In recent years, social media platforms such as Instagram, Twitter, and Facebook have gradually become important ways to disseminate information. One of these social platforms that have attracted more attention in past years is Instagram. Instagram has widely used for sharing photos and videos and is profitable for celebrities, businesses, and people with a considerable number of followers. In the meantime, this high profit made this platform prone to be the potential place to be used for malicious activities. One of the essential malicious activities in the Instagram platform is fake accounts. However, in this paper, an efficient method for identifying Instagram fake accounts is proposed. In the presented model. First, a dataset of legitimate and fake accounts is created. Then, the collected dataset has been used as input of the bagging classifier to classify fake users on the dataset. Furthermore, the proposed method compared to the five well-known machine-learning classifiers in terms of classification accuracy to better evaluate effectiveness of the method. The experimental results show that the proposed method performs better than other considered algorithms and correctly classified over 98% of the accounts with a low error rate.

Intrusion detection systems (IDS) are crucial for network security because they enable detection of and response to malicious traffic. However, as next-generation communications networks become increasingly diversified and interconnected, intrusion detection systems are confronted with dimensionality difficulties. Prior works have shown that high-dimensional datasets that simulate real-world network data increase the complexity and processing time of IDS system training and testing, while irrelevant features waste resources and reduce the detection rate. In this paper, a new intrusion detection model is presented which uses a genetic algorithm (GA) for feature selection and optimization algorithms for gradient descent. First, the GA-based method is used to select a set of highly correlated features from the NSL-KDD dataset that can significantly improve the detection ability of the proposed model. A Back-Propagation Neural Network (BPNN) is then trained using the HPSOGWO method, a hybrid combination of the Particle Swarm Optimization (PSO) and Grey Wolf Optimization (GWO) algorithms. Finally, the hybrid HPSOGWO-BPNN algorithm is used to solve binary and multi-class classification problems on the NSL-KDD dataset. The experimental outcomes demonstrate that the proposed model achieves better performance than other techniques in terms of accuracy, with a lower error rate and better ability to detect different types of attacks.

In recent years, there has been considerable interest among people to use short message service (SMS) as one of the essential and straightforward communications services on mobile devices. The increased popularity of this service also increased the number of mobile devices attacks such as SMS spam messages. SMS spam messages constitute a real problem to mobile subscribers; this worries telecommunication service providers as it disturbs their customers and causes them to lose business. Therefore, in this paper, we proposed a novel machine learning method for detection of SMS spam messages. The proposed model contains two main stages: feature extraction and decision making. In the first stage, we have extracted relevant features from the dataset based on the characteristics of spam and legitimate messages to reduce the complexity and improve performance of the model. Then, an averaged neural network model was applied on extracted features to classify messages into either spam or legitimate classes. The method is evaluated in terms of accuracy and F-measure metrics on a real-world SMS dataset with over 5000 messages. Moreover, the achieved results were compared against three recently published works. Our results show that the proposed approach achieved successfully high detection rates in terms of F-measure and classification accuracy, compared with other considered researches.

Parkinsons disease (PD) is a neurodegenerative nervous system disorder that mainly affects body movement, and it is one of the most common diseases, particularly in elderly individuals. This paper proposes a new machine learning approach to predict Parkinsons disease severity using UCIs Parkinsons telemonitoring voice dataset. The proposed method analyses the patient's voice data and classifies them into severe and nonsevere classes. At first, a subset of features was selected, then a novel approach with a combination of Rotation Forest and Random Forest was applied on selected features to determine each patients disease severity. Analysis of the experimental results shows that the proposed approach can detect the severity of PD patients in the early stages. Moreover, the proposed model is compared with several algorithms, and the results indicate that the model is highly successful in classifying records and outperformed the other methods concerning classification accuracy and F1-measure rate.