Development of a portable electronic nose for the classification of tea quality based on tea dregs aroma

• DOI: 10.2478/ijssis-2024-0019
• Publication Date: 2024-07-20T20:14:57Z
• Authors: Adi Djoko Guritno; Agus Harjoko; Megita Ryanjani T...; Diyah Utami Kusum...; Nur Achmad Sulist...
• Keywords: Electronic Nose; Hyperparameter; Multilayer perceptron; Sigmoid function; Perceptron

Abstract The current assessment of tea quality is considered subjective. This study aims to develop a portable electronic nose assess the aroma dregs objectively by relying on aromatic capture process through sensors and using multilayer perceptron (MLP). A MLP with some hyperparameter variations used compared five machine-learning classifiers. classification model ReLU activation function 3 hidden layers 100 nodes resulted in highest accuracy 0.8750 ± 0.0241. better than Sigmoid while increasing number does not necessarily enhance its performance. In future, this research can be improved adding nose, datasets used, ensemble learning or deep models.