Super peer selection strategy in peer‐to‐peer networks based on learning automata

A super peer is a peer that has the highest capacity in comparison with other peers in the network. It is trying to reduce the load of the rest of the peers and improve network performance. Selecting a super peer in a peer‐to‐peer–based network is a very crucial challenge. As the ability of peers are very different, by considering capacity of each peer and selecting a proper role, we can use network components much more efficiently. Because of the dynamicity of these networks, comparative methods of selecting super peers is of special importance. Comparative selection is continuously trying to select proper super peer. In recent studies, learning automata was introduced as a powerful learning model to solve this issue. In most of the studies, learning automata with an S model is employed. In this article, another selection method of learning automata with a P model environment is presented and its capability for super peer selection is shown. Moreover, simulation results show that removing some of the super peers would result in better performance in terms of inversion time in the high level of super‐peer capacity, required time for selecting proper super peer, and super peer tolerance.     

A multiple multilayer perceptron neural network with an adaptive learning algorithm for thyroid disease diagnosis in the internet of medical things

The Journal of Supercomputing - Medical information systems such as Internet of Medical Things (IoMT) are gained special attention over recent years. X-ray and MRI images are important sources of...     

A Computational Model to Predict Consumer Behaviour During COVID-19 Pandemic

Computational Economics - The knowledge-based economy has drawn increasing attention recently, particularly in online shopping applications where all the transactions and consumer opinions are...     

ISHO: improved spotted hyena optimization algorithm for phishing website detection

One of the major challenges in cyber space and Internet of things (IoT) environments is the existence of fake or phishing websites that steal users’ information. A website as a multimedia system provides access to different types of data such as text, image, video, audio. Each type of these data are prune to be used by fishers to perform a phishing attack. In phishing attacks, people are directed to fake pages and their important information is stolen by a thief or phisher. Machine learning and data mining algorithms are the widely used algorithms for classifying websites and detecting phishing attacks. Classification accuracy is highly dependent on the feature selection method employed to choose appropriate features for classification. In this research, an improved spotted hyena optimization algorithm (ISHO algorithm) is proposed to select proper features for classifying phishing websites through support vector machine. The proposed ISHO algorithm outperformed the standard spotted hyena optimization algorithm with better accuracy. In addition, the results indicate the superiority of ISHO algorithm to three other meta-heuristic algorithms including particle swarm optimization, firefly algorithm, and bat algorithm. The proposed algorithm is also compared with a number of classification algorithms proposed before on the same dataset.

     

RenyiBS: Renyi entropy basis selection from wavelet packet decomposition tree for phonocardiogram classification

The Journal of Supercomputing - Wavelet packet transform (WPT) is a powerful mathematical tool for analyzing nonlinear biomedical signals, such as phonocardiogram (PCG). WPT decomposes a PCG signal...