The cosmetic industry has witnessed significant growth in recent years, leading to increased demand for maintaining product quality and safety during storage and distribution. Cosmetic products consist of complex chemical formulations that are highly sensitive to environmental conditions such as temperature, humidity, and exposure to air. Any deviation from optimal storage conditions can accelerate chemical degradation, reduce product effectiveness, and even cause adverse health effects for consumers. This paper proposes an intelligent system that integrates Internet of Things (IoT) technology with machine learning techniques to monitor environmental conditions and predict cosmetic spoilage in real time. The system uses a DHT22 sensor to continuously measure temperature and humidity, while an ESP32 microcontroller processes and transmits the collected data to a cloud-based platform. A Random Forest algorithm is employed to analyze environmental patterns and classify spoilage risk levels into low, medium, and high categories. The system also includes a user-friendly dashboard that displays real-time data and predictions, along with an alert mechanism that notifies users when unsafe conditions are detected. This approach eliminates reliance on static expiration dates and manual inspections, providing a dynamic and intelligent solution for product quality assurance. Experimental results demonstrate improved monitoring accuracy, reduced wastage, and enhanced safety.
Rethna et al. (Thu,) studied this question.