Nitrogen fertilization application strategies improve yield of the rice cultivars with different yield types by regulating phytohormones.

Rice (Oryza sativa L.) is the most important food crop worldwide, and its sustainable development is essential to ensure global food security. Panicle morphological and physiological characteristics plays an important role in rice yield formation. However, under different nitrogen (N) fertilization strategies, it is not clear whether the morphological and physiological state of panicles at panicle development stage affects the formation of yield. To understand how the panicle differentiation and development, and grain yield are affected by the N fertilization strategies, and clarify the relationship between related traits and yield in the process of panicle development in different cultivars. In this study consisted of no N fertilizer and four N fertilization strategies, a panicle weight type (PWT) rice cultivar, Dongfu 114 (DF114) and a panicle number type (PNT) rice cultivar, Longdao 11 (LD11) were grown in the field. The results showed that N fertilization strategies could improve the nitrogen use efficiency and yield of rice, but the response of different rice varieties to N fertilizer strategies was different. Different from the DF114, the further increase of panicle N fertilizer ratio could not further improve the yield of LD11, and the highest grain yield of DF114 and LD11 was obtained under N4 and N3 conditions, respectively. In addition, this study found that N fertilizer strategies can affect the content of phytohormones in rice at the panicle differentiation stage, and then regulate the differentiation and development of rice panicles to affect yield. It is of great significance to optimize the application mode of N fertilizer according to the characteristics of varieties to improve rice yield and ensure food security.

Bleeding detection in Wireless Capsule Endoscopy based on Probabilistic Neural Network.

Wireless Capsule Endoscopy (WCE), which allows clinicians to inspect the whole gastrointestinal tract (GI) noninvasively, has bloomed into one of the most efficient technologies to diagnose the bleeding in GI tract. However WCE generates large amount of images in one examination of a patient. It is hard for clinicians to leave continuous time to examine the full WCE images, and this is the main factor limiting the wider application of WCE in clinic. A novel intelligent bleeding detection based on Probabilistic Neural Network (PNN) is proposed in this paper. The features of bleeding region in WCE images distinguishing from non-bleeding region are extracted. A PNN classifier is built to recognize bleeding regions in WCE images. Finally the intelligent bleeding detection method is implemented through programming. The experiments show this method can correctly recognize the bleeding regions in WCE images and clearly mark them out. The sensitivity and specificity on image level are measured as 93.1% and 85.6% respectively.