أبحاث أعضاء هيئة التدريس

أنت هنا

Knowledge On The Move عبدالله عبدالله الجمعة

Knowledge propagation is the challenge. Better society requires best knowledge management practices and use of latest tools and technologies. Knowledge management is dealing with the problem of different lagnuages in big counties. Also knowledge is present in different formes. It may be knowledge encoded in laws, decrees, standards, policies, rules and regulations and orders. All these froms of knwledge must be combined together so that it is readily available for general public in their own language. In addition there should be a porper knowledge propagation mechanism.........

...
Application of data mining: Diabetes health care in young and old patients عبدالله عبدالله الجمعة

This research concentrate upon predictive analysis of diabetic treatment using the regression based data mining technique. The Oracle Data Miner (ODM) had been employed as a software mining tool for predicting modes of treating diabetes. The support vector machine algorithm had been used in the experimental analysis. The datasets of Non Communicable Disease (NCD) risk factors, a standard report of Saudi Arabia in collaboration with WHO (World health organization) were employed. The dataset for different age groups of diabetic treatment had been studied and analyzed for the appropriate patterns of treatment. The five age groups had been put into two age groups denoted as p(y) and p(o) as young and old, respectively. The preferential order of treatment prediction had been investigated. We conclude that drug treatment for young age group patient can be delayed to avoid side effects and other treatments are preferred. Whereas for the old age group patients drug treatment along with other treatments are to be prescribed immediately as there are no other alternatives.

...
Denoising of Medical Images Using Multiwavelet Transforms and Various Thresholding Techniques عبدالله عبدالله الجمعة

The problem of estimating an image corrupted by additive white Gaussian noise has been of interest for practical reasons. Non-linear denoising methods based on wavelets, have become popular but Multiwavelets outperform wavelets in image denoising. Multiwavelets are wavelets with several scaling and wavelet functions, offer simultaneously Orthogonality, Symmetry, Short support and Vanishing moments, which is not possible with ordinary (scalar) wavelets. These properties make Multiwavelets promising for image processing applications, such as image denoising. The aim of this paper is to apply various non-linear thresholding techniques such as hard, soft, universal, modified universal, fixed and multivariate thresholding in Multiwavelet transform domain such as Discrete Multiwavelet Transform, Symmetric Asymmetric (SA4), Chui Lian (CL), and Bi-Hermite (Bih52S) for different Multiwavelets at different levels, to denoise an image and determine the best one out of it. The performance of denoising algorithms and various thresholding are measured using quantitative performance measures such as, Mean Square Error (MSE), and Root Mean Square Error (RMSE), Signal-to-Noise Ratio (SNR), Peak Signal-to-Noise Ratio (PSNR). It is found that CL Multiwavelet transform in combination with modified universal thresholding has given best results ...
Application of Classification based Data Mining عبدالله عبدالله الجمعة

The Present research work relates data mining to medical informatics. The proposed work shows various models for each type of diabetic intervention and anlysis is carried out using calssification based data mining techinique. The Area Under Curve (AUC) of ROC (Receiving Operating Cahracteristics)plots are calculated, the confusion matrix is formed, through which accuracy and cost of interventions have been evaluated. The AUC of ROC for all six modes of deabetic interventions are obtained and have been distinguished which mode of intervention is more approperiate....

...
Paradigm Shift in the Security-n-Privacy Implementation of Semi-Distributed Online Social Networking عبدالله عبدالله الجمعة

Social Networking Applications has gained tremendous response from all the sections of people across the entire world from last few years. Social networking has crossed all the boundaries and glued whole world population together. Users of OSN (Online Social Networking) sites can re-connect with school friends, find some activity or even life partners, and make new friends. OSN has also revolutionized the business community. Now the companies leverage OSN’s credibility and build their reputation, get invaluable information about the customers. The companies are also using OSN for the advertising and the recruitment processes. However, posting of user information on OSN poses greater threats/risks as identity theft, online stalking, and information leakage. The volume and accessibility of personal information available on social networking sites have attracted malicious people who seek to exploit this information. This imposes greater threat to the users’ privacy and security. In this article many security and privacy challenges currently faced by OSN applications are mentioned. The distributed OSN architecture with an external control module is proposed and a prototype is also presented which overcomes many of the privacy, security, accessibility and identity challenges in different perspectives faced by current OSN applications. ...
Network Security Using Job Oriented Architecture (SUJOA) عبدالله عبدالله الجمعة

In the modern world operating system,various security systems (Collection of various security components) are already installed or can be directly installed in it. They are responsible for checking the complete node for suspicious behaviour. There are some ntrusions having the ability to hide themselves from being checked called armouring intrusions. In this research article we present alternative organisation of security systems. To distinguish operating system applications and security systems, the node is completely virtualized with current virtualized systems. The node is then checked by security systems from outside and the right security components are provided through job oriented architecture. Since they run on a virtual machine the infected nodes can be halted, duplicated and moved to other nodes for further analysis and legal aspects. The coordinated architecture analysed in this research article and the results of a preliminary implementation with positive results are discussed. ...
FOR CONSTRUCTION OF MODIFIED MULTIWAVELET TRANSFORM AND IT'S IMPLEMENTATION IMAGE COMPRESSION عبدالله عبدالله الجمعة

The main aim of this research work is to compress an image that is to remove the redundancies from

an image to such an extent that after decompression the image should be reasonably recognized. In this

approach the proposed, newly constructed multiscaling ancl mitiwavelet functions are used in multiwavelet

Lransform. This modified multiwavelet transforrn is implemented to achieve better image compression ancl decompression. We have also implemented otl'rer multiwavelet transforms such as GHM, df, se , Bih52S and

Cadrbal2 and compared tl're results with proposed modified multiwavelet transform. The results are compared

based on image compression parameters such-as entropy, redundancy, compression ratio, peak signal-to-1oise

ratio and mean square eiror' It is found that the results'of proposed modified multiwavelei transform is better

compared to other multiwavelet trar-rsformation technrques.

...
Denoising of an Image Using Discrete Stationary Wavelet Transform and Various Thresholding Techniques عبدالله عبدالله الجمعة

Image denoising has remained a fundamental problem in the field of image processing. With Wavelet transforms, various algorithms for denoising in wavelet domain were introduced. Wavelets gave a superior performance in image denoising due to its properties such as multi-resolution. The problem of estimating an image that is corrupted by Additive White Gaussian Noise has been of interest for practical and theoretical reasons. Non-linear methods especially those based on wavelets have become popular due to its advantages over linear methods. Here I applied non-linear thresholding techniques in wavelet domain such as hard and soft thresholding, wavelet shrinkages such as Visu-shrink (nonadaptive) and SURE, Bayes and Normal Shrink (adaptive), using Discrete Stationary Wavelet Transform (DSWT) for different wavelets, at different levels, to denoise an image and determine the best one out of them. Performance of denoising algorithm is measured using quantitative performance measures such as Signal-to-Noise Ratio (SNR) and Mean Square Error (MSE) for various thresholding techniques. ...
Efficient Scheduling Scheme for Mobile Wireless Sensor Network محمد بن سعيد القحطاني


 

Among many solutions for reducing the energy consumptions of sensor nodes, scheduling the active and sleep cycles of sensor nodes is significantly important for Wireless Sensor Network (WSN). This solution allows a small number of sensors to be in active mode that also guarantees the coverage of the whole network area and all other sensors in inactive or sleep mode by turning their radio off. Recently, many node scheduling schemes have been proposed in the literature. However, most of the schemes are designed for static sensor nodes which are not feasible for the WSN applications where, mobility of sensors is significantly important. For instance, static node scheduling schemes cannot work in health monitoring and habitat monitoring since sensors attached to human body and animals are mobile. Moreover, most existing approaches only consider achieving energy efficiency but reducing end-to-end delay and collision probability is also important for the emergency real-time and many other applications.

 

Thus, this project introduces an efficient and coverage-based node activity scheduling scheme for Mobile WSN (MWSN) in terms of energy consumptions and end-to-end data transmission delay.

...
QR Code for https://cces.psau.edu.sa/ar/sources/research/10