pso algorithm

Integration and diversity of IOT terminals and their applicable programs make them more vulnerable to many intrusive attacks. Thus, designing an intrusion detection model that ensures the security, integrity, and reliability of IOT is vital. Traditional intrusion detection technology has the disadvantages of low detection rates and weak scalability that cannot adapt to the complicated and changing environment of the Internet of Things. Hence, one of the most widely used traditional methods is the use of neural networks and also the use of evolutionary optimization algorithms to train neural networks can be an efficient and interesting method. Therefore, in this paper, we use the PSO algorithm to train the neural network and detect attacks and abnormalities of the IOT system. Although the PSO algorithm has many benefits, in some cases it may reduce population diversity, resulting in early convergence. Therefore,in order to solve this problem, we use the modified PSO algorithm with a new mutation operator, fuzzy systems and comparative equations. The proposed method was tested with CUP-KDD data set. The simulation results of the proposed model of this article show better performance and 99% detection accuracy in detecting different malicious attacks, such as DOS, R2L, U2R, and PROB.

With the explosive growth in amount of information, it is highly required to utilize tools and methods in order to search, filter and manage resources. One of the major problems in text classification relates to the high dimensional feature spaces. Therefore, the main goal of text classification is to reduce the dimensionality of features space. There are many feature selection methods. However, only a few methods are utilized for huge text classification problems. In this paper, we propose a new wrapper method based on Particle Swarm Optimization (PSO) algorithm and Support Vector Machine (SVM). We combine it with Learning Automata in order to make it more efficient. This helps to select better features using the reward and penalty system of automata. To evaluate the efficiency of the proposed method, we compare it with a method which selects features based on Genetic Algorithm over the Reuters-21578 dataset. The simulation results show that our proposed algorithm works more efficiently.

According to this fact that wind is now a part of global energy portfolio and due to unreliable and discontinuous production of wind energy; prediction of wind power value is proposed as a main necessity. In recent years, various methods have been proposed for wind power prediction. In this paper the prediction structure involves feature selection and use of Artificial Neural Network (ANN). In this paper, feature selection tool is applied in filtering of inappropriate and irrelevant inputs of neural network and is performed on the biases of mutual information. After determining appropriate inputs, the wind power value for the next 24-hours is predicted using neural network in which BP algorithm and PSO and ICA evolutionary algorithms are used as training algorithm. With investigation and compare numerical results, better performance of PSO and ICA evolutionary algorithm is deduced with respect to BP algorithm. More accurate survey will result in more proper efficiency of imperialist competitive algorithm (ICA) in comparison to swarm particle algorithm. Thus, in this paper; accuracy of the wind power prediction for the next 24-hours is improved considerably using mutual information and providing an irrelevancy filter for reducing the input dimension by eliminating the irrelevant candidates and more effectively using Imperialist competitive evolutionary algorithm for training the neural network.