Single-channel blind separation of co-frequency signals based on convolutional network

Article Engineering, Electrical & Electronic

A lightweight and efficient neural network for modulation recognition

Shi Fengyuan et al.

Summary: This paper proposes a lightweight neural network, called "combined", for automatic modulation recognition, which consists of a lightweight backbone network and an optional network. The network achieves high recognition accuracy and single-model accuracy, setting a new record in the field.

DIGITAL SIGNAL PROCESSING (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

A hierarchical receptive network oriented to target recognition in SAR images

Ganggang Dong et al.

Summary: In recent years, there has been a resurgence in neural networks for learning high-level representations. However, the limited availability of radar images with label information restricts the fitting power of deep architectures. Moreover, the presence of speckles, which are multiplicative noise with statistical specificity, makes image interpretation difficult. To address these issues, this paper proposes a new hierarchical receptive neural network that encodes and refines features using signal-wise receptive modules and patch-wise receptive units.

PATTERN RECOGNITION (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Deep cascading network architecture for robust automatic modulation classification

Lintianran Weng et al.

Summary: This paper presents a robust DL-based AMC model to adapt to noise changes, achieved through a deep cascading network architecture. The model successfully integrates SNR environment perception and modulation classification, improving recognition performance on AMC tasks.

NEUROCOMPUTING (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence