Cloud computing is a widely recognized and established method. A vast number of individuals worldwide depend on cloud computing as a means to exchange data and securely store information. However, one of the prime concerns is security of the data over the cloud for storage and access purposes. Currently, the usage of blockchain technology has become a prevalent innovation that may effectively address security issues in cloud computing. It is a distributed data management platform that ensures confidentiality, privacy, and data integrity without the need for any intermediate organization. This research paper aims to integrate blockchain's inherent security features with data anonymization techniques to enhance cloud security and privacy. One other factor that is important is the trust among the entities that are involved during the process of cloud security through blockchain. The amalgamation of these technologies could revolutionize how sensitive data is protected in the cloud, offering a more secure and private environment. In this paper, comprehensive literature work pertaining to cloud security has been elaborated in consideration to the blockchain techniques utilization along with the anonymization methods. Data anonymization provides privacy by concealing identifying information; however, achieving a balance between privacy and data usefulness is complex, which motivates the work in this context. The main contribution is the comprehensive comparative evaluation and analysis of the reviewed literature while considering parameters like throughput, privacy, cost, scalability, performance, and reliability towards the blockchain based approaches for cloud security along with factors such as anonymity type, differential privacy and orientation of the approach in the anonymization side. Moreover, statistical evaluation of the studies has been done based on the inferences drawn. This paper also highlights the current research challenges for future works.

Quadratic Discriminant Analysis (QDA) is a widely used technique in supervised classification that model data with Gaussian distributions and class-specific covariance matrices. However, in real-world scenarios, many datasets do not conform to the Gaussian assumption or exhibit challenges such as high-dimensional feature spaces. To address these issues, this paper introduces a novel method, MMD-QDA, which transforms data into class-specific marginal Mahalanobis distance (MMD) representations. The transformed data is then classified using QDA to leverage its ability to handle varying class covariance effectively. Furthermore, this approach reduces the feature dimension to match the number of class labels in the dataset. This makes it particularly useful for datasets with a large number of features relative to the number of classes. The performance of the proposed MMD-QDA method is evaluated on 10 benchmark datasets obtained from UCI Machine Learning repository using metrics such as accuracy, precision, recall, f1-score, G-mean, and Cohen's Kappa. It is observed from simulation results that the proposed MMD-QDA achieved significant improvements, with average performance enhancements of 9.68%, 10.91%, 9.68%, 10.80%, 10.36%, and 14.83% respectively as compared to LDA and 11.99%, 7.07%, 11.99%, 12.35%, 9.44%, and 22.17 respectively as compared to QDA across the respective metrics.

The growing demand for adaptive learning software has highlighted the drawback of static content delivery. Focusing on content delivery, StudyPalz is an adaptive learning system designed to boost student productivity. Rather than offering generic content, it finds particular learning needs and provides modified tools including mind maps, short films, and mnemonic devices. Built on Django, StudyPalz starts with diagnostic quizzes to gauge conceptual knowledge. Depending on quiz results, it identifies weak areas and recommends focused study material as well as tailored re-attempt quizzes to strengthen learning.
In the interest of consistency and well-being, StudyPalz also includes a Pomodoro timer and task planner, encouraging focused, brief study intervals and good use of time. A field study of 150+ students and 200+ completed quizzes revealed misconceptions and the need for curriculum improvement, informing the potential for the platform to offer real-time feedback loops for instructors. Student feedback also indicated a preference for concise visual aids over static content. A case study of 10 students indicated a score improvement from 51 to 85 over five quizzes, representing a 66.67% improvement. StudyPalz overall integrates adaptive diagnostics, personalized content, and progress tracking to enable academic improvement. Its modular nature also provides opportunities for future AI-based tutoring and multilingual support.

This paper introduces a novel approach for forecasting CPU utilization in cloud computing environments using a Bi-LSTM model enhanced with an attention mechanism. By addressing dataset irregularities with an interpolation-based data preprocessing technique, the method ensures accurate representation and is validated by the Kolmogorov-Smirnov two-sample test. The attention mechanism within the Bi-LSTM model improves prediction accuracy by identifying key dataset features. Evaluated using the Alibaba Cluster Trace dataset, the approach demonstrates superior performance compared to established methods. Predicted utilization values facilitate fault-tolerant VM allocation and resource extension, reducing overutilized host occurrences and enhancing system reliability. This predictive allocation minimizes unnecessary VM migrations, decreases overhead, and ensures optimal host utilization, leading to more reliable services and improved adherence to SLAs.

The breakneck growth of the Internet of Things (IoT) has led to the proliferation of low-power communication protocols like MQTT, CoAP, and AMQP. Yet, all these current protocols have severe drawbacks: high energy consumption, high overheads from security measures, and unresponsiveness to congestion. To cope with these challenges, this paper presents the Adaptive Secure Energy-Efficient IoT Protocol (ASEIP), a new communication protocol that combines energy-conscious forwarding, light encryption, and adaptive congestion control. ASEIP uses a hybrid reliability mechanism that distinguishes between critical and non-critical data streams, thus trading off energy efficiency and reliable delivery. The protocol is executed and tested through the NetSim simulator, and its performance is compared with MQTT, CoAP, and AMQP under different traffic conditions and node concentrations. Simulation results show that ASEIP obtains up to 25% increased throughput, 18% reduced end-to-end delay, and 30% less energy consumption with comparable reliability. The results confirm ASEIP as a strong contender for large-scale IoT applications under resource-limited environments in areas like healthcare, smart cities, and environmental monitoring.

Fault detection has become an indispensable strategy in the current development of technical features as newer machinery grows increasingly complex, aiming to prevent costly downtime and safety risks. Traditional periodic inspection-based maintenance methods often lead to unexpected breakdowns and inefficient resource utilization. Former studies on predictive maintenance, which were based on sensors such as vibration or current monitors, have been adequate in this regard but lack early anomaly detection and are prone to latency issues in fast-paced industrial settings. The limitations mentioned above are addressed by proposing a real-time fault detection system that combines thermal imaging and machine learning techniques. Thermal cameras stream video from the real-time mapping of temperature distributions, and this process is further enhanced using WebRTC. Temperature variations are analyzed using a Convolutional Neural Network (CNN) and machine detection is performed using the You Only Look Once (YOLOv5) algorithm. Anomaly detection can be accomplished with the Isolation Forest algorithm. The outcome demonstrated an accuracy of 97.5% with a latency of 30 milliseconds. This scalable solution is likely to have industrial applications in the near future.