ResearchBib Share Your Research, Maximize Your Social Impacts
Sign for Notice Everyday Sign up >> Login

Smart IoT and Machine Learning - Based Framework for Water Quality and Crop Prediction Using Raspberry Pi

Journal: International Journal of Science and Research (IJSR) (Vol.11, No. 7)

Publication Date:

Authors : ; ;

Page : 929-934

Keywords : Internet of Things; Water Quality; Raspberry Pi; Adafruit; Thingspeak Cloud; Machine Learning; Support Vector Machine;

Source : Downloadexternal Find it from : Google Scholarexternal

Abstract

The water's quality plays a significant role in our daily lives. Forecasting water quality will be beneficial for reducing water pollution and safeguarding human health. A clever process for monitoring the water's quality instantly alerts the water analyzer when there is a problem. This method automatically determines the water's condition by interpreting sensor data using the Internet of Things. The development of machine - to - machine communication makes data analysis and communication easy and efficient. As an outcome of this effort, an "intellectual Based iot water quality system" to lakes has indeed been developed and is currently implementing in rural areas. The structure uses sensors for pH, turbid, and temperature to determine the properties of water quality like hydrogen ions and the entire amount of dissolved solvents. The yield prediction remains a major issue that needs to be addressed with the available data. Machine learning methods are a superior choice in this case. In agriculture, a variety of machine learning techniques are used and evaluated in order to forecast crop yield for following year. In this, a method for predicting agricultural productivity with historical data is put forth and applied. To achieve this, farm data are used to apply machine learning algorithms, such as Support Vector Machine and Random Forest that recommend fertilizer suitable for each unique crop.

Last modified: 2022-09-07 15:19:11