Traditional machine learning algorithms assume that data are exact or precise. However, this assumption may not hold in some situations because of data uncertainty arising from measurement errors, data staleness, and repeated measurements, etc. With uncertainty, the value of each data item is represented by a probability distribution function (pdf). In this paper, we propose a novel naive Bayes classification algorithm for uncertain data with a pdf. Our key solution is to extend the class conditional probability estimation in the Bayes model to handle pdf's. Extensive experiments on UCI datasets show that the accuracy of naive Bayes model can be improved by taking into account the uncertainty information.

No abstract

Transforming growth factor beta (TGFβ) plays a crucial role in tissue fibrosis. A number of studies have shown that TGFβ3 significantly attenuated tissue fibrosis. However, the mechanism involved in this effect is poorly understood. In this study we found that the expression level of TGFβ3 was higher in human myocardial infarction (MI) tissues than in normal tissues, and interestingly, it increased with the development of fibrosis post‐myocardial infarction (post‐MI). In vitro, human cardiac fibroblasts (CFs) were incubated with angiotensin II (Ang II) to mimic the ischaemic myocardium microenvironment and used to investigate the anti‐fibrotic mechanism of TGFβ3. Then, fibrosis‐related proteins were detected by Western blot. It was revealed that TGFβ3 up‐regulation attenuated the proliferation, migration of human CFs and the expression of collagens, which are the main contributors to fibrosis, promoted the phenotype shift and the cross‐linking of collagens. Importantly, the expression of collagens was higher in the si‐smad7 groups than in the control groups, while silencing smad7 increased the phosphorylation level of the TGFβ/smad signalling pathway. Collectively, these results indicated that TGFβ3 inhibited fibrosis via the TGFβ/smad signalling pathway, possibly attributable to the regulation of smad7, and that TGFβ3 might serve as a potential therapeutic target for myocardial fibrosis post‐MI.