Assessment of kiwifruit firmness by using airflow and laser technique

Abstract

Firmness is a valid and widely acknowledged indication of fruit quality that is directly connected to physical structure and mechanical qualities. The deformation signals of kiwifruit for firmness assessment were acquired using an assessment system based on airflow and laser technology in this investigation. Using partial least squares regression (PLSR), genetic algorithm optimization of bp neural network (GA-BP), and an extreme learning machine (ELM), deformation data from kiwifruit was used to create models of Magness-Taylor penetration firmness prediction. The ELM model outperformed the PLSR model, and GA-BP model in the prediction set, with a correlation coefficient of 0.876 and a root mean squared error of 3.576 N in the prediction set. These findings showed that an assessment system based on airflow and laser techniques can be utilized to assess the firmness of kiwifruit quickly and nondestructively.

Prediction of moisture content for a single maize kernel based on viscoelastic properties

“…That might be because the first derivative can amplify the noise signal, whereas the S-G smoothing method can eliminate the displacement variation and reduce the fluctuation. 31 Similar superiority of the S-G smoothing method in processing curves has also been reported in the analysis of meat samples by He et al, 25 and comparable results were demonstrated in the evaluation of fruit firmness by Sun et al 26 Furthermore, the PLSR prediction models established based on S-G smoothing data under different test parameters were compared. Among them, the PLSR model of the relaxation test under 100 N (S-G-PLSR 100N model) and the model of the frequency sweep test under 0.6 Hz (S-G-PLSR 0.6Hz model) were optimal.…”

“…A similar outcome was observed by Sun et al in the context of predicting the firmness of fruit. 26 These investigations have validated the feasibility of using viscoelastic properties as a basis for assessing material characteristics and have provided robust methods for predicting moisture content through viscoelastic tests.…”

“…In this study, two types of variables, the analyzed viscoelastic parameters and force‐time data, were employed as input variables to model the moisture content. According to studies on meat and fruit properties, linear models are effective in expressing the relationship between viscoelasticity and material properties 24‐26 . Multiple linear regression (MLR) is particularly useful for constructing models with a small number of input variables, whereas partial least squares regression (PLSR) is well‐suited for building models with a large number of input variables, especially for data with multicollinearity.…”

“…To a certain extent, S-G smoothing could eliminate the fluctuation value of the data. 26 However, there was a large difference between the original curves and the first-derivative curves.…”

“…According to studies on meat and fruit properties, linear models are effective in expressing the relationship between viscoelasticity and material properties. [24][25][26] Multiple linear regression (MLR) is particularly useful for constructing models with a small number of input variables, whereas partial least squares regression (PLSR) is well-suited for building models with a large number of input variables, especially for data with multicollinearity. This study therefore employed MLR and PLSR for model building based on the two types of variables, respectively.…”