Wounding induces suberin deposition, relevant gene expressions and changes of endogenous phytohormones in Chinese yam (Dioscorea opposita) tubers.

Wounds on Chinese yam (Dioscorea opposita ) tubers can ocurr during harvest and handling, and rapid suberisation of the wound is required to prevent pathogenic infection and desiccation. However, little is known about the causal relationship among suberin deposition, relevant gene expressions and endogenous phytohormones levels in response to wounding. In this study, the effect of wounding on phytohormones levels and the expression profiles of specific genes involved in wound-induced suberisation were determined. Wounding rapidly increased the expression levels of genes, including PAL , C4H , 4CL , POD , KCSs , FARs , CYP86A1 , CYP86B1 , GPATs , ABCGs and GELPs , which likely involved in the biosynthesis, transport and polymerisation of suberin monomers, ultimately leading to suberin deposition. Wounding induced phenolics biosynthesis and being polymerised into suberin poly(phenolics) (SPP) in advance of suberin poly(aliphatics) (SPA) accumulation. Specifically, rapid expression of genes (e.g. PAL , C4H , 4CL , POD ) associated with the biosynthesis and polymerisation of phenolics, in consistent with SPP accumulation 3days after wounding, followed by the massive accumulation of SPA and relevant gene expressions (e.g. KCSs , FARs , CYP86A1 /B1 , GPATs , ABCGs , GELPs ). Additionally, wound-induced abscisic acid (ABA) and jasmonic acid (JA) consistently correlated with suberin deposition and relevant gene expressions indicating that they might play a central role in regulating wound suberisation in yam tubers.

A Hybrid Deep Learning Model for Recognizing Actions of Distracted Drivers.

With the rapid spreading of in-vehicle information systems such as smartphones, navigation systems, and radios, the number of traffic accidents caused by driver distractions shows an increasing trend. Timely identification and warning are deemed to be crucial for distracted driving and the establishment of driver assistance systems is of great value. However, almost all research on the recognition of the driver's distracted actions using computer vision methods neglected the importance of temporal information for action recognition. This paper proposes a hybrid deep learning model for recognizing the actions of distracted drivers. Specifically, we used OpenPose to obtain skeleton information of the human body and then constructed the vector angle and modulus ratio of the human body structure as features to describe the driver's actions, thereby realizing the fusion of deep network features and artificial features, which improve the information density of spatial features. The K-means clustering algorithm was used to preselect the original frames, and the method of inter-frame comparison was used to obtain the final keyframe sequence by comparing the Euclidean distance between manually constructed vectors representing frames and the vector representing the cluster center. Finally, we constructed a two-layer long short-term memory neural network to obtain more effective spatiotemporal features, and one softmax layer to identify the distracted driver's action. The experimental results based on the collected dataset prove the effectiveness of this framework, and it can provide a theoretical basis for the establishment of vehicle distraction warning systems.