F
Feng Tong
Researcher at Xiamen University
Publications - 69
Citations - 603
Feng Tong is an academic researcher from Xiamen University. The author has contributed to research in topics: Underwater acoustic communication & Multipath propagation. The author has an hindex of 12, co-authored 53 publications receiving 409 citations.
Papers
More filters
Journal ArticleDOI
Non-Uniform Norm Constraint LMS Algorithm for Sparse System Identification
TL;DR: An approach by seeking the tradeoff between the sparsity exploitation effect of norm constraint and the estimation bias it produces is presented, from which a novel algorithm is derived to modify the cost function of classic LMS algorithm with a non-uniform norm (p-norm like) penalty.
Journal ArticleDOI
Tile-wall bonding integrity inspection based on time-domain features of impact acoustics
Feng Tong,S.K. Tso,X.M. Xu +2 more
TL;DR: In this article, a multilayer back-propagation artificial neural network (ANN) classifier is developed for automatic health monitoring of tile-walls with high surface non-uniformity.
Journal ArticleDOI
Distributed compressed sensing estimation of underwater acoustic OFDM channel
TL;DR: A Distributed Compressed Sensing (DCS) method is proposed to transform the problem of OFDM channel estimation into reconstruction of joint sparse signals, and the experimental performance under field test is provided to illustrate the superiority of the proposed DCS channel estimation method, compared to the classic algorithm as well as CS counterparts.
Journal ArticleDOI
Impact-acoustics-based health monitoring of tile-wall bonding integrity using principal component analysis
Feng Tong,S.K. Tso,M.Y.Y. Hung +2 more
TL;DR: In this article, the authors explored the clustering and classification ability of principal component analysis (PCA) as applied to the impact-acoustics signature in tile-wall inspection with a view to mitigating the adverse influence of surface non-uniformity.
Journal ArticleDOI
Evaluation of tile–wall bonding integrity based on impact acoustics and support vector machine
TL;DR: In this article, the authors employed the least-squares support vector machine (LS-SVM) classifier instead of the ANN to derive a bonding integrity recognition approach with better reliability and enhanced immunity to surface roughness.