Energy Minimized Intrusion Detection System (IDS) For Iot Environmental Sensors Using Optimized Deep Convolutional Network

Abstract

IoT environmental sensors are devices that use the Internet of Things (IoT) to monitor and measure various environmental conditions like temperature, humidity, air quality, and light levels. These sensors are susceptible to a variety of threats that could corrupt vital items or compromise data. To strike a balance between security and the resource limitations of IoT sensors, an Intrusion Detection System (IDS) solution that is both economical and energy-efficient is required. While preserving strong threat detection, these IDS solutions maximize processing speed and energy usage. In this paper, Energy and Cost Effective IDS for IoT, using DNN-CFOA model is proposed. In this work, Deep Convolutional Network (DNN) has been applied for the task of intrusion detection from patterns and Catch Fish Optimization Algorithm (CFOA) has been applied to optimize the weights of DNN model. According to experimental results, the suggested DNN-CFOA model performs better than the current models in terms of accuracy and F1-score metrics.