Palthe Ravi Naik

Developed a hybrid intrusion detection system for automotive Ethernet networks leveraging the Salp Swarm Algorithm for feature selection and Dense Neural Networks for classification. Achieved 99.93% accuracy on the AEID dataset by optimizing feature selection and reducing false positives. The system monitors network traffic to detect anomalies and prevent cyber threats in resource-constrained in-vehicle networks. Employed Python with libraries including NumPy, Pandas, PyShark, and scikit-learn.

Implemented machine learning and deep learning models on real-world datasets using Python, TensorFlow, and Scikit-learn. Performed data cleaning, feature engineering, and transformation. Developed regression, classification, clustering, and recommendation models. Applied CNNs for image classification and RNNs/LSTMs for sequence modeling. Conducted exploratory data analysis and visualized insights using Matplotlib, Seaborn, and Plotly.

Implemented machine learning and deep learning models on real-world datasets using Python, TensorFlow, and Scikit-learn. Performed data cleaning, feature engineering, and preprocessing with Pandas and NumPy. Developed supervised and unsupervised models including regression, classification, clustering, and recommendation systems. Applied CNNs for image classification and RNNs/LSTMs for sequence modeling. Conducted exploratory data analysis with Matplotlib, Seaborn, and Plotly.