Automated Video Anomaly Detection (VAD) plays a vital role in developing surveillance systems in public spots. Our study develops real-time anomaly detection via a hybrid Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) model, which uses the UCSD Pedestrian (Ped2) dataset. It introduces a methodology designed for detection accuracy enhancements by extracting CNN-based spatial features combined with learning LSTM-based temporal sequences. Preprocessing manages the class imbalance issue throughout several phases, including frame extraction, resizing, normalization, augmentation, and SMOTE balancing. Regarding the evaluation phase, several metrics such as accuracy, precision, recall, F1-score, and AUC are applied, indicating the superior performance of the CNN-LSTM model, which could outperform both the standalone CNN and LSTM models, having 93.5% accuracy, 91.8% precision, 90.2% recall, 91.0% F1-score, and an AUC of 0.947. Conclusively, our methodology is designed for improving the accuracy of the detection phase by integrating CNN-based spatial feature extraction along with LSTM-based temporal sequence learning.

Smart city architectures have been varying from one community to another. Each community leader develops their own perspective of smart cities. Some of these communities focus on data management, while others focus on provided services and infrastructure. In this research, an attempt to propose a clear, complete, and efficient perspective of smart citiesis accomplished. The proposed generic architecture clarifies the full capabilities, requirements, and layers' contribution to a successful smart city development. The proposed architecture utilizes Internet of Things tools as well as agile standards in the description of each layer. The research aims to discuss each layer in detail, the relationships among layers, the applied technology, and every aspect that leads to the success of using the recommended architecture. Although smart cities, IoT, and agile research have previously tackled the relation of each one of them with the other, up to the researchers' knowledge,the three paradigms have not been previously considered as a unified collaborative approach. In order to reach the research target, the proposed architecture intelligently utilizes these paradigms and presents a robust architecture with high-quality standards

Evolutionary algorithms such as genetic algorithms have proved their effectiveness and reliability in optimization solutions. The genetic algorithm is one of the most powerful algorithms in optimizing solutions to various problems. However, such algorithms suffer from performance issues resulting from bottlenecks in their mechanisms. This research proposes an effective solution for raising the performance of a genetic algorithm with the idea of merging its mechanism with one of the swarm intelligence techniques. The proposed solution presents an effective model for the initialization task as well as minimizing the iterations while ensuring the optimized solution. The mimic concept for natural processes has leveraged the genetic algorithm computation to the optimized level. Linking genetic algorithms and particle swarm intelligence algorithm has proved their effectiveness through a set of experiments. Moreover, the proposed adapted algorithm has been applied to two experiments to prove the effectiveness compared with literature and in the education field in generating the most effective track for students targeting to enhance the student’s performance which is considered one of the strategic targets in all economies

The course selection process in higher education has grown more complex as the students face the growing volume of academic options that must align with their personal and career goals. The traditional advising methods often fail to provide the personalized recommendations, resulting in the delayed graduations and the higher dropout rates. Therefore, the automated and intelligent course selection models and systems are becoming more important. These AI-based systems nearly deliver the tailored guidance to the students by analyzing their academic performance. In addition, this guidance is also based on the students’ individual characteristics, helping to create the personalized course recommendations. This study presents a predictive model for the personalized course advising, in which it incorporates data from the academic, personal, and the social dimensions. Then, this model uses and employs the advanced machine learning algorithms and the optimization techniques and methods to maximize the accuracy of course recommendations. The feature selection methods like Information Gain and Chi-Square are used, in addition to dedicated classifiers such as the Decision Trees (DT) and the K-Nearest Neighbors (KNN). To balance the dataset, the Synthetic Minority Oversampling Technique (SMOTE) is applied. In the implementation phase, first, the Knapsack Problem algorithm is applied to optimize the students’ course loads in order to ensure the recommendations match their abilities and the institutional requirements. Next, the KNN is applied and reaches an accuracy of 91.57% and outperforms the DT, which provides a practical solution for the problem of adaptive course advising.

Digitalization is currently not a concept the world seeks to apply; rather, it is a fact this world lives in. The transformation for the green world has strongly introduced the principle of eliminating hard copy resources while maintaining their digital versions. The immense amount of information that resides in electronic documents opened a wide road for research a long time ago. On the other hand, information extraction, text mining, and Natural Language Processing (NLP) are three concatenated fields that have gained their unique place in the digital world through time. This research aims to introduce a novel method for Arabic document classification. The research provides multi-tagging to the document according to a set of criteria, one of these tags is the hierarchical classification for the document that could play an efficient role in its related field. For example, documents in healthcare systems beehive could lead to exploring a new symptom of a disease, as it is known that symptoms could continuously mutate over time. The proposed method succeeds through the generated schema to relate between old and new symptoms, which makes it no surprise when evolving and gives a chance for pre-preparation and success to containment. The technical challenges of this study include the ability to successfully apply text mining techniques and machine learning. Additionally, the higher level of challenges that arise in this study is the fact that the processing is applied to Arabic text documents. Arabic has been known to be a complex language as it has its unique nature. The proposed method has been applied, compared with known methods, and its effectiveness has been confirmed by applying a classification task with an Accuracy equal to 99.5%

The exponential growth of data sources brings the challenge of maintaining the processing performance and reducing computation complexity. One of the vital solutions is the success in preserving the significant attributes. Consequently, this research focuses on proposing an effective method for feature selection which is based on the adaptation of the chicken swarm optimization algorithm. The research focuses on adapting the algorithm strategy in the process of searching the data space from random-based strategy to a more systematic method which ensures raising the algorithm performance. The study proposes a novel search strategy based on applying an effective clustering technique to effectively identify the main algorithm players which consequently enhance the algorithm performance. On the other hand, focusing on business objectives, this research proposes a novel framework that focuses on the patients’ backlogs. The study applies the proposed enhancement to eliminate the patients’ backlog while maintaining the prioritization. The proposed framework is generic and could be applied to the concept of backlogs in any domain. The experiment succeeded in confirming the applicability of the proposed adaptation for the chicken swarm optimization algorithm and reaching the business goal with a minimum accuracy percentage equal to 95.3% for random forest and a maximum of 98.9 for naive Bayes

Transportation management in Egypt faces challenges such as congestion, inefficiency, and a lack of transparency. This work proposes a smart contract-based transportation framework to address these issues and enhance the efficiency of Egypt's transportation system. By leveraging blockchain technology, smart contracts can facilitate and enforce decentralized and immutable transportation agreements. This approach also fosters increased trust among stakeholders and improves interactions between service providers. This paper presents a conceptual framework that integrates smart contracts, blockchain technology, GPS data, and sensor technologies to further optimize transportation operations. Empirical analysis and case studies demonstrate the effectiveness of smart contracts in improving the shipping registration system. The survey results show that smart contracts streamline processes enhance data security, reduce costs, and improve accuracy. The proposed model, developed on the NEAR platform, outperforms traditional methods and Ethereum-based models by offering faster registration, better cost-efficiency, and improved transaction tracking. This demonstrates the potential for modernizing and optimizing Egypt's transportation sector.

In this research, a set of data mining techniques are applied to target to balance between the industry requirement and user satisfaction. The proposed approach aims at exploring the most significant attributes for the industry services' evaluation. The exploration goal ensures a double-sided benefit for both the industry and the user. From one perspective, it raises the evaluation accuracy level for the main service's attributes which is most important to the user and consequently leads to higher user satisfaction. On the other side, it minimizes the user's collaboration effort in the evaluation process which raises the user's collaboration willingness. The proposed approach has been applied to the IoT services industry in Saudi Arabia. The results proved that eliminating insignificant attributes has provided minimal user effort with retaining the required evaluation accuracy and the success percentage reached 90%.

Nowadays, Businesses are mutating to social media platforms and websites as a new source of information and knowledge to get competitive advantages. Hence, the term NoSQL databases known as Internet era databases revealed as a solution because of raising urgency in the demand for scalability and performance. This paper presents an overview study for the evolution of databases, different forms of NoSQL databases in addition to their features, advantages and disadvantages. This paper also seeks to cover the shortage of focusing on the quality attributes based methodologies to NoSQL databases that have been largely overlooked in the previous studies and creates a brief comparison that illustrates this issue.

Delivering the most suitable products and services essentially relies on successfully exploring the potential relationship between customers and products. This immense need for intelligent exploration has led to the emergence of recommendation systems. In an environment where an immense variety exists, it is vital for buyers to own an intelligent exploratory map to guide them in finding their choices. Personalization has proven to be a successful contributor to recommenders. It provides an accurate guide t o explore the users' preferences. In the field of recommendation systems, the performance of the systems has been continuously measured by their success in accurate, personalized recommendations. There is no argument that personalization is one key success; however, this research argues that recommendation systems are not only about personalization. Other success factors should be considered in targeting optimality. The current research explores the hierarchy map representing the strengths and dependencies of the recommendation systems pillars associated with their influence level and relationships. Moreover, the research proposes a novel predictive approach that applies a hybrid of content and collaborative filtering recommendation systems to provide the most suitable customer recommendations effectively. The model utilizes a proposed features selection approach to detect the most significant features and explore the most effective associations' schemes for the recommendations label feature. The proposed model is validated using a benchmark dataset by extracting direct and transitive associations and following the identified schematic for the required recommendations. The classification techniques are applied, proving the model's applicability with an accuracy ranging from 96% to 99%.

The diversity of data sources resulted in seeking effective manipulation and dissemination. The challenge that arises from the increasing dimensionality has a negative effect on the computation performance, efficiency, and stability of computing. One of the most successful optimization algorithms is Particle Swarm Optimization (PSO) which has proved its effectiveness in exploring the highest influencing features in the search space based on its fast convergence and the ability to utilize a small set of parameters in the search task. This research proposes an effective enhancement of PSO that tackles the challenge of randomness search which directly enhances PSO performance. On the other hand, this research proposes a generic intelligent framework for early prediction of orders delay and eliminate orders backlogs which could be considered as an efficient potential solution for raising the supply chain performance. The proposed adapted algorithm has been applied to a supply chain dataset which minimized the features set from twenty-one features to ten significant features. To confirm the proposed algorithm results, the updated data has been examined by eight of the well-known classification algorithms which reached a minimum accuracy percentage equal to 94.3% for random forest and a maximum of 99.0 for Naïve Bayes. Moreover, the proposed algorithm adaptation has been compared with other proposed adaptations of PSO from the literature over different datasets. The proposed PSO adaptation reached a higher accuracy compared with the literature ranging from 97.8 to 99.36 which also proved the advancement of the current research.

Business is a war to get the attention you deserve from your enemies, and many competitors strive to gain a prominent position. Organizations are constantly seeking innovative ways to work to stay in a competitive business environment. Business process reengineering (BPR) is one of the most management approaches that are adopted by many organizations in order to achieve a dramatic increase in performance and cost reduction. Since the risks enfolded and failure rates related to BPR projects are very high, it is necessary to find ways to support success of BPR in a systematic approach. The major target of this article is to find the implementation of the proposed model to reengineer business processes (BPs) successfully via integrating critical success factors (CSFs) of BPR and BPs' performance. It is created to detect the inefficiencies and bottlenecks in the business process, decrease costs, time and increase quality of business processes, enhance financial environment and make an effective and efficient performance of the business process. It also applies a mining technique of association rule to examine the link between CSFs and several BPs and measures business processes' performance (intended BPR success) by process time, cycle time, quality and cost pre and post reengineering BPs. Thus, it uses a way to select the appropriate model for each business process. The proposed model will be implemented using a real world the Egyptian tax authority case study in order to prove its usefulness and efficiency. Then, inferred CSFs were applied according to each process, which proved the validity and success of the proposed model.

This paper proposes a new robust watermarking method for securing color medical images, where the proposed method relies on combining Slant, Singular Value Decomposition (SVD), and quaternion Fourier-Transform (QFT). The stimulus behind this combination is to improve the invisibility and durability of the proposed method. First, the input cover image is split into four equal parts for fast computation and then encrypted using one-time padding (OTP) encryption to increase robustness. Slant transform is applied to encrypted blocks to increase image compaction. The SVD is applied to the transformed image blocks to preserve quality during the embedding process. Finally, the QFT is applied to increase visual imperceptibility. The binary watermark is first compressed using SVD, scrambled using Arnold encryption to raise security, and then embedded in the modified QFT coefficients. The extraction procedures are the inverse operations of the embedding procedures. The proposed method achieves a good tradeoff between invisibility and robustness compared to existing schemes versus many geometrical, processing, and hybrid attacks. Also, the proposed method attains high visual imperceptibility. The extracted watermark seems to be the original watermark with minimum BER and high NC values. Empirical findings indicate that the proposed method is giving better invisibility and robustness results while maintaining a high capacity compared to other existing watermarking methods.

Engaging personalization in the education process is considered one of the success factors for raising the educational process quality by altering the educational institutions’ vision for gaining more flexibility while attaining the institution’s objectives. It is a fact that the situation of the COVID-19 pandemic is one of the main reasons that forwarded attention to online learning as an obligatory path rather than being optional until the arisen situation of the COVID-19 pandemic. This situation has altered the educational institutions’ perspective permanently. This research proposes an intelligent model which considers the personalized student characteristics in exploring the student learning styles variation, then considering this variation in building the student exam. Following this model ensures the compatibility of the conducted exam with the student’s capabilities as well as the course Intended Learning Outcomes (ILOs) coverage. The balance in building the exam with covering the course objectives as well as the appropriateness with the student’s personalized characteristics is the main objective of this research. The proposed model has been applied and proved its applicability in enhancing the students’ exam results to 92.36% and raising the exam quality level.

According to the advances in users' service requirements, physical hardware accessibility, and speed of resource delivery, Cloud Computing (CC) is an essential technology to be used in many fields.Moreover, the Internet of Things (IoT) is employed for more communication flexibility and richness that are required to obtain fruitful services.A multi-agent system might be a proper solution to control the load balancing of interaction and communication among agents.This paper proposes a multi-agent load balancing framework that consists of two phases to optimize the workload among different servers with large-scale CC power with various utilities and a significant number of IoT devices with low resources.Different agents are integrated based on relevant features of behavioral interaction using classification techniques to balance the workload.A load balancing algorithm is developed to serve users' requests to improve the solution of workload problems with an efficient distribution.The activity task from IoT devices has been classified by feature selection methods in the preparatory phase to optimize the scalability of CC.Then, the server's availability is checked and the classified task is assigned to its suitable server in the main phase to enhance the cloud environment performance.Multi-agent load balancing framework is succeeded to cope with the importance of using large-scale requirements of CC and (low resources and large number) of IoT.

Distributed Denial of Service (DDOS) attacks aim to exploit the capacity and performance of a network's infrastructure, making the cloud environment one of the biggest targets for attackers. Many efforts are being made in the field of technology to prevent them from disrupting the services provided. Machine Learning techniques are a means to protect against DDOS attacks. Data preprocessing, feature selection, and classifiers are the main components of any prevention framework. The focus of this study is to find and enhance the feature selection approach for increasing the accuracy of the classifiers in detecting DDOS attacks from regular traffic. We used four different techniques, including Pearson Correlation Coefficient (PCC), Random Forest Feature Importance (RFFI), Mutual information (MI), and Chi-squared(X2) measure which we tested on different classifiers. The first selection approach was based on the feature’s independency level then the second iteration was based on the feature’s importance. We also examined the claim of dropping attacks from the dataset for better accuracy. The best performing set of features was from using PCC and RFFI together for feature selection with average accuracy and precision of 99.27% and 97.60%, which is higher than the use of PCC for both measures by almost 2%. The accuracy is also higher by nearly 12% from the same approach dropping 50% of the attacks.

According to the advances in users' service requirements, physical hardware accessibility, and speed of resource delivery, Cloud Computing (CC) is an essential technology to be used in many fields. Moreover, the Internet of Things (IoT) is employed for more communication flexibility and richness that are required to obtain fruitful services. A multi-agent system might be a proper solution to control the load balancing of interaction and communication among agents. This paper proposes a multi-agent load balancing framework that consists of two phases to optimize the workload among different servers with large-scale CC power with various utilities and a significant number of IoT devices with low resources. Different agents are integrated based on relevant features of behavioral interaction using classification techniques to balance the workload. A load balancing algorithm is developed to serve users' requests to improve the solution of workload problems with an efficient distribution. The activity task from IoT devices has been classified by feature selection methods in the preparatory phase to optimize the scalability of CC. Then, the server's availability is checked and the classified task is assigned to its suitable server in the main phase to enhance the cloud environment performance. Multi-agent load balancing framework is succeeded to cope with the importance of using large-scale requirements of CC and (low resources and large number) of IoT.

This research proposes a multi-level predictive algorithm based on the k-means algorithm with multiple adaptations. The research highlights the main limitations of k-means and proposes a set of adaptations that enhance the clustering task results in accuracy with minimal centroid distance error. The study proposes three enhancements in selecting the number of clusters, identifying the initial point, and exploring the contributing features set. Moreover, prediction is performed through a multi-level paradigm targeting performance enhancement by following the partitioning approach. The research experimental study focused on applying the proposed algorithm to the healthcare supply chain as it is one of the most influential factors for health services delivery. The proposed algorithm is applied to a dataset that is offered by USAID which includes 31622 records with 104 attributes. The proposed algorithm aims to predict the valued information in the supply chain progress such as predicted delivery time, predicted delay time, and other vital attributes. The data source is the USAID dataset; however, the research utilized the dataset for multiple objectives in vital aspects prediction of the healthcare supply chain with an average accuracy of 97.45%.

Distributed Denial of services is one of the most dangerously planned attacks in cloud computing, resulting in huge losses of data and money for both the cloud services providers and the users of these services. Many efforts have been performed to help protect the cloud from these attacks using machine learning techniques. This study focuses on enhancing the efficiency of the Gaussian Naïve Bayes classifier, considered one of the cheapest and fastest classifiers. Still, it has some problems resulting from its equation’s statistical nature. The nature of this classifier is based on multiplication, resulting in inaccurate classification due to the zero-frequency issue and the fact that it assumes that features are independent. This research proposed a framework handling the selection of a set of highly independent features following an iterative feature selection approach using the Pearson Correlation Coefficient, Mutual Information, and Chi-squared and then selecting other subsets of features from these sets to reach a set of highly independent features. After that, we used a specific algorithm handling the data pre-processing to handle the zero-frequency problem where we used the Mode to replace the missing values, and if the mode was zero, it used the mean instead. Still, if the record’s label is zero, we get the value of the previous record with zero labels. After that, we handled the data imbalances using SMOTE. These enhancements increased both accuracy for the mutual information model by 2% and the average overall accuracy and precision by 1.5%.

In the era of cloud computing, the effectiveness of utilizing supervised machine-learning-based intrusion detection models for categorizing and detecting malicious network attacks depends on the preparation, extraction, and selection of the optimal subset of features from the dataset. Therefore, before beginning the training phase of the machine learning classifier models, it is required to remove redundant data, manage missing values, extract statistical features from the dataset, and choose the most valuable and appropriate attributes using the Python Jupyter Notebook. In this study, partitioning-based recursive feature elimination (PRFE) method was suggested to decrease the complexity space and training time for machine learning models while increasing the accuracy rate of detecting malicious attacks. On the information security and object technology cloud intrusion dataset (ISOT-CID), some of the most popular supervised machine learning classification techniques, including support vector machines (SVM) and decision trees (DT), have been assessed using the suggested PRFE technique. In comparison to some of the most popular filter and wrapper-based feature selection strategies, the results of the practical experiments demonstrated an improvement in accuracy, recall, F-score, and precision rate after using the PRFE technique on the ISOT-CID dataset. Additionally, the time required to train the machine-learning models was reduced.