A Deep Learning Approach for Wine Quality Assessment Using Dropout-Enhanced KAN Model

Description:

A machine learning dataset for assessing wine quality from physicochemical properties of red and white wines. It supports data-driven quality prediction using deep learning and advanced neural network models.

This dataset contains physicochemical measurements of red and white wines for data-driven wine quality assessment. It provides important chemical properties such as acidity, sugar, chlorides, sulfur dioxide, density, pH, sulphates, and alcohol content

Input: Physicochemical features.

Output: Wine quality score.

Tags:

#WineQuality #DeepLearning #KAN #MachineLearning #QualityPrediction #WineAnalysis #Regression #ArtificialIntelligence

References:

1. Wu, Z. (2026, March). Interpretability-Driven Metric Learning: Enhancing k-Nearest Neighbors for Wine Quality Assessment. In 2026 IEEE 8th International Conference on Communications, Information System and Computer Engineering (CISCE) (pp. 1114-1119). IEEE.

2.Nilwong, S., Peetakul, J., & Thanamitsomboon, T. (2026, May). Wine Quality Estimation System using Deep Neural Network with Reduced Measurable Features. In 2026 11th International Conference on Business and Industrial Research (ICBIR) (pp. 336-341). IEEE.