A machine learning method for juice human sensory hedonic prediction using electronic sensory features

Huihui Yang; Yutang Wang; Jinyong Zhao; Ping Li; Long Li; Fengzhong Wang

doi:10.1016/j.crfs.2023.100576

A machine learning method for juice human sensory hedonic prediction using electronic sensory features

Curr Res Food Sci. 2023 Aug 25:7:100576. doi: 10.1016/j.crfs.2023.100576. eCollection 2023.

Authors

Huihui Yang^{1

2}, Yutang Wang¹, Jinyong Zhao¹, Ping Li¹, Long Li^{1

2}, Fengzhong Wang^{1

2}

Affiliations

¹ Institute of Food Science and Technology, Chinese Academy of Agricultural Sciences (CAAS), Beijing, 100193, PR China.
² Weifang Institute of Food Science and Processing Technology, Weifang, 261000, PR China.

Abstract

This study proposed a method that combines fused electronic sensory analysis technology with artificial neural network to predict the human sensory hedonic of fruit juice. Quantitative descriptive analysis (QDA) and the scoring test method were utilized for human sensory evaluation. The first step involved modeling the fused e-sensory features with human sensory attributes, followed by establishing a fitting model of human sensory attributes and acceptance. The R² and RMSE values obtained were 0.77 and 0.42 (QDA method), and 0.63 and 0.63 (scoring test method). Finally, the relationship between the fusion e-sensory features and the human sensory hedonic was established. Model-1 achieved an R² of 0.95 and an RMSE of 0.04, while model-2 achieved an R² value of 0.88 and an RMSE value of 0.21. This study demonstrates the potential of fusing e-sensory technologies to replace human senses, which may lead to the development of devices with simultaneous multiple senses.

Keywords: Artificial neural network; Electronic sensory; Human sensory; Prediction.