Leveraging CNN and AlexNet Algorithms for Improved Coffee Leaf Disease Identification and Detection

The proposed study predicts Caffeine inflorescence diseases employing strong ML, and forecasting technologies. This research increases prediction abilities, evaluates cutting-edge technologies, and studies unique traits to forecast plant diseases faster and more correctly. Effective mitigation solutions are needed to prevent electrical disturbances from harming equipment, infrastructure, and system dependability in a rapidly evolving technological environment. Materials required are reputable data-gathering and analytics service Kaggle provided this study's core dataset. Group 1 uses convolutional neural networks. The study employed 48 sample sizes with 0.8 statistical power, 0.05 alpha, and 0.2 beta. Group 2 utilizes AlexNet. These figures are calculated using Clincalc. Google Colab runs accurate prediction software. Result: Group 1 used convolutional neural networks to achieve 78.65% accuracy, whereas Group 2 used AlexNet to achieve 68.24%. SPSS is used for accuracy and statistical data analysis. A two-tailed test determines if the two groups' accuracy differs statistically. Conclusion: Convolutional neural networks are more accurate than AlexNet algorithms.