当前位置: X-MOL 学术IEEE Trans. Cognit. Commun. Netw. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Evolutionary Optimization of Residual Neural Network Architectures for Modulation Classification
IEEE Transactions on Cognitive Communications and Networking ( IF 8.6 ) Pub Date : 2021-12-23 , DOI: 10.1109/tccn.2021.3137519
Erma Perenda 1 , Sreeraj Rajendran 2 , Gerome Bovet 3 , Sofie Pollin 1 , Mariya Zheleva 4
Affiliation  

Automatic modulation classification receives significant interest in the context of current and future wireless communication systems. Deep learning emerged as a powerful tool for modulation classification, as it allows for joint discriminative features learning and signal classification. However, the optimization of deep neural network architectures for modulation classification is a manual and time-consuming process that requires profound domain knowledge and much effort. Most state-of-the-art solutions focus mainly on classification accuracy, while optimization of network complexity is neglected. This paper presents a novel bi-objective memetic algorithm, BO-NSMA, to search optimal deep neural network architectures for modulation classification to maximize classification accuracy and minimize network complexity. The experiments show that BO-NSMA, with an initial population of six individuals and only ten generations, finds a deep neural network architecture that outperforms all human-crafted architectures. Furthermore, BO-NSMA discovered the first low-complexity Convolutional neural network architecture, which achieves slightly better performance than costly Recurrent neural network architectures, allowing a 2.9-fold reduction in network complexity with 1.43% performance improvement. Compared to counterparts from network architecture search, BO-NSMA finds the best architecture, which achieves up to 18.73% accuracy gain and up to an 82-fold reduction in network complexity. The results are validated using the Wilcoxon signed-rank test.

中文翻译:

用于调制分类的残差神经网络架构的进化优化

自动调制分类在当前和未来无线通信系统的背景下受到了极大的关注。深度学习成为调制分类的强大工具,因为它允许联合判别特征学习和信号分类。然而,用于调制分类的深度神经网络架构的优化是一个手动且耗时的过程,需要深厚的领域知识和大量的努力。大多数最先进的解决方案主要关注分类准确性,而忽略了网络复杂性的优化。本文提出了一种新颖的双目标模因算法 BO-NSMA,用于搜索用于调制分类的最佳深度神经网络架构,以最大限度地提高分类精度并最大限度地降低网络复杂性。实验表明,初始种群为 6 个人且仅 10 代的 BO-NSMA 发现了一种优于所有人造架构的深度神经网络架构。此外,BO-NSMA 发现了第一个低复杂度卷积神经网络架构,其性能比昂贵的循环神经网络架构略好,网络复杂度降低 2.9 倍,性能提升 1.43%。与网络架构搜索的同行相比,BO-NSMA 找到了最佳架构,该架构实现了高达 18.73% 的准确度增益和高达 82 倍的网络复杂度降低。使用 Wilcoxon 符号秩检验验证结果。发现了一种优于所有人造架构的深度神经网络架构。此外,BO-NSMA 发现了第一个低复杂度卷积神经网络架构,其性能比昂贵的循环神经网络架构略好,网络复杂度降低 2.9 倍,性能提升 1.43%。与网络架构搜索的同行相比,BO-NSMA 找到了最佳架构,该架构实现了高达 18.73% 的准确度增益和高达 82 倍的网络复杂度降低。使用 Wilcoxon 符号秩检验验证结果。发现了一种优于所有人造架构的深度神经网络架构。此外,BO-NSMA 发现了第一个低复杂度卷积神经网络架构,其性能比昂贵的循环神经网络架构略好,网络复杂度降低 2.9 倍,性能提升 1.43%。与网络架构搜索的同行相比,BO-NSMA 找到了最佳架构,该架构实现了高达 18.73% 的准确度增益和高达 82 倍的网络复杂度降低。使用 Wilcoxon 符号秩检验验证结果。与昂贵的循环神经网络架构相比,它的性能略好,网络复杂度降低了 2.9 倍,性能提高了 1.43%。与网络架构搜索的同行相比,BO-NSMA 找到了最佳架构,该架构实现了高达 18.73% 的准确度增益和高达 82 倍的网络复杂度降低。使用 Wilcoxon 符号秩检验验证结果。与昂贵的循环神经网络架构相比,它的性能略好,网络复杂度降低了 2.9 倍,性能提高了 1.43%。与网络架构搜索的同行相比,BO-NSMA 找到了最佳架构,该架构实现了高达 18.73% 的准确度增益和高达 82 倍的网络复杂度降低。使用 Wilcoxon 符号秩检验验证结果。
更新日期:2021-12-23
down
wechat
bug