Deep convolutional neural networks (DCNNs) have been successfully applied to plant disease detection. Unlike most existing studies, we propose feeding a DCNN CIE Lab instead of RGB color coordinates. We modified an Inception V3 architecture include one branch specific for achromatic data (L channel) and another chromatic (AB channels). This modification takes advantage the decoupling informatio...

One way to optimize wastewater treatment system infrastructure, its operations, monitoring, maintenance and management is through development of smart forecasting, monitoring failure prediction systems using machine learning modeling. The aim this paper was develop a model that able predict water pump based on the asymmetrical type data obtained from sensors such as levels, capacity, current fl...

Plant growth is inevitably affected by diseases, and one effective method of disease detection through the observation leaf changes. To solve problem in complex backgrounds, where distinction between plant diseases hindered large intra-class differences small inter-class differences, a complete plant-disease recognition process proposed. The was tested experiments research into traditional deep...

The Chinese hawthorn (Crataegus pinnatifida Bge. var. major N.E.Br.) is uniquely originated in northern China. The ecological and horticultural importance of Chinese hawthorn is considerable and some varieties are valued for their fruit or medicine extracts. Its taxonomy and phylogeny remain poorly understood. Apart from general plant morphological traits, pollen is an important trait for the c...

We propose an equation to evaluate the efficiency of a classification as function effort required and population size data collectors. The formula postulates “classification coefficient”, which relates not only complexity object be classified, but also availability representativeness. When applied phytocoenoses, suggests that system based on vascular plants offers best compromise between sampli...