Multi-Parameter Sensor Based Automation Farming

• Published in: E3S web of conferences Vol. 399; p. 4016
• Main Authors: D, Naveen Raju, J, Jeno Jasmine, A, Thilagavathy, G, Rambalaji, K, Sooraj, S, Praveenraj, D, Sri Prasanna kumar, A, Manjunathan
• Format: Journal Article Conference Proceeding
• Language: English
• Published: Les Ulis EDP Sciences 01-01-2023
• Subjects: Artificial intelligence; Automation; D C motors; Deep learning; Digital agriculture; Electric motors; Farming; Fertilizers; Irrigation; Irrigation systems; Irrigation water; Machine learning; Moisture content; Neural networks; Pumps; Sensors; Soil moisture; Soil temperature; Soil water; Support vector machines; Tracking systems; Water levels
• ISSN: 2267-1242; 2555-0403; 2267-1242
• DOI: 10.1051/e3sconf/202339904016

IOT innovation is used in the development of the Smart Farming Tracking the System. An Arduino Uno, a temperature humidity sensor, soil moisture sensor, water level sensor, water pumps, and DC motors strength this system. If the smart farming tracking system turns on, the sensors find the field’s water level and the soil’s moisture level. If the irrigation water stage falls below the level defined for a specific crop grown in the growing area, the irrigation system is going to start to pump water. The IOT warns concerning current level of water, soil moisture stage, and motor beginning will be shown on the LCD panel of the section. We are able to use the pumps by hand via a webpage. The farmers are additionally getting this data via mobile phone. By hitting a system- provided link, the individual using it may firmly prevent the water’s flow within the field. While carried out, the system will assist landowners to preserve suitable soil water and moisture levels, thus boosting yields with little work. The goal of this article is to identify grow illnesses and reduce losses in money. For picture appeal, we suggested an entirely based on deep learning method. We put the three most common Neural Network Designs to the test: Faster Region-based entirely judgment (SVM)Support Vector Machine Region-based entirely (RF) Random Forest method. The method suggested in the research can correctly detect many types of disease and is capable of dealing in complicated situations. In addition, the method may be expanded to recommend fertilizer according to extent evaluation as well as measurement. artificial intelligence (AI) entirely Machine Learning Response to this the combination the issue is a supervised categorization judgment.