Crop Quality Quantification: A Federated Learning CNN's Approach to Broccoli Leaf Disease Detection

This article proposes a thorough research study between federated learning and CNNs, where both methods are utilized for the detection and severity categorization of broccoli leaf diseases. The algorithm uses the data, the separation of four clients' enthused, to point out the severity of diseases among four categories that start from mild to critical illness. A federated learning system has used client data instead of a global model to train a learning model where privacy issues have not arisen. The study of the results revealed that the FedAvg algorithm-based federated learning method, which is precisely featured with that property, kept each individual's observation data as an origin point to create a highly effective global model. The research depended on macro-economic, micro-economic, and weighted averages to reflect the model's accomplishments at both local and international levels. For all the intensely local ratings whatsoever, the customers SB_1, SB_2, and SB_3 showed a macro average score of 92.17 and 96.49, respectively, at a swell of 96.64 and 97.1. These scores reflect that the model's accuracy and recall are improving, which is constantly witnessed among clients. Scores were calculated by burden weighting. Since the first computation of the score was 92.26, sb_1. In the long term, scores for sb_2, sb_3, and sb_4 trended upward, with sb_4 finally peaking at 97.08. After the weighted averages, the micro averages are statistically one in line; the outcome is 92.24 in sb_1 and 97.08 in sb_4. This invariably drives the model to the correct result, implying data consistency. All the local areas had a macro average score of 97.65, a micro score of 97.63, and a weighted average score of 97.63.