IEEE 2023: Improving Medicine Recommendation with Sentiment Analysis of Text Reviews and Machine Learning
Abstract: This study presents a comprehensive comparative analysis of the performance of Artificial Neural Networks (ANNs) and Random Forest Classifiers in binary classification tasks. The ANN model exhibited a commendable accuracy rate of 98%, showcasing its efficacy in accurately classifying instances. Additionally, the Random Forest Classifier demonstrated an equivalent accuracy rate of 98%, affirming its robustness as a classification tool. In-depth examination of confusion matrices provided valuable insights into the strengths and limitations of each model. The study also delves into the interpretability and computational complexity of both approaches, shedding light on their suitability for different applications. Overall, this research contributes to the understanding of the comparative performance of ANN and Random Forest Classifier models, offering valuable guidance for practitioners in selecting the most suitable approach for specific binary classification tasks.
IEEE 2023: Secure IDS with Machine Learning & Network Decoy System
Abstract: The rapid growth of network-based attacks and security breaches has highlighted the need for robust Intrusion Detection Systems (IDS) to protect computer networks and sensitive data. The main objective of the proposed system is to develop an Intrusion Detection System (IDS) integrated with a Decoy system, employing the powerful Random Forest and K-Nearest Neighbors (KNN) machine learning algorithms. The primary objective of this project is to design and implement intelligent IDS that can effectively detect and classify various types of network intrusions while minimizing false positives. To enhance the system's security, a Decoy system will be integrated, which aims to deceive potential attackers and divert their attention from the actual network resources. The proposed IDS will leverage the Random Forest algorithm, a powerful ensemble learning technique that combines multiple decision trees to achieve high accuracy and robustness. The project will also explore the application of the K-Nearest Neighbors (KNN) algorithm for intrusion detection. KNN is a non-parametric algorithm that classifies new data points based on the majority vote of their nearest neighbors.
No comments:
Post a Comment