Dynamically Mixed Group Convolution to Lighten Convolution Operation

Due to the computing capability and memory limitations, it is difficult to apply the traditional deep learning (DL) models to the edge devices (EDs) for realizing lightweight automatic modulation classification (AMC). Recently, many works attempt to use different ways to realize lightweight AMC methods for edge devices (EDs). However, the lightweight seems to be a contradiction with the classification performance in these lightweight networks. In this paper, we propose an efficient lightweight decentralized learning-based automatic modulation classification (DecentAMC) method using spatio-temporal hybrid deep neural network based on multi-channels and multi-function blocks (MCMBNN). Specifically, the lightweight network is designed from the perspectives of comprehensive consideration of lightweight and classification performance, which is composed of three parts to extract different features for realizing high classification performance and they are parameter estimator and transformer (PET) block, spatial information extraction block and temporal feature extraction & Softmax block. In addition, we use multi-channel input to extract complementary features of different channels for a better classification performance. The proposed DecentAMC method is an efficient training method, which is achieved by the cooperation in which multiple EDs update and upload the model weight to a central device (CD) for model aggregation to avoid the data privacy disclosure and reduce the computing power and storage pressure of CD. Experimental results show that the proposed MCMBNN can obtain an improved classification accuracy while reducing model complexity with the contributions of three blocks. Moreover, the proposed DecentAMC method can be deployed on EDs efficiently. Thus, the method has the advantages of avoiding data leakage on EDs and relieving the computing pressure of CD with relatively lower communication overhead. The simulation code and datasets are shared on GitHub. 1

show abstract

“…7. The parameters and out feature maps comparisons of group convolution and standard convolution [52] can be calculated by…”

Section: Spatial Information Extraction Blockmentioning

confidence: 99%

A Lightweight Decentralized-Learning-Based Automatic Modulation Classification Method for Resource-Constrained Edge Devices

Dong

Liu

Gui

et al. 2022

IEEE Internet Things J.

View full text Add to dashboard Cite

show abstract

Decentralized Automatic Modulation Classification Method Based on Lightweight Neural Network

Dong

et al. 2022

2022 IEEE 33rd Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)

View full text Add to dashboard Cite

Structure and Base Analysis of Receptive Field Neural Networks in a Character Recognition Task

Goga

Vargic

Pavlovičová

et al. 2022

Sensors

View full text Add to dashboard Cite

This paper explores extensions and restrictions of shallow convolutional neural networks with fixed kernels trained with a limited number of training samples. We extend the work recently done in research on Receptive Field Neural Networks (RFNN) and show their behaviour using different bases and step-by-step changes within the network architecture. To ensure the reproducibility of the results, we simplified the baseline RFNN architecture to a single-layer CNN network and introduced a deterministic methodology for RFNN training and evaluation. This methodology enabled us to evaluate the significance of changes using the (recently widely used in neural networks) Bayesian comparison. The results indicate that a change in the base may have less of an effect on the results than re-training using another seed. We show that the simplified network with tested bases has similar performance to the chosen baseline RFNN architecture. The data also show the positive impact of energy normalization of used filters, which improves the classification accuracy, even when using randomly initialized filters.

show abstract

Dynamically Mixed Group Convolution to Lighten Convolution Operation

Cited by 3 publications

References 7 publications

A Lightweight Decentralized-Learning-Based Automatic Modulation Classification Method for Resource-Constrained Edge Devices

A Lightweight Decentralized-Learning-Based Automatic Modulation Classification Method for Resource-Constrained Edge Devices

Decentralized Automatic Modulation Classification Method Based on Lightweight Neural Network

Structure and Base Analysis of Receptive Field Neural Networks in a Character Recognition Task

Contact Info

Product

Resources

About