Scholarlink

Fruit spoilage, predicted by factors such as temperature, humidity, and gas levels. This project aims to develop a predictive model for real-time monitoring and forecasting of fruit shelf life using IoT sensors and machine learning. The proposed system integrates multi-sensors with an ESP32 microcontroller to gather data on environmental conditions affecting fruit spoilage. A linear regression model is employed to predict spoilage days based on temperature, humidity, and gas concentration, achieving low error rates as indicated by RMSE (Root Mean Square) and MAPE (Mean Absolute Percentage Error) metrics. The results demonstrate strong predictive performance and reliable estimation of spoilage timelines. While linear regression offers a straightforward analysis, its limitations with non-linear patterns necessitate the exploration of more advanced models.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Fruit Deterioration Status and Shelf-Life Prediction Using Machine Learning

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • A. Selvi,
  • V. Geethapriya,
  • J. Kavitha,
  • V. Dhanush

摘要

Fruit spoilage, predicted by factors such as temperature, humidity, and gas levels. This project aims to develop a predictive model for real-time monitoring and forecasting of fruit shelf life using IoT sensors and machine learning. The proposed system integrates multi-sensors with an ESP32 microcontroller to gather data on environmental conditions affecting fruit spoilage. A linear regression model is employed to predict spoilage days based on temperature, humidity, and gas concentration, achieving low error rates as indicated by RMSE (Root Mean Square) and MAPE (Mean Absolute Percentage Error) metrics. The results demonstrate strong predictive performance and reliable estimation of spoilage timelines. While linear regression offers a straightforward analysis, its limitations with non-linear patterns necessitate the exploration of more advanced models.