The integration of IoT technology into wireless signal monitoring presents significant opportunities for both military and civilian applications, such as signal reconnaissance, anti-jamming, and device identification. Traditional methods for modulation recognition, which rely on likelihood estimation and manual feature extraction, often encounter challenges related to computational complexity and the need for expert knowledge. In contrast, machine learning (ML) and deep learning (DL) models, including Support Vector Machines (SVM) and Convolutional Neural Networks (CNN), deliver superior performance without the need for manual feature extraction.

In this paper, we propose the utilization of a Multiple Input Multiple Output (MIMO) neural network model for automatic modulation classification and direction of arrival (DOA) estimation. The proposed system is elaborated through functional block diagrams and comprises key components such as antenna arrays, analog preprocessing units, radio signal receivers, digital signal processors, MIMO neural networks, data processors, and display units. By integrating these components, the model is capable of simultaneously performing modulation classification and DOA estimation, thus providing an efficient and cost-effective solution for real-time signal monitoring. The proposed approach not only enhances the accuracy and efficiency of signal analysis but also reduces the overall system cost, making it highly suitable for diverse applications in the evolving landscape of wireless communications.