Task-driven adaptive statistical compressive sensing of gaussian mixture models

A framework for adaptive and non-adaptive statistical compressive sensing is developed, where a statistical model replaces the standard sparsity model of classical compressive sensing. We propose within this framework optimal task-specific sensing protocols specifically and jointly designed for classification and reconstruction. A two-step adaptive sensing paradigm is developed, where online sensing is applied to detect the signal class in the first step, followed by a reconstruction step adapted to the detected class and the observed samples. The approach is based on information theory, here tailored for Gaussian mixture models (GMMs), where an information-theoretic objective relationship between the sensed signals and a representation of the specific task of interest is maximized. Experimental results using synthetic signals, Landsat satellite attributes, and natural images of different sizes and with different noise levels show the improvements achieved using the proposed framework when compared to more standard sensing protocols. The underlying formulation can be applied beyond GMMs, at the price of higher mathematical and computational complexity. © 1991-2012 IEEE.

Using GIS and Remote Sensing Technologies to Identify Environmental Variables of Malaria Vector Breeding Sites in Western Kenya

This study used Landsat 8 satellite imagery to identify environmental variables of households with malaria vector breeding sites in a malaria endemic rural district in Western Kenya. Understanding the influence of environmental variables on the distribution of malaria has been critical in the strengthening of malaria control programs. Using remote sensing and GIS technologies, this study performed a land classification, NDVI, Tasseled Cap Wetness Index, and derived land surface temperature values of the study area and examined the significance of each variable in predicting the probability of a household with a mosquito breeding site with and without larvae. The findings of this study revealed that households with any potential breeding sites were characterized by higher moisture, higher vegetation density (NDVI) and in urban areas or roads. The results of this study also confirmed that land surface temperature was significant in explaining the presence of active mosquito breeding sites (P< 0.000). The present study showed that freely available Landsat 8 imagery has limited use in deriving environmental characteristics of malaria vector habitats at the scale of the Bungoma East District in Western Kenya.