Programs
- M. Tech. in Automotive Engineering -Postgraduate
- Fellowship in Uro Oncology & Robotic Urology 1 Year -Fellowship
Publication Type : Conference Paper
Publisher : IEEE
Url : https://doi.org/10.1109/ICICV64824.2025.11085564
Keywords : Training; Logistic regression; Technological innovation; Machine learning algorithms; Accuracy; Vectors; Classification algorithms; Bayes methods; Decision trees; Random forests; Decision tree; Support Vector Machine; Naïve Bayes’; K Nearest Neighbors Classifier; Logistic Regression; and Random Forest Classifier; Cross-validation score; Explainable artificial intelligence (XAI); LIME
Campus : Bengaluru
School : School of Computing
Year : 2025
Abstract : Recent inventions in different fields had given rise to gradual improvement in the agricultural field, this research work investigates the recognition and classification of fruits with renowned properties like mass, width, height, and color score by implementing ML algorithms such as Decision Tree Classifier, Support Vector Machine(SVM), Naïve Bayes’, K Nearest Neighbors Classifier, Logistic Regression, and Random Forest Classifier. Then, the K-Fold Cross Validation is introduced to improve the accuracy of the given algorithms respectively. It’s been observed that Machine algorithms can produce good accuracy even with just a handful of data, obviously with the minimum amount of training applied on the popular dataset ‘fruit color’. Implemented an Explainable artificial intelligence LIME (Local Interpretable Model Agnostic Explanations) strategy to make machine learning (ML) models more understandable. This strategy support in explaining how the model works, with the intention of making ML models more transparent and enhancing end-user trust in the output.
Cite this Research Publication : Sugunadevi C, B. Uma Maheswari, Enhanced Fruit Classification using K-Fold Cross-Validation and Interpretation with Explainable AI(XAI), [source], IEEE, 2025, https://doi.org/10.1109/ICICV64824.2025.11085564