In this paper, Due to the prevalence of dispersed, low-powered computers, the IoT is open to a wide range of threats. The purpose of this paper is to improve the safety of the Internet of Things (IoT) by developing a lightweight intrusion detection system (IDS) using feature selection and feature classification, two machine learning methods. The filter-based method was used to select features because it requires less processing power than other approaches. After evaluating logistic regression (LR), naive Bayes (NB), decision tree (DT), random forest (RF), k-nearest neighbour (KNN), support vector machine (SVM), and multilayer perceptron (MLP), we settled on MLP as our system's feature classification algorithm (MLP). Given its stellar results across multiple datasets, the DT algorithm was ultimately chosen for implementation in our system. The findings of the study can be used as a reference when deciding which feature selection technique to employ when engaging in machine learning.