Alanoud Al Mazroa’s research while affiliated with Princess Nourah bint Abdulrahman University and other places

Schizophrenia is a chronic and severe mental illness that significantly impacts the daily lives and work of those affected. Unfortunately, schizophrenia with negative symptoms often gets misdiagnosed, relying heavily on the clinician’s experience. There is a pressing need to develop an objective and effective diagnostic method for this specific type of schizophrenia. This paper proposes a new deep-learning method called Cascaded Atrous Convolutional Network with Adaptive Weight Fusion (CA-AWFM) for classifying schizophrenia from electroencephalogram (EEG) data that combines cascaded networks with atrous convolutions and an adaptive weight fusion module (AWFM). This is because schizophrenia involves intricate and subtle brain wave patterns that make it difficult to detect the disorder from EEG signals. As such, our model uses an “atrous” convolution operation to extract multi-scale temporal information and a cascade network structure that progressively improves the attribute representations across layers. For classification purposes, AWFM enables our model to modify the importance of features dynamically. We evaluated our technique using a publicly available dataset of EEG recordings acquired from patients who have schizophrenia and everyday individuals. The proposed model has significantly outperformed existing methods with a 99.5% accuracy rate. With the help of atrous convolutions, local and global dependencies within the EEGs can be effectively modeled in this way. At the same time, AWFM makes flexible prioritization of characteristics possible for improved classification performance. With such impressive figures achieved, it can be concluded that our approach should be considered as accurate enough for routine clinical use in identifying schizophrenic patients early on so they can receive intervention measures on time or when diagnosed late, then dealt with appropriately.

Over previous years, the Internet of Things (IoT) made to connect multifaceted things to the internet. It has led to a digital disturbance when by alternating method is utilized. It led to digital interruption through exchanging methods of expertise is used. Numerous industries, such as Smart Health Care (SHC) transport as well as smart grids have metamorphosed this time smarter than still using a cloud of things. Conversely, cybersecurity assaults endanger confidentiality, and so on. Through the widespread consumption of IoT expertise at SHC, novel security as well as privacy methods ought to be mentioned. MDC-BCO cyber secured technique together at storage and recovery is obtainable for SHC scheme using Cloud. The entire technique is divided into three phases. They are the sign in stage, device authentication stage, and device communication stage. The primary, sign is carried out by using Message Digest Crypto for every IoT tool through a cloud server (CS), guarantee scalable and manageable IoT structural design. Subsequently, authentication is carried out for every registered tool by Blockchain-based Chaotic Order. The encryption is performed by the device private key to verify the authentication to ensure network latency and security. Lastly, secured device communication is performed for each authorized user or device by using Chaotic Order. Secure data communication between the devices (i.e. patient and hospital or patient and doctors) is achieved by reducing end-to-end delay to make relationship requests among tools. Outcomes obtained as of simulations exposed improved achievement of the proposed technique compared to conventional blockchain-based techniques. From the experimental analysis, the MDC-BCO minimizes network latency, delay, and memory consumption by 24%, 16%, and 14% and improves security by 6% with MHEALTH dataset as compared to existing works.

Purpose This study aims to focus on the performance and emissions characteristics of different combinations of biofuel blends in aviation engines using machine learning models. The paper discusses both energy performance and emissions reduction, so it can be clarified in the title and abstract. Design/methodology/approach The blends tested were B10 (10% microalgae, 90% Jet A fuel), BB10 (10% biodiesel, 10% biogas, 80% Jet A fuel), B30 (30% microalgae, 70% Jet A fuel) and BB30 (30% biodiesel, 10% biogas, 60% Jet A fuel), respectively. All the blends are tested already in the previous study, and the results were trained using the ML models here, and the comparison was made.The machine learning models used were XGBoost, random forest and ridge regression. These models were trained using the actual data of thrust, thrust specific fuel consumption (TSFC), turbine inlet temperature (TIT), nitrogen oxides (NOx) emissions, carbon monoxide (CO) emissions and carbon dioxide (CO 2 ) emissions. Trained models were evaluated using experimental data, and their performance is assessed based on root mean squared error, mean absolute error and R-squared ( R ² ) metrics. Findings From the results, it is clear that the random forest model emerges as the most effective in predicting thrust, TIT and CO 2 emissions by reporting low error and high R ² . On the other hand, the ridge regression model outperforms other models in predicting TSFC, NOx emissions and CO emissions. Considering all results, most models capture the movements of reduced thrust, increased TSFC and slightly higher TIT. Meanwhile, the models have the ability to capture the lower NOx, CO and CO 2 emissions for biodiesel blends compared to Jet A fuel. The study also specifying that the models are used for regression would add clarity since the study focuses on predicting performance and emissions characteristics using continuous numerical outputs. Practical implications Based on all the predictions from the trained models, it is clear that the machine learning models can support understanding the performance and emissions characteristics of biodiesel blends and support decision-making processes in fuel selection and engine performance optimization. Originality/value The main objective of the study is to provide insights into the potential of biodiesel blends as alternative fuels in aviation using various machine learning models in predicting critical aviation parameters, including thrust, TSFC, TIT and emissions.

Introduction: The accurate and timely diagnosis of skin diseases is a critical concern, as many skin diseases exhibit similar symptoms in the early stages. Most existing automated detection/classification approaches that utilize machine learning or deep learning poses privacy issues, as they involve centralized computing and require local storage for data training. Methods: Keeping the privacy of sensitive patient data as a primary objective, in addition to ensuring accuracy and efficiency, this paper presents an algorithm that integrates Federated learning techniques into an IoT-based edge-computing environment. The purpose of the proposed technique is to protect the sensitive data by training the model locally on the edge device and transferring only the weights to the central server where the aggregation takes place. This process ensures data security at the edge level and eliminates the need for centralized storage. Furthermore, the proposed framework enhances the network's real-time processing capabilities using IoT-integrated sensors, which in turn facilitates swift diagnoses. In addition, this paper also focuses on the design and execution of the federated framework, which includes the processing power, memory, and the number of nodes present in the network. Results: The accuracy and effectiveness of the proposed algorithm are demonstrated using precise parameters, such as accuracy, precision, f1-score, and recall, along with all the intricacies of the secure federated approach. The accuracy achieved by the proposed algorithm is 98.6%. As the model was trained locally, the bandwidth utilization was almost negligible. Discussion: The proposed model can assist skin specialists in diagnosing conditions. Additionally, with federated learning, the model continuously improves as new input data accumulates, enhancing the accuracy of subsequent training rounds. KEYWORDS federated learning, healthcare technology, internet of things (IoT), edge computing, decentralized network architecture, distributed computing OPEN ACCESS EDITED BY MS (2025) Privacy-enhanced skin disease classification: integrating federated learning in an IoT-enabled edge computing.

Partially obscuring the face with a hat, sunglasses, scarf, or beard is referred to as partial occlusions. They are very common in forensic face recognition applications because facial images are captured in unconstrained environments. To address the issue of partial occlusion, two significant spatial domain approaches using deep learning techniques are proposed in this research work. The first approach exploits deep metric‐based learning (DML) and spatial features for face recognition. Convolution‐based face finding (CFF) technique using CNN for digital forensic face recognition tasks is employed in the second approach. Proposed approaches are experimented on the Disguised Faces in Wild (DFW) dataset, and a comparative analysis of the proposed approaches with existing approaches is presented. It is observed that the CFF technique using CNN provides a recognition accuracy of 93.75%, which performs better than DML and the existing approaches. The research work presented has significance, and results are promising in the field of unconstrained face recognition.

Introduction A brain tumor is a collection of abnormal cells in the brain that can become life-threatening due to its ability to spread. Therefore, a prompt and meticulous classification of the brain tumor is an essential element in healthcare care. Magnetic Resonance Imaging (MRI) is the central resource for producing high-quality images of soft tissue and is considered the principal technology for diagnosing brain tumors. Recently, computer vision techniques such as deep learning (DL) have played an important role in the classification of brain tumors, most of which use traditional centralized classification models, which face significant challenges due to the insufficient availability of diverse and representative datasets and exacerbate the difficulties in obtaining a transparent model. This study proposes a collaborative federated learning model (CFLM) with explainable artificial intelligence (XAI) to mitigate existing problems using state-of-the-art methods. Methods The proposed method addresses four class classification problems to identify glioma, meningioma, no tumor, and pituitary tumors. We have integrated GoogLeNet with a federated learning (FL) framework to facilitate collaborative learning on multiple devices to maintain the privacy of sensitive information locally. Moreover, this study also focuses on the interpretability to make the model transparent using Gradient-weighted class activation mapping (Grad-CAM) and saliency map visualizations. Results In total, 10 clients were selected for the proposed model with 50 communication rounds, each with decentralized local datasets for training. The proposed approach achieves 94% classification accuracy. Moreover, we incorporate Grad-CAM with heat maps and saliency maps to offer interpretability and meaningful graphical interpretations for healthcare specialists. Conclusion This study outlines an efficient and interpretable model for brain tumor classification by introducing an integrated technique using FL with GoogLeNet architecture. The proposed framework has great potential to improve brain tumor classification to make them more reliable and transparent for clinical use.

With the rapid advancements in artificial intelligence (AI), ensuring the privacy and security of patient medical images has emerged as a pressing concern in the field of image privacy protection. Traditional medical image encryption methods, however, have often been criticized for their lack of flexibility and insufficient security measures. To address these challenges, proposed a new image encryption algorithm that uses the R3 (rotate, rescale, randomize) Model to apply the concepts of chaotic and hyperchaotic systems to new image encryption approaches. Based on the hyperchaotic behavior of the circle map system and the unpredictable behavior of the Chua system, the proposed algorithm performs scaling, rotation, and randomization on the target image. Basically, the input medical image is scaled and rotated using a chaotic system to minimize the association between neighboring pixels. To create an encrypted image, the permuted image is next subjected to a diffusion operation with the assistance of S‐box. By using these chaotic systems unpredictable behavior and sensitivity to beginning conditions, an encryption technique with a huge key space of 2 ⁵²⁰⁸ is created, improving security overall and fortifying its resistance to brute‐force attacks. The speed at which the algorithm processes data and the minimal number of resources it consumes demonstrate its effectiveness, making it appropriate for real‐time applications. To evaluate the security and computational efficiency of the suggested encryption system, a series of grayscale medical photographs were subjected to extensive testing. In addition to having a large key space of about 2 ⁵²⁰⁸ , it also showed resistance to differential cryptanalysis, with NPCR and UACI values above 99.60% and 30.20%, respectively. The encrypted images' entropy was close to eight, suggesting improved system security. The technique is ideal for real‐time applications, with encryption speeds of 0.80 s for 512 × 512 images and 0.6 s for 256 × 256 images. The scheme's capacity to provide strong security with little computing overhead and complexity is demonstrated by experimental results.

Cementitious Green Hybrid Concrete (CGHC) is gaining recognition as a sustainable choice for low-volume roads, providing environmental benefits and improved mechanical strength over traditional concrete. CGHC reduces traditional cement demand, thus lowering carbon emissions, while its durability minimizes repair needs, extending structural lifespan and reducing resource consumption. This study employs Response Surface Methodology (RSM) with a Central Composite Design (CCD) to analyze the influence of varying proportions of cement, fine aggregate, and coarse aggregate on CGHC's compressive and flexural strengths. The investigation evaluates the impact of coconut shell (COS), lime powder (LP), and rice husk ash (RHA) as partial replacements—substituting COS for coarse aggregate, RHA for fine aggregate, and LP for cement across twenty M30 grade concrete mixes. Results show that RHA and LP replacements generally enhance strength, with RHA substitution at 20% for fine aggregate yielding optimal strength. In contrast, increased COS content reduces strength. This research demonstrates RSM's effectiveness in optimizing CGHC properties, underscoring its potential for eco-friendly road applications. Keywords: Response Surface Methodology (Rsm); Cementitious Green Hybrid Concrete (Cghc); Low volume roads, Central Composite Design (Ccd); Supplementary Cementitious Materials (SCMs)

Predicting the adhesive force between steel reinforcement and concrete is crucial as it influences stress distribution and the overall mechanical behavior of reinforced concrete. This study proposes a novel approach to enhance bond strength prediction using machine learning (ML) models optimized through Bayesian optimization (BO). A dataset comprising 401 beam tests with six key factors was used to train three distinct ML algorithms—Support Vector Regression (SVR), Random Forest (RF), and Extreme Gradient Boosting (XGBoost). The prediction models were first trained on the full dataset, with BO applied to fine-tune hyperparameters and improve accuracy. Among these models, the BO-XGBoost achieved the best performance, with an R² of 0.74, MAE of 1.412 MPa, and RMSE of 1.516 MPa on the test set, and R² = 0.80, MAE = 0.950 MPa, RMSE = 1.200 MPa on the training set. In addition, a simplified model was developed, incorporating only three critical variables—rebar thickness, reinforcement tensile strength, and concrete compressive capacity—to make the model more applicable in real-world engineering scenarios. To further interpret the model’s predictions, Shapley additive explanations (SHAP) were employed, revealing the specific influence of each variable on bond strength. This study demonstrates that the integration of ML with Bayesian optimization can significantly improve the accuracy of bond strength predictions, offering valuable insights for structural design optimization. Keywords: Machine Learning; Bond Strength; SHAP; Random Forest; XG Boost; SVR

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.