Search

This paper has harnessed the extensive IOT2023 dataset, encompassing both legitimate and malicious IoT data, for the purpose of training and testing machine learning classifiers. The performance of the Decision Tree Classifier has been even astonishing: 99% precision, 99% recall, and 99% accuracy. Summarily, the Decision Tree and the Random Forest classifiers have performed exceptionally, where the Random Forest had an upper hand, especially in identifying benign cases precisely, with 99% accuracy and precision. The K-Nearest Neighbors (KNN) classifier has also performed as good, with high precision and recall that gave a 99% accuracy and 92% precision. The choice of the best classifier will be able to depend on the unique needs of an application and in consideration of different valid performance metrics. There is a possibility of further refinement and fine-tuning that may bring these classifiers to a higher level of performance. Therefore, this work will further the state of the art in intrusion detection but also underline the very importance that so far does not receive enough attention in the real-world application: careful selection and refinement of models. Among them, the Random Forest has reached a 99% accuracy, 99% precision, 93% recall, and 84% F1-score. KNN has reached 99% in accuracy, 92% in precision, 82% in recall, and 84% in F1, which has proved to be a robust algorithm to provide a safe IoT ecosystem. [ABSTRACT FROM AUTHOR]

Metaheuristic algorithms have been effective in obtaining near-optimal solutions for NP-Complete problems like task scheduling. However, most of these algorithms still suffer from inadequate balance between local and global search when seeking a global solution, which often results in sub-optimal solutions. In this paper, an adaptive benefit factors based symbiotic organisms search (ABFSOS) is proposed, that adaptively tune SOS control parameters to strike a balance between local and global search procedures for faster convergence speed. Moreover, an adaptive constrained handling strategy is integrated into the proposed algorithm to effectively tune the values of the penalty function, thereby avoiding infeasible solutions and premature convergence. The performance of the proposed constrained multi-objective ABFSOS (CMABFSOS) was evaluated using large instances of both standard, and synthetic workloads, on a standard toolkit simulator (CloudSim). The non-dominated solutions obtained by the proposed CMABFSOS algorithm outperforms the compared algorithms (EMS-C, and ECMSMOO) for all the workload instances. The proposed CMABFSOS algorithm obtained significant improvement of hypervolume (convergence and diversity) over the compared algorithms for the workload instances. The performance improvement of CMABFSOS over EMS-C ranges from 17.02 to 47.73% across the workloads, while the performance improvement over ECMSMOO is between 19.98 to 52.18%. [ABSTRACT FROM AUTHOR]

Summary: The throughput of a TCP flow depends on the average size of Congestion Window (cwnd) of a congestion control mechanism being used during the communication. The size of cwnd depends upon the usage of available link bandwidth during communication. The response function is a measure of average throughput of a single TCP flow of congestion control mechanism as the level of random packet loss is varied. Nowadays, many organizations are deploying IoT based applications for the analytics of their Big Data. TCP CUBIC and TCP Compound are the default congestion control mechanisms in Linux and Microsoft Windows Operating Systems respectively. Whereas, TCP Reno which is also known as Standard TCP congestion control mechanism is act as a trademark congestion control mechanism. During communication among different IoT applications, TCP CUBIC flows use more available link bandwidth as compared to TCP Reno flows, thus, the average cwnd size of TCP CUBIC flows are greater than the TCP Reno flows. It implies that these both kinds of flows are not sharing available link fairly, which refers as low TCP friendliness of TCP CUBIC. It means that the throughput of TCP CUBIC flows is higher than the trademark congestion control mechanism, i.e., TCP Reno flows. As a result, friendliness behavior or fair share of available link bandwidth among TCP CUBIC flows and TCP Reno flows is decreased. In other words, TCP friendliness of TCP CUBIC flows is reduced. Now, it is important to decrease the average cwnd size of TCP CUBIC flows, such that available link bandwidth can be shared fairly among flows of TCP CUBIC and TCP Reno. The aim of this research is to enhance the TCP friendliness behavior of TCP CUBIC congestion control mechanism for IoT based applications using Big Data. In this paper, an Advance Response Function of TCP CUBIC (ARFC) is designed to share fairly available link bandwidth among flows of TCP CUBIC and TCP Reno. Results show that TCP friendliness behavior of TCP CUBIC is increased by using ARFC. Overall, 18.6% performance is increased by using ARFC. [ABSTRACT FROM AUTHOR]