1.1 --- a/grant.bib Wed Apr 22 05:26:06 2009 -0700 1.2 +++ b/grant.bib Fri Jul 03 05:17:28 2009 -0700 1.3 @@ -460,7 +460,7 @@ 1.4 @inbook{adamson_tracking_2005, 1.5 series = {Lecture Notes in Computer Science}, 1.6 title = {A Tracking Approach to Parcellation of the Cerebral Cortex}, 1.7 - volume = {Volume 3749/2005}, 1.8 + volume = {3749/2005}, 1.9 isbn = {978-3-540-29327-9}, 1.10 url = {http://dx.doi.org/10.1007/11566465_37}, 1.11 abstract = {The cerebral cortex is composed of regions with distinct laminar structure. Functional neuroimaging results are often reported with respect to these regions, usually by means of a brain “atlas”. Motivated by the need for more precise atlases, and the lack of model-based approaches in prior work in the field, this paper introduces a novel approach to parcellating the cortex into regions of distinct laminar structure, based on the theory of target tracking. The cortical layers are modelled by hidden Markov models and are tracked to determine the Bayesian evidence of layer hypotheses. This model-based parcellation method, evaluated here on a set of histological images of the cortex, is extensible to {3-D} images.}, 1.12 @@ -527,4 +527,35 @@ 1.13 author = {C Kemp and {JB} Tenenbaum and {TL} Griffiths and T Yamada and N Ueda}, 1.14 year = {2006}, 1.15 keywords = {infinite,model,relational} 1.16 +}, 1.17 + 1.18 +@article{serpico_new_2001, 1.19 + title = {A new search algorithm for feature selection in hyperspectral remote sensing images}, 1.20 + volume = {39}, 1.21 + issn = {0196-2892}, 1.22 + doi = {10.1109/36.934069}, 1.23 + abstract = {A new suboptimal search strategy suitable for feature selection in 1.24 +very high-dimensional remote sensing images (e.g., those acquired by 1.25 +hyperspectral sensors) is proposed. Each solution of the feature 1.26 +selection problem is represented as a binary string that indicates which 1.27 +features are selected and which are disregarded. In turn, each binary 1.28 +string corresponds to a point of a multidimensional binary space. Given 1.29 +a criterion function to evaluate the effectiveness of a selected 1.30 +solution, the proposed strategy is based on the search for constrained 1.31 +local extremes of such a function in the above-defined binary space. In 1.32 +particular, two different algorithms are presented that explore the 1.33 +space of solutions in different ways. These algorithms are compared with 1.34 +the classical sequential forward selection and sequential forward 1.35 +floating selection suboptimal techniques, using hyperspectral remote 1.36 +sensing images (acquired by the airborne visible/infrared imaging 1.37 +spectrometer {[AVIRIS]} sensor) as a data set. Experimental results point 1.38 +out the effectiveness of both algorithms, which can be regarded as valid 1.39 +alternatives to classical methods, as they allow interesting tradeoffs 1.40 +between the qualities of selected feature subsets and computational cost}, 1.41 + number = {7}, 1.42 + journal = {Geoscience and Remote Sensing, {IEEE} Transactions on}, 1.43 + author = {{S.B.} Serpico and L. Bruzzone}, 1.44 + year = {2001}, 1.45 + keywords = {algorithm,binary string,feature extraction,feature selection,geophysical measurement technique,geophysical signal processing,geophysical techniques,hyperspectral remote sensing,image processing,land surface,multidimensional signal processing,multispectral remote sensing,optical imaging,remote sensing,suboptimal search strategy,terrain mapping}, 1.46 + pages = {1360--1367} 1.47 } 1.48 \ No newline at end of file