Abstract. Rain water running through soils and wetlands will leach decomposing plant organic matter into streams and lakes in the form of dissolved organic carbon (DOC). In streams, lakes and eventually estuaries, DOC can be mineralized to CO2, precipitated to sediments or taken up in biological matter, and is thus an important part of many aquatic ecosystems. Using hydrological, climatological and geographical data from 32 sites located in Canada, we developed a neural network model which allowed us to estimate DOC export from the Canadian land mass. We reapplied the model to the 32 sites plus a further 43 basins to estimate area normalized exports for various regions of the country. We estimated that 14.3xl 06 t of DOC are currently exported from Canadian terrestrial ecosystems. We then modified climatological inputs to the model to reflect the predicted temperature and precipitation conditions under a doubled atmospheric COg regime. Our model suggests that DOC exports will increase by approximately 14% under a doubled COg atmosphere, mostly owing to increases in runoff. Our analysis also shows that DOC export is greatest in the spring in southern Canada and summer in the north.
This study was conducted to test a three-layered artificial neural network analysis of phonocardiogram recordings to diagnose, automatically and objectively, the condition of the heart in patients with heart murmurs. The data were recorded simultaneously in each of 49 patients with a heart murmur through eight microphones attached to the skin surface with adhesive tape, and were analysed by computer. The diagnosis was automated using a three-layered neural network technique. The neural network generated correct answers in over 70% of cases. Furthermore, about 80% of cases of two concurrent diseases were identified correctly. However, ventricular septal defects were incorrectly classified as aortic stenosis or aortic regurgitation, and patent ductus arteriosus was not diagnosed correctly. Accurate diagnoses can frequently be obtained using a neural network, but accuracy can be improved with further data accumulation.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.