Soil temperature and humidity straight away influence plant growth and the availability of plant nutrients. In this work, we carried out experiments to identify the relationship between climatic parameters and plant nutrients. When the relative humidity was very high, deficiency symptoms were shown on plant leaves and fruits. But, recognizing and managing these plant nutrients manually would become difficult. However, no much research has been done in this field. The main objective of this research was to propose a machine learning model to manage nutrient deficiencies in the plant. There were two main phases in the proposed research. In the first phase, the humidity, temperature, and soil moisture in the greenhouse environment were collected using WSN and the influence of these parameters on the growth of plants was studied. During experimentation, it was investigated that the transpiration rate decreased significantly and the macronutrient contents in the plant leave decreased when the humidity was 95%. In the second phase, a machine learning model was developed to identify and classify nutrient deficiency symptoms in a tomato plant. A total of 880 images were collected from Bingo images to form a dataset. Among all these images, 80% (704 images) of the dataset were used to train the machine learning model and 20% (176 images) of the dataset were used for testing the model performance. In this study, we selected K-means Clustering for key points detection and SVM for classification and prediction of nutrient stress in the plant. SVM using linear kernel performed better with the accuracy rates of 89.77 % as compared to SVM using a polynomial kernel.
A Study of Factors Influencing Plant Growth by WSN Approach and Plant Nutrient Deficiency Classification in Tomato Using SVM
