Agricultural activity recognition with smart-shirt and crop protocol

Accurate recognition of agricultural activity has a direct bearing on improving farm productivity in terms of achieving crop yield improvements, imparting precision training to farmers wherever needed, and measuring their efforts. Moreover, farm activities are not independent of each other. Cultivation of any crop is associated with a defined pattern of farmer activities called the crop protocol. With an indigenously developed garment for the farmer called smart-shirt, we propose a model for activity classification which has a mean activity prediction accuracy of over 88% for seven classes. The performance of numerous classifiers-SVM, Naive Byes, K-NN, LDA and QDA-is rigorously evaluated and compared for activity prediction. We also propose a model to use the a priori information associated with the crop protocol to recognize the major activity when presented with an unclear evidence of reported activities.