H
Harold H. Szu
Researcher at The Catholic University of America
Publications - 312
Citations - 4076
Harold H. Szu is an academic researcher from The Catholic University of America. The author has contributed to research in topics: Wavelet & Wavelet transform. The author has an hindex of 27, co-authored 311 publications receiving 3959 citations. Previous affiliations of Harold H. Szu include United States Department of the Navy & Naval Surface Warfare Center.
Papers
More filters
Journal ArticleDOI
Block-parallel decoding of convolutional codes using neural network decoders
TL;DR: An off-line trained and supervised neural network is proposed to decode convolutional codes one block at a time, using a Hamming neural network together with a winner-take-all circuit at each stage to select the decoded sequence.
Proceedings ArticleDOI
Representation and classification of unvoiced sounds using adaptive wavelets
TL;DR: This paper addresses the problems of both signal representation and classification, since it is natural to adaptively tune wavelets in conjunction with training the classifier in order to select the wavelet coefficients which contain the most information for discriminating between the classes.
Proceedings ArticleDOI
Brain Order Disorder 2nd Group Report of f-EEG
Francois Lalonde,Nitin Gogtay,Jay N. Giedd,Nadarajen A. Vydelingum,David G. Brown,Binh Q. Tran,Charles Hsu,Ming Kai Hsu,Jae Cha,Jeffrey Jenkins,Lien Ma,Jefferson M. Willey,Jerry Wu,Kenneth Oh,Joseph Landa,Cassie Lin,Tzyy-Ping Jung,Scott Makeig,Carlo Francesco Morabito,Qyu Moon,Takeshi Yamakawa,Soo-Young Lee,Jong-Hwan Lee,Harold H. Szu,Balvinder Kaur,Kenneth Byrd,Karen Dang,Alan T. Krzywicki,Babajide O. Familoni,Louis Larson,Susan Harkrider,Keith A. Krapels,Liyi Dai +32 more
TL;DR: It is asserted that the sources contained in the EEG signals may be discovered by an unsupervised learning neural network called blind sources separation (BSS) of independent entropy components, based on the irreversible Boltzmann cellular thermodynamics, where the entropy is a degree of uniformity.
Proceedings ArticleDOI
Local ICA for the Most Wanted Face Recognition
TL;DR: Facial disguises of FBI Most Wanted criminals are inevitable and anticipated in the design of automatic/aided target recognition (ATR) imaging systems.
Proceedings Article
Video-Assisted Global Positioning in Terrain Navigation: Hough Transform Solution.
TL;DR: A robust Hough transform-like method, facilitated by a class of CORDIC-structured computations, is shown feasible within the framework of terrain navigation, and empowers aerial surveillance systems to navigateively when the global position and inertial navigation sensors become faulty, inaccurate, or dysfunctional.