Al-Salam Journal for Engineering and Technology

Lower back pain is a common ailment that affects many people resulting from various spinal diseases such as disk bulge. Disc bulging, which refers to the narrowing of the intervertebral disc within the spinal canal, can cause lower back pain and lead to lumbar spine stenosis. Deep learning algorithms based on artificial intelligence are indispensable in the field of medicine, enhancing the precision of medical image diagnosis significantly and the ability to process massive amounts of data which contributes to reducing the workload on radiologists and doctors. Therefore, Deep learning techniques have become a more helpful tool to overcome this problem. For this purpose, this study employed the YOLO-v7, YOLOv8m object detection technique to build a model to detect lumbar spine disc discords using MRI data from 291 individuals suffering from lower back pain. The image data utilized for training the model were divided into three segments: 70% for training, 20% for validation, and 10% for testing, and validate the model results according to evaluation metrics. shows the optimal model validated externally utilizing new lumbar spine MRI images and assessment with the radiologist. YOLOv8m achieved a mean average in precision (93.7%), precision (90.5%), recall (79.2%), and F1-score (88.6%), accuracy (89.8%). A deep learning model demonstrated similar agreement to subspecialist radiologists in detecting and classifying lumbar spine stenosis on lumbar spine MRI. By selecting the most suitable YOLO model, doctors can significantly enhance their ability to detect lumbar spine stenosis at an early stage and effectively mitigate potential negative consequences for their patients.

In today's digital age where powerful communication media such as the Internet allow for efficient information exchange, copyright protection and authentication of digital content has become an important issue. Plain text is the most widely used means of exchanging information online, and it is important to verify the authenticity of the text. Very limited techniques are available for watermarking and authentication of Arabic text. This paper aims to develop a zero-watermark algorithm to protect the Arabic digital content from being tampering.
The algorithm creates an accurate zero watermark based on the characteristics of the content of the Arabic text itself. The watermark is determined by the frequency of appearance of prepositions and their specific locations (في، عن، من، على) in the text. The extraction algorithm used for extracting zero watermark and compared with the created one to prove the authenticity of the Arabic text. This method ensures that any change to the text will lead to a change in the extracted zero watermark, which will facilitate the detection process upon verification. Experimental results demonstrate the effectiveness of the algorithm in discovering text tampering (addition, deletion, and rephrasing), tested on nine different text samples with various lengths and attacks, the proposed approach is robust in detecting modifications to the text, even if they are minor, compared to the existing approach.

Soil heavy metal pollution is a global environmental issue that has gained significant public attention due to concerns about human health and agricultural safety, making it a critical area of research both nationally and internationally. Heavy metals, including cadmium, mercury, arsenic, lead, and chromium, are toxic to biological systems. These HMs enter the soil agro-ecosystem through natural processes from parent materials and anthropogenic activities, particularly from fossil fuel power plants (FFPP). Although HMs are naturally occurring components in the Earth crust, most environmental pollution and exposure are accumulated in soils which reflects the present and deserves continued attention. The review study examined the distribution and accumulation of HMs in Iraqi soil, the results of previous studies over long periods showed that the soil of Iraq was not contaminated with HMs in the last century, the level of HMs in the soil increased with the progress of time in various cities of Iraq accordingly of the increase in power demand and industrial actions dependent on burning fuel, result in soil pollution in adjacent areas of FFPP project. Pervious study results specify that the average value of chromium (361 µg/g), nickel (284 µg/g), cobalt (16.62 µg/g) for Al-Ramadi PP, and cadmium (12.27 µg/g) for Al Nasiriyah area. Furthermore zinc (191 µg/g), lead (131 µg/g), Copper (37 µg/g), for Al Haidariy FFPP. Likewise, research conducted on fly ash release from FFPP in central and southern Iraq indicated high levels of cadmium, zinc, iron, magnesium and copper that exceed international limits due to fuel combustion. These studies confirm the extent of HMs pollution in Iraq and impact on environmental quality and human health. Effective management of HMs pollution from fossil fuel power plants necessitates systematic identification of pollution hotspots and assessment of control measures.

Quantum computing does present a big threat to classic cryptography and hence endangers the security of Internet of Things devices. This paper is therefore concerned with proposing a Quantum-Resistant Homomorphic Encryption (QRHE) system tailored for Internet of Things (IoT) environments. The main view of this QRHE key system is basically protection against the quantum threat in the processing of information within Internet of Things network traffic. Aside from this, the system further allows the processing of data on encrypted information without prior decryption, which guarantees the confidentiality and integrity of the data processed. The lattice-based cryptography used in the system is based on the Learning With Errors (LWE) problem, which has already shown strength against classical and quantum attacks. In this paper, homomorphic encryption algorithm was introduced that allows both addition and multiplication between ciphertexts for the assurance of privacy during secure data aggregation and analysis. The experimental results demonstrated that even after several homomorphic operations, the proposed system maintained high accuracy of %98, proving its effectiveness in preserving data confidentiality and integrity. Although the computational cost for this proposed system was a little more compared to traditional methods, it still gave an all-rounded security solution suitable for Internet of Things applications in the quantum computing era.

Iris biometrics are considered the most accurate and reliable because of their uniqueness and immutability. One of the critical difficulties that require high accuracy in the identification process and quickness in differentiating. It is preferable to reduce dimensions while keeping higher-order precision. In this paper, a technique was proposed for extracting the features of the iris image as a biometric using Shar-Smell Optimization, which works on the region of interest of the iris image is specified using the Haugh transform, the unity of features required to fix some input parameters that are selected to control the result, as well as the use of Convex Hall in determining the area that surrounds the points designated by the Haugh transform.

Film cooling is an effective way for the blades to cool of an exceptionally powerful gas turbine. This process involves injecting a cooler fluid, typically air. The injected fluid forms a thin insulating layer or "film" that protecting the underlying material from thermal damage. However, due to the primary flow and film jet's interaction, a counter-rotating vortex pair is created, which causes severe jet-off and inadequate film coverage. Protrusion V-shaped and rectangular winglet vortex generators were employed In this research at the top place of the film hole to impede the counter-rotating vortex pair, in an effort to boost cooling's efficiency. Numerical simulations with Realizable k-ε were solved at a blowing ratio was between 0.5–2 and a 30° inclination angle. Results shows that vortex generators of both kinds can produce more anti-counter-rotating vortex pairs to be able to lessen the strength of the counter-rotating vortex pairs. The downwash vortices produced by the vortex generators lessen the detrimental effects of the counter-rotating vortex pair. Downwash vortices and counter-rotating vortex pair are engaged in a competitive mechanism, hence as the ratio of blowing rises, the vortex generators' favorable effects will diminish. So it was noted through this study that the best blowing ratio is (1.0). When the blowing ratio is 1.0, the results demonstrate improved film cooling performance for the flat plate. This was observed for both types of vortex generators. Specifically, the rectangular vortex generator showed this capability, with the average effectiveness of adiabatic film cooling surpassing the baseline case by 27.33%.

This study talked about importance of data protection during Internet communication and highlights the utilize of image encryption as a specialized method. Image encryptions contain the utilize of unique key values to hide and show messages within images, with algorithms that are difficult to decryption. This work focuses on a modified version of the Rivest-Shamir-Adleman (RSA) encryption system, which is compatible with grayscale and color images and is implemented in C#. Additionally, it combines Advanced Encryption Standard (AES) and cryptography techniques to enhance encryption protection. Decrypting a confused image contain complex computations with large seed numbers. This proposed addresses image encryption, presenting a higher level of security compared to the original RSA encryption scheme. This research proposed experts in information technology should consider utilizing the modified RSA encryption system to support security during image transmission.

Electrocardiogram (ECG) signals are particularly used in the diagnosis and supervision of different cardiovascular diseases. The accurate and efficient classification of ECG signals is of critical importance in clinical applications. FPGA-based systems have been identified to offer an efficient solution to the implementation of real-time ECG signal classification systems because of their parallel processing, reprogrammable nature, and low power consumption. Thus, this review paper aims to explore the existing ECG classification techniques with a focus on FPGA implementation. The review discussed several classification methods, including adaptive algorithms and neural networks, which have been optimized for arrhythmia detection. Notably, Neural network techniques like ANN, CNN, and spiking neural networks are preferable due to their ability to provide superior accuracy. For instance, Mathias et al. developed a high-precision neural network with an impressive accuracy of 99.82%. Similarly, Arona et al. deployed a DCNN on FPGA, achieving accuracies reaching up to 99.67%. Researchers widely used the MIT-BIH dataset to evaluate ECG classification techniques, This paper presents new trends and focuses on future research prospects in this field. Hence, the findings of the present review can help researchers and engineers in developing effective and efficient FPGA-based ECG monitoring and diagnostic systems for clinical and healthcare applications.

Cancer is a serious disease that leads to mortality if not exposed at a precocious phase. This is what makes it worrying, as no actual treatment has been found for this disease yet, and patients with the disease cannot be saved unless it is diagnosed early in the first and second stages. But, if it is discovered in the third and fourth stages, the patient has little chance of survival. This is why using machine learning is a beneficial technology to deal with these diseases to help in their early detection. Machine learning models effectively learn from a training dataset how to estimate entire processes. Many models are offered by machine learning to forecast cancer based on standard datasets gathered by healthcare websites, social media, and some other repositories. That is why there is an urgent need to apply machine learning algorithms to this dataset for early cancer detection in affected people. The essential goal of the review is to highlight and estimate the best approaches used and make it easier for other researchers to conduct relevant studies utilizing machine learning models on cancer. The survey indicates that the models are competitive and demonstrate the accuracy of the classifiers on the datasets they were trained on.

Ductility is a critical property in structural engineering, ensuring that beams can undergo significant deformation before failure, thereby giving plenty of notice before disastrous collapse. This study investigates the ductility properties of constructions that have been reinforced using FRP rods, which are increasingly popular due to their corrosion resistance, superior strength with low mass, and durability. Traditional steel reinforcement has well-documented ductility properties, but FRP bars, due to their brittle nature, pose challenges in achieving the desired ductility levels in structural applications. This research evaluates various factors influencing FRP-reinforced beams\' ductility, including the type of FRP material, the hybridization of FRP with other reinforcing materials, and the effect of utilizing fibres in the mixtures to enhance the mechanical characterstics of concrete. Studies have indicated that the ductility of beams can be enhanced using hybrid rebar systems, which integrate steel and fibre reinforced polymer. However, complex and expensive production methods limit their practical application. Using steel bars with FRP bars can significantly incresese seriviceability requiremts such as crack width and deflection, but they also lower corrosion resistance, especially in aggressive environments. The beams\' overall ductile behavior is primarily determined by the concrete\'s characteristics. Fibres greatly increase the mechanical characteristics, toughness, and ductility of the concrete mix, strengthening the bond between bars and the concrete and improving the overall performance of the beam.

This study introduces a novel optimization framework that assesses and enhances deep learning algorithm performance across autonomous car operating systems. The framework generates synthetic performance measures, including inference time, memory use, CPU/GPU utilization, and accuracy, to evaluate algorithm performance. By employing the Mountain Gazelle Optimizer (MGO), the study identifies the best deep learning algorithm and operating system setup for accuracy and resource efficiency. The proposed methodology normalizes performance indicators, defines a fitness function to assist optimization, and then iterates through numerous configurations to discover the optimum option. Extensive trials and scenario comparisons validate the effectiveness of our approach. Computational efficiency and accuracy improved significantly, revealing the ideal autonomous car system performance combinations. This study not only enhances deep learning optimization but also provides practical instructions for building robust autonomous car systems in varied operating contexts, thereby informing the development of future autonomous vehicles and offering actionable insights for developers and researchers in the field.

Deep learning research has actively focused on object detection due to its importance for applications such as image and video interpretation. Object detection is an important issue in computer vision and has close-related applications such as surveillance and autonomous vehicles. This paper explores the use of You Only Look Once (YOLO), a state-of-the-art deep learning framework, to detect objects in animal images. As we all know, the YOLO model is known for its high speed and high accuracy, and it has been applied to applications that require real-time processing. In order to optimize the YOLO model for correctly classifying among the images of animals in the presence of people and images of just animals who are happy, sad and excited, images of cats and dogs in three states were made to the pre-trained CNN. From the experimental data, it can be confirmed that there some improvements of using more accurate YOLO versions for recognizing animal emotions, making the accuracy from 70% to 96%. The model was able to achieve a mean Average Precision (mAP) of 91%. The results highlight that the model is well positioned to improve urban safety and security through a highly effective approach to animal detection.

AQM is used to meet targets for congestion control and low delay, high throughput in TCP/IP networks. But methods developed for AQM like Random Early Detection (RED) work strictly on the control parameters pre-set on them and thus may not respond very well to changing network conditions. Thus, this paper presents a composite AQM model using DRL based on DQN, and the ability to learn independently regarding the AQM weight parameter of the queue. The fact that DRL is adaptive means the effectiveness of the proposed system is also assured. As it is observed in implementing traditional model-based approach, the stability and performance degrade when tested in different network conditions; however, DRL’s ability to learn independently enables ML to solve network congestion as it happens. Consequently, more stability is achieved, the delay is lesser, more bandwidth is used and the overall packet drop rate is low; the proposed DRL-RED model is ideal for dynamic network environments. The proposed DRL-RED model is compared with the regular RED algorithm for both low density and high-density networks. This proposed model has achieved sustained throughput of up to 49.9 Mbps with 0.949 % reduction on delay and very low PLR of 8.38043%. From the comparative analysis, it is clear that the employment of DRL with RED improves the stock of network throughput, the reduction on packet drop frequency, and the general delay in network situations. There are two main disadvantages of this approach: first, it cannot reach the heavy-traffic, the problem partly solved by model-based approach; second, the values of the congestion-control parameters cannot be reset, an issue eradicated by DRL as a result of its inherent adaptiveness. Consequently, new stability and increased performance can be achieved under various network conditions.

This study examined the fractional boundary value issue at flexible derivatives, focusing on establishing the existence of solutions and uniqueness. We introduce conditions that advance our understanding of this complex mathematical domain by capitalizing on the innovative framework of contraction principles. Moreover, the versatility of the proposed method is emphasized by its effectiveness in dealing with a wide set for compatible fractional differential equations characterized by diverse boundary conditions.

Tomato disease classification is important for agricultural productivity and food security, yet achieving high accuracy stays challenging due to the complexity of disease symptoms. This study proposed a model classification utilizing DenseNet121 combined with an Autoencoder for feature extraction and Simple neural network (SNN) for classifier. The dataset contains 10 classes of tomato diseases. Experimental results shows that the proposed approach achieved a high accuracy of 99%, outperforming the performance of several approaches. The integration of the Autoencoder enhances feature extraction and dimensionality reduction, important for improved classification outcomes. This study highlights the efficacy of the proposed work in achieving state-of-the-art accuracy in tomato disease detection. Future work may focus on refining the model using advanced augmentation techniques and expanding the dataset to enhance its applicability across diverse agricultural conditions.

The increasing growth of Information and Communication Technology has influenced rapid changes in the method of data transmission and storage, especially through the Internet. These rapid exchanges and storage of large volumes of data have also brought in newer and unexpected challenges concerning security. Consequently, the protection of sensitive information against unauthorized access has emerged as a major concern for sectors such as finance, healthcare, government, and personal data management. With time, cryptographic techniques have emerged as the cardinal solutions that can keep data safe from breaches or cyber-attacks. Cryptography offers various techniques in encoding data to prevent unauthorized access to data and protect confidentiality, integrity, and authenticity. Chaotic encryption systems are one of the innovative approaches to cryptography to which much attention has been turned by the research community over time. Chaotic encryption systems are based on the principles of chaos theory and exhibit important features that include high sensitivity to initial conditions, unpredictable behavior, and complex dynamics. These properties are particularly helpful in encryption, as they allow for complex transforms of information, were, without the proper keys, it would be highly impossible for unauthorized entities to decipher encrypted content. Chaotic encryption has especially shown promising applications in image encryption, where traditional cryptography methods often cannot work properly due to the large data size and structure of the visual information. The principle of image encryption using chaotic maps then consists in using mathematical functions with inherent features of randomness and sensitivity, which introduce extreme complexity into the encryption images, resulting in a visually unrecognizable and resistant characteristic to cryptanalysis. Some chaotic systems such as the Logistic Map, Lorenz System, and Henon Map have been used to securely encrypt an image by scrambling its pixels and changing their intensities according to initial chaotic conditions. This paper reviews the efficacy and potential of chaotic encryption systems in enhancing the security of data, and more importantly, image data, through reviewing some basic principles of chaos theory, benefits, and limitations of different chaotic maps, and discussing some recent chaotic encryption methods.

Cement is a crucial engineering material, and the inclusion of some other substances can alter the characteristics of concrete. Due to the growing tendency to use cement more extensively, it has become imperative to utilize waste resources in order to manufacture environmentally friendly mortar or concrete. Due to the increasing need for eco-friendlier cementitious products, it is becoming increasingly important to assess the pozzolan activity index of prospective materials that can be used as substitutes for cement. The purpose of this research is to present a study that was carried out to evaluate the impact of castable silica waste (CSW) on the development of mortar strength, as well as the optimal usage of mortar CSW and the best substitution ratio in the creation of sustainable mortar. CSW, at three different weight percentages (10%, 20%, 30%), was used as a partial replacement for cement and added superplasticizer SP. A normal mortar using Ordinary Portland cement OPC was constructed to investigate the strength activity index. Cubic mortar samples were fabricated and examined at 7days and 28days. The strength of tests generally increases as the amount of castable silica waste CSW increases up to a certain point. Beyond this point, however, the strength values start to decline with the further addition of CSW. Among the four types of CSW mortars, the most effective amount of cement substitute is around 10%. This is higher than the other green mortars since increasing the amount of CSW decreases compressive strength. The primary objective of this research is to mitigate the carbon dioxide emissions generated by the cement industry and decrease environmentally detrimental waste by utilizing it as a partial substitute for cement.

There is an urgent need for precise and effective diagnosis techniques since thyroid diseases are becoming more common and have a major negative influence on public health. Conventional diagnostic methods frequently lack speed and accuracy, which causes therapy delays and unfavorable patient outcomes. The purpose of this study is to improve the predicted accuracy of thyroid illness detection by utilizing ensemble machine learning techniques. The dataset was preprocessed to ensure cleanliness and format compatibility with machine learning algorithms. Four classifiers were used to evaluate their predictive capabilities: Bagging Classifier, Support Vector Machine (SVM), AdaBoost, and Gaussian Naive Bayes. Bagging Classifier, utilizing 50 Decision Tree estimators, emerged as the most effective model. Bagging achieved the highest accuracy (99.87%), followed closely by AdaBoost (98.87%). SVM and Naïve Bayes performed comparatively lower, with accuracy scores of 94.58% and 93.69%, respectively. These findings highlight the effectiveness of ensemble methods for accurate and reliable thyroid disease prediction. These advancements could play a crucial role in developing automated tools for early detection and monitoring of thyroid disorders, ultimately improving patient outcomes and streamlining healthcare processes.

Optimization is a very important step in many automated systems in different sectors because minimizing the search space to find the best solution and hence minimizing the time required by any automated system. This paper implements and evaluates Particle Swarm Optimization (PSO) on four benchmark optimization functions: Rastrigin, Sphere, Rosenbrock, and Ackley by selecting and tuning parameter and enhancing algorithm performance in several optimization circumstances. The PSO algorithm\\\\\\\\\\\\\\\\'s performance is assessed based on the best solution, computational efficiency, and runtime to enhance theoretical knowledge of how the PSO algorithm interacts with mathematical landscapes by applying it to diverse scalar functions. The analyzing process uncovered the points of strength and weaknesses of the PSO algorithm to enhance the diverse applications. By comparing a specific swarm method and its applications with collection of functions, the study advances the mathematical understanding of the algorithm. The outcomes demonstrate that the PSO algorithm can effectively navigate complex search spaces and find optimal solutions for various optimization problems and the obtained result was fairly good by achieving fast speed up to 0.123 second.

Blockchain has revolutionized cryptocurrency since the advent of Bitcoin. Due to its decentralized nature, transparency, security measures, and ability to conduct transactions between untrusted parties, blockchain has received extensive attention recently. Consensus algorithms manage the blockchain and describe how peers achieve data consistency and integration. However, other hurdles persist for blockchain systems, including scalability and energy consumption, and they require to be overcome. The paper introduces a comprehensive overview of distributed ledger technologies (DLTs) with a deeper understanding of the blockchain. Moreover, we conduct a comparative analysis of the most widespread consensus mechanisms using various metrics. And briefly list potential threats, applications across several fields, and possible future directions.