Prince Mohammad bin Fahd University

Unmanned aerial vehicles (UAVs) have enabled numerous inventive solutions to multiple problems, considerably facilitating our daily lives; however, UAVs frequently rely on an open wireless channel for communication, making them susceptible to cyber-physical threats. Also, UAVs cannot execute complicated cryptographic algorithms due to their limited onboard computing capabilities. Balancing high-security levels and minimum computation costs is imperative when developing a security solution for UAVs. Consequently, several proxy signature schemes have been proposed in the literature to fulfil these requirements. Nevertheless, many of these solutions face the issue of high computation costs, and some exhibit security vulnerabilities that could not be more feasible options for UAV communication. Considering these constraints in mind, in this article, we introduce an improvised certificate-based proxy signature scheme (ICPS), which leverages the concept of hyperelliptic curve cryptography (HECC) to meet the security and efficiency requirements of UAV networks. The proposed ICPS scheme offers a range of notable features, including its ability to address key escrow and secret key distribution issues. The proposed ICPS scheme's security hardness has been evaluated using the widely known security tool, the random oracle model (ROM), proving its resilience against known and unknown cybersecurity threats. Finally, this study conducts a performance comparison of the proposed scheme against existing schemes, emphasizing its outstanding cost-efficiency. Notably, the computation cost is measured at 5.3536 ms and the communication cost at 1120 bits, substantially lower than relevant existing schemes.

The study makes use of systematic literature review (SLR) to examine how industry innovations can support sustainable manufacturing. The results show that these technologies greatly improve manufacturing sustainability, even though previous studies have tended to focus more on broad ideas than on particular shop floor activities and planning. The study emphasizes the quick development of a service-oriented, network-based manufacturing paradigm and points out a vacuum in the literature with respect to in-depth assessments of these fields. This study lays the groundwork for future research by providing insights into the role and convenience of Industry technologies in diverse production operations. These studies can then build comprehensive frameworks that integrate these technologies to attain sustainability in both small and large enterprises. The report highlights the significance of lean production and the contributions of AI and machine learning to the advancement of manufacturing sustainability. It also identifies important research obstacles and suggests future research areas.

To prevent water scarcity, wastewater must be discharged to the surface or groundwater after being treated. Another method is to reuse wastewater in some areas after treatment and evaluate it as much as possible. In this study, it is aimed to recover and reuse the caustic (sodium hydroxide, NaOH) used in the recycling of plastic bottles from polyethylene terephthalate (PET) washing wastewater. Chemical substances used in the industry will be significantly reduced with chemical recovery from wastewater. Ultrafiltration (UP150) and nanofiltration (NP010 and NP030) membranes were used for this purpose in our study. Before using nanofiltration membranes, pre-treatment was performed with coagulation-flocculation process to reduce the pollutant accumulation on the membranes. Different coagulants and flocculants were used to find suitable coagulants and flocculants in pre-treatment. The pre-treated wastewater using aluminum oxide, which supplied the highest chemical oxygen demand (COD) removal (76.0%), was used in a dead-end filtration system to be filtered through NP010 and NP030 membranes at different pressures (10–30 bar). In the same filtration system, raw wastewater was filtered through a UP150 membrane. Among these treatment scenarios, the best method that could remove pollutants and provide NaOH recovery was selected. After each treatment, pH, conductivity, COD, and NaOH analyses were performed. The maximum NaOH recovery (98.6%) was obtained with the UP150 membrane at 5 bar.

Sustainable management of textile industrial wastewater is one of the severe challenges in the current regime. It has been reported that each year huge amount of textile industry discharge especially the dye released into the environment without pre-treatment that adversely affect the human health and plant productivity. In the present study, different bacterial isolates had been isolated from the industrial effluents and investigated for their bioremediation potential against the malachite green (MG) dye, a major pollutant of textile industries. The biochemical and molecular characterization of the bacterial strain showed the resemblance of most potent strain ED24 as Pseudomonas aeruginosa, which showed effective bioremediation potential against the MG dye. During response surface analysis (RSM), best MG degradation conditions have been observed at pH 7.0, 37 °C, 48 h, and 200 mg/L dye concentration, with highest degradation efficiency of 96.56 ± 0.8622 percent. Subsequently, supplementing various carbon and nitrogen sources increases MG decolorization by 1 to 2%, with beef extract (97.23%), sodium nitrate (97.46%), and maltose (98.67%). FT-IR results revealed the disappearance of distinct peaks, namely, 3328.275 cm⁻¹, 2102.842 cm⁻¹, 1101.140 cm⁻¹, and 559.04 cm⁻¹ from MG, and the formation of major intermediate compounds like leucomalachite green, benzoic acid, diacetamide, benzeneacetic acid, hexyl ester, ethyl 4-acetoxy butanoate, butanoic acid, and 2-methyl in GC–MS analysis of degraded dye sample confirms the biodegradation by bacterial strain ED24. The phytotoxicity studies on mung bean seeds confirmed MG dye toxicity reduction up to 67.53%, 54.16%, and 67.53% in biomass accumulation, root, and shoot lengths, respectively. Also, the microbial toxicity of MG was completely reduced on soil microflora Bacillus flexus, Stenotrophomonas maltophilia, Escherichia coli, Staphylococcus aureus, and Alternaria spp. The dual mitigation, both in microbial and plant systems, indicates the strong remediation potential of P. aeruginosa ED24 to break down MG dye ecologically sustainably.

Estimating cargo power is vital because it allows for efficient planning and optimization of transportation logistics, ensuring the appropriate allocation of resources and maximizing operational effectiveness. It also facilitates the assessment and mitigation of the environmental impact of transportation by optimizing fuel consumption and reducing emissions. This chapter proposes a cutting-edge machine learning solution for accurate cargo power prediction. The Pearson correlation is employed to identify the most relevant features for the regression task, thereby aiding in the reduction of dimensionality. Multiple machine learning models are utilized for this purpose, and a comprehensive performance comparison is conducted. The results demonstrate that the proposed ensemble learning-based stacking model outperformed all other models, achieving an impressive coefficient of determination of 0.96. This research offers significant advancements to the field of shipping logistics optimization and provides practical insights for enhancing transportation efficiency and environmental sustainability.

Time series data, prevalent in diverse domains, reflects underlying dynamic processes crucial for informed decision-making. Our research marks a modest stride in comprehending these dynamics. In the context of disease surveillance, Time series forecasting and early warning indicators allow us to anticipate plausible infection waves and their severity. While Deep Learning techniques might deliver accuracy, they often obscure underlying dynamics. On the other hand, statistical methods can be either too approximate or overly complex to capture real-world nuances. Our work bridges this gap, harnessing the strengths of both worlds: we derive understanding from the dynamical system from observed data and proceed to forecast based on this knowledge. This fusion of understanding and prediction will be of paramount interest to decision-makers across various domains. To this end, we propose a data-driven ‘Higher Order Dynamic Mode Decomposition’ (HODMD) based time-series forecasting that decomposes complex time-series data into coherent modes and provides accurate forecasts of future trends. By leveraging the capabilities of HODMD, we aim to enhance time-series forecasting and early warning detection in the context of disease surveillance, which holds significant potential for policymakers and healthcare officials to make timely interventions. The COVID-19 India data has been used to validate the potential of our approach. Contribution of this work is two fold. Accurate and Interpretable COVID-19 Case Forecasting: Our proposed HODMD-based method offers accurate predictions while maintaining interpretability, providing decision-makers with a comprehensive understanding of the disease dynamics. Eigen Values as an Indicator to Predict the Direction of Dynamics: Interpreting eigenvalues as early warning indicators provides interpretable alarms to stake holders. The proposed approach not only accurately predicts infection waves well in advance but also maintains competitive performance metrics. This makes our method a valuable tool for decision-makers and healthcare officials, offering insights that can guide strategic planning and interventions effectively.

The large-scale evolution of Internet and devices connected to the internet have led to various companies and organizations to protect their data on the internet to implement large scale IoT networks such as IIoT in the industrial point of view. Such large-scale networks need to be protected from malicious attacks. This makes it crucial for the need of an intrusion detection system that can protect the privacy and the data in an IoT network and keep the network secure. Most of the existing works are based on a supervised approach where the data in expected to be labelled and use complex deep learning architectures. In our research we propose an unsupervised intrusion detection model that was implemented using the FUZZY C Means algorithms using autoencoders that provide the best detections of the intrusions into the networks. Various other models like the Gaussian-Mixture Model, K means and the HMM have also been used to develop an unsupervised intrusion detection system. The WUSTL_IIOT_2021 and the OPCUA datasets has been used to compliment the effectiveness of our algorithms and to demonstrate the need for more unsupervised approaches for IDS. By our proposed method we have obtained a maximum accuracy of 97% on the Fuzzy-C Means approach and 95% on GMM, HMM and K-Means. Our proposed approach is well in competition with the existing IDS using various complex supervised techniques. These results are superior to the existing frameworks as the system does not expect the data to be labelled as it would mean that the system already know about the features that would cause an attack which is not expected in practical conditions.

Doctors can effectively manage patients’ treatments and diseases by leveraging advanced medical imaging, which significantly minimizes guesswork and enhances diagnoses and treatments.The use of Deep Learning (DL) has been increasing recently in the area of medical imaging for various diseases like Parkinson’s, Alzheimer’s, Blood Cancer etc. When it comes to medical imaging, one common problem prevailing is that of class imbalance. There have been several proposals for the classification of Parkinson’s Disease (PD) using Machine Learning (ML) and Deep Learning (DL) techniques on an imbalanced dataset. These approaches have utilized various image pre-processing techniques on datasets such as T1-weighted and T2-weighted MRI images. One of the challenges faced by DL and ML models is the class imbalance problem in the data, where the Parkinson’s class has a majority of the data, and the normal class has a minority. To address this issue, the study implements transfer learning, a technique that improves model performance by generating better feature representations when there is limited data. While transfer learning is commonly used to enhance performance on tasks with limited data, its effectiveness on medical images, such as MRI, is not well established. However, recent studies have shown promising results. In this study, we propose a novel transfer learning approach for the classification of Parkinson’s disease using an imbalanced Parkinson’s Progression Markers Initiative (PPMI) dataset. The approach uses large scale pre-trained networks, specifically Big Transfer (BiT) models developed by Kolesnikov. BiT mainly stresses on using of Group Normalization (GN) with Weight Standardization (WS) instead of Batch Normalization (BN). The other focus is on using of BiT-HyperRule for fine tuning, where the values which have previously performed better on the natural images are used for fine-tuning for all type of datasets. The study employs different architectures of BiT models, including BiT-S and BiT-M, namely BiT-S50x1, BiT-S50x3, BiT-S101x1, BiT-S101x3, BiT-S152x4, BiT-M50x1,BiT-M50x3, BiT-M101x1, BiT-M101x3, BiT-152x4 which are publicly available. The results show that the proposed approach using BiT-M152x4 outperforms the State of Art Model, Re-weighted Adversarial Graph Convolutional network (RA-GCN), which was experimented on the imbalanced PPMI dataset. RA-GCN was giving an accuracy of 76%, whereas the BiT-M152x4 (the best performing model) was able to give an accuracy of 86.71%. As an extension to this work, we experimented with the BiT models even on the imbalanced Blood Cell Count and Detection (BCCD) dataset with the same values of hyper-parameters that was used for the PPMI dataset, and got the better results compared to existing State-Of-Art model which was 74% for VGG16, whereas the best model in our experiment which is BiT-M152x4 gave an accuracy of 98.52%.

The rapid digitization of healthcare systems has led to a vast accumulation of electronic medical records (EMRs), offering an invaluable source of patient data that can significantly advance medical research and improve patient care. However, sharing EMRs for research purposes presents challenges, particularly concerning data privacy, security, and the limitations of traditional centralized data-sharing models. This paper introduces a novel approach that leverages blockchain technology to facilitate federated learning with EMRs, thereby addressing these challenges. Federated learning enables multiple institutions to collaboratively train a robust machine learning model without sharing raw data, preserving privacy and security. By integrating blockchain, this framework enhances data integrity, immutability, and trust, all in a decentralized environment. The blockchain serves as a transparent and secure ledger, recording model updates and aggregating them through a consensus-based mechanism. Smart contracts further enforce data usage policies, allowing only authorized access and maintaining control over data ownership and sharing. This approach empowers medical researchers and institutions to collaborate more effectively, accelerating the discovery of treatments, advancements in personalized medicine, and insights into rare diseases. It also enables patients to contribute to medical research while retaining control over their personal data, fostering a patient-centered approach to healthcare innovation. Experimental results confirm the efficacy and efficiency of this blockchain-enabled federated learning framework, highlighting its potential to transform medical research and adhere to stringent privacy and security standards. This study emphasizes the pivotal role of blockchain in enhancing big data analytics within healthcare, paving the way for improved collaboration, innovation, and patient outcomes.

Power consumption management is vital in achieving sustainable and low‐carbon green communication goals in 6G smart agriculture. This research aims to provide a low‐power consumption measurement framework designed specifically for critical data handling in smart agriculture application networks. Deep Q‐learning combined with game theory is proposed to allow network entities such as Internet of Things (IoT) devices, Intelligent Reflecting Surfaces (IRSs), and Base Stations (BS) to make intelligent decisions for optimal resource allocation and energy and power consumption. The learning capabilities of DQL with strategic reasoning of game theory, a hybrid framework, have been developed to realize an adaptive routing plan that emphasizes energy‐conscious communication protocols and underestimates the environment. It further enables the investigation of multi‐IRS performance through several key metrics assessments, such as reflected power consumption, energy efficiency, and Signal‐to‐Noise Ratio (SNR) improvement.

The cone–disk system (CDS) involves a cone, which contacts a disk at its tip. This type of flow problem is used in some devices in medical sciences, such as viscosimeters and conical diffusers. The 3-D flow of a bio-nanofluid within the gap of a CDS is examined for the four selected arrangements: (i) rotating cone with stationary disk, (ii) rotating disk with stationary cone, (iii) co-rotation of cone and disk, and (iv) counter-rotation of cone and disk. The well-known Buongiorno’s nanofluid model is applied to illustrate the flow behavior with Stefan blowing. The governing system constitutes the continuity, momentum, energy, conservation of nanoparticle volume fraction (NPVF) equation, and density of the motile microorganism (DMM) equations. The Lie group approach is used to obtain invariant transformations. Numerical simulations are done for various rotational Reynolds numbers and various gap angles to explore the flow, heat, NPVF, and DMM transport features. The radial and tangential skin friction factors, Nusselt, Sherwood, and density numbers are calculated and inspected using tabular and graphical results. The slip and blowing parameters are demonstrated to affect the fluid friction, heat, NPVF, and DMM transfer rates from the disk and cone for the selected models.

This work uses a supervised machine learning approach to examine the boundary layer flow of a non-Newtonian fluid affected by homogeneous and heterogeneous reactions over a convectively heated surface. Similarity variables transform the governing nonlinear PDEs into ODEs, which are solved using the bvp4c technique followed by the application of a supervised machine learning model. The model successfully captures different velocity, energy, and concentration profiles for every situation, precisely predicting flow and thermal properties. Performance metrics that demonstrate the model's accuracy and predictive power in a variety of scenarios include Mean Squared Error (MSE) and R-squared values. Scenarios 3 and 6 exhibit the maximum accuracy and lowest mean square error (MSE) in Table 1. On the other hand, the material parameter ${\lambda }_{1}$ enhances fluid velocity while decreasing the temperature field, and porosity parameter S enhances momentum boundary layer. Error histograms and three-dimensional contour plots are examples of visual assessments that highlight the model's consistency and capacity to identify data trends. Differences in predictions between machine learning and bvp4c with MATLAB indicate that machine learning (ML) can handle a large variety of complex data. Homogeneous and heterogeneous reactions have several uses in the technical and scientific sectors. A lot of reactors are made to take use of both homogeneous and heterogeneous reactions in order to increase efficiency and selectivity. Heterogeneous reactions are used to regulate air pollution, like in car catalytic converters to lower emissions.

Topological indices are crucial tools for predicting the physicochemical and biological features of different drugs. They are numerical values obtained from the structure of chemical molecules. These indices, particularly the degree-based TIs are a useful tools for evaluating the connection between a compound’s structure and its attributes. This study addresses the research problemof how to optimize drug design for HIV treatment using degree-based topological indices. The need for safer and more effective medicines for HIV is further emphasized by the advent of drug resistance and severe negative effects from current therapies. Employing degree-based graph invariants, the study investigates 13 HIV drugs by applying a quantitative structure-property relationship (QSPR) technique to associate their molecular structures with their physical properties. HIV drugs are ranked using the Analytic Hierarchy Process (AHP) according to specific parameters. The findings of the study demonstrate how well these approaches can determine the most effective possible drug combinations and designs, offering insightful information in developing improved HIV treatments.

In this research, a systematic approach is employed to derive novel wave solutions for the coupled nonlinear Schrödinger equation. The transformation of the coupled partial differential equation into ordinary differential equation is achieved by utilizing a complex wave variable. Exponential function combinations are applied to construct the wave solutions. The accuracy of the derived solitons is validated through symbolic computations performed in Wolfram Mathematica, accompanied by graphical visualizations of the proposed solutions. The model is converted into a dynamical system, enabling qualitative and sensitivity analysis. Additionally, introducing perturbed terms is examined, revealing chaotic patterns in the system. The impact of variations in amplitude and frequency parameters on the system’s dynamical behaviour is thoroughly investigated. The findings underscore the efficiency and reliability of the applied techniques, demonstrating their applicability to a wide range of complex nonlinear systems.

Potassium‐sulfur (K‐S) batteries are severely limited by the sluggish reaction kinetics of the cyclooctasulfur (cyclo‐S8) electrode with low conductivity, which urgently requires a novel cathode to facilitate activity to improve sulfur utilization. In this study, using the wet chemistry method, the molecular clip of Li⁺ is created to replace cyclo‐S8 molecular with the highly active chain‐like S6²⁻ molecular. The molecular clip strategy effectively lowers the reaction barrier in potassium‐sulfur systems, and the stretching of S─S bonds weakens the binding between sulfur atoms, facilitating the transformation of potassium polysulfides (KPSs). The as‐prepared cathode exhibits a reversible capacity of 894.8 mAh g⁻¹ at a current rate of 0.5 C. It maintains a long cycle life of 1000 cycles with a stable coulombic efficiency in the potassium–sulfur cells without cathode catalysts. Operando XRD and Raman spectra combined with density functional theory (DFT) calculations, revealing the high efficiency of enhanced conversion of potassium polysulfide for high‐performance K‐S batteries.

Nowadays, the digitalization boom witnesses the culmination of the Internet of Things (IoT), the big data and the cloud storage which is further fueled by data analytics techniques to identify useful patterns from the data stored in the cloud to understand the business and the government processes alike. In this competitive scenario, it is equally important to ensure the intactness of the big data stored in the cloud from the IoT sensors. Though many data audit schemes have been proposed till date, very few notable works have been proposed towards IoT based data storage. Apart from this, the previous protocols incur relatively more computational and communication overheads and they lack support for privacy’. Hence, the proposed approach strives to provide data audit for the IoT based cloud data storage in three dimensions. Proposing a novel data audit protocol to suit the IoT based systems is the first dimension of this research work. The second dimension utilizes identity-based cryptography to provide anonymous identity thereby preserving the privacy of the data aggregation gateways. The third dimension ensures the proposed protocol to suit resource constrained environments with the relatively cheaper computation and the communication overheads. The implementation results provide convincing evidence that the proposed protocol performs better than the significant works existing in the literature.

Skin diseases impact millions of people around the world and pose a severe risk to public health. These diseases have a wide range of effects on the skin’s structure, functionality, and appearance. Identifying and predicting skin diseases are laborious processes that require a complete physical examination, a review of the patient’s medical history, and proper laboratory diagnostic testing. Additionally, it necessitates a significant number of histological and clinical characteristics for examination and subsequent treatment. As a disease’s complexity and quantity of features grow, identifying and predicting it becomes more challenging. This research proposes a deep learning (DL) model utilizing transfer learning (TL) to quickly identify skin diseases like chickenpox, measles, and monkeypox. A pre-trained VGG16 is used for transfer learning. The VGG16 can identify and predict diseases more quickly by learning symptom patterns. Images of the skin from the four classes of chickenpox, measles, monkeypox, and normal are included in the dataset. The dataset is separated into training and testing. The experimental results performed on the dataset demonstrate that the VGG16 model can identify and predict skin diseases with 93.29% testing accuracy. However, the VGG16 model does not explain why and how the system operates because deep learning models are black boxes. Deep learning models’ opacity stands in the way of their widespread application in the healthcare sector. In order to make this a valuable system for the health sector, this article employs layer-wise relevance propagation (LRP) to determine the relevance scores of each input. The identified symptoms provide valuable insights that could support timely diagnosis and treatment decisions for skin diseases.

Recovering diagnostic-quality cardiac MR images from highly under-sampled data is a current research focus, particularly in addressing cardiac and respiratory motion. Techniques such as Compressed Sensing (CS) and Parallel Imaging (pMRI) have been proposed to accelerate MRI data acquisition and improve image quality. However, these methods have limitations in high spatial-resolution applications, often resulting in blurring or residual artifacts. Recently, deep learning-based techniques have gained attention for their accuracy and efficiency in image reconstruction. Deep learning-based MR image reconstruction methods are divided into two categories: (a) single domain methods (image domain learning and k-space domain learning) and (b) cross/dual domain methods. Single domain methods, which typically use U-Net in either the image or k-space domain, fail to fully exploit the correlation between these domains. This paper introduces a dual-domain deep learning approach that incorporates multi-coil data consistency (MCDC) layers for reconstructing cardiac MR images from 1-D Variable Density (VD) random under-sampled data. The proposed hybrid dual-domain deep learning models integrate data from both the domains to improve image quality, reduce artifacts, and enhance overall robustness and accuracy of the reconstruction process. Experimental results demonstrate that the proposed methods outperform than conventional deep learning and CS techniques, as evidenced by higher Structural Similarity Index (SSIM), lower Root Mean Square Error (RMSE), and higher Peak Signal-to-Noise Ratio (PSNR).