This study aims to design a neural model for a linear or nonlinear systems by using an Evolutionary Programming algorithm (EP) to choose the optimal structural construction for the network. We have used Matlab to design Neural Networks using (EP), be
cause of its flexibility and ability to represent matrices (Cell Arrays, Multi Dimension Arrays). The experimental results confirm the efficiency with which this algorithm (EP) obtains the optimal network. We have tested the algorithm performance and the resulting model robustness by canceling one of the hidden layer nodes of the best net resulting from applying (EP). The effectiveness of that canceling on the resulting model output is also tested, and this study has shown the efficiency of the algorithm (EP) for the class of systems used.
In this study we developed an adaptive model inspired by internal models in the cerebellum and this approach called Feedback Error Learning (FEL). FEL is the origin of Learning Feed-Forward Control (LFFC). It depends on Feedback Controller and Feed-F
orward Controller which is a Neural Network, and this Neural Network uses feedback controller output as training signal. We developed this approach to control a robot arm, and to balance inverted pendulum and to control bus suspension system. We developed this approach by adding a second Neural Network, and this new Neural Network uses FEL controller output as training signal. We simulate these systems by using Matlab and Simulink, and we find that this development improves control performance.
The Protocol Independent Multicast - Sparse Mode (PIM-SM) uses one center (referred here as the Rendezvous Point “RP”) for all sources in a multicast group. PIM-SM distributes the multicast traffic of a source through a so-called shared distribution
tree, whose root is at a predefined core called Rendezvous Point (RP). It also builds source-specific trees to the sources whose data rates exceed a defined threshold. In the literature, several investigations are done to improve and provide an efficient mechanism for the dynamic relocation of the RP depending on the sources or the members of the multicast group. In this paper, we extend the investigation of three search algorithms used to find the optimal RP position. To evaluate the performance of these algorithms, Estimated Tree Cost (ETC) and our improvement Enhanced Estimated Tree Cost (EETC), are used. The reason behind our choice these two methods is a comparative investigation of the RP-selection methods proposed in the literature. From the comparison we can see that ETC finds the most optimal position of the rendezvous point. The Hill-Climbing algorithm and the standard PIM-SM protocol with static RP-selection are used as a reference for comparison. Our algorithms result in a lower network load compared to RP-selection algorithm. However, they need additional control messages.
This paper presents parallel computers architectures especially Superscalar
processors and Vector processors, building a simulator depending on the basic
characteristics for each architecture, the simulator simulates their mechanism of work
progra
mmatically at the aim of comparing the performance of the two architectures in
executing Data Level Parallelism (DLP) and Instruction Level Parallelism ILP.
The results shows that the effectiveness of executing instructions in parallel depends
significantly on choosing the appropriate architecture for execution, according to the type
of parallelism that can be applied to instructions, and the vector features in the vector
architecture achieve remarkable improvement in performance that cannot be ignored in
execution of DLP, simplify the code and reduce the number of instruction. The provided
simulator is a good core that can be developed and modified especially in the field of
education for the students of Computer Science and Engineering and the research field.
This paper presents an algorithm for designing a system that classifies standard
human facial expressions which are fear, disgust, sad , surprise, anger, happiness, and the
normal expression . The facial expression that is presented in the input im
age of the system
can be classified depending on extracting appearance features then, it is entered into
neural network to complete the classification process using Matlab as a programming
language.
Multiple stages completed the work, which are, (collection images, pre-processing of
the images, feature extraction, training neural network, classification and testing). Our
system has been able to achieve the highest rating when the expression of anger reached
100 %, while the lowest rating was at the expression of sad by 30%.
Fetus images produced by 2D ultrasound devices are ambiguous and lack precision. This led to the need
for offering a 3D visualization of the fetus, which allows visualizing width, height, and angle, in order to
get additional information about the
fetus, and detect fetus abnormalities.
We explain in this paper our method in producing 3D models of the fetus from 2D images using a
computer system without the need for changing the 2D imaging devices, and without using position
sensors.
Our method is based on passing the probe over the pregnant woman's abdomen and make a manual scan
for the entire body of the fetus from top of the head till the bottom of his feet, then it saves this scan as a
video clip then send, it to the computer which segments the video into multiple images which are saved and
later processed using digital processing principles of images. Then these processed images are
reconstructed to produce the volume matrix and then display it in a 3D form using 3D model construction
methods.
We applied our software on various fetuses of different ages and got volume images which are considered
good in comparison with the images offered by currently available systems and devices. The precision of
the images we got, differs according to the change in fetus pose, amniotic liquid, and fetus size, The
obstetrician or gynecologist can retrieve more precise details by changing the angle and displaying volume
images of certain part of the fetus body.
Available bandwidth has a significant impact on the performance of many applications that
run over computer networks. Therefore, many researchers pay attention to this issue through
the study of the possibility of measuring the available bandwidth,
and disseminating tools for
measuring this metric. We present a method to estimate the available bandwidth for a path,
by building, sending, and receiving probe packets. We measure the time gap between probing
packets before sending and after receiving, then we estimate the available bandwidth. This
method relies on an easy and fast algorithm. Applications can use this method before they
start exchanging data over the Internet.
This research designs web search engine kernel overrule in searching of specific
fields and indexing indicated sites.
This research contain information about search in web , retrieval system , types of
search engines and basic architectures of bui
lding search engines .It suggests search engine
architecture kernel of dedicated search engine to do final planner of search engine
architecture ,and build parts of search engine and execute test to get results .
The study suggests designing a weighting model for iris features and selection of the
best ones to show the effect of weighting and selection process on system performance.
The search introduces a new weighting and fusion algorithm depends on the i
nter and intra
class differences and the fuzzy logic. The output of the algorithm is the feature’s weight of
the selected features. The designed system consists of four stages which are iris
segmentation, feature extraction, feature weighting_selection_fusion model
implementation and recognition. System suggests using region descriptors for defining the
center and radius of iris region, then the iris is cropped and transformed into the polar
coordinates via rotation and selection of radius-size pixels of fixed window from center to
circumference. Feature extraction stage is done by wavelet vertical details and the
statistical metrics of 1st and 2nd derivative of normalized iris image. At weighting and
fusion step the best features are selected and fused for classification stage which is done by
distance classifier. The algorithm is applied on CASIA database which consists of iris
images related to 250 persons. It achieved 100% segmentation precision and 98.7%
recognition rate. The results show that segmentation algorithm is robust against
illumination and rotation variations and occlusion by eye lash and lid, and the
weighting_selection_fusion algorithm enhances the system performance.
This paper proposes a new approach for the segmentation of the retina images to obtain the optic nerve and blood vessels regions. We used retinal images from DRIVE and STARE databases which include different situations like illumination variations, d
ifferent optic nerve positions (left, right and center). Illumination problem has been solved by preprocessing stage including image histogram-based illumination correction. Next, some morphological operations were used to filter the preprocessed image to obtain the ROI region, then, the center and radius of optic nerve were determined, and the optic nerve region was extracted from the original image. In blood vessels segmentation, we applied the illumination correction and median filtering.Then the closing, subtraction and morphological operations were done to get the blood vessels image which was thresholded and thinned to get the final blood vessels image.
