VERSA NET FUSION WITH HYBRID FEATURE SELECTION FOR INTRUSION DETECTION IN IOT

Internet of Things (IoT) networks require intrusion detection to protect against illegal access, but existing techniques sometimes struggle to handle enormous amounts of data accurately. To tackle these issues, the suggested method implements a hybrid feature selection and Versa Net-based detection framework. The process starts with thorough data pre-processing, which involves removing inconsistent and superfluous entries and managing missing values by mean imputation. Then, Z-score normalization is used to standardize numerical features and guarantee dataset consistency. A multimodal approach is used in feature extraction: While flow-based, entropy-based, correlation-based, protocol-based, statistical, and flow-based features offer a comprehensive overview of the data's underlying structure, Independent Component Analysis (ICA) separates statistically independent components. A hybrid optimization method for feature selection finds and selects the most essential features by fusing the advantages of the Pelican and Chimp algorithms. Versa Net results from the detection framework's integration of neural network architectures, including Squeeze Net, Google Net, Alex Net, and Dense Net. These networks use dense blocks, inception modules, fire modules, and convolutional layers to extract a variety of characteristics. The outputs are flattened, concatenated, and sent to a fully connected output layer for anomaly detection after feature extraction. The goal of this comprehensive strategy is to improve intrusion detection in IoT environments by increasing its accuracy to 0.978005 and efficiency.