An intelligent mobile application for diagnosis of crop diseases in Pakistan using fuzzy inference system.

Highlights • Largest producers of crops include south Asian countries including Pakistan. • There is lack of exploitation of technology for enhancements in agriculture sector. • Diagnosis of crops diseases in rural areas is a challenge. • Intelligent mobile application with easy to use interface has been developed using fuzzy inference system. • Highly promising results leading up to 99% of accurate disease diagnosis have been achieved. Abstract South Asian countries are amongst the largest producers of crops with favourable climate conditions and fertile soil. However, traditional agricultural mechanisms are in place and inadequate effort has been put into exploit the usage of technology. One of the main problems being faced by agriculture sector in Pakistan and other developing countries is that crop diseases are not diagnosed timely and efficiently. Conventional methods for disease diagnosis in crops lead to less accurate and inefficient diagnosis, consequently leading to low productivity. In this paper, an intelligent approach for the diagnosis of crop diseases is proposed which is capable of working over Android mobile devices using fuzzy inference system as the main decision making engine at the backend. The system is capable enough to communicate to the farmers in Pakistan in their local language Urdu and assist them in diagnosing diseases in their crops. Agriculture experts in government sector can get equal benefit from it in diagnosis and prevention of crops diseases. It takes symptoms of the crops as input with a provision of vague input and generates the output in the form of diagnosed disease using its inference engine. The proposed system caters two main crops of Pakistan, cotton and wheat and is capable to diagnose their main diseases. The proposed system has been tested on a pool of 100 real crop problems and its inference engine has shown excellent performance in prediction of the right disease which is up to 99% accurate. [ABSTRACT FROM AUTHOR]