Firmness prediction and modeling by optimizing acoustic device for watermelons. (January 2016)

• Record Type: Journal Article
• Authors: Mao, Jianhua; Yu, Yonghua; Rao, Xiuqin; Wang, Jianping
• Is Part Of: Journal of food engineering. Volume 168(2016:Jan.)
• Page Start: 1
• Page End: 6
• Publication Date: 2016-01
• Subjects: Acoustic -- Watermelon -- Firmness -- Resonant frequency -- Artificial neural network; Food industry and trade -- Periodicals; Food -- Analysis -- Periodicals; Aliments -- Industrie et commerce -- Périodiques; Aliments -- Analyse -- Périodiques; Aliments -- Recherche -- Périodiques; 664.005
• DOI: 10.1016/j.jfoodeng.2015.07.009
• Languages: English
• ISSNs: 0260-8774

Abstract

Highlights: Influence of hitting ball and tray were investigated to optimize acoustic device. Indicator MI 1 was more appropriate to determine firmness compared with f 2 m . Linear regression and artificial neural network were used to build firmness models. Increase of nodes in hidden layer of ANN did not improve models performance much. Abstract: Firmness can be used to indicate ripeness of many agro-products, usually determined by acoustic impulse method nondestructively. An acoustic device was developed after investigating the influence of hitting ball and fruit tray on spectrum. Three firmness indices such as f 2 m, MI 1 (index of the first order moment) and MI 2 (index of the second order moment) were proposed to correlate with firmness of watermelon. Significant correlation was found out between firmness and these indices using linear regressive model and nonlinear model of artificial neutral network (ANN). It was concluded the linear model was more suitable than nonlinear model using ANN because of little difference of correlation coefficients. Although more computations needed, index MI 1 was considered more precisely to use as firmness indices than f 2 m in the case of splitting peaks with almost the same amplitude around the first resonant frequency.