AN INTELLIGENT IOT AND MACHINE LEARNING FRAMEWORK FOR TEMPERATURE REGULATION AND SILKWORM CONDITION MONITORING IN SERICULTURE

Abstract

Sericulture is highly sensitive to environmental conditions, particularly temperature
variations that significantly affect silkworm growth, cocoon quality, and productivity. Traditional
manual methods of monitoring and maintaining optimal environmental conditions are labourintensive,
inaccurate, and prone to human error. To address these limitations, this research
proposes an intelligent IoT-based automatic temperature detection, control, and monitoring
system integrated with machine learning for silkworm condition analysis. The prototype utilizes a
NodeMCU ESP8266 microcontroller interfaced with a DHT11 temperature and humidity sensor,
IR sensor, LCD display, buzzer, heater, and a cooling system. The system continuously senses
temperature and automatically operates a heater when the temperature falls below a predefined
threshold and activates cooling when temperature exceeds the allowable limit. An IR sensor is
incorporated to detect insect intrusion into the silkworm rearing trays and trigger protective alerts.
In addition, a machine learning-based image classification model is developed for silkworm health
status detection using uploaded silkworm images, classifying them into categories such as healthy,
diseased, or abnormal growth stage. Real-time monitoring and control operations are accessible
through IoT connectivity, ensuring continuous observation and improved decision-making for
farmers. Experimental results demonstrate improved accuracy, automation efficiency, and
reduction in human intervention. The proposed solution significantly enhances the productivity
and quality of silk cocoon formation and contributes to modernizing sericulture management