Artificial cognition for applications in smart agriculture: A comprehensive review

Agriculture contributes to 6.4% of the entire world's economic production. In at least nine countries of the world, agriculture is the dominant sector of the economy. Agriculture not only provides the fuel for billions of people but also employment opportunities to a large number of people. The agricultural industries are seeking innovative approaches for improving crop yielding because of unpredictable climatic changes, the rapid increase in population growth and food security concerns. Thus, artificial intelligence in agriculture also called “Agriculture Intelligence” is progressively emerging as a part of the industry's technological revolution. The aim of this paper is to review various applications of agriculture intelligence such as precision farming, disease detection, and crop phenotyping with the help of numerous tools such as machine learning, deep learning, image processing, artificial neural network, deep learning, convolution neural network, Wireless Sensor Network (WSN) technology, wireless communication, robotics, Internet of Things (IoT), different genetic algorithms, fuzzy logic and computer vision to name a few. With the help of these technologies, the use of the colossal volume of chemicals can be used reduced, which would result in reduced expenditure improved soil fertility along with elevated productivity.