Computer Aided Brain Tumor Diagnosis using Coati Optimization Algorithm with Explainable Artificial Intelligence Approach

Wajdi

doi:https://doi.org/10.54216/FPA.170203

Fusion: Practice and Applications | 2025

Enhancing Cloud Computing Efficiency with Crocodile Optimization Algorithm: A Novel Approach to Distributed Workload and VM Management

Cloud computing has introduced itself as a mighty mechanism for delivering customers through the service model with on-demand, scalable, and instant access to computer resources. It will conduct effective load balancing and resource management, high importance so that the cloud system works with optimized performance and resource utilization. This gives a new strategy in load balancing and virtual machine (VM) control in cloud computing applied in the field using the Crocodile Optimization Algorithm (COA) for better performance. Inspired by crocodile hunting behaviors, the COA-based strategy is adopted to balance loads and manage VMs. This approach seeks to balance the number of the workload given to VMs with respect to the processing power of VMs and also the distribution of workload. It best uses resources in such a way that tasks are dynamically distributed to VMs in such a way that response time is at its minimum, and thus overall efficiency is enhanced in cloud computing. On the other hand, COA-based load balancing incorporates VM management techniques like migration and scaling to be adjustable in relation to the changing conditions of the workload. This allows dynamically adjusting the allocation of resources with respect to current demands, in such a way that assures optimal utilization of computational resources with high performance. The proposed approach was evaluated using simulations through CloudSim, one of the most adopted tools for simulating cloud computing. The COA effectively works are divided between the VM, which in turn will lead to better response time for the user request and improve cloud resource utilization. That is to mean, subsequent research would be some type of unique attempt in the area of load balancing and VM management in cloud computing, based on the Crocodile Optimization Algorithm. This approach improves efficient cloud computing through the balancing of load distribution, maximization of resource utilization, and lowering of response time.

groups

Ibrahim A. Ibrahim mail -

Warshine Barry mail -

Narek Badjajian mail

link https://doi.org/10.54216/FPA.170205

Volume & Issue

Vol. Volume 17 / Iss. Issue 2

Details open_in_new

Fusion: Practice and Applications | 2025

Securing Drug Traceability: Block chain-Enhanced Privacy Protection and Anti-Counterfeit Measures in Pharmaceutical Supply Chains

The pharmaceutical industry encounters numerous challenges in the management of medications and ensuring their authenticity, as well as safeguarding sensitive information within the supply chain. Maintaining the integrity of drug manufacturing processes, transaction records, and patient data from unauthorized access or tampering is crucial. Any breach in security could undermine trust throughout the entire supply chain.  To mitigate these concerns, a multi-layered approach is employed. Initially, data encryption using QR codes with Attribute-Based Encryption provides a foundation for securing information. This is followed by an innovative strategy that combines Red Panda Optimization (RPO) Algorithm and Group Teaching Optimization algorithms (GTOA) to optimize encryption key selection. Finally, Multi-Party Computation (MPC) protocols along with Shamir's Secret Sharing enhances overall security measures. These procedures ensure that only authorized individuals have access to critical information essential for identifying counterfeit products and maintain confidentiality through Secure MPC verification without compromising sensitive details.

groups

Abdulrahman Mohammed Alshehri mail -

Thamer Alhussain mail

link https://doi.org/10.54216/FPA.170206

Volume & Issue

Vol. Volume 17 / Iss. Issue 2

Details open_in_new

Fusion: Practice and Applications | 2025

Machine Learning and Deep Learning Approaches for Detecting DDoS Attacks in Cloud Environments

Distributed Denial of Service (DDoS) attacks pose a significant threat to cloud computing environments, necessitating advanced detection methods. This review examines the application of Machine Learning (ML) and Deep Learning (DL) techniques for DDoS detection in cloud settings, focusing on research from 2019 to 2024. It evaluates the effectiveness of various ML and DL approaches, including traditional algorithms, ensemble methods, and advanced neural network architectures, while critically analyzing commonly used datasets for their relevance and limitations in cloud-specific scenarios. Despite improvements in detection accuracy and efficiency, challenges such as outdated datasets, scalability issues, and the need for real-time adaptive learning persist. Future research should focus on developing cloud-specific datasets, advanced feature engineering, explainable AI, and cross-layer detection approaches, with potential exploration of emerging technologies like quantum machine learning.

groups

Muhammad Asif Khan mail -

Mohd Faizal Ab Razak mail -

Zafril Rizal Bin M Azmi mail -

Ahmad Firdaus mail -

Abdul Hafeez Nuhu mail -

Syed Shuja Hussain mail

link https://doi.org/10.54216/FPA.170207

Volume & Issue

Vol. Volume 17 / Iss. Issue 2

Details open_in_new

Fusion: Practice and Applications | 2025

Optimization of Federated Learning Communication Costs through the Implementation of Cheetah Optimization Algorithm

Recently, Federated Learning (FL) has promptly gained aggregate interest owing to its emphasis on the data privacy of the user. As a privacy-preserving distributed learning algorithm, FL enables multiple parties to construct machine learning (ML) algorithms without exposing sensitive information. The distributed computation of FL may lead to drawn-out learning and constrained communication processes, which necessitate client-server communication cost optimization. The two hyperparameters that have a considerable effect on the FL performance are the number of local training passes and the ratio of chosen clients. Owing to training preference across different applications, it is challenging for the FL practitioner to manually choose these hyperparameters. Even though FL has resolved the problem of collaboration without compromising privacy, it has a transmission overhead because of repetitive model updating during training. Various researchers have introduced transmission-effective FL techniques for addressing these issues, but sufficient solutions are still lacking in cases where parties are in charge of data features. Therefore, this study develops an Optimization of Federated Learning Communication Costs through the Implementation of the Cheetah Optimization Algorithm (OFLCC-COA) technique. The OFLCC-COA technique is mainly applied for effectually optimizing the communication process in the FL to minimize the data transmission cost with the guarantee of enhanced model accuracy. The OFLCC-COA technique enhances the robust performance in unsteady network environment via the transmission of score values instead of large weights. Besides, the OFLCC-COA technique improves the communication efficiency of the network by transforming the form of data that clients send to servers. The performance analysis of the OFLCC-COA model occurs utilizing different performance measures. The simulation outcomes indicated that the OFLCC-COA model obtains superior performances over other methods in terms of distinct metrics

groups

Khalid Alleihaibi mail

link https://doi.org/10.54216/FPA.170208

Volume & Issue

Vol. Volume 17 / Iss. Issue 2

Details open_in_new

Fusion: Practice and Applications | 2025

Enhancing Urban Connectivity: Dynamic Implementation and Integration of Multi-IRS Systems in Smart Cities

This is in preparation to stand out in urban connectivity to be used faster for Multi-Intelligent Reflecting Surfaces (Multi-IRS) in the latest thirst response. It will determine in advance the application of IRS technology for electromagnetic wave control, so that it is fine-tuned at full power to boost signal transmission and coverage across the urban areas in high-density population. It outlines flexible strategies on how to integrate the Multi-IRS system with both past and urban future establishments in a view of making connected connectivity. In reality, multi-IRS integrated with foundational smart city technologies such as IoT, 5G networks, AI, and others are nothing but a leap toward accomplishing unparalleled data flow and connectivity, both very essential for the modern urban ecosystem. Detailed case studies have demonstrated how multi-IRS systems can enable the breaking of traditional barriers in connectivity: more essentially, it can offer higher bandwidth, lower latency, and increased communication effectiveness. This development marks one of the serious steps under the concept of smart cities, where the data will be spreading and flowing without barriers between the multifarious urban systems and services. Lastly, the paper concludes with a future-looking view of urban connectivity underscored through continuous innovation and research of multi-IRS applications within the smart city landscape. The study points out the fact that dynamic IRS implementation creates an indispensable role in the pathway for upcoming development in smart city connectivity solutions, thus making a case for sustained collaborative efforts in research, policy formulating, and technological innovation for realizing the full potential of IRS technology in taming the connectivity challenges of contemporary urban settings. Performance comparison between a sequential beam search and a proposed model across varying Rician Factors, showing the proposed model's superior channel gain progression from -57 dB at 5 dB to -48 dB at 30 dB, outperforming the sequential method in environments with strong direct signals.

groups

Israa Ali Al-Neami mail -

Alza A. Mahmod mail -

Alaa H Ahmed mail -

Sergey Drominko mail -

Erina Kovachiskaya mail

link https://doi.org/10.54216/FPA.170209

Volume & Issue

Vol. Volume 17 / Iss. Issue 2

Details open_in_new

Fusion: Practice and Applications | 2025

A Comprehensive Survey on AlexNet improvements and fusion techniques

Machine- and deep-learning techniques have been used in numerous real-world applications. One of the famous deep-learning methodologies is the Deep Convolutional Neural Network. AlexNet is a well-known global deep convolutional neural network architecture. AlexNet significantly contributes to solving different classification problems in different applications based on deep learning. Therefore, it is necessary to continuously improve the model to enhance its performance. This survey study formally defined the AlexNet architecture, presented information on current improvement solutions, and reviewed applications based on AlexNet improvements. This work also presents a simple survey based on a fusion of AlexNet with different machine-learning techniques for recent research in biomedical applications. In the survey results for about 11 research papers for both improvement and fusion techniques of AlexNet, it was clear that the fusion was the superior one with 99.72, and the improved one was 99.7%. In the conclusion and discussion section, there was a comparison between the improved techniques and fusion techniques of AlexNet and a proposal for future work on AlexNet development.

groups

Bahaa S. Rabi mail -

Ayman S. Selmy mail -

Wael A. Mohamed mail

link https://doi.org/10.54216/FPA.170210

Volume & Issue

Vol. Volume 17 / Iss. Issue 2

Details open_in_new

Fusion: Practice and Applications | 2025

Enhancing Object Detection and Classification Using White Shark Optimization with Deep Learning on Remote Sensing Images

Remote sensing (RS) object detection is extensively applied in the fields of civilian and military. The important role of remote sensing is to identify objects like planes, ships, harbours airports, etc., and then it can attain position information and object classification. It is of considerable importance to use RS images for observing the densely organized and directional objects namely ships and cars parked in harbours and parking areas. The object detection (OD) process involves object localization and classification. Due to its wide coverage and longer shooting distance, Remote sensing images (RSIs) have hundreds of smaller objects and dense scenes. Deep learning (DL), in particular convolution neural network (CNN), has revolutionized OD in different fields. CNN is devised to automatically learn the hierarchical representation of data, which makes them fit for feature extraction. Hence, the study proposes a new white shark optimizer with DL-based object detection and classification on RSI (WSODL-ODCRSI) method. The purpose of the WSODL-ODCRSI model is to classify and detect the presence of the objects in the RSI. To accomplish this, the WSODL-ODCRSI model uses a modified single-shot multi-box detector (MSSD) for the OD process. The next stage of OD is the object classification process, which takes place with the use of the Elman Neural Network (ENN) algorithm. The WSO algorithm is exploited as a parameter-tuning model for improving the object classification results of the ENN approach. The stimulated study of the WSODL-ODCRSI algorithm has been established on the benchmark data set and the outcomes underlined the promising performance of the WSODL-ODCRSI model on the object process of classification

groups

Reda Salama mail

link https://doi.org/10.54216/FPA.170211

Volume & Issue

Vol. Volume 17 / Iss. Issue 2

Details open_in_new

Fusion: Practice and Applications | 2025

Analysis of Objective Functions for Ribonucleic Acid Multiple Sequence Alignment Fusion Based on Harmony Search Algorithm

Four kinds of smaller molecules known as ribonucleotide bases-adenine (A), cytosine (C), guanine (G), and uracil (U) combine to form the linear molecule known as ribonucleic acid (RNA). Aligning multiple sequences is a fundamental task in bioinformatics. This paper studies the correlation of different objective functions applying to RNA multiple sequence alignment (MSA) fusion generated by the Harmony search-based method. Experiments are performed on the BRAliBase dataset containing different numbers of test groups. The correlation of the alignment score and the quality obtained is compared against coffee, sum-of-pairs (SP), weight sum-of-pairs (WSP), NorMD, and MstatX. The results indicate that COFFEE and SP objective functions achieved a correlation coefficient (R²) of 0.96 and 0.92, respectively, when compared to the reference alignments, demonstrating their effectiveness in producing high-quality alignments. In addition, the sum-of-pairs takes less time than the COFFEE objective function for the same number of iterations on the same RNA benchmark.

groups

Mubarak Saif mail -

Rosni Abdullah mail -

Mohd. Adib Hj. Omar mail -

Abdulghani Ali Ahmed mail -

Nurul Aswa Omar mail -

Salama A. Mostafa mail

link https://doi.org/10.54216/FPA.170201

Volume & Issue

Vol. Volume 17 / Iss. Issue 2

Details open_in_new

Fusion: Practice and Applications | 2025

The Detection of Glaucoma in Fundus Images Based on Convolutional Neural Network

Glaucoma is a common disease affecting the human retina, primarily caused by elevated intraocular pressure. Early intervention is crucial to prevent damage to the affected organs, which could lead to their dysfunction. This paper focuses on enhance diagnosis accuracy of the system to determine if a patient is at risk of developing glaucoma. In this paper a novel convolutional neural network (CNN) designed, specifically for the detection of glaucoma in fundus images. This architecture optimizes for the unique characteristics of fundus imagery, enhancing detection accuracy, and also compiled a large and diverse dataset of fundus images, crucial for training and validating our CNN model. The dataset includes a significant number of images with detailed annotations, ensuring robust model training. In addition, implemented sophisticated image preprocessing methods to enhance the quality of the fundus images. These techniques, including noise reduction and contrast enhancement, significantly improve the input data quality for the CNN. The system operates in three stages. First, it preprocesses the image by cropping, enhancing, and resizing it to a consistent 256×256 pixels. Next, it employs an advanced feature extraction to analyses key features of the optic disc and optic cup in retinal images. Finally, the Soft-Max function classifies the images, identifying those with glaucoma and distinguishing them from normal eye samples. The model's performance was thoroughly evaluated using various metrics like accuracy, Sensitivity, specificity, and the area under the curve are metrics used to evaluate the performance of a diagnostic test. Sensitivity measures the test's ability to correctly identify positive cases, specificity assesses its accuracy in identifying negative cases, and the area under the curve indicates the overall effectiveness of the test across different thresholds. The results achieved by the proposed system were thoroughly analyzed, revealing a high accuracy rate in glaucoma classification, reaching 99%.

groups

Ali Yakoob Al-Sultan mail

link https://doi.org/10.54216/FPA.170202

Volume & Issue

Vol. Volume 17 / Iss. Issue 2

Details open_in_new

Fusion: Practice and Applications | 2025

Computer Aided Brain Tumor Diagnosis using Coati Optimization Algorithm with Explainable Artificial Intelligence Approach

Brain tumors (BT) are a difficult and dangerous medical condition, and the accurate and early analysis of these tumors is crucial for suitable treatment. Explainability in clinical image diagnosis role a vital play in the correct analysis and treatment of tumors that supports medical staff's optimum understanding of the image analysis performances rely upon deep methods. Artificial intelligence (AI), in certain deep neural networks (DNNs) has attained remarkable outcomes for clinical image analysis in many applications. However, the need for explainability of deep neural approaches has been assumed that major restriction before executing these approaches in medical practice. Explainable AI, or XAI, is a vital module in this context as it supports medical staff and patients in understanding the AI's decision-making model, enhancing trust and transparency. It leads to optimum patient care and performance but making sure that medical staff can make learned decisions depends on AI-driven insights. Therefore, this study develops a novel Computer-Aided Brain Tumor Diagnosis using Coati Optimization Algorithm with an Explainable Artificial Intelligence (CABTD-COAXAI) approach. The purpose of the CABTD-COAXAI technique is to exploit XAI and hyperparameter-tuned deep learning (DL) approaches for automated BT analysis. To accomplish this, the CABTD-COAXAI technique follows a Gaussian filtering (GF) based noise removal process. Besides, the CABTD-COAXAI technique utilizes the EfficientNetB7 methods for the feature extraction process. Additionally, the hyperparameter tuning of the EfficientNetB7 method is performed by the use of COA. Furthermore, the classification of the BT process can be performed by the usage of a convolutional autoencoder (CAE). Finally, the CABTD-COAXAI system combines the XAI method named LIME to effectively understand and explainability of the black-box model for automated BT diagnosis. The simulation result of the CABTD-COAXAI technique has been tested on a benchmark BT database. The extensive outcomes inferred that the CABTD-COAXAI method reaches superior performance over other models in terms of different measures

groups

Wajdi Alghamdi mail

link https://doi.org/10.54216/FPA.170203

Volume & Issue

Vol. Volume 17 / Iss. Issue 2

Details open_in_new