[Pang, Lihui] Sungkyunkwan Univ, Dept Software, Suwon 440746, South Korea.
通讯机构：
[Lihui Pang] S
School of Electrical Engineering, University of South China, Hengyang, China<&wdkj&>Department of Software, Sungkyunkwan University, Suwon, South Korea
语种：
英文
关键词：
Blind signal separation;Kernel density estimation;Maximum likelihood estimation;Neural networks;Time–frequency overlapped signal
This work was supported in part by the National Natural Science Foundation of China (Nos. 61901209, 61871210 and 61901149), in part by Natural Science Foundation of Hunan Province (No. 2022JJ40377) and in part by the Scientific Research Project of Hunan Provincial Education Department (No. 19C1591).
机构署名：
本校为第一机构
院系归属：
电气工程学院
摘要：
AbstractThe blind signal separation (BSS) algorithm obtains each original/source signal from the observed signal collected by the receiving antenna or sensor. Objective/loss/cost function and optimization method are two key parts of BSS algorithm. Modifying the objective function and optimization from the perspective of neural network (NN) is a novel concept in BSS domain. $$L_2$$
L
2
regularization is adopted as a term of maximum likelihood estimation (MLE)-based objective function like in Liu et al.(Sensors 21(3):973, 2021); however, w...
