Summary Block chain is extensively seen as a potential alternative in the safety and efficiency problems of the vast internet of things (IoT) data to allow safe and successful data storage/processing/sharing. In this manuscript, a secured authentication and deep slime mould optimized kernel learning (DSM‐KL) ascertained performance optimization of a hybrid block chain‐enabled framework for a multiple wireless sensor network (WSN) is proposed to recover data security performance and efficiency. To reflect the reality of the multi‐WSN network better, local block chain and public block chain are deployed, and a hybrid block chain model is created as per the various capabilities and energy of different nodes. A multi‐WSN network model is intended. It has numerous nodes on IoT. Based on dissimilar functions of nodes, the IoT nodes are divided into base stations, cluster heads and ordinary nodes based on its capabilities that facilitate management and cooperation of nodes. A DSM‐KL algorithm for dynamically selecting/adjusting block producer, consensus algorithm, block size and block interval to recover efficiency to handle both dynamic and broad dimensional properties of IoT systems is designed. The simulation process is executed in the MATLAB platform. The proposed DSM‐KL attains lower drop 27.53%, higher delivery ratio 28.56%, lower drop 28.64%, lower energy depletion rate 38.63%, higher network active time 38.47%, lower overhead 26.47% and higher throughput 27.67%, and the performances are compared with the existing methods such as deep reinforcement learning (DRL) and block chain and reinforcement learning (RLBC), respectively.

Nowadays, intrusion detection systems (IDSs) enabled with computational intelligence for electing the suitable classifiers to learn the patterns of various types of network attacks are under study. Selection mechanism of single or ensemble classifiers based on performance and ranking is to be enabled in the IDS framework to make accurate pattern predictions. A new anomaly based network intrusion detection system framework is proposed using context adaptive classification through the technique for order of preference by similarity to ideal solution (TOPSIS) ranking mechanism with hierarchy based chi-square and bat algorithms for feature selection.Parameters like accuracy, false positive rate (FPR), and classification model building time are explored for choosing the best and situation aware classifiers using TOPSIS.For experimentation, NSL-KDD and UNSW-NB15 datasets are used. The proposed system opts decision tree (DT) algorithm for NSL-KDD and produces 98.77% accuracy, 0.03% FPR with 8 features. Ensemble learner is selected for the UNSW-NB15 dataset using DT and support vector machine classifiers with 9 features. Combined classifier predicts 89.43% accuracy and 3.215% FPR. Experimentation on the proposed methodology with the state of the art approaches produces promising results.

Multimedia applications such as Video-on-Demand (VoD), Live streaming, Internet stock quotes, Internet radio, audio/music delivery, video surveillance are of growing interest among general public. Existing systems that support these kinds of applications such as centralized server, independent server nodes, and proxy incur significant delay and serve only less number of videos. In this research, a multi-server system that utilizes a split and merge scheme is proposed to reduce the waiting time. This system helps us to achieve load balancing, while increasing the number of videos being served. Our simulation model consists of a single main multimedia server and a set of streaming servers. The performance of the proposed system for various K values is evaluated in the VoD scenario. The results show that the proposed multi-server scheme performs better in terms of initial latency and number of videos being served, compared to the other existing schemes. Index Terms—Component, formatting, style, styling, insert.