Smart Detection System for Pesticide Contamination in Fruits and Vegetables
Kannabiran. K *
Department of Horticulture Kalasalingam Academy of Research and Education Virudhnagar, Tamilnadu, India.
G. Jagadeesh kumar
Department of Computer science and Engineering Kalasalingam Academy of Research and Education Virudhnagar, Tamilnadu, India.
N. Venkatesh
Department of Computer science and Engineering Kalasalingam Academy of Research and Education Virudhnagar, Tamilnadu, India.
K.Sai Chaitanya
Department of Computer science and Engineering Kalasalingam Academy of Research and Education Virudhnagar, Tamilnadu, India.
P.Sri Venkata Manikanta
Department of Computer science and Engineering Kalasalingam Academy of Research and Education Virudhnagar, Tamilnadu, India.
K.Gangadharan
Department of Mechanical Engineering Kalasalingam Academy of Research and Education Virudhnagar, Tamilnadu, India.
*Author to whom correspondence should be addressed.
Abstract
Pesticide contamination in fruits and vegetables has become a serious concern due to its detrimental effects on human health and the environment. Currently, the widespread utilization of pesticides such as Glyphosate, Chlorpyrifos, Neonicotinoids, Mancozeb, and Pyrethroids during fruit and vegetable cultivation has been associated with adverse health effects in humans. To grow more food for more people, people developed innovative techniques. These days, fruits and vegetables are essential for providing us with the nutrition and energy we require. But occasionally, chemicals are applied to aid in their growth. The goal of the present study is to use an Arduino Mega 2560 microprocessor, which is integrated with an LCD display, spectral triad sensor, pH sensor, gas sensor, and buzzer, to identify pesticides in fruits and vegetables. The system uses real-time sensor data collection and Random Forest analysis powered by machine learning (ML) and the Internet of Things (IoT). The spectral triad sensor captures comprehensive spectral data while the gas and pH sensors monitor the presence of pesticides and acidity. Using the Random Forest method, the machine learning model examines the sensor data to identify potential pesticide contamination. The results are displayed on LCD in addition to a buzzer alert.
Keywords: Pesticide Detection, arduino mega 2560, spectral triad sensor, ph sensor, gas sensor, machine learning (ml), random forest algorithm, internet of things (iot), real-time monitoring, food safety, sensor data analysis, lcd display, buzzer alert