This paper introduces TDL-RGTA, a formal Temporal Defeasible Logic framework that enhances Role-Based Access Control (RBAC) by integrating organizational groups and contextual tasks into a dynamic, logic-based authorization model. Conventional RBAC and its temporal variants (TRBAC) are inherently static, struggling with real-time policy conflicts, context-specific exceptions, and the need for explainable decisions. TDL-RGTA addresses these limitations by employing defeasible reasoning under temporal constraints, in which permissions are dynamically derived from an agent’s role, active group membership, and task context. The framework introduces three key innovations: 1) group-task binding, which scopes role permissions to specific departmental contexts; 2) localized role hierarchies, which confine inherited permissions within an organizational group to prevent cross-departmental privilege leaks; and 3) structured, rule-based explanations, which provide transparent, auditable trails for every access decision by logging the rules triggered and overridden during reasoning; and 4) automated, distributed enforcement of the Separation of Duties across organizational boundaries. A hospital emergency-response case study demonstrates how TDL-RGTA maintains security, adapts in real-time to emergencies, and provides a formal foundation for compliance with standards such as NIST SP 800-53. The results establish TDL-RGTA as a secure, adaptive, and explainable access control framework, particularly well-suited for complex, decentralized environments, such as multi-agent systems.

In dynamic and regulated environments, sensitive resources are accessed remotely via heterogeneous devices and diverse networks, all of which are governed by complex access control policies. These environments experience unpredictable changes, with threats evolving during authenticated sessions, which increases the risk of security breaches and unauthorized access. This raises the need for transparent, explainable, and verifiable access decisions, even in the presence of policy conflicts. Adaptive risk-based access control models are context-sensitive, derive access decisions from surrounding environmental conditions, and yet produce access decisions that cannot be traceable or justifiable. Moreover, these models rely on classical monotonic reasoning which cannot detect or resolve simultaneously applicable conflicting policies. Most risk-based approaches lack principled enforcement of zero trust architecture principles: least privilege access proportional to evaluated risk, continuous verification of evolving context, and revision of access decisions. This paper proposes a Context-aware Temporal Defeasible Logic framework for risk-based access control (CTDL-RAC). It provides a unified solution by formally integrating an adaptive risk evaluation that derives graduated, context-sensitive risk outcomes mapped to proportional access responses. It employs a Context-aware, Temporal Defeasible Logic (CTDL) reasoning engine to handle conflicting policies transparently and to generate policy-traceable access decisions. The Zero Trust architecture principles are enforced in the framework by allowing for continuous evaluation of contextual conditions and active decisions, thus ensuring that access control is aligned with the current security state. The framework is implemented in a hospital setting and tested in an SWI-Prolog prototype, demonstrating policy compliance, conflict resolution, and explainable decision derivation.

Security is one of the most challenging requirements to construct and develop smart cities. That is due to fact that smart city utilizes IoT advanced solutions to provide the integration of the numerous, and heterogeneous smart devices. The heterogeneity of IoT creates the opportunity to launch multiple cyberattacks against different smart city services. Thus, security have been considered as a major issue in smart city development and research. In this survey, we provide an overview of the research works that have investigated security in smart city from different aspects. We demonstrate researches that have explored security of smart city from general perspective. Then, we introduce an overview of the use of machine learning to secure smart cities. Finally, we present the development of ontologies for security purposes, from general perspective and for smart city in particular. We highlight the most significant observations on the presented research works which need to be considered in future to enhance security in IoT-based smart city.

Ontologies offer a powerful means of structuring medical knowledge for AI-driven diagnosis. This paper investigates the conceptual design of a framework that integrates ontologies and logical reasoning to automate the diagnosis of nutrition-related medical conditions. There is a significant gap in the literature on direct diagnosis using ontologies and logical reasoning for such conditions. By proposing a theoretical framework, this work aims to enhance diagnostic accuracy, efficiency, and reliability while providing explainable diagnoses. It is important to note that this study is part of an ongoing Ph.D. thesis and that the implementation of the proposed framework is planned in future work. This approach has the potential to improve patient outcomes and reduce healthcare costs significantly.

The healthcare industry is facing mounting pressure due to population increase, a higher prevalence of diseases, and an expanding volume of patient data collected by hospitals. While machine learning (ML) has been successfully used to develop data management systems, the enormous volume of sensitive medical data and privacy issues frequently limit its broad use. Furthermore, the absence of accurate and organized clinical data continues to be a key impediment to the efficient application of standard ML models in healthcare. To solve these challenges, Federated Learning (FL), an advanced method within the larger ML field, has emerged as a possible option. FL provides collaborative model training without the requirement to centralize data, ensuring anonymity while managing large datasets from multiple institutions. This paper provides a comprehensive review of recent research on Federated Learning for Healthcare (FLHC) with deep learning models. It describes the development framework of FLHC systems for various healthcare activities, as well as cutting-edge methodologies based on deep-federated learning architectures. Also, it examines the common benchmark datasets and evaluation criteria used in FLHC, emphasizing numerous obstacles and intriguing research avenues in the field. This thorough study seeks to provide a wide view on FLHC by exploring the most recent approaches and tactics for improving healthcare data management while resolving privacy and accuracy concerns.

Deep learning, a machine learning branch, is the core infrastructure in today's technology evolution. A deep learning model's performance improves with the training data's size. However, privacy and ownership matters prevent the combination of medical data with traditional centralized storage. Decentralized learning approaches enable collaborative model training by distributing the learning process among several nodes. This paper focuses on Federated Learning, a recent and emerging technique that employs a weighted federated learning approach for diabetes prediction to address the diversity of data distribution among multiple clients in federated learning settings. The utilized approach dynamically adjusts each client's weight based on its contribution to the global model improvement. Experiments conducted across ten distributed clients using public CDC datasets with 253,680 records and three classes for diabetes prediction demonstrate that the approach consistently outperforms traditional federated learning and centralized learning methods in terms of accuracy F1 score. In the final rounds, this approach achieves over 90% accuracy in addition to preserving data privacy and reducing loss effectively. The FL approach for diabetes detection aims to address privacy concerns and improve accuracy while maintaining the centralized framework and leveraging an advanced algorithmic approach.

Over the past decade, knowledge resources have become central to advancing digital health, particularly in nutrition research. Nutrition is crucial for human growth, development, metabolism, and immunity, making it a key focus in public health and personalized medicine. Ontologies and Knowledge Graphs (KGs) have emerged as essential tools for addressing challenges in this field. This systematic review, conducted following the PRISMA guidelines, focuses primarily on the use of ontologies in human nutrition, including their applications, development methodologies, construction resources, evaluation criteria, and associated challenges. KGs are considered in a secondary role to support the preliminary analysis and provide insights into related applications. The review covers studies published between 2014 and 2024. A comprehensive search across Scopus, Web of Science, IEEE Xplore, and ACM Digital Library identified 58 studies, including 45 utilizing ontologies and 13 employing KGs. The findings reveal a growing use of these tools to develop personalized recipes, nutrient intake recommendations, food suggestions, dietary plans, and recommendation systems. However, significant gaps persist in the standardization of methodologies, resource integration, and evaluation criteria, limiting interoperability and scalability for personalized applications. Ontology-based systems dominate knowledge representation, while KGs are being explored for personalization in diet planning and data integration. To our knowledge, this is the first systematic review to exclusively focus on the intersection of ontologies with a preliminary analysis of KGs in human nutrition. By bridging computational techniques with nutritional science, this review establishes the foundation for innovative applications in digital health and personalized nutrition, contributing to improved public health outcomes.

Autism spectrum disorder (ASD) is a developmental disorder that encompasses difficulties in communication (both verbal and non-verbal), social skills, and repetitive behaviors. The diagnosis of autism spectrum disorder typically involves specialized procedures and techniques, which can be time-consuming and expensive. The accuracy and efficiency of the diagnosis depend on the expertise of the specialists and the diagnostic methods employed. To address the growing need for early, rapid, cost-effective, and accurate diagnosis of autism spectrum disorder, there has been a search for advanced smart methods that can automatically classify the disorder. Machine learning offers sophisticated techniques for building automated classifiers that can be utilized by users and clinicians to enhance accuracy and efficiency in diagnosis. Eye-tracking scan paths have emerged as a tool increasingly used in autism spectrum disorder clinics. This methodology examines attentional processes by quantitatively measuring eye movements. Its precision, ease of use, and cost-effectiveness make it a promising platform for developing biomarkers for use in clinical trials for autism spectrum disorder. The detection of autism spectrum disorder can be achieved by observing the atypical visual attention patterns of children with the disorder compared to typically developing children. This study proposes a deep learning model, known as T-CNN-Autism Spectrum Disorder (T-CNN-ASD), that utilizes eye-tracking scans to classify participants into ASD and typical development (TD) groups. The proposed model consists of two hidden layers with 300 and 150 neurons, respectively, and underwent 10 rounds of cross-validation with a dropout rate of 20%. In the testing phase, the model achieved an accuracy of 95.59%, surpassing the accuracy of other machine learning algorithms such as random forest (RF), decision tree (DT), K-Nearest Neighbors (KNN), and multi-layer perceptron (MLP). Furthermore, the proposed model demonstrated superior performance when compared to the findings reported in previous studies. The results demonstrate that the proposed model can accurately classify children with ASD from those with TD without human intervention.

Recently, smart contracts were introduced as a necessity to automatically execute specific operations within blockchain systems. The popularity and diversity of blockchain systems attracted intensive attentions from academia, industry and other sectors. Blockchain systems were implemented using different programming languages that used in defining the triggering events and their consequent actions within the smart contract. In this article, we propose a digital evidences preservation framework that supports logic-based smart contracts to manage entries associated with digital evidences. Combining logic-based approach and blockchain systems may result in ensuing contracts that have technical advantages over procedural coding. The paper shows the motivation for choosing logic-based approach to define a smart contract. We introduce the rules and structure of the proposed logic-based contract.

Time-series analysis is a widely used method for studying past data to make future predictions. This paper focuses on utilizing time-series analysis techniques to forecast the resource needs of logistics delivery companies, enabling them to meet their objectives and ensure sustained growth. The study aims to build a model that optimizes the prediction of order volume during specific time periods and determines the staffing requirements for the company. The prediction of order volume in logistics companies involves analyzing trend and seasonality components in the data. Autoregressive (AR), Autoregressive Integrated Moving Average (ARIMA), and Seasonal Autoregressive Integrated Moving Average with Exogenous Variables (SARIMAX) are well-established and effective in capturing these patterns, providing interpretable results. Deep-learning algorithms require more data for training, which may be limited in certain logistics scenarios. In such cases, traditional models like SARIMAX, ARIMA, and AR can still deliver reliable predictions with fewer data points. Deep-learning models like LSTM can capture complex patterns but lack interpretability, which is crucial in the logistics industry. Balancing performance and practicality, our study combined SARIMAX, ARIMA, AR, and Long Short-Term Memory (LSTM) models to provide a comprehensive analysis and insights into predicting order volume in logistics companies. A real dataset from an international shipping company, consisting of the number of orders during specific time periods, was used to generate a comprehensive time-series dataset. Additionally, new features such as holidays, off days, and sales seasons were incorporated into the dataset to assess their impact on order forecasting and workforce demands. The paper compares the performance of the four different time-series analysis methods in predicting order trends for three countries: United Arab Emirates (UAE), Kingdom of Saudi Arabia (KSA), and Kuwait (KWT), as well as across all countries. By analyzing the data and applying the SARIMAX, ARIMA, LSTM, and AR models to predict future order volume and trends, it was found that the SARIMAX model outperformed the other methods. The SARIMAX model demonstrated superior accuracy in predicting order volumes and trends in the UAE (MAPE: 0.097, RMSE: 0.134), KSA (MAPE: 0.158, RMSE: 0.199), and KWT (MAPE: 0.137, RMSE: 0.215).

The term “multi-agent systems” (MAS) refers to a mechanism that is used to create goal-oriented autonomous agents in a shared environment and have communication and coordination capabilities. This goal-oriented mechanism supports distributed data mining (DM) to implement various techniques for distributed clustering, classification, and prediction. Different distributed DM (DDM) techniques, MASs, the advantages of MAS-based DDM, and various MAS-based DDM approaches proposed by researchers are reviewed in this study.

The recommender system (RS) improves the users’ experience when searching for and buying items by providing recommendations. This paper presents a new hybrid RS called SemCF. SemCF integrates the item’s semantic information and the historical rating data to generate the recommendations. The semantic information is used to determine the users with the same interests, while rating data is used to estimate the similarity between users in terms of satisfaction level. SemCF produces a unified list of neighbors based on these similarities and uses it in the prediction step. The proposed method is evaluated on two benchmark datasets. The experimental results show its superiority compared to the results of alternative techniques and the ability of SemCF to mitigate cold-start and sparsity.

Although learning from data is effective and has achieved significant milestones, it has many challenges and limitations. Learning from data starts from observations and then proceeds to broader generalizations. This framework is controversial in science, yet it has achieved remarkable engineering successes. This paper reflects on some epistemological issues and some of the limitations of the knowledge discovered in data. The document discusses the common perception that getting more data is the key to achieving better machine learning models from theoretical and practical perspectives. The paper sheds some light on the shortcomings of using generic mathematical theories to describe the process. It further highlights the need for theories specialized in learning from data. While more data leverages the performance of machine learning models in general, the relation in practice is shown to be logarithmic at its best; After a specific limit, more data stabilize or degrade the machine learning models. Recent work in reinforcement learning showed that the trend is shifting away from data-oriented approaches and relying more on algorithms. The paper concludes that learning from data is hindered by many limitations. Hence an approach that has an intensional orientation is needed.

Distributed Data Mining (DDM) has been proposed as a means to deal with the analysis of distributed data, where DDM discovers patterns and implements prediction based on multiple distributed data sources. However, DDM faces several problems in terms of autonomy, privacy, performance and implementation. DDM requires homogeneity regarding environment, control, administration and the classification algorithm(s), and such that requirements are too strict and inflexible in many applications. In this paper, we propose the employment of a Multi-Agent System (MAS) to be combined with DDM (MAS-DDM). MAS is a mechanism for creating goal-oriented autonomous agents within shared environments with communication and coordination facilities. We shall show that MAS-DDM is both desirable and beneficial. In MAS-DDM, agents could communicate their beliefs (calculated classification) by covering private and non-sharable data, and other agents decide whether the use of such beliefs in classifying instances and adjusting their prior assumptions about each class of data. In MAS-DDM, we will develop and use a modified Naive Bayesian algorithm because (1) Naive Bayesian has been shown to be the most used algorithm to deal with uncertain data, and (2) to show that even if all agents in MAS-DDM use the same algorithm, MAS-DDM preforms better than DDM approaches with non-communicating processes. Point (2) provide an evidence that the exchange of information between agents helps in increasing the accuracy of the classification task significantly.

International programs are spread in private schools in Jordan, especially in Amman. Each program has specific characteristics and requirements to be considered when the parents choose the suitable program for their child according to his/her learning abilities, program requirements and characteristics. This paper presents machine learning experiments to generate predictive model that determines whether the IB program is fit for the student or not. The predictive model can produce list of the most important features (skills and requirements) that help building the model. This paper examines the quality of the predictive model after testing several machine learning algorithms on data collected from a conducted survey. The quality of the predictive model was enhanced after extracting new features based on Approaches to Learning (ATL) skills in the IB program. The results show that machine learning, with efforts made on building special features, can be used to build an effective model for determining the suitable international program.

Exploration and exploitation are the two main concepts of success for searching algorithms. Controlling exploration and exploitation while executing the search algorithm will enhance the overall performance of the searching algorithm. Exploration and exploitation are usually controlled offline by proper settings of parameters that affect the population-based algorithm performance. In this paper, we proposed a dynamic controller for one of the most well-known search algorithms, which is the Genetic Algorithm (GA). Population Diversity Controller-GA (PDC-GA) is proposed as a novel feature-selection algorithm to reduce the search space while building a machine-learning classifier. The PDC-GA is proposed by combining GA with k-mean clustering to control population diversity through the exploration process. An injection method is proposed to redistribute the population once 90% of the solutions are located in one cluster. A real case study of a bankruptcy problem obtained from UCI Machine Learning Repository is used in this paper as a binary classification problem. The obtained results show the ability of the proposed approach to enhance the performance of the machine learning classifiers in the range of 1% to 4%.

Click fraud is a serious problem facing online advertising business. The malicious intent of clicking online ads either committed by humans or by non-humans, forced financial losses on advertisers utilizing pay-per-click advertising. Non-human traffic is usually designed to inflate web traffic for fraudulent purposes. In this paper, we demonstrate a hybrid approach consisting of two-level fingerprint applied in two phases to detect illegitimate non-human traffic. The first-level fingerprint is a pattern generated using immutable information about a user navigating a website's pages. It will be used in the first traffic illegitimacy detection phase to infer rules about illegitimate non-human traffic from a developed ontology about web traffic legitimacy. The second-level fingerprint is generated using behavioral ad click patterns, which will be used in the second detection phase by applying a Machine-Learning (ML) algorithm. To test the proposed approach, a real commercial website for ads, called Waseet.com, was used. The access logs of the website server were utilized for the purpose of this research. The experiments show that our proposed hybrid approach using the ontology of web traffic illegitimacy and the ML k-NN classifier detects around (98.6%) of fake clicks.

This paper, lays down the logical foundations for a personalized medical prescription system. The proposed system employs detailed pharmaceutical and medical knowledge about a medication and its effects or side effects on the patient, which may go beyond what is available in medication leaflets. The ontology was initially built for the proposed system and employs the description logic system, ALC, for knowledge representation. However, the uncertain nature of medical and medicinal knowledge poses some problems such as drug-drug interactions and drug-disease interactions, which render ALC inadequate to represent and reason within a system such as a personalized medical prescription system. Indeed, there is a need for a more flexible representation that allows reasoning with incomplete knowledge and possibly inconsistent cases. ALC is extended with defeasible rules to obtain defeasible ALC. Defeasible ALC allows the prevention of adverse drug interactions, detection drug-drug interactions and detection of drug-disease interactions. The ultimate purpose of this paper is providing to provide a standard knowledge base system toward a medical prescription capable of dealing with incomplete knowledge, conflicting information (inconsistencies) and exceptions cases, which will enhance individual healthcare and provide an appropriate prescription. This is accomplished by expanding the capabilities of description logic with defeasible rules, to achieve an accurate prescription decision for any patient's condition(s). Once implemented, a personalized medical prescription system intends to assist, not to replace, the clinician during medical prescription(s) or the pharmacist(s).

Extracting clinical data from medical or clinical reports is a crucial effort. These records contain the most valuable pieces of evidence of treatments in humans. Integration of information extraction (IE) and ontology can produce a great tool for clinical concept extraction. The aim of this paper is to present a quick overview of the research work which has applied IE and ontology approaches in medical or clinical concepts extraction. This paper also presents our proposed framework based on the integration of both approaches mentioned above for extracting clinical concepts.

Preterm birth, defined as a delivery before 37 weeks' gestation, continues to affect 8-15% of all pregnancies and is associated with significant neonatal morbidity and mortality. Effective prediction of timing of delivery among women identified to be at significant risk for preterm birth would allow proper implementation of prophylactic therapeutic interventions. This paper aims first to develop a model that acts as a decision support system for pregnant women at high risk of delivering prematurely before having cervical cerclage. The model will predict whether the pregnancy will continue beyond 26 weeks' gestation and the potential value of adding the cerclage in prolonging the pregnancy. The second aim is to develop a model that predicts the timing of spontaneous delivery in this high risk cohort after cerclage. The model will help treating physicians to define the chronology of management in relation to the risk of preterm birth, reducing the neonatal complications associated with it. Data from 274 pregnancies managed with cervical cerclage were included. 29 of the procedures involved multiple pregnancies. To build the first model, a data balancing technique called SMOTE was applied to overcome the problem of highly imbalanced class distribution in the dataset. After that, four classification models, namely Decision Tree, Random Forest, K-Nearest Neighbors (K-NN), and Neural Network (NN) were used to build the prediction model. The results showed that Random Forest classifier gave the best results in terms of G-mean and sensitivity with values of 0.96 and 1.00, respectively. These results were achieved at an oversampling ratio of 200%. For the second prediction model, five classification models were used to predict the time of spontaneous delivery; linear regression, Gaussian process, Random Forest, K-star, and LWL classifier. The Random Forest classifier performed best, with 0.752 correlation value. In conclusion, computational models can be developed to predict the need for cerclage and the gestation of delivery after this procedure. These models have moderate/high sensitivity for clinical application.