| dc.description.abstract | Using machine learning and artificial intelligence techniques, this thesis presents a novel approach to detecting meat freshness. The proposed system consists of an MQ135 gas sensor and an MQ4 methane natural gas sensor to capture the odors emitted by the meat samples, an ESP32 cam, and an Arduino UNO microcontroller to process the sensor data and extract relevant features. A dataset of labeled meat samples with known freshness levels is used to train a machine learning model. To classify the meat samples into different freshness levels, the model employs a variety of classification algorithms, including Support Vector Machines, Random Forests, and K-Nearest Neighbors. The suggested method successfully classifies the freshness of meat samples with an accuracy of over 90%, highlighting the potential of machine learning and artificial intelligence in enhancing the accuracy and efficiency of this process. The technology is transportable and compatible with current meat processing equipment. This gives the food business a dependable, automated method to raise the security and caliber of beef goods. Overall, the study's findings show that the suggested system is a reliable way to classify the freshness of meat. In previous studies on meat freshness classification, gas sensors and color sensors were utilized. However, the use of color sensors presented a challenge in cases where meat sellers added color to the meat, which could hinder the identification of meat freshness. To address this issue, an ESP32-CAM camera sensor was employed to determine meat freshness in this study. The approach involved utilizing image processing artificial intelligence (AI) techniques. Additionally, MQ135 and MQ4 gas sensors were utilized to detect meat freshness. | en_US |
