L
Leonardo Alves Dias
Researcher at University of Birmingham
Publications - 6
Citations - 42
Leonardo Alves Dias is an academic researcher from University of Birmingham. The author has contributed to research in topics: Throughput (business) & Field-programmable gate array. The author has an hindex of 2, co-authored 6 publications receiving 22 citations. Previous affiliations of Leonardo Alves Dias include Federal University of Rio Grande do Norte & Federal University of Paraíba.
Papers
More filters
Journal ArticleDOI
Parallel Implementation of K-Means Algorithm on FPGA
TL;DR: This paper proposes a fully parallel implementation of the K-means algorithm on FPGA to optimize the system’s processing time, thus enabling real-time applications and unlike most implementations proposed in the literature, even parallel ones do not have sequential steps, a limiting factor of processing speed.
Journal ArticleDOI
Fully parallel implementation of Otsu automatic image thresholding algorithm on FPGA
TL;DR: In this article, a high-throughput implementation of the Otsu automatic image thresholding algorithm on Field Programmable Gate Array (FPGA) aiming to process high-resolution images in real-time was proposed.
Journal ArticleDOI
A Shift-Register Based BIST Architecture for FPGA Global Interconnect Testing and Diagnosis
TL;DR: The proposed BIST approach takes advantage of FPGA low-level resources in order to generate cyclic test patterns, analyse testing response and store test results in a simple way, thereby reducing time requirements.
Journal ArticleDOI
A full-parallel implementation of self-organizing maps on hardware
TL;DR: In this paper, a fully parallel architecture for the self-organizing maps (SOMs) is introduced to optimize the system's data processing time, which is validated on FPGA and evaluated concerning hardware throughput and the use of resources.
Proceedings ArticleDOI
A New Hardware Approach to Self-Organizing Maps
TL;DR: A new hardware approach to SOM implementation is proposed, exploiting parallelization, to optimize the system’s processing time, and allows the parallelization of the data dimensions instead of the map, ensuring high processing speed regardless of data dimensions.