Equilibrium Optimizer with Deep Learning Model for Detecting SMS Spam

Abstract

Despite the proliferation of messages sent over the Internet, text messaging is still used as a communication service. Smartphone users often suffer from unwanted text messages that may contain fraudulent links. This study presents a novel approach that combines the Equilibrium Optimizer (EO) algorithm with a Deep Learning model for detecting SMS spam messages. The proposed method aims to enhance the performance of spam classification by leveraging the optimization capabilities of the EO algorithm and the powerful feature representation of Deep Learning models. The EO algorithm is utilized to optimize the training process of the Deep Learning model, enabling it to effectively learn and classify spam messages from legitimate ones. Experimental results on a real-world SMS spam dataset demonstrate the effectiveness of the proposed approach in achieving high accuracy and robust spam detection performance. The integration of the EO algorithm with Deep Learning models offers a promising solution for improving SMS spam detection systems and combating the increasing threat of spam messages in mobile communication networks.