Characterizing Hyperspectral Data Layouts: Performance and Energy Efficiency in Embedded GPUs for PCA-based Dimensionality Reduction.
Jaime Sancho AragónSergio Sánchez RamírezRaquel Lazcano LópezDaniel Madroñal QuintínRubén Salvador PereaEduardo Juárez MartínezCésar Sanz ÁlvaroPublished in: DCIS (2019)
Keyphrases
- energy efficiency
- hyperspectral data
- dimensionality reduction
- principal components
- random projections
- principal component analysis
- power consumption
- energy consumption
- wireless sensor networks
- principle component analysis
- hyperspectral
- sensor networks
- data center
- hyperspectral images
- hyperspectral imagery
- smart home
- high performance computing
- routing protocol
- low dimensional
- high dimensional data
- embedded systems
- dimension reduction
- response time
- pattern recognition
- feature extraction
- data points
- high dimensional
- multispectral
- feature selection
- linear discriminant analysis
- high dimensionality
- kernel pca
- lower dimensional
- dimensionality reduction methods
- face recognition
- feature space
- input space
- infrared
- databases
- independent component analysis
- singular value decomposition
- sensor nodes
- remote sensing
- sparse representation
- data compression
- management system
- support vector
- data management
- data sets
- cloud computing