Development of a Hybrid System Based on the CIELAB Colour Space and Artificial Neural Networks for Monitoring pH and Acidity During Yogurt Fermentation

Monitoring pH and acidity during yoghurt fermentation is essential for product quality and process efficiency. Conventional measurement methods, however, are invasive and labour-intensive. This study developed artificial neural network (ANN) models to predict pH and titratable acidity during yoghurt...

Descripción completa

Detalles Bibliográficos
Autores: Alvarado Mamani, Ulises|||0000-0003-2574-3209, Tacuri, Jhon, Coloma, Alejandro, Gallegos Rojas, Edgar, Callo, Herbert, Valencia-Sullca, Cristina|||0000-0002-8064-883X, Curasi Rafael, Nancy|||0000-0001-8148-4366, Castillo Zambudio, Manuel|||0000-0001-8087-7475
Tipo de recurso: artículo
Fecha de publicación:2025
País:España
Institución:Universitat Autònoma de Barcelona
Repositorio:Dipòsit Digital de Documents de la UAB
Idioma:inglés
OAI Identifier:oai:ddd.uab.cat:319138
Acceso en línea:https://ddd.uab.cat/record/319138
https://dx.doi.org/urn:doi:10.3390/dairy6040041
Access Level:acceso abierto
Palabra clave:Fermentation
PH
Acidity
CIELAB colour space
Artificial neural networks
Descripción
Sumario:Monitoring pH and acidity during yoghurt fermentation is essential for product quality and process efficiency. Conventional measurement methods, however, are invasive and labour-intensive. This study developed artificial neural network (ANN) models to predict pH and titratable acidity during yoghurt fermentation using CIELAB colour parameters (L, a*, b*). Reconstituted milk powder with 12% total solids was prepared with varying protein levels (4.2-4.8%), inoculum concentrations (1-3%), and fermentation temperatures (36-44 °C). Data were collected every 10 min until pH 4.6 was reached. Forty models were trained for each output variable, using 90% of the data for training and 10% for validation. The first two phases of the fermentation process were clearly distinguishable, lasting between 4.5 and 7 h and exceeding 0.6% lactic acid in all treatments evaluated. The best pH model used two hidden layers with 28 neurons (R = 0.969; RMSE = 0.007), while the optimal acidity model had four hidden layers with 32 neurons (R = 0.868; RMSE = 0.002). The strong correlation between colour and physicochemical changes confirms the feasibility of this non-destructive approach. Integrating ANN models and colourimetry offers a practical solution for real-time monitoring, helping improve process control in industrial yoghurt production.

Similares en LA Referencia