1.Introduction The strength-ductility trade-offdilemma has long been a per-sistent challenge in Al matrix composites(AMCs)[1,2].This is-sue primarily arises from the agglomeration of reinforcements at the grain bounda...1.Introduction The strength-ductility trade-offdilemma has long been a per-sistent challenge in Al matrix composites(AMCs)[1,2].This is-sue primarily arises from the agglomeration of reinforcements at the grain boundaries(GBs),which restricts local plastic flow dur-ing the plastic deformation and leads to stress concentration[3,4].Recently,the development of concepts aimed at achieving hetero-geneous grain has emerged as a promising approach for enhanc-ing comprehensive mechanical properties[5,6].展开更多
Automatic modulation classification(AMC)is an essential technique in both civil and military applications.While deep learning has surpassed traditional methods in accuracy,distinguishing high-order modulations remain ...Automatic modulation classification(AMC)is an essential technique in both civil and military applications.While deep learning has surpassed traditional methods in accuracy,distinguishing high-order modulations remain challenging.Current efforts prioritize complex network designs,neglecting the integration of deep features and tailored feature engineering to reslove high-order ambiguities.Therefore,a multi-feature extraction framework is proposed,which directly concatenates the deep feature extracted by a newly designed lightweight neural network and the proposed spectrum secondary features or de-noised high-order statistical features.The proposed features and lightweight network both demonstrate superior overall accuracy than other competing features or networks.Furthermore,the effectiveness of the feature extraction framework is also validated.The average classification accuracy on high-order modulation sets reaches 67.39% on the RadioML2018.01A dataset,increasing more than 2%compared with the other competitive networks under the framework.The results indicate the effectiveness of the proposed feature extraction framework for its representational ability by combing the deep features with the proposed domain features.展开更多
基金support by the National Natural Science Foundation of China(Grant Nos.U23A20546 and 52271010)the Chinese National Natural Science Fund for Distinguished Young Scholars(Grant No.52025015)the Natural Science Foundation of Tianjin City(No.21JCZDJC00510).
文摘1.Introduction The strength-ductility trade-offdilemma has long been a per-sistent challenge in Al matrix composites(AMCs)[1,2].This is-sue primarily arises from the agglomeration of reinforcements at the grain boundaries(GBs),which restricts local plastic flow dur-ing the plastic deformation and leads to stress concentration[3,4].Recently,the development of concepts aimed at achieving hetero-geneous grain has emerged as a promising approach for enhanc-ing comprehensive mechanical properties[5,6].
基金supported by the National Natural Science Foundation of China(12273054).
文摘Automatic modulation classification(AMC)is an essential technique in both civil and military applications.While deep learning has surpassed traditional methods in accuracy,distinguishing high-order modulations remain challenging.Current efforts prioritize complex network designs,neglecting the integration of deep features and tailored feature engineering to reslove high-order ambiguities.Therefore,a multi-feature extraction framework is proposed,which directly concatenates the deep feature extracted by a newly designed lightweight neural network and the proposed spectrum secondary features or de-noised high-order statistical features.The proposed features and lightweight network both demonstrate superior overall accuracy than other competing features or networks.Furthermore,the effectiveness of the feature extraction framework is also validated.The average classification accuracy on high-order modulation sets reaches 67.39% on the RadioML2018.01A dataset,increasing more than 2%compared with the other competitive networks under the framework.The results indicate the effectiveness of the proposed feature extraction framework for its representational ability by combing the deep features with the proposed domain features.
