Category: Machine intelligence techniques for agricultural

A brief review is given for application of machine learning in agricultural sector. Also, a case study for detecting various tomato leaf diseases using several machine learning algorithms is presented. As a single case the efficacy of deep learning for detecting the diseases along with comparative results has been shown. So, this chapter may help the… Continue reading Conclusion

In this work, 250 tomato leaf images were taken from Plant Village Dataset. Out of which, 50 were the healthy tomato leaf images and 200 were the diseased tomato leaf images. To evaluate the similarities or differences of each disease, we first visualize the histogram of each analyzed image and compare it with a sample… Continue reading Results and discussion

It is a popular activation function as observed from literature. In softmax activation function the exponential of the input signal are considered. Further, the sum of all these values are computed. Next to it the ratio of the exponential to sum of exponential are evaluated as the output function. The advantage of this function is… Continue reading Softmax

It is one of the most used activation functions in DNN. The major advantage behind this activation function is that it does not trigger all the neurons at the same time and converts all the negative input into zero so that the neuron does not get activated. Training performance in this activation function is much… Continue reading Rectified linear unit (Relu)

DNN is a type of advanced neural network based on machine learning model where multiple number of layers are present in the input and output layers. The difference between a simple neural network and DNN is presented in Figure 13.12. This model is one of the popular artificial neural networks and can be used for different… Continue reading Deep neural network (DNN)

Random forest is a type of classifier which is the combination of multiple classifiers. It works by ensemble learning procedure, and multiple learning mechanisms are used for solving a particular problem. Here, in this method a number of assumptions are constructed and by combining them the problem is solved. Let us consider θm is a random… Continue reading Random forests

KNN is one of the most used classification model which is based on analog learning. Here in this method a comparison is done between the training and the testing tuples for finding the similarity. The input to the classifier consists of k-training samples in the feature set. The output of the KNN classifier is a… Continue reading K-nearest neighbor (KNN) classifier

Among all, neural network–based SVM is one of the most powerful and efficient feed-forward neural networks used for classification and regression problem. It can be used for both linear and nonlinear data classification. It is basically a binary classifier where a nonlinear mapping is considered for transforming the original training data into a higher dimension.… Continue reading Support vector machine

An artificial neural network (ANN) is a generalized mathematical model which is based on biological nervous systems. The fundamental elements of neural networks are artificial neurons. Input, output and hidden are three basic layers of a simple neural network as presented in Figure 13.7. In feed-forward networks, the data flows from input to output units, firmly… Continue reading Neural network

With the help of features extracted earlier, a machine or deep learning based classifier can classify the diseases in tomato plants and an early disease predicator will predict the disease.