An IoT Based Smart Organic Drip Fertigation System for Eco-Friendly Agriculture using SVM Classifier and ThingSpeak
Sujaritha M1, Sanjana R2
1DR. M.Sujaritha*, Professor, Department of Computer Science & Engineering, Sri Krishna College of Engineering and Technology, Coimbatore, India.
2R. Sanjana, Department of Computer Science & Engineering, Sri Krishna College of Engineering and Technology, Coimbatore, India.
Manuscript received on March 18, 2020. | Revised Manuscript received on April 02, 2020. | Manuscript published on April 30, 2020. | PP: 709-713 | Volume-9 Issue-4, April 2020. | Retrieval Number: D6767049420/2020©BEIESP | DOI: 10.35940/ijeat.D6767.049420
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In agriculture, large-scale farming and feeding of effective organic nutrients to plants, in wide-ranging irrigation field becomes a serious scenario faced by majority of sectors in present agricultural system. In present, adapting the method of irrigation and continuous monitoring of irrigation system in agricultural field is becoming difficult for the farmers in adverse situations. The main intention of this paper is to feed the crops with organic nutrient content and to automate the continuous monitoring of water level, temperature, salt content present in water using Internet of Things (IoT). An IOT based Organic Drip Fertigation system mainly helps the farmers to automatically sense the difficulties that may occur due to the presence of salt content in water also automates fertigation method (the usage of organic nutrients) to make comparatively high yield than the ordinary methods. As a result, the proposed system helps in reducing soil erosion as only the required nutrients are injected via the drip system in order to reduce the usage of chemical fertilizers. In this paper, we use Support Vector Machine (SVM) to classify three (Temperature, Ph, Flow) feature vectors. The classification results will predict whether the obtained data is normal or abnormal and explore the accuracy of classification prediction by using SVM. Finally, the classification result obtained by applying SVM is uploaded to the ThingSpeak cloud.
Keywords: Fertigation, Irrigation, soil erosion, SVM, Things Speak.