Al-Salam Journal for Engineering and Technology

Malware or malicious applications can cause catastrophic damage to not only computer systems but
also data centers, web, and mobile applications from various industries; the Ministry of Interior, in particular, is the
most important educational institution because they are more vulnerable to security breaches. Keeping stakeholder
data safe from unwanted actors is a big concern that brings us to the concept of malware detection and prevention.
Deep learning and data mining using artificial intelligence (AI) can be an efficient approach for developing antimalware systems. Following suit, this study gave a thorough examination of malware detection methodologies and
procedures. Initially, we attempted to provide a comprehensive description of malware, artificial intelligence, and
data mining, as well as a listing of these technologies. The suggested system was described (whether this data is
files, photographs, videos, or import limitations and is processed and identified by mining and deep learning data,
and the system was trained on data). So far, our findings suggest that artificial intelligence and data mining can be
used to construct anti-malware systems to detect and prevent malware assaults or security threats in software
applications geared toward technological wonderland and its real-world application in the Ministry of Interior. To
conclude, we outline dozens of possibilities for overcoming the observed restrictions and intend to expressly
continue our efforts toward significant advancements in malware detection and prevention by implementing this
proposal. We give a detailed look at the current ways to find malware, their flaws, and ways to make them more
effective. We also explain how we're working on integrating the system. Our study shows that adopting future
approaches to developing malware detection applications should provide significant advantages. Understanding
this structure should help researchers do more research on malware detection and prevention using AI and data
mining.

Predicting heart attack possibility is a crucial step in saving human life because it is one of the leading
causes of death. How improve and/or achieve as accurate as possible prediction value is a challenging task. Though
Deep Learning networks, such as Recurrent Neural Networks (RNNs) and Long Short-Term Memory networks
(LSTMs), have been widely used to predict medical events, the issue of providing perfect prediction outcomes is still
progressing. The training data insufficiency is a major hindrance to these network's performance. Accordingly, to
overcome that issue, this research develops a method for heart attack prediction by using the Conditional Tabular
Generative Adversarial Network (CTGAN) model. By anticipating and warning the patient that he may be having a
heart attack, he to take the appropriate preventative steps, the proposed method in this research can help to reduce
deaths from heart attacks and preserve patients' lives. The suggested method uses the CTGAN model to expand the
patient's laboratory test results to build a synthetic trained database. Then, the RNN and LSTM are trained on the
generated dataset to enhance the prediction accuracy, and both RNN and LSTM are evaluated before and after the
database expansion. The experimental results show that the accuracy of RNN and LSTM is increased to 100% and
99% from 80% and 65%, respectively and the precision of RNN and LSTM is increased to 100% for each of them
from 68% and 0, respectively. Finally, sensitivity(recall) increased for RNN and LSTM from 77% and 0 to 100% and
98%, respectively.

In the last decade, the number of digital images has increased dramatically. Noise is unwanted
particles or signals contaminating the image during the captured image and transmission. Image noise reduces the
image quality and increases the processing failure ratio. It is highly recommended to remove the noise, and before
removing the noise, we have to know the type of noise, which highly assists in suggesting the proper de-noise
algorithm. This study introduces a method to effectively detect and recognize image noise of various types
(Gaussian, lognormal, Rayleigh, Salt & Pepper, and Speckle). The proposed model consists of two stages: the first
stage is detecting the noise in an image using Convolutional Neural Network. The second stage classifies the noisy
images into one of five types of noise using a new method based on a combination of deep wavelet machine
learning classifiers, we select five machine learning classifiers (support vector machine, decision tree, random
forest, logistic regression, and K-nearest neighbor) to choose the more efficient classifier ultimately. The
combination of wavelet with machine learning, specifically SVM, can highly enhance the results, where the
accuracy was (91.30 %) through many experiments conducted to build a sturdy classification model.

In this work, an overview of implementing machine learning (ML) models in antenna design and
optimisation has been proposed. This includes deep learning on ML structure, categories, and frameworks to obtain
useful and general insights about methods of predicting, collecting, and analysing high throughput fast data using
ML techniques. An in-depth overview on the various published research works related to designing and optimising
of antennas using ML is proposed, including the different ML- techniques and algorithms that have been used to
generate antenna parameters such as S-parameters, radiation pattern, and gain values. However, the designing of
modern antennae is still complicated regarding structure, variables, and environmental factors. Moreover, the cost
of time and computational resources are unavoidable and unacceptable for most users. To address these challenges,
ML methods-based antennas have been developed and applied to improve the reduction in the efficiency and
accuracy of antenna modelling. This can be involved methods to rain models on data that can be utilised to predict
the antenna performance for a given set of antenna design variables. This work summarises the developed and
applied MLs that have been proposed to improve the efficiency and accuracy of antenna modelling.

Security has become one of the main tasks to maintain the safety of transmitted or stored
information. Text encryption is one of the essential tools for text hiding. On the other hand, steganography coding
is an effective tool to increase the security. This paper present's a proposed security which combine with a hiding
technique for an important text with a selected audio. The encryption file hiding by phase coding in compressed
audio. Such procedure aims to increase security and reduce overall transmitted data. As a result, the hiding and
showing processing may affect the selected audio and lose some spectral data. To address this problem, an
enhancement based on the Wiener filter is deployed to re-extract the original audio after decompression in the
received file. The results, show that high security with achieved by obtaining the hided text and complete audio
spectral data of used audio and proposed system achieved an improvement in encryption, compression, and
masking at the same time.

Multiple-input multiple-output (MIMO) antenna is a technology that uses multiple antennas at both
the transmitter and receiver to improve the performance of wireless communication systems. One of the challenges
in designing MIMO antennas is to reduce the complexity of the antenna array, while still maintaining good
performance. One way to reduce complexity is to use shared antennas. Shared antennas are antennas that are used
by multiple elements of the MIMO array. This can reduce the number of required antennas and simplify the design
of the antenna array. The B-shape of the MIMO antenna by using CST program can also be used to reduce
complexity. For example, hexagonal MIMO antennas have been shown to have good performance and can be
implemented with a simple design. Additionally, the use of defected ground planes (DGPs) can be used to improve
the isolation between the elements of a MIMO antenna array, which can also reduce complexity. The design of
MIMO antennas is a complex and challenging task. However, by using shared antennas and other design
techniques and AI, it is possible to reduce the complexity of MIMO antennas while still maintaining good
performance.

This danger can undoubtedly be eliminated using cryptography and steganography. And Combining
encryption with steganography can assist in achieving high levels of data security, making this approach s uperior
to using either of these techniques alone to send data across an unreliable route that is open to hacking. Vis ible
steganography is one of the most secure steganography techniques. When the data text is ins erted, the image\'s
color frequency may vary slightly, which would be highly evident to anyone. We suggest levels of data security to
get around the image\'s apparent behavior, where the language of the data is first transformed into an unintelligible
cipher. An additional degree of protection is added by incorporating the cipher into an encrypted picture file before
dividing it into shares. As a result, the ideas of steganography and cryptography are both applied to offer two levels
of security and then a visual cryptography system is used to partition the picture into s hares s o that it may be
transferred over a network channel.

In the context of the Internet of Things (IoT), lightweight steganography provides a revolutionary
combination of technology and security, where data concealment meets the efficiency requirements of IoT devices.
Lightweight steganography, as opposed to conventional steganographic methods, focuses on concealing
information inside digital content while using the least amount of computer resources and energy. Secure data
transfer is essential in the IoT world because linked devices may communicate with one another without
interruption. IoT devices may communicate private data discreetly while conserving system resources, thanks to
the elegant approach offered by lightweight steganography. This novel method makes use of complex algorithms
that gently change data packets, turning them into bearers of hidden information without raising any red flags. The
secrecy of IoT ecosystems is strengthened by lightweight steganography's easy integration of covert
communication channels. In addition to improving data security, this technology also optimizes bandwidth usage
and increases device battery life. A future when linked devices may transmit information safely, effectively, and
surreptitiously is predicted as the IoT environment develops. This would usher in a period of unmatched data
security and resource optimization.

The problems such as evolution and withering of population, immersion of glucose by the body,
escalation of epidemics and reversal of gross domestic product (GDP) over time, Law of heating or cooling given
by Newton, radioactive disintegration law, and velocity of an object which is falling vertically downwards under
the operation of gravity pull, in physical or basic sciences, are delineated by differential equations. These problems
delineated by differential equations are generally solved by the calculus method which requires complicated
computations. In the present article, an advanced integral transform-Rohit transform (RT) is conferred for solving
the problems delineated by differential equations in physical or basic sciences. The results come by confirming that
the RT is a simple and more effective scientific tool for dealing with such problems delineated by differential
equations in physical or basic sciences than the ordinary calculus method.

Power plants that employ turbine blades to generate electricity usually need them to have certain
qualities, like high strength, fatigue and corrosion resistance, and temperature tolerance. Super alloys and ceramic
composites are common materials used in their construction. Defects or imperfections that might impair the
performance and lifetime of turbine blades are a typical issue in their production. Casting flaws, material
inclusions, and inadequate cooling during manufacturing are a few examples of these faults. Power plants use strict
inspection procedures and quality control measures to reduce these problems and guarantee the dependability of
their turbine blades. Improvements in material composition and design are usually required when changing the
materials used in turbine blades to boost their effectiveness and performance. Depending on the particular use and
intended result, turbine blades can undergo a variety of alterations. Advanced alloy material modifications,
coatings, ceramic matrix composites (CMCs), airfoil design optimization, cooling technologies, and tip
modifications are a few examples of typical modifications. It's important to note that the specific modifications
applied to turbine blades can vary widely depending on the type of turbine (gas, steam, wind, etc.), the operating
conditions, and the goals of the modification.

The research progress of numerical simulation of parabolic trough solar collector was introduced.
Especially the numerical simulation studies of the internal flow field in the collector tube and the external flow
field of the concentrator were reviewed. In the study of the internal flow field in the collector tube, the type of heat
transfer fluids and the characteristics of optical concentration have a significant effect on the heat collection
performance and thermal stress distribution, especially in the water/steam medium heat collection loop. The unique
gas-liquid two phase flow superposition of the non-uniform heat flux distribution outside the tube may lead to
serious thermal stress bending deformation of the collector tube. In the study of the external flow field of the
concentrator, due to the high actual wind speed and the low structural strength of the ultra-thin lens, the
concentrator is subjected to wind load deformation, resulting in the loss of optical efficiency, and even leading to
the failure of the parabolic trough collector structure, which directly affects the normal operation of the whole
collector field.

The volume of internet transactions has rapidly increased in recent years. E-commerce and egovernance have both seen significant development in recent years. This has led to a rise in the number of persons
adopting online payment options. The number of transactions that take place every day has increased exponentially
as a result of this. The frequency of online scams has also increased as a result of the rise in online transactions. It
is becoming more and more important to identify these fraudulent transactions as soon as possible in order to take
the necessary measures and minimize any damages brought on by the fraud. In this study, ML models are proposed
that might leverage previously known data and attempt to anticipate frauds using knowledge gained from the
earlier data. Fraudulent actions often pose a danger to digital payment systems. Customers may avoid financial loss
by having fraud transactions caught during money transfers. This article focuses on mobile-based money transfers
for fraud detection. This research proposes a DL architecture for monitoring and identifying fraudulent activity.
Deceptive transactions are found by implementing and using a RNN on a synthetic financial dataset produced by
PaySim. The suggested technique has 99.87% accuracy, an F1-Score of 0.99for detecting illegitimate transactions.

Cyberspace has evolved into a vital resource and dynamic hub for modern living as a result of a
rising reliance on information, technology, and communication. As a result, cyber security concerns are a
worldwide phenomenon with disastrous effects. Because of its worldwide connectivity and data explosion,
cyberspace is complicated and unpredictable, and as cyber infrastructures get more intricate and dynamic, so does
the threat surface. Cyberspace management, or securing and assuring security, calls for the use of sophisticated
complex systems. Natural tendencies that facilitate adaptability for survival have been generated by nature through
evolution in complex systems, including animal and plant life. By using them in cyber security, predation -
avoidance and anti-predation strategies used by non-extinct prey could be exploited or adopted as mechanisms for
adaptability. An overview of the existing situation of is provided in this chapter. With the explosion of data
generation, finding optimal solutions to data-driven issues is becoming increasingly difficult, if not impossible. It is
becoming increasingly clear that the use of intelligent bio-inspired algorithms is required for addressing highly
complex problems and providing working solutions in a timely manner, especially when dealing with dynamic
problem definitions, fluctuating constraints, incomplete or imperfect information, and limited computation
capacity. As a result, more and more intelligent algorithms are being investigated for solving various complex
issues.

This paper presents a numerical approach to solve the 2-dimensional reaction-diffusion problem, a
crucial model in physics and chemistry, with applications ranging from pattern formation to material science.
Focusing on addressing a stationary linear elliptic problem within a rectangular domain, boundary conditions are
determined through a finite-difference formulation. The Conjugate-Gradient Method is employed for the numerical
solution, facilitating efficient computation. Key findings are elucidated: Firstly, the grid size for the symmetric
matrix A is intricately linked to a bijective function, enabling the transition of indices to grid points. Notably, the
solution to this elliptic problem exhibits a concave-up profile. Secondly, various solvers such as the Conjugate
Gradient, Gauss-Seidel, and Jacobi techniques are viable, with the Conjugate Gradient method chosen for its
superior accuracy, especially when considering computational efficiency. Moreover, the relationship between grid
size and solution accuracy is explored, revealing a proportional dependence. Refinement of the grid leads to
increased iteration counts but reduced implementation time, owing to the linearity of the function . The
convergence criterion ensures high accuracy in solutions, as demonstrated in the provided figures.