No abstract

No abstract

Cloud resiliency is an important issue in successful implementation of cloud computing systems. Handling cloud faults proactively, with a suitable remediation technique having minimum cost is an important requirement for a fault management system. The selection of best applicable remediation technique is a decision making problem and considers parameters such as i) Impact of remediation technique ii) Overhead of remediation technique ii) Severity of fault and iv) Priority of the application. This manuscript proposes an analytical model to measure the effectiveness of a remediation technique for various categories of faults, further it demonstrates the implementation of an efficient fault remediation system using a rulebased expert system. The expert system is designed to compute a utility value for each remediation technique in a novel way and select the best remediation technique from its knowledgebase. A prototype is developed for experimentation purpose and the results shows improved availability with less overhead as compared to a reactive fault management system.

No abstract

Eighty-five percent of the plants are affected by diseases caused by organisms like fungus, bacteria, and virus, which devastate the natural ecosystem. The most common clues provided by the plants affected by fungal diseases are defaming of the plant color. In literature, several traditional rule-based algorithms and normal image processing techniques are used to identify the fungal plant diseases. However, the traditional approach suffers from poor disease identification accuracy. Convoluted neural network (CNN) is one of the potential deep learning neural networks used for image recognition and classification in plant pathology. In this chapter, some of the potential CNN architectures used for plant disease detection like LeNet, AlexNet, VGGNet, GoogLeNet, ResNet, and ZFnet are discussed with the architecture and advantages. The efficiencies achieved by ResNet and ZFNet are found to be good in terms of accuracy and error rate.