Journal of Al-Qadisiyah for computer science and mathematics

Adaptive Features Selection Technique for Efficient Heart Disease Prediction

2023-02-17T18:49:37+00:00

Heart disease is a common disease that causes death and is difficult to detect manually. A more efficient classification model that relies on machine learning methods to achieve higher classification accuracy, attracts the attention of researchers to design an effective prediction model. Moreover, it plays an important role in the practical application of medical cardiology with the aim of early detection of heart diseases. In this paper, an efficient and accurate heart disease detection system is proposed based on the proposed adaptive feature selection technique using four machine learning methods: Support Vector Machine (SVM), Logistic Regression (LR), Decision Tree (DT), and Random Forest (RF). Two feature selection methods were used to design the proposed technique, mutual information (MI) and recursive feature elimination (RFE) to determine the optimal number of selected features that increase the performance of the classification models and reduce the time complexity of model implementation. The proposed technique was implemented on the two standard databases from the UCI machine learning repository: Cleveland heart disease and heart Statlog Cleveland. The best model was selected and saved as a prediction model using the cross-validation method. The results show that each data has a different number of features chosen according to the classifier model. For the first heart disease dataset, the best heart disease detection system Support Vector Machine-mutual information (SVM-MI) achieved the highest classification accuracy of approximately 96.755 compared to the other classifier models used. While the Random Forest-mutual information (RF-MI) model achieved an accuracy of 97.4% for the second data set. The proposed technique produced the highest prediction performance in terms of accuracy, f1 score, accuracy, and metric retrieval compared to the latest research in this field.

Designing the electronic payment system for the UOITC university using Zain Cash wallet

2023-02-17T18:49:45+00:00

The payment system is a suggested project that will construct an adequate information management system, for the University of Information Technology and Communication . The proposed system will be sufficient for documenting cash payments of university fees, and eliminating mistakes caused by the manual approach of collecting student payment information. The main objective of this project is to design and implement an electronic payment system(EPS). allows students of private government University in addition evening students at the university, to pay tuition fees using the electronic payment system through the Zain Cash Wallet service. The computer-based payment documentation system of the UOITC was implemented using PHP languages, MYSQL database. Results indicate that the design of an efficient system enhances the payment system of the UOITC; the work satisfied all the objectives intended.

A Survey of Medical Image Analysis Based on Machine Learning Techniques

2023-02-17T18:49:50+00:00

Machine learning is a result of the availability and accessibility of a massive amount of data collected via sensors and the internet. The concept of machine learning demonstrates and spreads the fact that computers can improve themselves. Deep learning is causing a paradigm shift in medical image analysis. A medical image is a visual representation of the interior of a body, typically used for diagnostic or therapeutic purposes. Researchers and policymakers interested in healthcare outcomes should read this; this research provides an overview of machine learning at a high level. Computer vision is the field of using computer algorithms to understand and analyze visual data, and machine learning is a key tool for developing these algorithms. This review discovered that there are three varieties of machine learning strategies: supervised, unsupervised, and semi-supervised, and they seem to be gaining traction in risk assessment, disease prognosis, and image-based diagnosis, with increasing success. Convolutional neural networks (CNNs), k-means clustering, random forests, transductive learning, and support vector machines are among the most commonly used algorithms. Image analysis using CNN is the most effective method for medical imaging.

Building an ontology for diagnosing Sidr tree diseases

2023-02-17T18:49:57+00:00

Sidr trees are among the important trees in Iraq, especially in the southern regions of the country, as in Basra Governorate. The Sidr crop contributes a good share of the economy in many regions. In addition, it is used in various fields such as medicine. Various pathogens affect the Sidr tree due to many diseases, which cause serious problems that weaken or stop the production of the plant, and may eventually cause the plant to die. Therefore, we find that direct work, whether at the individual level of farmers or institutions specialized in agricultural prevention, for the development of solutions to detect and diagnose diseases quickly, with high accuracy, and recommend treatment for Sidr diseases is necessary and inevitable. In this work, we build an ontology to represent information about Sidr tree diseases. The proposal of this ontology is to support agricultural practices and systems geared towards helping farmers in the early prediction of diseases from their morphological symptoms. The ontology was developed under Protégé 5.5.0 using the Web Ontology Language (OWL) format and defined Competency Questions, DL-Query, and SPARQL queries. It includes 217 classes, 13 object properties, 6 data properties, and 1762 axioms. Experiments conducted through a data set showed the effectiveness of ontology in diagnosing Sidr tree diseases using one or more observations of symptoms provided by farmers. As a contribution to this work, it presents the first ontology to recover knowledge about the diseases of the Sidr tree and the possibility of using this ontology in designing easy-to-use computerized systems (relying on semantic web technologies) that help the farmer in diagnosing diseases and suggesting appropriate treatment quickly, accurately and at a lower cost.

The Hierarchical Classification for The Rituals of Hajj Using Ontology

2023-02-17T18:50:03+00:00

In our dynamic world, knowledge is linked to data and information that already exists, and knowledge management can be shared and linked. In a broader scope, it can be used to structure ontology. Using ontology helps users understand structure easier and faster. In recent years, there has been a growing interest in developing and building an ontology for many fields.

However, relatively few works related to the religious aspect were conducted, especially regarding the pilgrimage and its rituals. This research paper was proposed given the importance of this field in Islam and the knowledge and exchange of everything related to it. Therefore, the proposed field was represented in ontology by showing the relationships between the categories that make up this field, which was organized hierarchically. When the relationship is already defined, the structure of the ontology can be modeled in the field of knowledge (pilgrimage and its rituals), and an appropriate methodology has been used for this work, which we will explain later.

This paper proposes to perform a hierarchical classification of pilgrimage rituals using an ontology file generated using the Protégé tool for modeling the ontology structure. This ontology structure will help share knowledge about Hajj and its rituals.

Age Invariant Face Recognition Model Based on Convolution Neural Network (CNN)

2023-02-17T18:50:09+00:00

Building an intelligent system similar to the human perception system in face recognition is still an active area of research, despite the advancements in technologies and face recognition research carried out when age changes. Deep learning algorithms have outperformed conventional methods in with regard to accuracy and effectiveness of recognition a variety of difficulties, including position, expression, lighting, and aging. But aging is one of the problems that affects the face the most, as it plays a significant role which directly affects facial features, so we notice some people who are very difficult to distinguish and may not be known at all because of the strong change in their features. As a result, we researched deep learning techniques generally and the convolutional neural network (CNN) specifically. This strategy is employed by a number of significant stages: The first side, includes preparing the dataset related to the subject of the study, Isolate the data between training, validation and testing. As for the second part of the work, data preprocessing, such a data augmentation, Normalization, Face detection, and resizing. After then, begin a features extraction operation by the convolution neural network (CNN) that is suggested. After all that, the classification stage begins, which was done by using the (SoftMax) function, because we have approximately (570) classes. In the testing phase, we perform the task of checking the two images entered whether they belong to the same person or not. In this paper, adopted the (Age) and (FG-Net) datasets, Finally, the verification accuracy rate for the proposed system reached 98.7 % on the (Age) dataset, and reached 99.4 % on the (FG-Net) dataset.

New random version of stability via fixed point method

2023-02-17T18:50:15+00:00

We studied the stability of the cubic functional equation:

3 ß( +3 ƴ)-ß(3 + ƴ)=12 [ß( + ƴ)+ß( - ƴ)]+80 ß(ƴ)-48 ß( ). (1.1)

via fixed point method in random normed space (ȐṄ −space).

Build Network Intrusion Detection System based on combination of Fractal Density Peak Clustering and Artificial Neural Network

2023-03-07T07:25:59+00:00

Imbalanced data poses a serious problem in intrusion detection systems. In this article, we propose a network intrusion detection system based on fractal density peak clustering and an artificial neural network (FD-ANN). The proposed detection system consists of three parts: data clustering based on the density-peak clustering (DPC) method, using the fractal concept as a membership weight of all data to the cluster, and a neural network to classify the data. The DPC method uses categorization of the tare data into subgroups with strongly correlated attributes to reduce the size of the training data and the imbalance of the sample. Each subgroup has its neural network to train the data. Based on fractal membership weights, the output of all classifiers of the sub-neural networks is combined using the aggregation function. The benchmarks of this model are based on the data sets NSL-KDD and UNSW-NB15. The proposed solution outperforms other known classification approaches in terms of overall accuracy, recall, precision, and F1 score.

Hybrid Extend Particle Swarm Optimization (EPSO) model for Enhancing the performance of MANET Routing Protocols

2023-04-03T13:51:55+00:00

The routing protocols in MANETs are designed to provide efficient and reliable communication in a highly dynamic and resource-constrained environment. It is very efficient and requires low computational and memory resources compared to most routing protocols. Therefore, mobility and the number of nodes significantly impact the performance and reliability of routing protocols. This paper proposes a hybrid extended particle swarm optimization (EPSO) model to improve the performance of MANET routing protocols. It determines the optimal mobility and the number of hubs and nodes that satisfy the best possible version of MANET. MANET requires a robust routing algorithm that can adapt to a network that arbitrarily changes its topology at any time. The proposed model in the NS2 simulator proves the model's validity in improving the performance of MANET. The proposed model sets the general parameters of routing protocols and achieves high performance with fewer discarded packets and low delay when sending and receiving over MANET. The MANET sent 167 packets in the proposed model, and the number of discarded packets was less than 1%.

Deploying Facial Segmentation Landmarks for Deepfake Detection

2023-04-03T13:57:28+00:00

Deepfake is a type of artificial intelligence used to create convincing images, audio, and video hoaxes and it concerns celebrities and everyone because they are easy to manufacture. Deepfake are hard to recognize by people and current approaches, especially high-quality ones. As a defense against Deepfake techniques, various methods to detect Deepfake in images have been suggested. Most of them had limitations, like only working with one face in an image. The face has to be facing forward, with both eyes and the mouth open, depending on what part of the face they worked on. Other than that, a few focus on the impact of pre-processing steps on the detection accuracy of the models. This paper introduces a framework design focused on this aspect of the Deepfake detection task and proposes pre-processing steps to improve accuracy and close the gap between training and validation results with simple operations. Additionally, it differed from others by dealing with the positions of the face in various directions within the image, distinguishing the concerned face in an image containing multiple faces, and segmentation the face using facial landmarks points. All these were done using face detection, face box attributes, facial landmarks, and key points from the MediaPipe tool with the pre-trained model (DenseNet121). Lastly, the proposed model was evaluated using Deepfake Detection Challenge datasets, and after training for a few epochs, it achieved an accuracy of 97% in detecting the Deepfake

Computer Vision System For Backflip Motion Recognition in Gymnastics Based On Deep Learning

2023-04-03T14:02:01+00:00

Reliance on computer vision systems in the sports field is one of the very important topics, which are of high importance, especially in the arbitration process or evaluating the accuracy of the player’s performance of the movement. It is better to rely on computer vision systems that are more accurate in the arbitration process. In this article, a method was presented to distinguish one of the important movements of the gymnastics player, by relying on deep learning techniques. The dataset was built based on high-quality video clips found on YouTube for tournaments held from the period 2018-2022, due to the absence of The dataset available. This data was divided into three sections: 70% for training, 10% for validation, and 20% for testing. Two models of the convolutional neural network yolov7 and yolov5 were trained, and the results obtained after testing the results of the models show that the seventh version was the best , Recall, Precision and Mean Average Precision criteria were adopted to evaluate the performance of these technologies.

The Role of Artificial Intelligence in Medicine Applications

2023-04-03T14:05:38+00:00

The goal of research on artificial intelligence aims to make machines and software similar to human performance, so measuring the degree to which an artificial intelligence system can resemble human capabilities is used to determine the types of artificial intelligence. Thus, by comparing the machine with humans in terms of versatility and performance, it becomes possible to categorize artificial intelligence, with multiple types of artificial intelligence, where artificial intelligence that can perform human-like functions with equal levels of efficiency will be considered as a sophisticated type of artificial intelligence, while Artificial intelligence with limited functionality and performance is considered a simpler and less sophisticated type Based on this scale, and in general, artificial intelligence can be classified. Depending on the species classification of AI-enabled devices based on their similarity to the human brain, and their ability to "think" and possibly "feel" like humans. According to this classification system, there are four types of artificial intelligence systems: “interactive machines, limited memory machines, theory of mind, and self-aware artificial intelligence

A General Overview on the Categories of Image Features Extraction Techniques: A Survey

2023-04-03T14:14:05+00:00

In the image processing’s field and computer vision it’s important to represent the image by its information. Image information comes from the image’s features that extracted from it using feature detection/extraction techniques and features description. Features in computer vision define informative data. For human eye its perfect to extract information from raw image, but computer cannot recognize image information. This is why various feature extraction techniques have been presented and progressed rapidly. This paper presents a general overview of the feature extraction categories for image.

Automated Binary Classification of Diabetic Retinopathy by SWIN Transformer

2023-04-03T14:21:06+00:00

Diabetic retinopathy is a medical condition that affects the eyes and is caused by damage to the blood vessels in the retina (the light-sensitive part of the eye) due to high blood sugar levels in individuals with diabetes. This damage can lead to vision loss or even blindness. It is a common complication of diabetes and a leading cause of blindness in working-age adults. In this paper, to automatically classify images of the retina as having either diabetic retinopathy or not. The goal of this classification is to assist medical professionals in diagnosing diabetic retinopathy more accurately and efficiently, potentially improving patient outcomes. In this process, the Swin transformer model is trained on the APTOS dataset of retinal images and then used to automatically classify new images as either positive or negative for diabetic retinopathy. Used CLAHE and Gaussian, to improve the input image, and the model achieved a Test Accuracy of 96%, Sensitivity of 96%, F1 Score of 96% for Swin-T and Test Accuracy of 98% for Swin-B, Sensitivity of 98%, and F1 Score of 98%.

A Cryptosystem for Database Security Based on RC4 Algorithm

2023-04-28T16:44:42+00:00

Because of vulnerable threats and attacks against database during transmission from sender to receiver, which is one of the most global security concerns of network users, a lightweight cryptosystem using Rivest Cipher 4 (RC4) algorithm is proposed. This cryptosystem maintains data privacy by performing encryption of data in cipher form and transfers it over the network and again performing decryption to original data. Hens, ciphers represent encapsulating system for database tables

Principally g-radical Supplemented Modules

2023-02-17T18:49:34+00:00

In this article we present a proper generalization of the class of g-radical supplemented modules. This class termed by P-g-radical supplemented. We determined it is structure. Several of these modules' characterizations, properties, and instances are described.

Numerical Method For Solving Fuzzy Singular Perturbation Problems With Initial Condition

2023-02-23T21:08:21+00:00

In this paper, We present a modified approach that makes use of the neuro-fuzzy system to solve fuzzy singular perturbation problems for ODEs with IC. The name of this modified approach is the modified neuro-fuzzy system method (MNFS). The foundation of this novel approach is to swap off each x in the input vector training. set = , a first-order polynomial which will be as = , . By using MNFS, it is possible to train the neural network outside of the initial and last point range by choosing training points based on the open interval (a, b). By resolving a few numerical cases and comparing the results to those calculated using different numerical techniques, we demonstrate this improved a technique and how neural networks demonstrate yield answers with accurate and strong generalization. The suggested approach is illustrated with a number of instances.

Modification Fuzzy Artificial Neural Networks For Solving Fuzzy Singular Perturbation Problems With Boundary Condition

2023-02-23T21:18:19+00:00

Throughout this work through the using of a neuro-fuzzy system, we have developed a new technique. This updated approach is known neuro – fuzzy system method (MNFS). to develop a numerical method for resolving (FSPPs) for ordinary differential equations with BC. The activation function for hyperbolic tangents used to determine the hidden units' sigmoid function and the parameters of a fuzzy neural network and its formula is: .Standard training algorithms and analytical techniques were contrasted with the suggested strategy. Our research revealed the provided approach stands out for its excellent accuracy of the results, low error rate, and much faster speed than that of conventional methods. A number of examples are used to demonstrate the suggested strategy.

2-Semi-Bounded Linear Operators

2023-03-02T20:21:26+00:00

In this Article, we introduced a new definition of 2- semi bounded operator in 2- inner product space. Then, we investigate a new Space of bounded operators and proved it as vector space. After that we show this space as Banach space. Finally, we discussed some properties of this space.

Q_(P-)Continuous Multifunctions and Q_- Closed Multifunctions

2023-04-03T14:25:24+00:00

In this paper, by means of sets, we introduce we have provided some basic definitions that we need in the research in addition to the definition of, continuous multifunctions and investigate certain ramifications of continuous multifunctions, along with their several properties, characterizations and mutual relationships. Further we introduce new types of multifunctions, called multifunctions via open sets. The relationship between these multifunctions and continuous multifunction are studied .

Generalization Approximation Spaces Using Combined Edges Systems of a finite number of undirected graphs

2023-04-03T14:33:29+00:00

In this paper we will study approximate coefficients. New based on a finite family of Lower approximation and Upper approximation and we present a generalization of some concepts and definitions and boundary and we will also study the accuracy factor for this family

ODigraphic Topology On Directed Edges

2023-04-03T14:41:07+00:00

In this paper, we study the odigraphic topology for a directed edges of a digraph. We give some properties of this topology, in particular we prove that is an Alexandroff topology and when two digraphs are isomorphic, their odigraphic topologies will be homeomorphic. We give some properties matching digraphs and homeomorphic topology spaces. Finally, we investigate the connectedness of this topology and some relations between the connectedness of the digraph and the topology .

Solving Fractional Partial Differential Equations by Triple g-Transformation

2023-04-03T14:47:44+00:00

In this article, we use triple g-transformation for solving fractional partial differential equations. There are many studies about finding solutions of fractional partial differential equation by using many transformations like Laplace transform, Fourier transform and Elzaki transform. In this paper we use triple g-transformation because this transformation can be used to solve most of the fractional partial differential equations by choosing the appropriate functions .

A Certain Class of Analytic Functions Associated with Beta Negative Binomial Distribution Defined on Complex Hilbert Space

2023-04-03T14:52:39+00:00

In this work , we show and research a new class of univalent and analytic functions with negative coefficients linked to the beta negative binomial distribution on a complicated Hilbert space. We find fascinating geometric features such as the convex set, coefficient estimates, distortion and growth theorems, starlikeness and convexity radii, and describe the extreme points for functions in this class.

Normal-Compound Gamma priors with Count Data

2023-04-03T14:57:54+00:00

Count data models have become very common in several disciplines in recent years. Since these types of models can often be studied incorrectly using OLS methods, several solutions have been proposed to address this problem. One of these methods the normal-scale mixture method with different types of priors of the scale parameter. The importance of this method is to solve the issue of the bias-variance tradeoff by adding a local scale parameter to reduce the variance at the origin and reduce the bias at the tails. In this paper, a compound-gamma prior is placed for the scale parameter and the relevant Gibbs sampler is solved for posterior inference. The comparison of the performance of the proposed model with some other existing methods using both very sparse and low sparsity simulated data shows that the proposed model performs very well.

Some Generalizations of g-lifting Modules

2023-04-03T15:02:01+00:00

In this work we will attempt to define and investigate new classes of modules named -g-supplemented and -g-radical supplemented as a proper generalization of class of g-lifting modules and identify several distinct characterizations of these modules. Additionally, we'll attempt to explain the concepts of projective g-covers and g-semiperfect modules. It is shown that the two buildings of g-semiperfect and -g-supplemented modules are the same for the class of projective modules.

About e-gH modules

2023-04-03T15:21:33+00:00

This article introduced and explored the concept of the -gH module and its relation to many other module types.

On Sandwich Results of Meromorphic Multivalent Functions Defined by a New Hadamard Product Operator

2023-04-05T14:19:37+00:00

The goal of this research is to establish differential subordination and superordination findings for meromorphic multivalent functions defined by a new operator in a punctured open unit disk. We get a number of sandwich-type results.

On Sandwich Results of Meromorphic Univalent Functions Defined by New Hadamard Product Operator

2023-04-05T14:29:33+00:00

" In the present paper, we obtain differential subordination and superordination results for meromorphic univalent functions defined by a new Hadamard product operator in a punctured open unit disk. We get a number of sandwich-type results.

Third-Order Differential Subordination and Superordination Results for Analytic Univalent Functions Using Hadamard Product Operator

2023-04-11T09:19:00+00:00

In this paper, we aim to obtain some results of third-order of differential subordination and superordination with sandwich theorems for analytic univalent functions using the operator Some new results has been introduced.

I-Pre- Cauchy Triple sequences of Fuzzy Number and Double Orlicz functions

2023-04-11T18:06:06+00:00

The Cubic Rank Transmuted Gumbel Distribution

2023-04-07T20:57:56+00:00

A Cubic Rank Transmuted Gumbel distribution (CTGD) in this research is extend the work of cubic transmuted distribution families. CTGD improves the flexibility of transmuted distributions and allows for the modeling of more complex data. Its hazard rate function, moment-generating function, moments, quantile function, entropy and order statistics, are only a few of the key statistical characteristics that we examine. Finally, the Cubic Transmuted Gumbel Distribution is applied to three real datasets to test its applicability and evaluate how well estimate approaches function for the CTGD, Gumbel(G), and transmuted Gumbel (TG) distributions. The observed results demonstrated that, for the used data sets, CTGD provides a superior fit than G and TG distributions.