Archives

The study was carried out to develop the machine learning algorithm to predict and classify the farmers into adopters and non-adopters in Kolar district of Karnataka for the year 2013. Multi-layered perceptron method of artificial neural network was computed by considering the various socio-economic characteristics of farmers as input vectors and adoption behaviour of the farmers as output vector in order to assess the socio economic factors influencing on adoption of drought coping mechanisms. The MLP method of ANN has trained by considering input layer with 12 input nodes, single hidden layer with 5 hidden nodes and an output layer with 2 output nodes. The hyperbolic tangent function used as activation function in hidden layers and the error is the cross entropy error because softmax activation function is applied to the output layer. The result shows that the cross entropy error is 33.17 and the following variables such as Crop insurance (100%), followed by Education (59.2%), Extension visits (58.5%), Income status (53.4%), Crop Diversification (47.4%), Animal Husbandry (28.6%) and Farm Size (24.0%) were significantly influencing on adoption process.

Key words: Animal Husbandry, Crop Diversification, Drought