edge, and cloud computing environments. Many studies have introduced novel methodologies, such as Deep Reinforcement Learning, Artificial Intelligence, and hybrid models; however, the majority rely on simulations, making it difficult to validate the practical efficacy of these techniques thoroughly. Future...
New technology is needed to meet the latency and bandwidth issues present in cloud computing architecture specially to support the currency of 5G networks. Accordingly, mobile edge computing (MEC) came into picture as novel emerging solutions to overcome many cloud computing issues. In this contempora...
Recently, we observe that the edge nodes that acquire the dataset of heterogeneous IoT devices are becoming overwhelmed with the issue of tuple non-classification at the level of data encapsulation. This issue raises a few concerns such as (a) ineffective tuple wrapup, (b) bundle compression ...
Deep learning (DL) and reinforcement learning (RL) are two different types of ML and they have shortcomings, respectively. DL may fail to detect attacks precisely due to overfitting or insufficient training data. Hence, a suitable training dataset is a key for DL to reducing error rates. Then...
The real-time data should be processed whether locally, or by the edge nodes and the cloud, which is solved by our ADMM algorithm. The newly collected data will be continuously added to the dataset as the ADMM iteration proceeds. Eventually, the optimal choices are acquired by the approximate...
Furthermore, DBSCAN has high computation complexity like K-Means as the DBSCAN algorithm is executed using the entire dataset. However, DBSCAN is ineffective in resource-limited IoT with huge high-dimensional data. For example, when the density of data is uneven and the distance between clusters ...
The resultant dataset adheres to a specific encoding/serialisation approach and is subsequently relayed to the upper processing layer, denoted as the Real-time Edge Processing. As the above adaptation operations do not require substantial computing power, they can be executed on nodes close to the ...
Data availability The dataset used is publicly available.References Ge M, Fu X, Syed N, Baig Z, Teo G, Robles-Kelly A (2019) Deep learning-based intrusion detection for IoT networks. In: 2019 IEEE 24th Pacific Rim International Symposium on Dependable Computing (PRDC), Kyoto, Japan pp 256...
s. Here the only disadvantage is that, fixed window size approach is used during data offloading, which is a rigid approach for all kinds of data whereas Fog Computing model uses the reinforcement learning approach but dataset size used is small and can’t be relied for real world ...
ABSTRACT In this project, we propose a new comprehensive realistic cyber security dataset of IoT and IIoT applications, called Edge-IIoTset, which can be used by machine learning-based intrusion detection systems in two different modes, namely, centrali