Biometric identification from medical images is of increasing interest in forensic-motivated research, particularly in scenarios where conventional soft-tissue-based modalities may become unreliable. This study presents an anatomically motivated feasibility framework that investigates the discriminative potential of skeletal-only cues extracted from chest X-ray radiographs for person identification. Leveraging the relative structural stability of bone anatomye propose a deep metric learning framework utilizing a Triplet Network with a ResNet-based backbone to extract and cluster discriminative skeletal embeddings. The framework is evaluated on the NIH ChestXray14 dataset as a large-scale clinical proxy for anatomical variability, achieving an identification accuracy of 97.3% under the considered experimental protocol. To analyze the learned embedding space, dimensionality reduction techniques including UMAP and t-SNE are employed to visualize identity clustering and inter-subject separability. Furthermore, explainable artificial intelligence (XAI) techniques, specifically Grad-CAM, are applied to provide anatomically grounded interpretations of the regions contributing to identity discrimination. The study is positioned as a proof-of-concept investigation aimed at establishing a methodological and analytical foundation for skeletal-based biometric modeling rather than as a fully validated forensic deployment system. The results highlight the potential of skeletal-only representations for identity discrimination and underline the importance of future validation on dedicated forensic and post-mortem datasets, as well as enhanced segmentation protocols, to further advance explainable and privacy-aware biometric research.

Parkinson's disease (PD), the second most prevalent neurodegenerative disorder globally, afflicting approximately 10 million individuals, necessitates early detection for optimal management. In this paper, we propose deep learning models to discern Parkinson's disease through the nuanced analysis of handwriting with the overall objective of achieving transparency and trustworthiness through the integration of Explainable and Interpretable AI.Leveraging transfer learning from well-established VGG16 and VGG19 architectures and introducing two bespoke CNN models (PD-Detect1 and PD-Detect2), we meticulously scrutinize diverse datasets (HandPD, NewhandPD, Parkinson Drawing) to ascertain the efficacy of our approach. LIME and SHAP Explainable AI techniques are employed to pinpoint specific regions of the spiral drawings that significantly influence the predictions made by the VGG16 and PD-Detect2 models. Additionally, Convolutional Filter Visualization and Grad-CAM are utilized to illustrate how the convolutional layers of the PD-Detect2 model function. Finally, LIME is applied to the PD-Detect2 model to identify visual markers of handwriting symptoms in the spiral drawing.Remarkable results underscore our reliance on VGG16 and VGG19 for precise identification, achieving an outstanding 100% accuracy in the waves drawing dataset. PD-Detect1 exhibits commendable performance with an accuracy of 94.44% in the meander of NewhandPD dataset, while VGG16 achieves an accuracy of 95%. VGG16 records 95% accuracy while PD-Detect2 achieves 85% accuracy in the spiral drawing dataset. Both results further bolstered to 100% with the application of classic data augmentation techniques. The Positive/Negative superpixels from LIME and SHAP highlight the key regions used by VGG16 and PD-Detect2 for predictions, while PD-Detect2 places more emphasis on disease-related features. Visualizing convolutional filters provided insight into the functionality of each layer within the PD-Detect2 model, while the Class Activation Maps produced by Grad-CAM highlighted the image regions most influential to the model's decision. Ultimately, LIME's superpixels identified visual markers of handwriting symptoms associated with Parkinson's disease.Explainable AI and Interpretable AI enhance the quality of CNN models and support the decision-making process, enabling healthcare professionals to more accurately assess disease probability and monitor treatment responses. This leads to a more effective system for the early diagnosis of Parkinson's disease through prediction and visual monitoring of handwriting symptoms.

E-learning was developed in one of the steps of the education world, thus providing personalized and flexible learning environments. Nevertheless, the puzzle is yet to get the students to participate in an Open Classroom (OCR) setting in a way that is actively involved. They mostly work alone with digital platforms as they always did, and teachers cannot manage the task of organizing collaboration in this virtual room. Therefore, we introduce a hybrid Convolutional Neural Networks (CNN)-Vision Transformers (ViT) model to detect real-time engagement. In particular, CNN layers are exploited for local features, while the ViT network uses global attention mechanisms to grab spatial and contextual clues, e.g., facial expressions, and body postures. This method is superior because it integrates two different types of modules, which can take advantage of the pros in a limited field and a coverage context, and we can thus achieve a deeper observation of student action. The model was taught with the Video-based Student Engagement Measurement Dataset and there was a success of 85

With the rapid expansion of e-learning platforms, maintaining academic honesty during online assessments has become increasingly challenging. Traditional monitoring methods often fall short in detecting advanced cheating behaviors and may raise privacy concerns among students. To address these limitations, we propose LSTM-SWAP, a hybrid deep learning model that combines Long Short-Term Memory (LSTM) networks with a specialized attention mechanism called Sliding Window Attention Processor (SWAP) that focuses on key patterns in student behavior over time. This approach allows the model to highlight important behavioral cues while filtering out irrelevant data, thereby improving detection accuracy. Unlike conventional systems that rely on fixed features, LSTM-SWAP adapts dynamically to new and evolving cheating strategies, ensuring resilience against emerging threats. Additionally, the model is designed to reduce false alarms, promoting fairness by minimizing the risk of misidentifying honest students. We evaluated our model on a behavioral dataset based on mouse movement patterns using stratified fivefold cross-validation, achieving an average accuracy of 97.73

The trend toward distance education in higher education, which was accelerated in adoption by COVID-19, has amplified the requirement for personalized course recommendations and accurate classification of Massive Open Online Courses (MOOCs). However, many frameworks use static, rule-based systems that are hard to change and do not allow for diverse course structures. This paper proposes a hybrid technique for the classification of MOOCs courses based on the integration of Convolutional Neural Networks (CNN) and the Lion Optimization Algorithm (LOA). It ensures better performance in classification by including the strongest pattern recognition capability of CNN and the powerful hyperparameter optimization by LOA. We also contrasted our approach with various algorithms, including biologically motivated optimization algorithms like the Whale Optimization Algorithm (WOA), Particle Swarm Optimization (PSO), and Ant Colony Optimization (ACO). We also contrast deep learning architectures like Bidirectional Encoder Representations from Transformers (BERT) and Long Short-Term Memory (LSTM) and transformer-based embeddings (sentence embeddings from a pretrained transformer (SimCSE) plus an MLP classifier). We conduct our evaluation on a new dataset that has not been studied in the literature. These experimental results show that the CNN/LOA outperforms the other methods, with testing accuracy at 96.34

Internet of Things (IoT) among of all the technology revolutions has been considered the next evolution of the internet. IoT has become a far more popular area in the computing world. IoT combined a huge number of things (devices) that can be connected through the internet. The purpose: this paper aims to explore the concept of the Internet of Things (IoT) generally and outline the main definitions of IoT. The paper also aims to examine and discuss the obstacles and potential benefits of IoT in Saudi universities. Methodology: the researchers reviewed the previous literature and focused on several databases to use the recent studies and research related to the IoT. Then, the researchers also used quantitative methodology to examine the factors affecting the obstacles and potential benefits of IoT. The data were collected by using a questionnaire distributed online among academic staff and a total of 150 participants completed the survey. Finding: the result of this study reveals there are twelve factors that affect the potential benefits of using IoT such as reducing human errors, increasing business income and worker’s productivity. It also shows the eighteen factors which affect obstacles the IoT use, for example sensors’ cost, data privacy, and data security. These factors have the most influence on using IoT in Saudi universities.

Precisely dating historical manuscripts represents a paramount endeavor in the comprehension and the interpretation of their historical significance as well as in the preservation of our cultural heritage; however, despite the strides made in computer-based dating methodologies, the quest for heightened robustness persists. Recent advancements in vision transformers, renowned for their success across diverse image processing domains, have stimulated our inquiry into their potential applicability in the domain of historical manuscript dating. In our pursuit of achieving efficient refinement of the manuscript and ensuring pristine datasets for subsequent analysis, we initiate a meticulous dataset preprocessing step. This involves employing accurate methodologies for denoising through the Non-Local-Means algorithm, and binarization using the Canny-edge detector. Following these preprocessing steps, we delve into the intricate realm of feature detection using the Harris-corner detector. This detector is employed to extract keypoints from the manuscript, and we subsequently apply clustering to these keypoints using the k-means algorithm. Our dual objective here is to extract significant patches of specific dimensions and engage in a systematic augmentation of our dataset. Through this process, we aim to amplify the depth and diversity of our dataset, thereby empowering our models with an enriched corpus of historical knowledge. The final phase of our proposed system unfolds as we leverage the latent power of the sophisticated deep learning architecture known as vision transformers. The model is finetuned to our specific task and re-learned with the automatically extracted handcrafted features, emerges as a formidable classification framework. As an added layer of refinement, we deploy a majority vote mechanism on image patches, meticulously engineered to heighten system accuracy. Our rigorous testing regimen, carried out on the well-known MPS historical document dataset, has yielded results of remarkable caliber. Our system's prowess is vividly reflected in its performance metrics, boasting an impressive Mean Absolute Error (MAE) of 3.97 for document-level evaluations and a resounding 7.42 MAE for patch-level assessments. The significance of this work lies in its potential to revolutionize historical manuscript dating, not only by enhancing precision but also by providing a versatile framework adaptable to diverse historical contexts and document types. Beyond its immediate applications, this research paves the way for a deeper understanding of historical narratives, cultures, and the invaluable insights that lie within the annals of our past.

Determining the script of historical manuscripts is pivotal for understanding historical narratives, providing historians with vital insights into the past. In this study, our focus lies in developing an automated system for effectively identifying the script of historical documents using a deep learning approach. Leveraging the ClAMM dataset as the foundation for our system, we initiate the system with dataset preprocessing, employing two fundamental techniques: denoising through non-local means denoising and binarization using Canny-edge detection. These techniques prepare the document for keypoint detection facilitated by the Harris-corner detector, a feature-detection method. Subsequently, we cluster these keypoints utilizing the k-means algorithm and extract patches based on the identified features. The final step involves training these patches on deep learning models, with a comparative analysis between two architectures: Convolutional Neural Networks (CNN) and Vision Transformers (ViT). Given the absence of prior studies investigating the performance of vision transformers on historical manuscripts, our research fills this gap. The system undergoes a series of experiments to fine-tune its parameters for optimal performance. Our conclusive results demonstrate an average accuracy of 89.2 and 91.99% respectively of the CNN and ViT based proposed framework, surpassing the state of the art in historical script classification so far, and affirming the effectiveness of our automated script identification system.

Information communications technology (ICT) refers to the technology used for communication and managing information must be utilized to enhance the environment, economics, mobility, and governance, among other facets of urban life, in order to create smart cities. However this progress is frequently accompanied by a number of challenges and unfavorable outcomes. This study aims to uncover ICT difficulties related to smart city infrastructure through an extensive literature review. In addition, a survey was carried out among Saudi nationals to find out what they thought about, anticipated, and worried about in terms of smart city concepts and features. The study also looked at a literature checklist of ICT problems, which included dangers to information security, incompatibilities across systems, privacy concerns, and deficiencies in digital capabilities. Based on the findings it appears that privacy breaches and information security concerns are the most important issues. This is explained by heightened susceptibility and potential, cyberattacks and a pervasive ignorance of the protection of personal data. Because of the anticipated high costs and difficulties with adaption and utilization, the public is concerned about incompatibility between systems and services. Furthermore, older individuals and those with lesser educational achievement have different digital skills.

Pulmonary disease identification and characterization are among the most intriguing research topics of recent years since they require an accurate and prompt diagnosis. Although pulmonary radiography has helped in lung disease diagnosis, the interpretation of the radiographic image has always been a major concern for doctors and radiologists to reduce diagnosis errors. Due to their success in image classification and segmentation tasks, cutting-edge artificial intelligence techniques like machine learning (ML) and deep learning (DL) are widely encouraged to be applied in the field of diagnosing lung disorders and identifying them using medical images, particularly radiographic ones. for this end, the researchers are concurring to build systems based on these techniques in particular deep learning ones. In this paper, we proposed three deep-learning models that were trained to identify the presence of certain lung diseases using thoracic radiography. The first model, named “CovCXR-Net”, identifies the COVID-19 disease (two cases: COVID-19 or normal). The second model, named “MDCXR3-Net”, identifies the COVID-19 and pneumonia diseases (three cases: COVID-19, pneumonia, or normal), and the last model, named “MDCXR4-Net”, is destined to identify the COVID-19, pneumonia and the pulmonary opacity diseases (4 cases: COVID-19, pneumonia, pulmonary opacity or normal). These models have proven their superiority in comparison with the state-of-the-art models and reached an accuracy of 99,09%, 97.74%, and 90,37% respectively with three benchmarks.

Person identification through chest X-ray radiographs stands as a vanguard in both healthcare and biometrical security domains. In contrast to traditional biometric modalities, such as facial recognition, fingerprints and iris scans, the research orientation towards chest X-ray recognition has been spurred by its remarkable recognition rates. Capturing the intricate anatomical nuances of an individual's rib cage, lungs and heart, chest X-ray images emerge as a focal point for identification, even in scenarios where the human body is entirely damaged. Concerning the field of deep learning, a paradigm is exemplified in contemporary generations, with promising outcomes in classification and image similarity challenges. However, the training of convolutional neural networks (CNNs) requires copious labelled data and is time-consuming. In this study, we delve into the rich repository of the NIH ChestX-ray14 dataset, comprising 112,120 frontal-view chest radiographs from 30,805 unique patients. Our methodology is nuanced, employing the potency of Siamese neural networks and the triplet loss in conjunction with refined CNN models for feature extraction. The Siamese networks facilitate robust image similarity comparison, while the triplet loss optimizes the embedding space, mitigating intra-class variations and amplifying inter-class distances. A meticulous examination of our experimental results reveals profound insights into our model performance. Noteworthy is the remarkable accuracy achieved by the VGG-19 model, standing at an impressive 97%. This achievement is underpinned by a well-balanced precision of 95.3% and an outstanding recall of 98.4%. Surpassing other CNN models utilized in our research and outshining existing state-of-the-art models, our approach establishes itself as a vanguard in the pursuit of person identification through chest X-ray images.

The present study developed a Detection Android cybercrime Model (DACM), deploying the design science approach to detect different Android-related cybercrimes. The developed model consists of five stages: problem identification and data collection, data preprocessing and feature extraction, model selection and training, model evaluation and validation, and model deployment and monitoring. Compared to the existing cybercrime detection models on the Android, the developed DACM is comprehensive and covers all the existing detection phases. It provides a robust and effective way to spot cybercrime in the Android ecosystem by following Machine Learning (ML) technology. The model covers all the detection stages that are normally included in similar models, so it provides an integrated and holistic approach to combating cybercrime.

This research explores the influence of e-commerce on traditional enterprises. The study explores the effectiveness of e-commerce, potential hazards, and overall implications for business operations by utilizing secondary research methodologies and literature. The findings underscore the need for a solid IT infrastructure for e-commerce success. Positive results include revenue diversification and worldwide market expansion, while negative outcomes include fraud concerns and service disruptions. The report highlights the rapid expansion of e-commerce in Saudi Arabia and forecasts future trends such as artificial intelligence, mobile commerce dominance, blockchain technology, and cryptocurrency adoption. It also addresses policy concerns such as consumer protection, cross-border trade, and taxation. Finally, the study highlights the revolutionary impact of e-commerce, providing insights for scholars, entrepreneurs, and politicians navigating the dynamic junction of technology and business.

Writer identification form historical manuscripts presents a challenging problem with significant implications for understanding the authorship of ancient texts. In this paper, we propose a novel deep learning framework tailored for the task of historical manuscripts writer identification. Our approach leverages data-driven features, harnessing the power of neural networks to extract and learn discriminative patterns from handwritten historical documents. The key innovation of our framework lies in its ability to automatically discover and utilize relevant features from data to profile the writer, eliminating the need for manual feature engineering. Our methodology encompasses three well-defined steps: initially, manuscript preprocessing involves image denoising using advanced techniques such as non-local means and total-variation, followed by binarization using a Canny-edge detector. In the subsequent phase, we employ Harris corner detector for automatic key-point detection and clustering, allowing us to identify the regions of interest within the documents. Lastly, the features extracted from these regions are subjected to classification through transfer learning, utilizing a deep learning-based model specifically trained on the extracted patches. To achieve the final document-level identification, we enhance the system accuracy by implementing a majority vote scheme, where the aggregated decisions from multiple patches contribute to the ultimate classification outcome. We validate our approach on “ICDAR 2017” dataset, spanning different periods and writing styles of historical manuscripts. Experimental results demonstrate the superior performance of our method in accurately identifying the authors of historical documents, surpassing existing techniques. Moreover, our framework exhibits robustness in scenarios where limited training data is available. This work not only contributes to the field of historical manuscripts analysis but also highlights the potential of deep learning in solving intricate problems in the realm of document analysis and authorship attribution. Our framework offers a promising avenue for scholars and historians to gain deeper insights into the authors of historical texts, opening new doors for historical research and preservation.

Hate speech is defined as an expression that targets an individual or community on the aspects like religion, sexual orientation, race, political opinion, and origin. Recently, hate speech on social media especially in the Arabic language has been exponentially increased and led to severe causes. Various studies had been conducted on social media platforms adopted by people to broadcast their opinions. This work aims to develop a model that is able to handle detection and classification of Arabic hate speech and offensive language. The experiments are carried out in using various machine learning (ML) and deep learning (DL) models. In this work, Arabic Hate Speech Detection (AHSD) model is proposed which composed of pre-processing, feature extraction, detection, and classification to identify hate speech on the Arabic benchmark dataset. The proposed model shows improved results. The transfer learning approach model exhibits superior performance compared to all other ML models in terms of accuracy, precision, recall, and F1 scores, achieving improvements of 84

Cultural tourism is a continuously rapidly developing product which the global travel sector has experienced. Cultural products are a vital part of the economy and post-modern society. Satisfaction is a prominent factor in tourism and marketing literature. This paper aims to analyze customer satisfaction in historic sites through electronic word-of-mouth. We developed a new method through text mining, clustering and supervised learning techniques. The method is developed through latent dirichlet allocation for customer online reviews analysis, learning vector quantization to find important customers segments and Adaptive Neuro-Fuzzy Inference System for customer preference prediction in historic sites. The data are collected from TripAdvisor which is a comprehensive online review system in tourism and hospitality. The results revealed that electronic word-of-mouth (eWOM) effectively reveals customer satisfaction in historic sites through data analytical approaches.

The automated proficiencies of the Kingdom of Saudi Arabia, in vision 2030, influence a decade of continual expenditure in contemporary automation and unified government platforms. It affords a reliable base for the COVID-19 response’s significant facets, encompassing continued connection to many e-government systems. The worldwide COVID-19 epidemic has reinvigorated the role of e-government. The health crisis has altered SADAIA to lunch Tawakkalna m-government application to execute business continuity strategies, offer important services to people, and assure their fulfilment. The study intends to assess the impact of the COVID-19 pandemic on users’ satisfaction with m-government services and Health Care apps in the Al-Madinah region. It analyses the elements that enable people’s use of online government services, and m-government services are a solution to handle the crisis. The finding shows that trust in e-government, trust in the internet, ease of use and usefulness are the important factors in using the application during the pandemic.

Several millions of people suffer from Parkinson's disease globally. Parkinson's affects about 1% of people over 60 and its symptoms increase with age. The voice may be affected and patients experience abnormalities in speech that might not be noticed by listeners, but which could be analyzed using recorded speech signals. With the huge advancements of technology, the medical data has increased dramatically, and therefore, there is a need to apply data mining and machine learning methods to extract new knowledge from this data. Several classification methods were used to analyze medical data sets and diagnostic problems, such as Parkinson's Disease (PD). In addition, to improve the performance of classification, feature selection methods have been extensively used in many fields. This paper aims to propose a comprehensive approach to enhance the prediction of PD using several machine learning methods with different feature selection methods such as filter-based and wrapper-based. The dataset includes 240 recodes with 46 acoustic features extracted from 3 voice recording replications for 80 patients. The experimental results showed improvements when wrapper-based features selection method was used with K-NN classifier with accuracy of 88.33%. The best obtained results were compared with other studies and it was found that this study provides comparable and superior results.

Bioactive compounds in plants, which can be synthesized using N-arylation methods such as the Buchwald-Hartwig reaction, are essential in drug discovery for their pharmacological effects. Important descriptors are necessary for the estimation of yields in these reactions. This study explores ten metaheuristic algorithms for descriptor selection and model a voting ensemble for evaluation. The algorithms were evaluated based on computational time and the number of selected descriptors. Analyses show that robust performance is obtained with more descriptors, compared to cases where fewer descriptors are selected. The essential descriptor was deduced based on the frequency of occurrence within the 50 extracted data subsets, and better performance was achieved with the voting ensemble than other algorithms with RMSE of 6.4270 and R2 of 0.9423. The results and deductions from this study can be readily applied in the decision-making process of chemical synthesis by saving the computational cost associated with initial descriptor selection for yield estimation. The ensemble model has also shown robust performance in its yield estimation ability and efficiency.