Phishing attacks put users' sensitive information at serious risk and are a rising concern in cybersecurity. In order to minimize the possible damage brought on by these assaults, it is essential to detect and categorize phishing websites correctly. In this study, we provide an Apriori-based analysis method for identifying and categorizing website phishing. The Apriori algorithm, which is frequently used in association rule mining, provides a distinctive viewpoint for examining the traits and patterns of phishing websites. This study aims to find significant associations that can help distinguish between legal and phishing websites by using the Apriori algorithm to a dataset of website attributes and related phishing labels. An extensive collection of website labels and attributes, including URL structure, HTML content analysis and other behavioral indicators from UCI, was gathered for the study. We compared the effectiveness of the Apriori-based approach to other phishing detection techniques now in use, such as other machine learning algorithms. In order to create the best rules for this study, the researchers chose to alter the 11,000 datasets run on Weka Software using the Apriori Algorithm. Further, the researchers developed the ten best rules for association on how the Apriori algorithm may be utilized to improve phishing attack detection. This study could improve web security protocols and help prevent phishing attempts, protecting user data and lessening the financial toll of cybercrime.

The impact of the COVID-19 pandemic on global education, with the massive closure of schools and universities. It highlights the challenge of adapting to distance learning modalities and the loss of students' knowledge. In this context, the use of Artificial Intelligence (AI) has become a promising alternative to improve distance education; it is presented as a solution to automate administrative tasks and personalize learning. The research work conducted focuses on how an AI-based e-learning system has improved academic management and learning at the institution. The study involved the participation of 20 experts, who evaluated the prototype in terms of efficiency, usability, technology, functionality, and design. As a result of the evaluation of the criteria, 93% in design and 92% in functionality were obtained. Likewise, 68.9% of experts determined that the system has a "Good" efficiency, with the highest percentage followed by 64.4% of "very good" efficiency. In conclusion, efficiency has a high degree of satisfaction due to being fast and efficient.

Big data Processing and the IoT have recently gained popularity as study topics in MEC and thorough research is sought for well-informed decisions. Mobile edge equipment, such as base stations, routers, and edge servers, usually have limited processing capabilities compared to traditional data centers. According to this perspective, this research constructs MEC using Intelligent Outlier Detection with a Multidimensional Generative Adversarial Network (IOD-MDGAN). The suggested structure uses servers at the edge, mobile phones, and cloud resources to achieve minimal latency, lower bandwidth usage, and more scalability. To eliminate outliers from the data, the suggested model uses an adaptive synthetic sampling-based outlier identification technique. Complete start and completion timings for base station connectivity are included in the statistics to gather the information for every mobile user. Data pre-processing for the Adaptive Median Filter (AMF) filter eliminates the noisy data from raw data samples. Feature selection was used for Particle Swarm Optimization (PSO) to choose a suitable group of characteristics. To differentiate between several class labels, an extended immediate memory-based classification model is needed. The innovative nature of the study is demonstrated by the designs of the PSO algorithm for feature selection with the Synthetic Minority Over-sampling Technique (SMOTE) approach for massive data. The results show that the IOD-MDGAN technique has better latency (78 ms), higher throughput (750 Mbps), a faster detection rate (96 ms), a higher data delivery ratio (900 ms), and a higher cost-effectiveness (79). Adapted big data processing architectures designed for MEC provide significant potential for reshaping data use inside mobile applications.

The designed judicial system is frequently unavailable to people, it is needed in a long time to process and is expensive. Blockchain technology proposes a potential explanation for these cases by facilitating the construction of a virtual judge that can automate considerable dispute resolution processes. This study suggests utilizing blockchain technology with Network Function Virtualization (NFV) to create a virtual judge offering benefits like efficiency, security, accessibility, transparency, and confidence. By using smart contracts in practice, legal procedures could be performed independently, ensuring impartial, transparent, and bias-free decisions. The results of this study show that the virtual judge system improves accessibility, drastically reduces the time and expense of court cases, and keeps the integrity of judicial procedures with gratitude to decentralized administration. Through a relative investigation of the Virtual Judge system's implementation parameters in both its NFV-enabled and non-enabled states, we show how virtualization improves scalability, performance, and energy efficiency. In conclusion, presented a new view of the evolution of blockchain-based dispute resolution and stressed the significance of keeping an open mind about the possible applications of blockchain technology across a range of sectors, including dispute resolution. Blockchain technology's capacity to develop a virtual judge has the possibility to fully transform the method that matches are determined by delivering a transparent, effective, safe, reliable, and accessible platform for resolving conflicts in a combination of conditions.

Optical Character Recognition (OCR) is crucial for identifying and extracting information from scientific documents. However, recognizing online handwritten physics expressions remains a relatively unexplored area of research. In the existing literature, most of the researchers worked on CNN classification to identify mathematical expressions. The traditional Convolution Neural Network (CNN) has limitations for extracting sequential data. This study proposes a CRNN (Convolution Recurrent Neural Network)-LSTM (Long Short-Term Memory) model that uses sequence a to-sequence approach for recognition of online handwritten physics expressions to enhance the feature extraction process for the sequential data which overcomes the limitations of CNN. A dataset was constructed from 100 users using a Java-based interface, covering five commonly used types of physics expressions: (1) Electric flux; (2) Maxwell’s equations; (3) Inductance; (4) Pointing vector, and (5) Moment of inertia. This dataset identifies 25 unique Physics symbols. The Online Handwritten Physics Expression (OHPE) dataset comprises a total of 500 physics expressions, including operators, special symbols, alphabets, and numbers. The proposed architecture of CRNN-LSTM architecture consists of convolution layers followed by LSTM layers for sequence processing. CTC (Connectionist Temporal Classification) loss function is used to train the model, which is particularly used to predict the sequence of symbols within the physics expressions. The performance evaluation has been carried out and the accuracy of symbol level and expression level prediction is reported. In the final stage the trained model is evaluated to make the predictions on the unseen test set images with the recognition accuracy of 96.36% at the expression level and 98.10% at the symbol level.

This study examines the implementation of Test Case Prioritization (TCP) using the Greedy Algorithm (GA) to enhance regression testing efficiency within a financial technology company's software development cycle. With testing durations increasing significantly, this study aims to address inefficiencies by applying the Greedy Algorithm to optimize test suite size and fault detection. The research methodology involves applying the Greedy Algorithm during the Regression Testing phase, comparing the prioritized suite with the original suite using metrics such as Average Percentage Fault Detection (APFD) and Test Suite Size Reduction (TSSR). Results show that the Greedy Algorithm achieved substantial improvements in both test suite size and fault detection effectiveness across different projects. For Project A, the test suite was reduced from 51-22 test cases, achieving a TSSR of 56.8%, with an APFD increase of 206.21%, rising from 0.0853-0.2613. Project B demonstrated even greater optimization, reducing the test suite from 36-8 test cases, resulting in a TSSR of 77.8% and an APFD improvement of 83.92%, rising from 0.3194-0.5875. These outcomes underscore the algorithm’s effectiveness in eliminating redundant test cases, accelerating testing, and enhancing fault detection thereby supporting the company's goal of faster release cycles without compromising quality.

Arabic is one of the oldest languages still in use today. As a result, several Arabic-speaking regions have developed dialects that are unique to them. Dialect and emotion recognition have various uses in Arabic text analysis, such as determining an online customer's origin based on their comments. Furthermore, intelligent chatbots that are aware of a user's emotions can respond appropriately to the user. Current research in emotion detection in the Arabic language lacks awareness of how emotions are exhibited in different dialects, which motivates the work found in this study. This research addresses the problems of dialect and emotion classification in Arabic. Specifically, this is achieved by building a novel framework that can identify and predict Arabic dialects and emotions from a given text. The framework consists of three modules: A text-preprocessing module, a classification module, and a clustering module with the novel capability of building new dialect-aware emotion lexicons. The proposed framework generated a new emotional lexicon for different dialects. It achieved an accuracy of 88.9% in classifying Arabic dialects, which outperforms the state-of-the-art results by 6.45 percentage points. Furthermore, the framework achieved 89.1-79% accuracy in detecting emotions in the Egyptian and Gulf dialects, respectively.

In the current Internet era, there are now trillions of gadgets online, and the Internet of Things is becoming a necessary part of daily life. IoT devices are connected, but this also makes them vulnerable to cyberattacks. Cyberattacks targeting Internet of Things (IoT) systems have increased dramatically in both volume and sophistication in the last year. Determining the importance and explainability of significant feature selection is not done in conventional feature selection, which acts as a black box method. Classical machine learning suffers from overload and class imbalance issues in IoT-based cloud security which is the major issue that results in botnet attack detection. To overcome these two issues, this study developed a model of a feature map to encode conventional data to a quantum feature space and then utilize the newly created quantum data in the cognitive circuit, which motivates to development of Quantum Shapley Additive Explanation with Variational Quantum Classifier (QSHAP-VQC) is implemented. This makes it possible to employ classical data in a quantum circuit. To minimize a cost function, a VQC employs hybrid quantum-classical techniques that involve parameterized circuits and gates whose parameters are improved via a classically based optimization loop. A quantum-classical hybrid loop consisting of these steps is eventually broken when the classical optimization finds the ideal parameters. For training data, the usual cost function is a comparison of the actual and expected outputs. The proposed QSHAP-VQC achieves the highest rate of accuracy in the detection of attacks in an IoT cloud environment.

This research explores the sentiment expressed in Snapchat user reviews within the Indonesian context, leveraging advanced natural language processing techniques and classification models. With a focus on the Indonesian user base, 8,015 reviews from the Google Play Store were analyzed using naive bayes, Support Vector Machines (SVM), and random forest models. The results indicated that the random forest model outperformed others with an 83% accuracy rate, followed by SVM at 81% and naive bayes at 80%. The analysis of frequently mentioned words in positive and negative reviews unveiled key aspects influencing user satisfaction. Positive reviews highlighted terms like 'bagus' (good) and 'suka' (like), while negative reviews often mentioned 'jelek' (bad) and technical issues like 'download.' The study contributes valuable insights for developers to enhance user experience on the Snapchat platform and suggests directions for future research in sentiment analysis of social media reviews.

Examinations are among the most widely used and effective methods for assessing knowledge mastery, both domestically and internationally, and are extensively used in various talent-selection processes. Currently, offline exam venues usually rely on on-site manual invigilation combined with exam-monitoring videos to further strengthen invigilation efforts. However, this invigilation method not only utilizes large amounts of human and material costs but also cannot comprehensively detect cheating behavior during exam processes and thus fairness cannot be guaranteed. To improve the efficiency of video reviews during invigilation, save labor costs, and strengthen invigilation efforts, this study proposes the use of target detection algorithms to achieve automatic detection of cheating actions in the exam room. To improve the speed of video detection, a student's abnormal-behavior detection method was proposed based on improved YOLOv8 and attention mechanism to achieve real-time detection of cheating actions in an exam room on a regular performance computer. The results showed that the detection accuracy of the improved YOLOv8 model reached 82.71%, thus meeting the application requirements.