Shima Nasiri; Saman Abdanan; Mokhtar Heidari
Abstract
Introduction: Texture represents one of the four principal factors defining food/fruit quality, together with appearance, flavour and nutritional properties (Bourne, 2002), and plays a key role in consumer acceptability and recognition of quince. Textural characteristics of quinces defined by “crispness”, ...
Read More
Introduction: Texture represents one of the four principal factors defining food/fruit quality, together with appearance, flavour and nutritional properties (Bourne, 2002), and plays a key role in consumer acceptability and recognition of quince. Textural characteristics of quinces defined by “crispness”, “juiciness”, “hardness”,“firmness” and “mealiness” are often key drivers of consumer preference. Many non-destructive methods, including image analysis, spectroscopy, ultrasound and sound techniques, have been developed to diagnose internal and external defects in fruits and vegetables. Cheng and Haugh (1994) used a frequency of 250-kHz, rather than 1-MHz, to detect hollow heart. They were not able to transmit successfully the ultrasound wave through the whole tuber using 1-MHz transducers but found the 250-kHz transducers to be practical for a transmission path length of up to 89.7 mm. In a research an acoustic setup was developed to simultaneously detect the resonant frequencies from equator and from calyx shoulder of pear. The researchers proposed index based on these two frequencies was used for firmness evaluation of non-spherical pear; Compared with two types of single frequency-based indices, the firmness sensitivity of the dual-frequency index is mostly close to that of MT penetration test. The firmness index can classify pears with a high total accuracy (93.4%), making it suitable for nondestructive detection of firmness of differently shaped pears (Zhang et al., 2018). The goal of this study was to develop a nondestructive method based on acoustic impulse response of quince fruit using genetic programming and artificial neural network during storage. Materials and Methods: In the experiment 120 quince fruits (Cydonia oblonga) were harvested from a field near Isfahan 181 days after full flowering of the trees. For each cultivar, only samples of similar size and without visible external damage were chosen. The samples were packed in sterile nylon bags and stored at 4°C. Non-destructive test (acoustic response) as well as destructive test (chemical measurement and penetration test) were performed every 15 days for 4 months (Akbari Bisheh et al., 2014). Total soluble solids (TSS) were determined by a hand refractometer device (model: MT03 Japan) and expressed as °Brix. Ascorbic acid of the juice was measured by titration with copper sulfate and potassium iodide based on the Barakat et al. (1973) procedure. Titratable acidity was measured according to the AOAC method. To determine the total phenol content of juice, the Waterhouse method (2000) was used. Determination of the pH of the fruit extract using a pH meter (Portable Model P-755, Japan). Physical attributes of the samples including volume as well as major, minor, intermittent diameters and mass were calculated using the relations proposed by Stroshine and Hammand (1994). Penetration test was conducted by the material test machine (SANTAM, STM-20 model, Iran).In order to analyze the response sound signal of quince in time and frequency domain, a system equipped with a sample holder with foam rubber covered surface, an impact mechanism, a microphone and an electronic circuit was utilized. To record impact sound features a microphone was positioned next to the fruit and was hit at three speed level (0.3, 0.9 and 1.5 m/s). After recoding sound, five features (acoustic peak, maximum acoustic pressure, mean acoustic pressure and natural frequency) were extracted and used as inputs for models. In order to predict the stiffness, four methods of genetic programming, neural network and existing mathematical models (FI and SIQ-FT) were used. In order to carry out statistical analysis, analysis of variance (ANOVA) and Duncan's multiple range test at 5% probability level were performed according to the completely randomized design (CRD). Results and discussion: In this study, Duncan's multiple range comparison test was used to investigate the significant difference between destructive and non-destructive parameters at 5% probability level. According to the results, acoustic peak, maximum acoustic pressure, mean acoustic pressure and natural frequency were decreased by increasing storage time. Statistical analysis of the destructive tests also showed a decreasing trend at the 5% level. In several papers, two mathematical equations have been used to obtain the relationship between the mass resonance frequency and the sound of impact. In this study, genetic programming and neural network modeling were used to compare the results of these relationships. The regression coefficients between the actual and the predicted values for the resonance-mass relation and the effect of the sound from the collision were R2= 0.601 and R2= 0.754, respectively. Also, the regression values obtained from genetic programming and neural network modeling were R2= 0.9567 and R2 = 0.933, respectively. In a research, the overall R2 value amounts for stiffness prediction was reported to be 0.79 (Schotte et al., 1999). Abbaszadeh et al. (2013) evaluated watermelons texture using their vibration responses. They declared their proposed method could predict textural acceptability of watermelons with determination coefficients 0.99. According to the obtained values, the best methods for stiffness prediction were genetic programming and f neural network methods, respectively.
Shima Nasiri; Saman Abdanan; Maryam Nadafzadeh
Abstract
Introduction: The development of brown spots on banana peel has a notable effect on the texture, color and taste of this fruit. So that the appearance of these spots reduces the quality of the fruit and affect its sale market. In recent years, in order to evaluate the quality and classification of agricultural ...
Read More
Introduction: The development of brown spots on banana peel has a notable effect on the texture, color and taste of this fruit. So that the appearance of these spots reduces the quality of the fruit and affect its sale market. In recent years, in order to evaluate the quality and classification of agricultural products, the various systems based on computer vision technology have been widely considered. These systems as the computer image analysis methods have been successful in measuring the visual quality of different products (Riyadi et al., 2007; Roseleena et al., 2011; Rodriguez-pulido et al. 2012). According to research by Probha and Kumar (2015), the extracted color properties from the banana image were more effective than other features in identifying the different stages of the banana ripening. Also, Mendoza and Aguilera (2004) detected the different stages of banana ripening based on the color, texture parameters and the distribution of brown spots on banana peel using image processing technique with a precision of 98%. Nadafzadeh et al. (2018) designed a non-linear mathematical model using the Genetic Programming (GP) to predicting and evaluating the activity of polyphenol oxidase enzymes (PPO) and peroxides (POD) during the browning process of the banana peel; using the extracted parameters from image as inputs of proposed model, the correlation coefficients to predicting of PPO and POD enzymes were obtained 0.98 and 0.97, respectively.The aim of this study was to investigate the changes of color, dimensions and chemical parameters of several banana fruit groups (different in terms of appearance) as well as their marketability (the total acceptance of fruit) by Gaussian regression model (GPR) during the storage period. Therefore, using the proposed method in this research, the required product can be available according to the consumer demand. Materials and Methods: In this study, one hundred banana samples were prepared from a market on the first day of the experiments. Samples were different in terms of shape and size, and were classified into 5 different groups. Group A had small size and curvature; B group compared to Group A had more curvature; the curvature of the samples in the group C was high, and in terms of size were medium. While the size of the bananas in group D was large, they had a small curvature. Also, the features of the group E were similar to the group D, but the curvature was greater in this group (group E). All of the samples were kept at the ambient temperature (25° C) away from the direct light for 7 days. During the days of experiments (days 0, 2, 4 and 6), five samples were examined from each group: after taking images of samples under the constant light conditions, and performing of manual measurements, they were subjected to destructive tests (laboratory tests) and sensory tests. After the images acquisition of samples, the preprocessing operations such as image enhancement, noise removal by the area opening, and the implementation of the image segmentation process using the method of Otsu adaptive thresholding were conducted (Gonzalez et al., 2004). Finally, 11 color parameters (R, G, B, L, a, b, h, s, v, C, H) and 4 dimensional characteristics (diameter, curvature radius, long and small length) were extracted from each image. In the laboratory method, the TSS value was measured by a digital refractometer, and amount of pH and acidity were also measured by a fruit juice analysis titrator. Eventually, in order to investigate the changes of measured parameters, statistical analysis was performed in a randomized complete block design by SAS 9.3 software at a significance level of 5% using Duncan's multiple comparison test. Results and discussion: Gradually along with the appearance of dark spots on the banana peel, many of the qualitative parameters such as the color, dimensions and chemical features were changed during the storage period. According to results of the Duncan's multiple range test, the values of color coordinates R, G, B, L, b, h, v, C, and H gradually reduced, and the values of these parameters were significant in all the experiments days (p<0.05). The parameter S also had a decreasing trend during the storage period, and the changes of this parameter was significant in the first days of the experiments compared to the ending days; during this period, the color parameter a increased significantly. Due to the changes of the banana fruit texture, the amount of the curvature radius, the small and large lengths, total soluble solids, pH and total titration acidity gradually decreased. Based on the results of the statistical analysis, there were no significant differences between dimensional parameters measured by non-destructive method and manual measurement (p>0.05). It is worth noting that in this study, the spent time to conduct the manual measurements of the dimensional parameters of a banana sample was 510 seconds, while all of these measurements were performed using a digital image processing method at 1.015 seconds. Therefore, it can be said that when the number of samples is high, using of the proposed method is also very cost-effective in terms of time, and it has high accuracy during the measurement. In the sensory evaluation, the results show that the best and most acceptable group of bananas were groups C, D and E, which had long size and low curvature; these groups of bananas had delicious texture, desirable flavor and low levels of brown spots on their peel. In the following, the non-destructive parameters were used to the development of Gaussian regression model (GPR), and finally, it was shown that the quality of banana fruit as well as its marketability (the total acceptance of fruit) are predictable during the storage period by GPR with a correlation coefficient of 0.91, MAPE (20.47), RMSE (0.43), SRE (0.71) and RAV (0.20).The appearance quality of the banana fruit is very effective in its acceptability for customer. In this research, the image processing technique as a non-destructive method was used to extract a set of color (R, G, B, L, a, b, h, s, v, C and H) and morphological properties (diameter, curvature radius, long length and small length) from banana image in order to evaluate its quality during storage. According to the results of Duncan's statistical analysis at the probability level of 5% and Pearson correlation results, the most suitable parameters were chosen to apply in Gaussian regression model. The results showed that the image processing technique is capable to evaluating the changes of color and dimensional parameters of banana fruit, and also the proposed model have a satisfactory performance (R2=0.91) in predicting the overall acceptance parameter of the banana.
