Xin-Gang Zhang | PubMed Health

PubMed2004

Automated soil resources mapping based on decision tree and Bayesian predictive modeling.

This article presents two approaches for automated building of knowledge bases of soil resources mapping. These methods used decision tree and Bayesian predictive modeling, respectively to generate knowledge from training data. With these methods, building a knowledge base for automated soil mapping is easier than using the conventional knowledge acquisition approach. The knowledge bases built by these two methods were used by the knowledge classifier for soil type classification of the Longyou area, Zhejiang Province, China using TM bi-temporal imageries and GIS data. To evaluate the performance of the resultant knowledge bases, the classification results were compared to existing soil map based on field survey. The accuracy assessment and analysis of the resultant soil maps suggested that the knowledge bases built by these two methods were of good quality for mapping distribution model of soil classes over the study area.

Algorithms↗

PubMed2004

Aspiration of dead space in the management of chronic obstructive pulmonary disease patients with respiratory failure.

INTRODUCTION: Carbon dioxide clearance can be improved by reducing respiratory dead space or by increasing the clearance of carbon-dioxide-laden expiratory gas from the dead space. Aspiration of dead space (ASPIDS) improves carbon dioxide clearance by suctioning out (during expiration) the carbon-dioxide-rich expiratory gas while replacing the suctioned-out gas with oxygenated gas. We hypothesized that ASPIDS would allow lower tidal volume and thus reduce exposure to potentially injurious airway pressures. METHODS: With 8 hemodynamically stable, normothermic, ventilated patients suffering severe chronic obstructive pulmonary disease we tested the dead-space-clearance effects of ASPIDS. We compared ASPIDS to phasic tracheal gas insufflation (PTGI) during conventional mechanical ventilation and during permissive hypercapnia, which was induced by decreasing tidal volume by 30%. The mean P(aCO(2)) reductions with PTGI flows of 4.0 and 6.0 L/min and during ASPIDS (at 4.0 L/min) were 32.7%, 51.8%, and 53.5%, respectively. Peak, plateau, and mean airway pressure during permissive hypercapnia were significantly lower than during conventional mechanical ventilation but PTGI increased peak, plateau, and mean airway pressure. However, pressures were decreased during permissive hypercapnia while applying ASPIDS. Intrinsic positive end-expiratory pressure also increased with PTGI, but ASPIDS had no obvious influence on intrinsic positive end-expiratory pressure. ASPIDS had no effect on cardiovascular status. CONCLUSIONS: ASPIDS is a simple adjunct to mechanical ventilation that can decrease P(aCO(2)) during conventional mechanical ventilation and permissive hypercapnia.

Aged↗