N
Nagarajan Kandasamy
Researcher at Drexel University
Publications - 126
Citations - 3236
Nagarajan Kandasamy is an academic researcher from Drexel University. The author has contributed to research in topics: Neuromorphic engineering & Spiking neural network. The author has an hindex of 25, co-authored 121 publications receiving 2919 citations. Previous affiliations of Nagarajan Kandasamy include Vanderbilt University & University of Michigan.
Papers
More filters
Journal ArticleDOI
Approximation Modeling for the Online Performance Management of Distributed Computing Systems
TL;DR: This paper develops a hierarchical control framework to solve performance management problems in distributed computing systems operating in a data center and shows that a computing system managed by the proposed control framework with approximation models realizes profit gains that are, in the best case, within 1% of a controller using an explicit model of the system.
Journal ArticleDOI
Physical Layer Encryption for Wireless OFDM Communication Systems
TL;DR: Simulation and hardware evaluation results demonstrate that the proposed system is capable of providing secure communication from an eavesdropper with no decrease in performance as compared with the baseline case of a standard OFDM transceiver.
Posted Content
Improving Dependability of Neuromorphic Computing With Non-Volatile Memory
TL;DR: In this paper, a reliability-oriented approach is proposed to map machine learning applications to neuromorphic hardware, with the aim of improving system-wide reliability without compromising key performance metrics such as execution time of these applications on the hardware.
Journal ArticleDOI
A self-managing wide-area data streaming service
Viraj Bhat,Manish Parashar,Hua Liu,Nagarajan Kandasamy,Mohit Khandekar,Scott Klasky,Sherif Abdelwahed +6 more
TL;DR: The design and implementation of a self-managing data-streaming service based on online control strategies is presented and a Grid-based fusion workflow scenario is used to evaluate the service and demonstrate its feasibility and performance.
Posted Content
DFSynthesizer: Dataflow-based Synthesis of Spiking Neural Networks to Neuromorphic Hardware
TL;DR: DFSynthesizer as mentioned in this paper is an end-to-end framework for synthesizing SNN-based machine learning programs to neuromorphic hardware, which uses Synchronous Dataflow Graph (SDFG) to represent a clustered SNN program.