The rapid proliferation of smart devices in Internet of Things (IoT) networks has amplified the security challenges associated with device communications. To address these challenges in 5G-enabled IoT networks, this paper proposes a multi-level blockchain security architecture that simplifies implementation while bolstering network security. The architecture leverages an adaptive clustering approach based on Evolutionary Adaptive Swarm Intelligent Sparrow Search (EASISS) for efficient organization of heterogeneous IoT networks. Cluster heads (CH) are selected to manage local authentication and permissions, reducing overhead and latency by minimizing communication distances between CHs and IoT devices. To implement network changes such as node addition, relocation, and deletion, the Network Efficient Whale Optimization (NEWO) algorithm is employed. A localized private blockchain structure facilitates communication between CHs and base stations, providing an authentication mechanism that enhances security and trustworthiness. Simulation results demonstrate the effectiveness of the proposed clustering algorithm compared to existing methodologies. Overall, the lightweight blockchain approach presented in this study strikes a superior balance between network latency and throughput when compared to conventional global blockchain systems. Further analysis of system under test (SUT) behavior was accomplished by running many benchmark rounds at varying transaction sending speeds. Maximum, median, and lowest transaction delays and throughput were measured by generating 1000 transactions for each benchmark. Transactions per second (TPS) rates varied between 20 and 500. Maximum delay rose when throughput reached 100 TPS, while minimum latency maintained a value below 1 s.

Data Mining is a rising field utilized in educational purposes to enhance the insightful and learning strategy for students. It centers around perceiving, extricating and calculating information related to the educational procedure and rising student performance. Mining in a learning field is known as educational data mining with investigating most recent strategies to search out data from instructional fields. The aim behind our study is to judge the students performance by taking different parameters like scholastic accomplishments (CGPA), sex, class test grade, condition of class, Fund/Scholarships/Private and so on. In our exploration we will utilize classification and clustering Bayesian classification-mean algorithms, neural networks, Naive bayes, Web based system and nearest neighbor methods strategies to investigate understudy execution. The issue is to distinguish the student whose execution is poor in their courses. So as indicated by their execution and capacity, there will be an opportunity to take some remedial activities. In this paper, we anticipate the last grades utilizing diverse information mining calculations to foresee the last execution of students with the goal that we can get increasingly precise qualities. It issues a prediction for each student solely when the normal precision of the forecast is satisfactory.