Using microscopy to investigate stomatal behaviour is a common technique in plant physiology research. Manual inspection and measurement of stomatal features is a low throughput process in terms of time and human effort, which relies on expert knowledge to identify and measure stomata accurately. This process represents a significant bottleneck in research pipelines, adding significant researcher time to any project that requires it. To alleviate this, we introduce StomaAI (SAI): a reliable and user-friendly tool that measures stomata of the model plant Arabidopsis (dicot) and the crop plant barley (monocot grass) via the application of deep computer vision. We evaluated the reliability of predicted measurements: SAI is capable of producing measurements consistent with human experts and successfully reproduced conclusions of published datasets. Hence, SAI boosts the number of images that biologists can evaluate in a fraction of the time so is capable of obtaining more accurate and representative results.

The control of traffic signals is fundamental and critical to alleviate traffic congestion in urban areas. However, it is challenging since traffic dynamics are complicated in real-world scenarios. Because of the high complexity of the optimisation problem for modeling the traffic, experimental settings of existing works are often inconsistent. Moreover, it is not trivial to control multiple intersections properly in real complex traffic scenarios due to its vast state and action space. Failing to take intersection topology relations into account also results in inferior solutions. To address these issues, in this work we carefully design our settings and propose a new dataset including both synthetic and real traffic data in more complex scenarios. Additionally, we propose a novel baseline model with strong performance. It is based on deep reinforcement learning with an encoder-decoder structure: an edge-weighted graph convolutional encoder to excavate multi-intersection relations; and an unified structure decoder to jointly model multiple junctions in a comprehensive manner, which significantly reduces the number of the model parameters. By doing so, the proposed model is able to effectively deal with the multi-intersection traffic control optimisation problem. Models are trained/tested on both synthetic and real maps and traffic data with the Simulation of Urban Mobility (SUMO) simulator. Experimental results show that the proposed model surpasses multiple competitive methods. The traffic data and the code can be found at https://git.io/JPdU1.

No abstract