Advancement in network technology has vastly increased the usage of the Internet. Consequently, there has been a rise in traffic volume and data sharing. This has made securing a network from sophisticated intrusion attacks very important to preserve users’ information and privacy. Our research focuses on combating and detecting intrusion attacks and preserving the integrity of online systems. In our research we first create a benchmark model for detecting intrusions and then employ various combinations of feature selection techniques based upon ensemble machine learning algorithms to improve the performance of the intrusion detection system. The performance of our model was investigated using three evaluation metrics namely: elimination time, accuracy and F1-score. The results of the experiment indicated that the random forest feature selection technique had the minimum elimination time, whereas the support vector machine model had the best accuracy and F1-score. Therefore, conclusive evidence could be drawn that the combination of random forest and support vector machine is suitable for low latency and highly accurate intrusion detection systems.

With the rise of internet usage malwares pose a great threat to user security and privacy. Therefore, to mitigate the problem it is essential to develop an efficient malware detection framework. In our research we experimented with various machine learning and feature scaling algorithms. Chi-Square was used as the feature selection technique which selected a set of 48 features from a feature space of 128 features. The empirical results provide us with conclusive evidence that Random Forest is the best algorithm for detection of malware achieving an accuracy of 91.300% on our dataset followed by Gradient Boosting and Support Vector Machines.

The advancement in network technology has led to an exponential rise in the number of internet users across the globe. The increase in internet usage has resulted in an increase in both the number of malicious websites and cybercrimes reported over the years. Therefore, it has become critical to devise an intelligent solution that can detect malicious websites and be used in real-time systems. In our paper, we perform a comparative analysis of various feature selection techniques to build a time-efficient and accurate predictive model. To build our predictive model, a set of features are selected by feature selection methods. The selected features consist of at least 70% of the categorical features in all feature selection techniques examined in this paper. Keeping the end goal of real-time deployment of models in context the cost of processing or storing these features is far cheaper when compared to text or image-based features. We started out with a class imbalance in our data which was later dealt with using the Synthetic Minority Oversampling Technique. Our proposed model also bested the existing work in the literature when compared over various evaluation metrics. The result indicated that Embedded feature selection was the best technique considering the accuracy of the model. The Filter-based technique may also be used in the context of developing a low latency system at the cost of the accuracy of the model.

With the rise in human population and emergence of the medical crisis across the whole globe, it has become essential to develop smart systems to automate the process of identification of medical conditions and therefore provide timely aid to the patient. As the first step to develop such a system in this paper we aim to create a natural language based medical condition identification system. The user would provide a text review of how they feel with few other categorical features, based upon that our model would identify the potential medical condition the user is suffering from. We employed three different machine-learning algorithms and mitigated class imbalance in our dataset. Empirical results indicate that Random Forest is the best machine-learning algorithm among all the investigated models with an accuracy of 80.39%, whereas the accuracy of the AdaBoost model improved the highest with an absolute value of 7.77% after mitigating class imbalance