D
D.K. McIver
Researcher at Boston University
Publications - 13
Citations - 2827
D.K. McIver is an academic researcher from Boston University. The author has contributed to research in topics: Land cover & Statistical classification. The author has an hindex of 7, co-authored 13 publications receiving 2595 citations. Previous affiliations of D.K. McIver include Oracle Corporation.
Papers
More filters
Proceedings ArticleDOI
Global land cover classification results from MODIS
Mark A. Friedl,D.K. McIver,Xiaoyang Zhang,J.C.F. Hodges,A. Schnieder,A. Bacinni,Alan H. Strahler,Amanda Cooper,Feng Gao,Crystal L. Schaaf,W. Liu +10 more
TL;DR: The MODIS global land cover product as discussed by the authors provides maps of global ground cover at 1-km spatial resolution using several classification systems, principally that of the IGBP, to generate these maps, a supervised classification methodology is used that exploits a global database of training sites interpreted from high resolution imagery in association with ancillary data.
Patent
Methods and apparatus for optimizing markdown pricing
Shail Mehta,Reed B. Breneman,John C. Stauffer,D.K. McIver,Vishwamitra S. Ramakrishnan,Zhidong Lu,Pavandeep Kalra,Brian Sheppard +7 more
TL;DR: In this article, the authors present a method and apparatus for optimizing markdown scheduling that group multiple retail sites into bins (or buckets) for purposes of scheduling markdown pricing on an item (or group of related items) sold by those sites.
Proceedings ArticleDOI
Mapping urban areas using coarse resolution remotely sensed data
TL;DR: In this article, the authors used a supervised decision tree classifier for mapping urban land cover from coarse-resolution remotely sensed MODIS one kilometer data and found that the incorporation of DMSP-OLS data successfully improves urban classification results.
Proceedings ArticleDOI
Integration of domain knowledge in the form of ancillary map data into supervised classification of remotely sensed data
TL;DR: A method for incorporating prior probabilities in remote sensing-based land cover classification using a supervised decision tree classification algorithm is presented, which allows poorly separable classes to be distinguished based on ancillary information, but does not penalize rare classes.
Proceedings ArticleDOI
Classification of urban areas at continental scales using remotely sensed data
TL;DR: In this paper, a supervised decision tree classifier is used to obtain continental and global scale maps of urban land cover from remotely sensed imagery, specifically utilizing newly available one kilometer data from the MODIS sensor, and the technique of boosting is exploited to improve classification accuracy and to provide a means to correct major sources of error using available prior information.