RESUMO
Internet of Things (IoT) devices are leading to advancements in innovation, efficiency, and sustainability across various industries. However, as the number of connected IoT devices increases, the risk of intrusion becomes a major concern in IoT security. To prevent intrusions, it is crucial to implement intrusion detection systems (IDSs) that can detect and prevent such attacks. IDSs are a critical component of cybersecurity infrastructure. They are designed to detect and respond to malicious activities within a network or system. Traditional IDS methods rely on predefined signatures or rules to identify known threats, but these techniques may struggle to detect novel or sophisticated attacks. The implementation of IDSs with machine learning (ML) and deep learning (DL) techniques has been proposed to improve IDSs' ability to detect attacks. This will enhance overall cybersecurity posture and resilience. However, ML and DL techniques face several issues that may impact the models' performance and effectiveness, such as overfitting and the effects of unimportant features on finding meaningful patterns. To ensure better performance and reliability of machine learning models in IDSs when dealing with new and unseen threats, the models need to be optimized. This can be done by addressing overfitting and implementing feature selection. In this paper, we propose a scheme to optimize IoT intrusion detection by using class balancing and feature selection for preprocessing. We evaluated the experiment on the UNSW-NB15 dataset and the NSL-KD dataset by implementing two different ensemble models: one using a support vector machine (SVM) with bagging and another using long short-term memory (LSTM) with stacking. The results of the performance and the confusion matrix show that the LSTM stacking with analysis of variance (ANOVA) feature selection model is a superior model for classifying network attacks. It has remarkable accuracies of 96.92% and 99.77% and overfitting values of 0.33% and 0.04% on the two datasets, respectively. The model's ROC is also shaped with a sharp bend, with AUC values of 0.9665 and 0.9971 for the UNSW-NB15 dataset and the NSL-KD dataset, respectively.
RESUMO
BACKGROUND: Tobacco smoking is a major health issue worldwide. In addition to several health problems, smoking can also cause buccal cavity ulcers and buccal cavity cancer in case of chronic smoking. Tobacco smoking may also lead to deranged morphology of red blood cells (RBCs), which results in reduced oxygen carrying capacity of the blood. AIM: (a) To investigate and compare the changes in the RBC morphology of smokers and nonsmokers. (b) To investigate and compare the normal buccal flora of smokers and nonsmokers. METHODOLOGY: A total of 81 men were included in the study. Study population was divided into two groups: group 1; smokers (n = 50) and group 2; nonsmokers, which served as control (n = 31). After informed written consent from the study participants, a 5 mL of venous blood was drawn under sterile conditions for complete blood analysis and RBC morphology. Samples from buccal cavity were collected by cotton swab and cultured in sterile petri dishes to identify the bacterial growth. Data of RBC morphology and buccal microbiota were compared between smokers and nonsmokers. RESULTS: Buccal microflora results showed heavy growth in smokers compared with nonsmokers. Mean values of RBCs, Platelets, WBCs, HGB (hemoglobin), and MCV (mean corpuscular volume) did not differ between smokers and nonsmokers. Mean red cell distribution (RDW) width significantly was lower in smokers than nonsmokers. Macrocytic RBCs was more in smokers (60%) compared with nonsmokers (4%). CONCLUSIONS: Our results showed an increase in the percentage of macrocytic RBCs and a decrease in the red cell distribution width (RDW) in smokers compared with nonsmokers. Buccal Microflora was significantly higher in smoker group in contrast to nonsmoker group.
