Papers by Qeethara Al Shayea
Protection of the environment from medical waste hazards is becoming a serious problem. There is ... more Protection of the environment from medical waste hazards is becoming a serious problem. There is a big relation between medical waste and disease injury. The main idea of this study is predict the relation between medical wastes and diseases in Hashemite Kingdom of Jordan using Artificial Neural Networks (ANNs) model. There are six predictor parameters associated with solid and liquid wastes in the medical services sector which are affecting the diseases injury. This study deals with two types of diseases the first one is acute hepatitis and the other is typhoid. Generalized Regression Neural Network (GRNN) is used to predict the diseases injury. It is noticed a significant improvement in the prediction made by GRNN due to its generalization property. Results showed that all six parameters associated with solid and liquid medical wastes which have the largest regression value affect the acute hepatitis injuries and the typhoid injuries. It is also showed that the medical waste affec...
Artificial neural networks are finding many uses in the medical diagnosis application. The goal o... more Artificial neural networks are finding many uses in the medical diagnosis application. The goal of this paper is to evaluate artificial neural network in disease diagnosis. Two cases are studied. The first one is acute nephritis disease; data is the disease symptoms. The second is the heart disease; data is on cardiac Single Proton Emission Computed Tomography (SPECT) images. Each patient classified into two categories: infected and non-infected. Classification is an important tool in medical diagnosis decision support. Feed-forward back propagation neural network is used as a classifier to distinguish between infected or non-infected person in both cases. The results of applying the artificial neural networks methodology to acute nephritis diagnosis based upon selected symptoms show abilities of the network to learn the patterns corresponding to symptoms of the person. In this study, the data were obtained from UCI machine learning repository in order to diagnosed diseases. The dat...
An Efficient Approach to 3D Image Reconstruction
† MIS Department, Al Zaytoonah University of Jordan, Amman, Jordan †† Computer Science Department... more † MIS Department, Al Zaytoonah University of Jordan, Amman, Jordan †† Computer Science Department, Al Anbar University, Anbar, Iraq Summary The images can be visualized in three dimensional (3D) using standard techniques, these 3D techniques are used to enhance the view of images. Converting two dimensional (2D) images into 3D images is an important part of image application. An efficient approach of 3D image reconstruction is implemented to perform a certain process that applied to X-ray medical image. In this paper we have demonstrated that the proposed approach is a useful technique for effective 3D visualization. This approach is implemented via four steps; preprocessing, image enhancement, image contour then image reconstruction and visualization. The obtained results show a good reconstruction of the tested image.
In order to achieve fault tolerance, highly reliable system often require the ability to detect e... more In order to achieve fault tolerance, highly reliable system often require the ability to detect errors as soon as they occur and prevent the speared of erroneous information throughout the system. Thus, the need for codes capable of detecting and correcting byte errors are extremely important since many memory systems use b-bit-per-chip organization. Redundancy on the chip must be put to make fault-tolerant design available. This paper examined several methods of computer memory systems, and then a proposed technique is designed to choose a suitable method depending on the organization of memory systems. The constructed codes require a minimum number of check bits with respect to codes used previously, then it is optimized to fit the organization of memory systems according to the requirements for data and byte lengths.
Journal of Advanced Social Research, 2012
Artificial neural networks are widely used in business disciplines. The objective of this study i... more Artificial neural networks are widely used in business disciplines. The objective of this study is to provide independent real estate market forecasts on home prices using artificial neural networks. The Cascade Forward Back Propagation (CFBP) neural network is used to forecast house price, based on selected 13 parameters which are considered as forecast variables. The results of applying the CFBP neural networks methodology to forecast house price based upon selected parameters show abilities of the network to learn the patterns. In all cases, the percent correctly forecast in the simulation sample is above 94 percent. Empirical results support the potential of artificial neural network on house price forecast. CFBP neural networks are successfully used model for prediction, classification and forecasting. Keywords: Cascade Forward Back Propagation (CFBP), Artificial Neural Network, Business Intelligence.
Real images may consist of many objects. These objects may be situated in different directions. O... more Real images may consist of many objects. These objects may be situated in different directions. Object tracking is an important process for identification of objects via the captured image. The main objective of this work is to construct an efficient information algorithm that detects the direction of objects. This algorithm is designed and implemented based on statistical measurements, histogram, entropy, moment and gradient. The obtained results indicate that this algorithm leads merging many techniques to generate an efficient and effective approach.
Bankruptcy prediction has been an important and widely studied topic. The goal of this study is t... more Bankruptcy prediction has been an important and widely studied topic. The goal of this study is to predict bank insolvency before the bankruptcy using artificial neural networks, to enable all parties to take remedial action. Artificial neural networks are widely used in finance and insurance problems. Generalized Regression Neural Network (GRNN) is used to evaluate the predictor variable used to predict the insolvency. The most important predictor variable influencing insolvency is consistently having the largest regression. Results showed that the most affecting factor in banks insolvency evaluation is the net income, total equity capital, cost of sales, sales, cash flows and loans. The Feed-forward back propagation neural network is used to predict the bankruptcy. The results of applying Feed-forward back propagation neural network methodology to predict financial distress based upon selected financial ratios show abilities of the network to learn the patterns corresponding to fi...
Biometric Face Recognition Based on Enhanced Histogram Approach
Int. J. Commun. Networks Inf. Secur., 2018
Biometric face recognition including digital processing and analyzing a subject's facial stru... more Biometric face recognition including digital processing and analyzing a subject's facial structure. This system has a certain number of points and measures, including the distances between the main features such as eyes, nose and mouth, angles of features such as the jaw and forehead with the lengths of the different parts of the face. With this information, the implemented algorithm creates a unique model with all the digital data. This model can then be compared with the huge databases of images of the face to identify the subject. The recognition features are retrieved here using histogram equalization technique. A high-resolution result is obtained applying this algorithm under the conditions of a specific image database.
WSEAS Transactions on Computers archive, 2010
The detection of embedded object from ground penetrating radar GPR imagery is our goal. The GPR i... more The detection of embedded object from ground penetrating radar GPR imagery is our goal. The GPR image is a cross sectional slices. The embedded objects are metal and/or plastic type. In many fields demand for visualizing objects scanned as cross sectional slices is growing. This research has many real world applications, such as robotic environments, medicine, remote sensing, inspection of industrial parts and geology. An even better way is to visualize the underground object by reconstruction a threedimensional model of those objects from the slices. Objects here are stable underground while, camera is moving. The task of object track in a cross sectional slices consists of two parts: first gather information on changes between succeeding slices (object detection), and second process this information appropriately to obtain the track of an object. If the object is like cable or pipe. The proposed method starts with two dimensional 2D image preprocessing for each slice. The preproce...
Urinary System Diseases Diagnosis Using Artificial Neural Networks
Summary The goal of this paper is to evaluate artificial neural network in urinary diseases diagn... more Summary The goal of this paper is to evaluate artificial neural network in urinary diseases diagnosis. Artificial neural networks are widely used in medical problems. Artificial neural networks are used to disease diagnosis. Feed-forward back propagation neural network is used as a classifier to distinguish between infected or non-infected with two types of urinary disease. Inflammation of urinary bladder and nephritis of renal pelvis origin are diagnosis by artificial neural network. The results of applying the artificial neural networks methodology to diagnosis based upon selected symptoms show abilities of the network to learn the patterns corresponding to symptoms of the person. In this study, the data were obtained from UCI Machine Learning Repository in order to diagnosed diseases. The data is separated into inputs and targets. The symptoms will act as the inputs to the neural network. The targets for the neural network will be identified with 1's as infected and will be i...
Marketing campaigns of banking institutions is vital in all banks. The marketing campaigns were b... more Marketing campaigns of banking institutions is vital in all banks. The marketing campaigns were based on phone calls. Phone calls have an important influence in the behavior of customers. This paper proposed neural network to evaluate the bank marketing. This assessment will highlight the importance of marketing in the banks and thus the importance of phone calls. A feed-forward back propagation neural network with tan-sigmoid transfer functions is used in this paper to predict if the customer subscribes the deposit. The data set is obtained from UCI machine learning repository. The results of applying the proposed neural network methodology to predict subscribe based upon selected phone calls parameters show abilities of the network to learn the patterns corresponding to customer subscribes the deposit. The percent correctly classified in the simulation sample by the proposed neural network is 90 percent. Evaluating Marketing Campaigns of Banking Using Neural Networks Qeethara Kadh...
The prediction of a stock market price has been influenced by a set of the highly nonlinear finan... more The prediction of a stock market price has been influenced by a set of the highly nonlinear financial and nonfinancial indicators may serve as a warning system for investors. In this research, the predicting of the future close price of Dow Jones Index Stocks was conducted using artificial neural networks. Feed forward neural network was used to predict next day closing in Dow Jones stock market. Nonlinear Autoregressive Exogenous (NARX) model is implemented by using feed forward neural network. To optimize the stock market price prediction, the performance of NARX model was examined and compared with different training algorithms. Although these algorithms had adequate results in predicting the NARX model with training, validation and testing. The Bayesian regularization has had the best performance in testing compared with levenberg-marquardt algorithm and the scaled conjugate gradient algorithm. While, the levenbergmarquardt algorithm has had less epochs in the best training performance of the network than the other algorithms. The performance of this model is found as a dominant model for stock market prediction.
Customer data is critical to marketing success. The goal of this study is to predict customer beh... more Customer data is critical to marketing success. The goal of this study is to predict customer behavior using a supervised learning neural network. Feed-forward back propagation network with tan-sigmoid transfer functions is used as a classifier to predict whether a customer will buy in this month or not. Scaled conjugate gradient (SCG) algorithm is used with proposed neural network. This algorithm combines the model-trust region approach with the conjugate gradient approach. The results of applying the proposed artificial neural networks methodology to predict based upon recency, frequency, monetary, and time (RFMT) model show abilities of the network to learn the patterns corresponding to RFMT of the customer. The data set is obtained from UCI machine learning repository. The percent correctly classified in the simulation sample by the proposed neural network is 89 percent.
In credit business, banks are interested in learning whether a prospective consumer will pay back... more In credit business, banks are interested in learning whether a prospective consumer will pay back their credit. The goal of this paper is to classify the credit risk which an applicant can be categorized as a good or bad consumer using artificial neural networks, to enable all parties to take remedial action. The Feed-forward back propagation neural network is used to classify a consumer into two classes depending on selected parameters. One of the classes is credit worthy and likely to repay its financial obligation. The other class which is not credit worthy and whose applications for credit will be rejected due to a high possibility of defaulting on its financial obligation. Two well known and available datasets have been used (German and Australian dataset) to test the proposed neural network. The results of applying the artificial neural networks methodology to classify credit risk based upon selected parameters show abilities of the network to learn the patterns. In German dat...
In order to achieve fault tolerance, highly reliable system often require the ability to detect e... more In order to achieve fault tolerance, highly reliable system often require the ability to detect errors as soon as they occur and prevent the speared of erroneous information throughout the system. Thus, the need for codes capable of detecting and correcting byte errors are extremely important since many memory systems use b-bit-per-chip organization. Redundancy on the chip must be put to make fault-tolerant design available. This paper examined several methods of computer memory systems, and then a proposed technique is designed to choose a suitable method depending on the organization of memory systems. The constructed codes require a minimum number of check bits with respect to codes used previously, then it is optimized to fit the organization of memory systems according to the requirements for data and byte lengths.
Efficient Window Approach of FIR Filter Design (MSK2)
There are several windows used to truncate the impulse response in order to fix filter size. Kais... more There are several windows used to truncate the impulse response in order to fix filter size. Kaiser and Tukey windows are the most important types; from which we can generate other types of windows depending on the variation of ripple parameter. The proposed new window approach is called MSK2 that was implemented to compare its parameters with these two main windows. The characteristics of MSK2 are tested for the 100 window size. The proposed new window is generated via mixing Kaiser and Tukey windows. After implementing the filter with the proposed new window it is obvious that the performance is good and stable.
INTRODUCTIONTelemedicine can be defined as the use of information and communication technology (I... more INTRODUCTIONTelemedicine can be defined as the use of information and communication technology (ICT) to deliver medical services and information from one location to another. In other words, telemedicine can be seen as a way of distributing medical expertise and services to medically underserviced areas, such as remote and rural areas, using ICT as a communication platform. Though any communication system can be used in telemedicine, rapid development in computer technology and easiness to purchase has led to more amenability to computer-based telemedicine technologies that are IP-based. Services offered by telemedicine are designed to help improve healthcare access and information service, while reducing the isolation of healthcare providers and residents in rural areas. Telemedicine can also reduce the time and allay the costs of rural patient transportation significantly. Telemedicine includes applications in areas such as pathology and radiology, as well as consultations in spec...
Predicting the Effects of Medical Waste in the Environment Using Artificial Neural Networks: A Case Study
Protection of the environment from medical waste hazards is becoming a serious problem. There is ... more Protection of the environment from medical waste hazards is becoming a serious problem. There is a big relation between medical waste and disease injury. The main idea of this study is predict the relation between medical wastes and diseases in Hashemite Kingdom of Jordan using Artificial Neural Networks (ANNs) model. There are six predictor parameters associated with solid and liquid wastes in the medical services sector which are affecting the diseases injury. This study deals with two types of diseases the first one is acute hepatitis and the other is typhoid. Generalized Regression Neural Network (GRNN) is used to predict the diseases injury. It is noticed a significant improvement in the prediction made by GRNN due to its generalization property. Results showed that all six parameters associated with solid and liquid medical wastes which have the largest regression value affect the acute hepatitis injuries and the typhoid injuries. It is also showed that the medical waste affec...
Neural Networks in Bank Insolvency Prediction
Summary The current paper aims to predict bank insolvency before the bankruptcy using neural netw... more Summary The current paper aims to predict bank insolvency before the bankruptcy using neural networks, to enable all parties to take remedial action. Artificial neural networks are widely used in finance and insurance problems. Artificial neural networks are used to predict the insolvency. The back propagation network and the Kohonen self-organizing map (SOM) are used as the representative types for supervised and unsupervised artificial neural networks respectively. The results of applying the artificial neural networks methodology to predict financial distress based upon selected financial ratios show abilities of the network to learn the patterns corresponding to financial distress of the bank. In all cases, the percent correctly classified in the simulation sample by the feed-forward back propagation network is above 92 percent. After simulate the SOM network the percent correctly classified is above 94 percent. In spite of the limited data used in this study, artificial neural ...
Uploads
Papers by Qeethara Al Shayea