Estimation Model for Bread Quality Proficiency Using Fuzzy Weighted Relevance Vector Machine Classifier

Abstract

Estimation of the quality of food products is vital in determining the properties and validity of the food concerning the baking and other manufacturing processes. This article considers the quality estimation of the wheat bread that is baked under standard conditions. The sensory data are collected in real-time, and the obtained data are analysed using the efficient data analytics to predict the quality of the product. The dataset obtained consists of 300 bread samples prepared in 15 days whose vital physical, chemical, and rheological measures are sensed. The measures of the read are obtained through sensory tools and are gathered as a dataset. The obtained data are generally raw, and hence, the required features are obtained through dimensionality reduction using the Linear Discriminant Analysis (LDA). The processed data and the attributes are given as input to the classifier to obtain final estimation results. The efficient Fuzzy Weighted Relevance Vector Machine (FWRVM) classifier model is developed for this achieving this objective. The proposed quality estimation model is implemented using the MATLAB programming environment with the required setting for the FWRVM classifier. The model is trained and tested with the input dataset with data analysis steps. Some state-of-the-art classifiers are also implemented to compare the evaluated performance of the proposed model. The estimation accuracy is obtained by comparing the number of correctly detected bread classes with the wrongly classified breads. The results indicate that the proposed FWRVM-based classifier estimates the quality of the breads with 96.67% accuracy, 96.687% precision, 96.6% recall, and 96.6% F-measure within 8.96726 seconds processing time which is better than the compared Support vector machine (SVM), RVM, and Deep Neural Networks (DNN) classifiers.

Applications of imaging systems for the assessment of quality characteristics of bread and other baked goods: A review

“…They concluded that computer vision models which are inspired by the visual cortex mechanism have great potential to be used for the quality assessment of biscuits and other baked goods. Ali et al (2021b) used a Fuzzy Weighted Relevance Vector Machine (FWRVM) classifier to estimate the quality characteristics of wheat bread baked during regular baking situations. They estimated the properties of the bread samples to formulate the features by using the sensor-based analysis employed in the industry.…”

“…Ali et al. (2021b) used a Fuzzy Weighted Relevance Vector Machine (FWRVM) classifier to estimate the quality characteristics of wheat bread baked during regular baking situations. They estimated the properties of the bread samples to formulate the features by using the sensor‐based analysis employed in the industry.…”

“…Such systems will help the quality inspectors and operations managers during the production process as well as the consumers to make informed decisions before the purchase of a given product (Abasi et al., 2018; Ali & Hashim, 2022; Amani et al., 2020). Also, applications of machine learning and deep learning algorithms should be improved and employed to improve existing algorithms for processing images (Ali et al., 2021a; Xiao et al., 2022). These improved algorithms will promote the industrial utilization of machine vision systems in the bakery industry.…”

“…Different approaches and systems have been established and applied to assess the quality characteristics of bread and other baked products. Various researchers have explored the use of physical and chemical methods to measure the quality characteristics of bread and analyze their quality (Adebayo-Oyetoro et al, 2015;Ali et al, 2021b;Eshetu et al, 2018;Mustafa & Andreescu, 2018). Nevertheless, the conventional methods of evaluating the quality characteristics are tedious, error-prone, time-consuming, destructive, and demand a large number of user inputs and time.…”

“…Also, the accuracy and repeatability of sensory assessment of food quality is less and often a function of several factors; among which are the subjective discretion of the panel members, their perceptions, and fatigue level. As such, these methods are not suitable for automated or dynamic studies (Ali et al., 2021b; Hassoun et al., 2022). Therefore, there is a great need for automatic and efficient techniques to enhance bread production and predict its quality characteristics.…”