The ripening of fruits is a process that involves a series of physical and chemical changes. During this period, various alterations occur, including changes in color, texture, flavor, and aroma. The progressive deterioration of fruit quality over time is a process that can be influenced by various factors, such as temperature, humidity, and primarily ethylene gas. The importance of detection lies in the ability to determine the optimal time for consumption, storage, and transportation. Harvesting fruits at the proper ripeness stage not only allows for consumption with good sensory quality but also prolongs their shelf life. In this study, the utilization of two sensors is proposed to detect the ripeness state of two fruits: the light sensor and the ethylene gas sensor. After data collection, a multilayer perceptron neural network is trained to analyze the collected data and verify if it is possible to accurately predict the ripeness state. The combination of light and ethylene gas sensors offers a comprehensive approach to assessing the ripening process of fruits. The light sensor captures information about changes in the color and pigmentation of the fruits, while the ethylene gas sensor is sensitive to the production of this hormone associated with fruit ripening.The use of a multilayer perceptron neural network allows for exploring complex patterns in the data collected by the sensors, enabling a deeper and more accurate analysis of the ripeness state. This approach can provide valuable insights to optimize fruit storage and distribution processes, contributing to the reduction of losses and ensuring the quality of agricultural products.
|
