The objective of this study was to predict by means of Artificial Neural Network (ANN), multilayer perceptrons, the texture attributes of light cheesecurds perceived by trained judges based on instrumental texture measurements. Inputs to the network were the instrumental texture measurements of light cheesecurd (imitative and fundamental parameters). Output variables were the sensory attributes consistency and spreadability. Nine light cheesecurd formulations composed of different combinations of fat and water were evaluated. The measurements obtained by the instrumental and sensory analyses of these formulations constituted the data set used for training and validation of the network. Network training was performed using a back-propagation algorithm. The network architecture selected was composed of 8-3-9-2 neurons in its layers, which quickly and accurately predicted the sensory texture attributes studied, showing a high correlation between the predicted and experimental values for the validation data set and excellent generalization ability, with a validation RMSE of 0.0506.

O requeijão cremoso é um tipo de queijo fundido originalmente brasileiro, fabricado em todo território nacional com algumas variações de tecnologia. Este é um dos principais tipos de queijos produzido e consumido no Brasil e apresenta como característica o elevado teor de gordura. Por outro lado, a gordura apresenta papel fundamental na aparência, sabor e textura de requeijão, portanto desenvolver um produto light com qualidade sensorial semelhante à versão tradicional é um grande desafio à indústria de alimentos. Nesse contexto, o objetivo deste trabalho foi avaliar a composição química e a aceitabilidade sensorial de requeijão cremoso light, com diferentes níveis de redução de gordura, em relação à textura e impressão global. O experimento seguiu um delineamento de superfície de resposta, o Delineamento Composto Central Rotacional (DCCR) com dois fatores (gordura e umidade). A aceitabilidade sensorial foi avaliada por 100 consumidores, utilizando a escala hedônica de nove pontos. Os resultados obtidos demonstraram que os requeijões com diferentes níveis de redução de gordura apresentaram aceitabilidade sensorial semelhante quando combinados a um aumento proporcional do teor de umidade. Os produtos que apresentaram extrato seco desengordurado (ESD) de aproximadamente 19,3%, originados de diferentes combinações entre gordura e umidade, foram os que apresentaram melhor aceitação por parte dos consumidores, demonstrando a importância do ESD na aceitabilidade sensorial.

Cream cheesecurd is a type of processed cheese, originally Brazilian, produced throughout the entire Brazilian territory with some technological variations. This is one of the main types of cheese produced and consumed in Brazil and it is known for presenting an elevated fat content. On the other hand, the fat plays a fundamental role in appearance, flavor and texture of cheese, then developing a light product with sensory quality similar to the traditional version is a major challenge to food industry. In this context, the objective of this study was to evaluate the chemical composition and sensory acceptability of light cream cheesecurd with different levels of fat reduction for texture and overall impression. The experiment followed a design of response surface, the Central Composite Rotatable Design (CCRD) with two factors (fat and moisture). The sensory acceptability was evaluated by 100 consumers, by the hedonic scale of nine points. The results showed that the cheesecurds with different levels of fat reduction had similar sensory acceptability when combined with a proportional increase in moisture content. The products that presented dry defatted extract (DDE) of approximately 19.3%, originated from different combinations of fat and moisture, were those with better acceptance by consumers, demonstrating the importance of DDE in sensory acceptance.