Optimization of Real-Time Signal Processing Algorithm in Electronic Information Systems Integrating Convolutional Neural Networks

In recent years, the demand for real-time signal processing in electronic information systems has significantly increased, driven by the growth of applications in areas such as Internet of Things (IoT), mobile devices, healthcare monitoring, and communication systems. However, real-time processing of signals presents a significant challenge due to the complexity of the signals, the need for high classification accuracy, and the limited computational resources available in embedded systems. This paper presents an optimized real-time signal processing algorithm that integrates Convolutional Neural Networks (CNNs) with an advanced pre-processing framework and a multi-scale feature extraction technique. The proposed method aims to address these challenges by enhancing the accuracy of signal classification while minimizing computational overhead, making it suitable for deployment in resource-constrained environments. The methodology incorporates domain-specific prior knowledge during the pre-processing stage, utilizes a multi-scale feature extraction mechanism, and applies a hybrid optimization technique to dynamically balance the trade-off between accuracy and computational efficiency. Experimental results show that the proposed method outperforms both traditional signal processing techniques and baseline CNN models, achieving superior classification accuracy, lower inference times, and better scalability across diverse hardware platforms, including high-performance GPUs and low-power embedded systems. These findings demonstrate the potential of deep learning-based approaches for real-time signal processing in practical, resource-constrained applications.

Перевод пока недоступен