Energy consumption characterization of a Massively Parallel Processor Array (MPPA) platform running a hyperspectral SVM classifier.
Daniel MadroñalRaquel LazcanoHimar FabeloSamuel OrtegaRubén SalvadorGustavo Marrero CallicóEduardo JuárezCésar SanzPublished in: DASIP (2017)
Keyphrases
- energy consumption
- massively parallel
- svm classifier
- hyperspectral
- mesh connected
- processor array
- parallel computers
- support vector machine
- wireless sensor networks
- support vector machine svm
- remote sensing
- infrared
- support vector
- energy efficiency
- image classification
- multispectral
- sensor networks
- fine grained
- parallel computing
- image data
- feature vectors
- data transmission
- high performance computing
- routing protocol
- sensor nodes
- data center
- training set
- kernel function
- base station
- parallel machines
- parallel implementation
- semi supervised
- training data
- parallel algorithm
- processing elements
- database systems
- feature space