• Publications
  • Influence
Clustering and Artificial Neural Networks as a Tool to Generate Membership Functions
TLDR
This work show an application of the classical clustering algorithm, c-mean mixed with Artificial Neural Networks to build membership functions of fuzzy systems, the simulations were done with MATLAB. Expand
  • 11
Classification and Quantification of Occlusion Using Hidden Markov Model
TLDR
We train one HMM for each body part relevant for gait recognition and classify the scene of occlusion as one of the three cases of occLusion, namely, self Occlusion (single individual moving), occluded in a crowd moving in same direction and occlusions due to movement of human beings approaching from opposite direction. Expand
  • 1
The network service plane: An approach for inter-domain network reservations
TLDR
This paper introduces an architecture for managing a wide range of different administrative domains, that already have its own management systems. Expand
  • 5
Learning how to grasp under supervision
The problem of grasping a generic sphere is addressed. A supervised learning approach using a multilayer neural network for learning the position in 3D space and the radius of the sphere isExpand
  • 2
wtss: An R Client for a Web Time-Series Service
TLDR
An R client that provides remote access to satellite image time series from a Web Time Series Server. Expand
An optimal software-pipelining method for instruction-level parallel processors based on scaled retiming
TLDR
Software pipelining is an instruction-level loop scheduling method for achieving high performance fine-grain parallelism on VLIW (very long instruction word) processors. Expand
  • 4
Towards a Spatial Data Infrastructure for Big Spatiotemporal Data Sets CONFERENCE
The recent technological advances in geospatial data collection, such as mobile phones, Earth observation and GPS (Global Positioning System) satellites, have created bigger spatiotemporal data setsExpand
  • 1
  • PDF
Spatio-temporal change detection from multidimensional arrays
TLDR
We extend the EFP to account for the spatial autocorrelation between spatial neighbors and assess the effects of spatial correlation when applying BFAST on satellite image time series. Expand