the human brain. The term segmentation includes not only the detection and localization, but also the delineation of activation region in the brain. Perfect segmentation is important especially for the detection and position of brain tumor. In spite of the existing segmentation methods, we have proposed a novel estimation method for accurate segmentation irrespective of noise level. The Recurrent ESNN is an estimation method able to produce an accurate segmentation when compared to the contextual clustering segmentation method. In order to show the accuracy of segmentation, the existing Contextual clustering (CC) segmentation method has been considered. Peak Signal to Noise Ratio (PSNR) of the segmented image of ESNN is 6 and found to be higher than PSNR of CC 57. The segmented images can be used in Medical Imaging application like 3D Reconstruction.

Keywords: Echo state neural network (ESNN), intelligent segmentation, Functional magnetic resonance imaging (fMRI), Contextual clustering (CC)

[Journals], [Books], [Conferences], [Research], [Contact us], [Indexing], [Reports], [E-Library], [FAQ],
[Upcoming Conferences with Expired Deadline], [History of the WSEAS Conferences]
          Copyright WSEAS