Enhanced Multi-Layer Bat Optimization(EMBO) Approach for Data Acquisition and Security Management in Web Platform

Intrusion Detection Systems (IDS) have grown to be essential to network and computer security. However, it complicates the training phase and makes it time-consuming to detect vulnerabilities in data sharing on the network. To solve this problem, we introduced a Multi-Layer Perceptron Neural Network (MLPNN) technique in data science to classify malicious and non-malicious network traffic. In addition, we preprocess the data by normalizing the mean original value using the Z-score Min-Max Scaling (ZSMMS) technique. In addition, we select the best feature by analyzing the weight and bias values with the Improved Bat Optimization (IBO) algorithm. After that, we propose the MLPNN technique to classify network traffic and improve accuracy. Finally, the Optimal Padding Advanced Encryption Standard (OPAES) algorithm will be implemented to enhance the security of the website. Additionally, by producing an IDS model and using metrics such as accuracy, recall, time complexity, and security performance, the website's security performance can be improved to 95.7%.