Cybersecurity has emerged as a critical global concern. Intrusion Detection Systems (IDS) play a critical role in protecting interconnected networks by detecting malicious actors and activities. Machine Learning (ML)-based behavior analysis within the IDS has considerable potential for detecting dynamic cyber threats, identifying abnormalities, and identifying malicious conduct within the network. However, as the number of data grows, dimension reduction becomes an increasingly difficult task when training ML models. Addressing this, our paper introduces a novel ML-based network intrusion detection model that uses Random Oversampling (RO) to address data imbalance and Stacking Feature Embedding based on clustering results, as well as Principal Component Analysis (PCA) for dimension reduction and is specifically designed for large and imbalanced datasets. This model’s performance is carefully evaluated using three cutting-edge benchmark datasets: UNSW-NB15, CIC-IDS-2017, and CIC-IDS-2018. On the UNSW-NB15 dataset, our trials show that the RF and ET models achieve accuracy rates of 99.59% and 99.95%, respectively. Furthermore, using the CIC-IDS2017 dataset, DT, RF, and ET models reach 99.99% accuracy, while DT and RF models obtain 99.94% accuracy on CIC-IDS2018. These performance results continuously outperform the state-of-art, indicating significant progress in the field of network intrusion detection. This achievement demonstrates the efficacy of the suggested methodology, which can be used practically to accurately monitor and identify network traffic intrusions, thereby blocking possible threats.

Diabetes is a very common disease affecting individuals worldwide. Diabetes increases the risk of long-term complications including heart disease, and kidney failure among others. People might live longer and lead healthier lives if this disease is detected early. Different supervised machine learning models trained with appropriate datasets can aid in diagnosing the diabetes at the primary stage. The goal of this work is to find effective machine-learning-based classifier models for detecting diabetes in individuals utilizing clinical data. The machine learning algorithms to be trained with several datasets in this article include Decision tree (DT), Naive Bayes (NB), k-nearest neighbor (KNN), Random Forest (RF), Gradient Boosting (GB), Logistic Regression (LR) and Support Vector Machine (SVM). We have applied efficient pre-processing techniques including label-encoding and normalization that improve the accuracy of the models. Further, using various feature selection approaches, we have identified and prioritized a number of risk factors. Extensive experiments have been conducted to analyze the performance of the model using two different datasets Our model is compared with some recent study and the results show that the proposed model can provide better accuracy of 2.71% to 13.13% depending on the dataset and the adopted ML algorithm. Finally, a machine learning algorithm showing the highest accuracy is selected for further development. Next, we integrate this model in a web application using python flask web development framework. The results of this study suggest that an appropriate preprocessing pipeline on clinical data and applying ML-based classification may predict diabetes accurately and efficiently.