Volume (9) - Issue (I), ACSE-BIME ISSN: Print 1687-4811, Online 1687-482X &
CD-ROM 1687-4838
Guest Editor: Prof. Dr.
|
@ARTICLE |
{P1160950101, |
| AUTHOR = |
{Ghazi Bousaleh and Rafic Hage Chehade and Fahd Hassoun}, |
| TITLE = |
{Analytical Approach For the Study of Radiated Emission of Hospital Cabling System Conveying a Transmission PLT}, |
| JOURNAL = |
{ICGST International Journal on Bioinformatics and Medical Engineering, BIME}, |
| YEAR = |
{2009}, |
| MONTH= |
{December}, |
| VOLUME = |
{09}, |
| ISSUE = |
{I}, |
| PAGES= |
{1-4}, |
| ABSTRACT= |
{Advances of high speed transmission on electrical communication (PLT: Power Line Transmission) in hospitals, taking into account the problems by CEM, more particularly by radiated emission associated with the characteristics of the deployed systems and the cables used. In addition, a telegraphic transmission system can comprise variations of the geometry, and can lead to an increase in the electromagnetic radiation, being able to obstruct the operation of the medical electrical appliance. This article presents a theoretical study allowing to reach the distribution of the radiated field by a cable of non uniform geometrical energy. The formalism suggested is based on the modified theory of the lines, insofar as the linear parameters vary according to the geometry of the line installed in the old hospital}, |
| NOTE= |
{PLC
(Power
Line
Communication),
CPL
(Power
line
communication),
CEM
(Electromagnetic
Compatibility),
Radiation,
PLT}
} |
(Status: Accepted)
|
@ARTICLE |
{P1160950102, |
| AUTHOR = |
{Hafida Bouziane and Belhadri Messabih and Abdellah Chouarfia}, |
| TITLE = |
{Machine Learning for Protein Secondary Structure Prediction}, |
| JOURNAL = |
{ICGST International Journal on Bioinformatics and Medical Engineering, BIME}, |
| YEAR = |
{2009}, |
| MONTH= |
{December}, |
| VOLUME = |
{09}, |
| ISSUE = |
{I}, |
| PAGES= |
{5--10}, |
| ABSTRACT= |
{Determining experimentally the protein 3D structure, let it be with X-ray crystallography or nuclear magnetic resonance spectroscopy techniques, is difficult and time
consuming, when it is possible. Since the number of known sequences is currently exploding, as the result of large-scale sequencing projects, the gap between the sets
of known protein sequences and known protein structures is widening rapidly. Performing predictions thus appears necessary to fill this gap. This can be done rather easily when an homolog of the query sequence of known structure is available in the databases. Unfortunately, this favourable case is still minority. Using machine learning techniques appears as an appealing solution to develop "de novo" prediction methods. A first step towards tertiary structure prediction consists in projecting this structure onto one dimension, i.e., onto a string of secondary structural assignments for each amino acid. This step is very important and useful in understanding
how the amino acid sequence of a protein determines its native state. .A great many methods are already available to predict this structure "ab initio” without any additional biochemical work. In this article, we introduce a prediction method based on feed-forward multi-layer neural networks.}, |
| NOTE= |
{Amino
acids,
Machine
learning,
Proteins,
Neural
networks,
Secondary
structure}
} |
(Status: Accepted)
|
@ARTICLE |
{P1160950103, |
| AUTHOR = |
{R. Khemakhem and O. Ben Sassi and A. Ben Hamida and A. Taleb-Ahmed}, |
| TITLE = |
{Monomodal and Multimodal Registration using the ICP Algorithm}, |
| JOURNAL = |
{ICGST International Journal on Bioinformatics and Medical Engineering, BIME}, |
| YEAR = |
{2009}, |
| MONTH= |
{December}, |
| VOLUME = |
{09}, |
| ISSUE = |
{I}, |
| PAGES= |
{11--16}, |
| ABSTRACT= |
{This paper presents the main approach of medical images registration. The registered images are assumed to be rigidly aligned using the ICP algorithm. The tasks to be realized consists in making a monomodal registration intra-subjects based on two MRI images, and a multimodal registration intra-subjects based on MRI images and an EEG exam. The multimodal registration is preceded by the resolution of inverse problems in EEG to make the reconstruction of the active sources. For the multimodal registration, the sLORETA-FOCUSS inverse problem methods is used, which gives good results for neuronal activity reconstruction. So, good registration
results have been obtained.}, |
| NOTE= |
{EEG,
MRI,
ICP
algorithm,
Segmentation,
Monomodal
Registration,
Multimodal
Registration,
sLORETA-FOCUSS}
} |
(Status: Accepted)
|
@ARTICLE |
{P1160950104, |
| AUTHOR = |
{S. Ktata and K. Ouni}, |
| TITLE = |
{Comparison of Compression Methods for ECG Signals}, |
| JOURNAL = |
{ICGST International Journal on Bioinformatics and Medical Engineering, BIME}, |
| YEAR = |
{2009}, |
| MONTH= |
{December}, |
| VOLUME = |
{09}, |
| ISSUE = |
{I}, |
| PAGES= |
{17--23}, |
| ABSTRACT= |
{Recently, Electrocardiogram (ECG) compression still attracts the attention, due to the huge amount of data that has to be stored/transmitted. This paper investigates a set of ECG signal compression methods to compare their performances in compressing. Three different transform methods are developed for ECG signals using, a discrete Fourier transform (DFT), a discrete cosine transform (DCT) and a discrete wavelet transform (DWT). The performance has been evaluated on the basis of
compression ratio (CR), percent-root-mean-square difference (PRD) and fidelity of the reconstructed signal. These results show that the discrete wavelet transform is
more effective than the other methods for getting minimum PRD.}, |
| NOTE= |
{Compression,
ECG,
TFD,
TCD,
TOD}
} |
(Status: Accepted)
|
@ARTICLE |
{P1160950105, |
| AUTHOR = |
{O. DRIDI MEKNI and M. BEN AHMED}, |
| TITLE = |
{Semantic Search of Medical Resources on the Base of Meta-information and Semantic Annotation}, |
| JOURNAL = |
{ICGST International Journal on Bioinformatics and Medical Engineering, BIME}, |
| YEAR = |
{2009}, |
| MONTH= |
{December}, |
| VOLUME = |
{09}, |
| ISSUE = |
{I}, |
| PAGES= |
{25--30}, |
| ABSTRACT= |
{Semantic search has been one of the motivations of the Semantic Web since it was envisioned. In my thesis, I research the development of a new retrieval model for the exploitation of knowledge represented in ontologies to improve search over large document repositories. In my proposed approach I consider an adaptation of the classic model of Information Retrieval (IR), including a metainformation process, and a semantic annotation of document. In this approach, semantic search is based on meta-information and semantic annotation in order to index document semantically. The method has been tested on medical corpora, showing promising results respect to keyword-based search, and providing ground for further analysis and research.}, |
| NOTE= |
{annotation,
medical
corpus,
meta-information,
ontology,
semantic
search}
} |
(Status: Accepted)
|
@ARTICLE |
{P1160950106, |
| AUTHOR = |
{Mohammed S. Zahrani}, |
| TITLE = |
{Enhancement of Multimodal Biometric Verification Using a Combination of Fusion Methods}, |
| JOURNAL = |
{ICGST International Journal on Bioinformatics and Medical Engineering, BIME}, |
| YEAR = |
{2009}, |
| MONTH= |
{December}, |
| VOLUME = |
{09}, |
| ISSUE = |
{I}, |
| PAGES= |
{31--34}, |
| ABSTRACT= |
{Various fusion techniques have been widely used in combining separate information from different modalities to provide complementary data. The main aim of this paper is to present investigations for enhancing the accuracy of multimodal biometrics through the introduction of appropriate fusion method combination. The effectiveness of the proposed method is to benefit from both complementary data as well as complementary of fusion methods in increasing the authentication accuracy. Such technique, in building a multimodal biometrics system, has not widely been investigated. The proposed fusion process is divided into two stages. In the
first stage, score fusion in unimodal biometrics based on multiple matching algorithms is accomplished. This is achieved by those classifiers that have good learning mechanism such as Support Vector Machines (SVM) and Logistic regression (LR). The simple Brute Search Force (BFS) is also used for this task. In the second stage, the obtained fused scores for face and voice modalities are further incorporated by either SVM, LR or BFS. Experimental investigation is conducted using face and speech modalities. The results clearly show the benefits gained from using a combination of fusion methods at the unimodal and multimodal levels}, |
| NOTE= |
{Multimodal
biometrics,
score-level
fusion,
biometric
verification,
fusion
techniques}
} |
(Status: Accepted)
|
@ARTICLE |
{P1160950107, |
| AUTHOR = |
{L. Lalaoui and T. Mohamadi and M. Chemachema}, |
| TITLE = |
{Support Vector Machine (SVM) and the Neural Networks for Segmentation the Magnetic Resonance Imaging}, |
| JOURNAL = |
{ICGST International Journal on Bioinformatics and Medical Engineering, BIME}, |
| YEAR = |
{2009}, |
| MONTH= |
{December}, |
| VOLUME = |
{09}, |
| ISSUE = |
{I}, |
| PAGES= |
{35--39}, |
| ABSTRACT= |
{In this paper a classification algorithms MLP and SVM for the segmentation tissue of brain magnetic resonance images is proposed. Magnetic resonance imaging (MRI) segmentation is an important technique to differentiate abnormal and normal tissues in MR image data. The method interleaves classification with estimation of the model parameters, improving the classification at each iteration. This approach uses the information from the proton density (PD)- and T2-weighted and lattice relaxation time (T1) attenuation images. This works presents an NNN’s and SVM (Support Vector Machine) for segmentation of mixed tissue in each voxels, for each voxels en calculate the mean, variance and co-variance are the input of neural network, to evaluate the performance on computed the misclassify rate image data
and mixed tissue models. Segmentation tissue results from various algorithms are compared and the effectiveness and robustness of the proposed approach are demonstrated.}, |
| NOTE= |
{IRM,
neural
network,
Segmentation,
support
vector
machine.}
} |
(Status: Accepted)
|
@ARTICLE |
{P1160950108, |
| AUTHOR = |
{Mohamed KALLEL and Mohamed Salim BOUHLEL and Jean-Christophe LAPAYRE}, |
| TITLE = |
{A New Multiple Watermarking Schema for Medical Image in Frequency Field}, |
| JOURNAL = |
{ICGST International Journal on Bioinformatics and Medical Engineering, BIME}, |
| YEAR = |
{2009}, |
| MONTH= |
{December}, |
| VOLUME = |
{09}, |
| ISSUE = |
{I}, |
| PAGES= |
{41--44}, |
| ABSTRACT= |
{A multiple watermarking technique can be used to ensure record of the commentaries realised by practitioners in the collaborative work. Multimedia applications need high requirements on their security, for this reason the use of digital watermarking is a field that has received an increasing degree of interest to protect media against piracy. The fundamental challenge of this paper is to hide information into a digital image file so that the information is not perceived. In fact, an overview of the multiple watermarking schema in the frequency domain is presented to ensure a record and a traceability on the collaborative work between practitioners.}, |
| NOTE= |
{multiple
watermarking,
frequency
field,
TeNeCi
platform,
medical
image}
} |
|
