Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 2 of 2
Full-Text Articles in Community Health
Coupling Self-Organizing Maps With A Naïve Bayesian Classifier: Stream Classification Studies Using Multiple Assessment Data, Nikolaos Fytilis, Donna M. Rizzo
Coupling Self-Organizing Maps With A Naïve Bayesian Classifier: Stream Classification Studies Using Multiple Assessment Data, Nikolaos Fytilis, Donna M. Rizzo
College of Engineering and Mathematical Sciences Faculty Publications
Organizing or clustering data into natural groups is one of the most fundamental aspects of understanding and mining information. The recent explosion in sensor networks and data storage associated with hydrological monitoring has created a huge potential for automating data analysis and classification of large, high-dimensional data sets. In this work, we develop a new classification tool that couples a Naïve Bayesian classifier with a neural network clustering algorithm (i.e., Kohonen Self-Organizing Map (SOM)). The combined Bayesian-SOM algorithm reduces classification error by leveraging the Bayesian's ability to accommodate parameter uncertainty with the SOM's ability to reduce high-dimensional data to lower …
Risk Factors Associated With Clinical Malaria Episodes In Bangladesh: A Longitudinal Study, Ubydul Haque, Gregory E. Glass, Arne Bomblies, Masahiro Hashizume, Dipak Mitra, Nawajish Noman, Waziul Haque, M. Moktadir Kabir, Taro Yamamoto, Hans J. Overgaard
Risk Factors Associated With Clinical Malaria Episodes In Bangladesh: A Longitudinal Study, Ubydul Haque, Gregory E. Glass, Arne Bomblies, Masahiro Hashizume, Dipak Mitra, Nawajish Noman, Waziul Haque, M. Moktadir Kabir, Taro Yamamoto, Hans J. Overgaard
College of Engineering and Mathematical Sciences Faculty Publications
Malaria is endemic to Bangladesh. In this longitudinal study, we used hydrologic, topographic, and socioeconomic risk factors to explain single and multiple malaria infections at individual and household levels. Malaria incidence was determined for 1,634 households in 54 villages in 2009 and 2010. During the entire study period 21.8% of households accounted for all (n = 497) malaria cases detected; 15.4% of households had 1 case and 6.4% had ≥2 cases. The greatest risk factors for malaria infection were low bed net ratio per household, house construction materials (wall), and high density of houses. Hydrologic and topographic factors were not …