K
Keshab K. Parhi
Researcher at University of Minnesota
Publications - 768
Citations - 21763
Keshab K. Parhi is an academic researcher from University of Minnesota. The author has contributed to research in topics: Decoding methods & Adaptive filter. The author has an hindex of 68, co-authored 749 publications receiving 20097 citations. Previous affiliations of Keshab K. Parhi include University of California, Berkeley & University of Warwick.
Papers
More filters
Proceedings ArticleDOI
PermDNN: efficient compressed DNN architecture with permuted diagonal matrices
TL;DR: In this article, the authors proposed PermDNN, a novel approach to generate and execute hardware-friendly structured sparse DNN models using permuted diagonal matrices, which eliminates the drawbacks of indexing overhead, non-heuristic compression effects and time-consuming retraining.
Journal ArticleDOI
Statistical Analysis of MUX-Based Physical Unclonable Functions
Yingjie Lao,Keshab K. Parhi +1 more
TL;DR: This paper presents a rigorous statistical analysis of various types of multiplexer-based (MUX-based) PUFs including the original MUX PUF, the feed-forwardMUX PUFs, the modifiedFeed-forward cascade MUXPUF, and multiplexinger-demultiplexer (Mux/DeMUX) PUF to show the best uniqueness and randomness and the best reliability.
Journal ArticleDOI
A fast VLSI adder architecture
H.R. Srinivas,Keshab K. Parhi +1 more
TL;DR: The proposed adder, referred to as the sign-select conversionAdder, is faster than all previous high-speed two's-complement binary adders for large word lengths and is very well suited for VLSI implementation.
Proceedings ArticleDOI
Seizure prediction using cost-sensitive support vector machine
TL;DR: It is demonstrated that the classifier based on a Cost-Sensitive Support Vector Machine (CSVM) can distinguish preictal from interictal with a high degree of sensitivity and specificity, when applied to linear features of power spectrum in 9 different frequency bands.
Journal ArticleDOI
VLSI architectures for lattice structure based orthonormal discrete wavelet transforms
T.C. Denk,Keshab K. Parhi +1 more
TL;DR: It is shown that architectures that are based on the quadrature mirror filter (QMF) lattice structure require approximately half the number of multipliers and adders than corresponding direct-form structures.