|
|
|
 |
Search published articles |
 |
|
Showing 2 results for Feature Selection
Farhad Soleimanian Gharehchopogh, Mohammad Sakhidek Hovshin,
Volume 9, Issue 1 (8-2020)
Abstract
Unfortunately, among internet services, users are faced with several unwanted messages that are not even related to their interests and scope, and they contain advertising or even malicious content. Spam email contains a huge collection of infected and malicious advertising emails that harms data destroying and stealing personal information for malicious purposes. In most cases, spam emails contain malware that is usually sent to users in the form of scripts or attachments, and the user infects the computer with malware by downloading and executing the attached file. In this paper, a new model for detecting spam e-mail is proposed based on the hybrid of the Harmony Search Algorithm (HAS) with the Magnetic Optimization Algorithm (MOA). The proposed model is used to select the effective features and then the classification is performed using the K Nearest Neighbor's (KNN) algorithm. In the proposed model, using the MOA was found the best features for the HSA, and the harmony matrix is formed based on them. Then the HSA changes based on the update and rate of step-change in each step of the harmony vectors so that the best vector is selected as the vector of characteristics among them. The results show that the accuracy of the proposed model on the Spam base dataset with 200 iterations is 94.17% and also the accuracy of the diagnostic model of the proposed model is more than other models.
Fateme Pishdad, Reza Ebrahimi Atani,
Volume 13, Issue 2 (12-2024)
Abstract
With the advancement and development of Internet of Things (IoT) applications, the need for securing infrastructure in this domain has gained particular importance due to the limitations of computational and storage resources. Botnets are among IoT security challenges in which, by infecting computational nodes of this technology, they are capble of turning the network into a collection of compromised machines under the control of attackers. This paper proposes an anomaly detection system based on ensemble learning to prevent and identify IoT botnet attacks at the initial scanning stage and DDoS attacks. This system uses feature selection and optimal hyperparameter tuning for each classifier to increase model accuracy and prevent overfitting. The data used in this paper is taken from the BoT-IoT dataset, which covers activities related to different stages of the botnet lifecycle. For feature selection and classification, two ensemble learning algorithms, LightGBM and Random Forest, are used, and hyperparameter optimization is performed using the TPE method. Results demonstrated that the LightGBM algorithm achieved an error rate of 0.98% and an accuracy of 99.02%, while the Random Forest algorithm exhibited an error rate of 0.01% and an accuracy of 99.99%, indicating highly satisfactory performance in attack detection. The proposed models, with increased training and prediction time, have offered significantly higher accuracy compared to previous models.
|
|
