This paper proposes an accurate and dynamic method for diagnosing of crop diseases. This method adopts Bayesian networks to represent the relationships among the symptoms and crop diseases. This method has one main difference from the existing diagnosis methods - it does not use all the symptoms in the diagnosis, but purposively selects a subset of symptoms which are the most relevant to diagnosis; the active symptom selection is based on the concept of a Markov blanket in a Bayesian network. Theoretical analysis demonstrates that the proposed method can significantly enhance the performance of crop disease diagnosis.
Keywords: plant disease recognition, mathematical model, Bayesian network, machine learning, Markov blanket
The problem of increasing the efficiency of compiling test plans when testing complex software systems is considered. Automation tools for the development of test plans allow us to describe this document in a rather generalized way, without taking into account many of the attributes required for the success of the further stages of testing the software systems. The use of the developed automated system (AS), described in the article, allows to reduce the complexity of creating test plans due to the presence of a clear sequence of steps in the preparation of the document, providing the specialist with background information and advising effects. In the future, this AS can be used both directly in the development of test plans in the course of real software projects, and in training novice specialists in the skills of filling out these documents.
Keywords: software testing, test plan, automated system