Search

Intelligent rice disease recognition methods based on deep neural networks can predict the degree of disease on the basis of, for example, the number of disease spots on an image, so that preventive measures can be taken. Currently, intelligent recognition methods for rice diseases suffer from the disadvantages of poor versatility and low accuracy. This paper uses eight common image classification networks to classify and identify four rice diseases. ResNet50 was selected as the feature extraction network and an enhanced feature fusion and target adaptive network (EFFTAN), referred to as EFFTAN, is proposed. The EFFTAN was used to detect four rice spot diseases in the rice leaf disease image samples dataset; the mean average precision of the final detection was 95.3%, and effective detection was also achieved for the dense spot features. [ABSTRACT FROM AUTHOR]

• Introduce a novel formulation that integrates technical and organizational resilience. • Propose a comprehensive resilience analysis framework incorporating various metrics. • Utilize a new multi-objective linear programming model for optimizing resource allocation. • Present a detailed flowchart for validating the resilience analysis framework in a power system. In urban infrastructure systems, resilience is crucial for maintaining functionality, minimizing losses, and expediting recovery during disruptive incidents. Effective allocating resources across various phases of emerging disturbances can generally enhance the system's capacity to cope with disasters. However, it is imperative to recognize that distinct resource allocation strategies may lead to divergent outcomes in terms of resilience performance. Therefore, this study develops a framework for optimizing resource allocation based on multiple resilience objectives by understanding the interplay between resilience performance and dynamic decision-making. The resilience processes are first formalized into distinct stages, considering the technical and organizational resilience of the infrastructure system in the event of disruption. Building upon this foundation, five decision scenarios are proposed, contingent on the allocation or non-allocation of resources to each resilience stage. A multi-resilience-objective mixed-integer linear programming (MROMILP) model is formulated to optimize the resource allocation scheme for each resilience stage within the constraints of internal resources. Finally, the model and framework are tested using a power system as a tangible example. The integrated multi-stage quantitative resilience assessment and optimization method proposed in this study can assist decision-makers in making dynamic and continuous trade-offs between resources and resilience targets. [ABSTRACT FROM AUTHOR]