Development of Spectroscopic Sensor System for an IoT Application of Adulteration Identification on Milk Using Machine Learning

Abstract

Adulteration in milk is a common scenario for gaining extra profit, which may cause severe harmful effects on humans. The qualitative spectroscopic technique provides a better solution for detecting the toxic contents of milk and foodstuffs. All the available spectroscopic methods for milk adulterant detection are based on laboratory-based with costly equipment. This laboratory-based detection takes a long time and is more expensive, which may not be afforded by a common man. To overcome this issue, this research work involves the design and development of a low-cost,portable, multispectral, AI-based, non-destructive spectroscopic sensor system that can be used to detect the milk adulterant in real-time. The designed sensor system uses the spectroscopic method with wavelength ranges from (410-940nm) which consists of three different bands Ultraviolet(UV), visible, and Infra-Red(IR) spectrum to improve the accuracy of detection. The sensor system is connected to the internet via the developed IoT application module, which displays the detected adulterant results in a dedicated web page designed for this purpose. This IoT application enables the adulterant detected results published on the internet immediately with location information for bringing transparency. Adulterant detection problem is formulated as a classification problem and solved by machine learning algorithms of a decision tree, Naive Bayes, linear discriminant analysis, support vector machine and neural network model. The average accuracy of linear discriminant analysis, support vector machine, Naive Bayes, decision tree and neural network model are obtained as 88.1%,90%,90%,91.7% and 92.7% respectively. Genetic algorithm framework is formulated for hyperparameter tuning of neural network model which improved the accuracy from 92.7% to 100%. The model is trained for five different classes of four adulterants, namely Sodium Salicylate, Dextrose, Hydrogen Peroxide, Ammonium Sulphate, and one pure milk sample. INDEX TERMSBack propagation Algorithm , K-means clustering , Machine learning , Milk Adulteration , Multispectral spectroscopy , Neural network I. INTRODUCTION N OWADAYS,food adulteration is a common scenario among shopkeepers in gaining extra immediate profits.Adulteration is added in foods like ripening mangoes, adding chalk powder on turmeric, starch on curry powder, blending papaya seeds on black pepper, etc. This adulteration venture leads to harmful effects for humans on a long-term basis. The fluid cow milk consumption is about 77.68 million metric tons in India. In December 2019, statistics showed that India plays the best role in cow milk consumption [1]. Milk has powerful nutrients such as lactose, fat, proteins, minerals, and vitamins in a significant proportion, which helps to provide a better human diet [2]. Since the peoples consume the milk daily in their diet, detection of adulterants in the milk is one of the significant research to ensure the health safety of the humans. Spectroscopy-based adulteration detection is one of the met...

Identification of polar liquids using support vector machine based classification model

“…The ideal point on the figure is in the top left corner, where the false positive rate is 0 and the real positive rate is 1. The area under the curve for each class is obtained as 1 [16], [17]. This shows that all the six polar liquids are classified with an accuracy of 1.…”

Forecasting drinking milk price based on economic, social, and environmental factors using machine learning algorithms

“…One of the studies aimed to develop a spectroscopic sensor system using the neural network algorithms used to design ML‐capable multispectral spectroscopic sensors, sample preparation, spectral data collection, their processing, and analysis for IoT Application milk adulteration identifications. The neural network algorithm provided the best estimation results (accuracy rate of 0.927) in this study (Sowmya & Ponnusamy, 2021). Mu et al (2020) preferred ML algorithms to perform milk source identification and milk quality estimation and reached the best estimation results with the RF algorithm.…”

Predicting adulteration of grated Parmigiano Reggiano cheese with Ricotta using electrophoresis, multivariate nonlinear regression and computational intelligence methods

“…It is used in many prominent areas of machine‐learning applications such as adulterant detection in milk and other dairy products, such as cheese and ghee (Goyal et al . 2021; Sowmya and Ponnusamy 2021). Thus, methods of data analysis, mostly methods of multivariate statistics, are necessary to extract the latent information contents of data sets from food adulteration.…”

“…Naïve Bayes is a simple and effective nonlinear classifier with excellent performance in classifying complex data (with high degrees of nonlinearity) due to its ability to capture hidden and nonlinear relationships. It is used in many prominent areas of machinelearning applications such as adulterant detection in milk and other dairy products, such as cheese and ghee (Goyal et al 2021;Sowmya and Ponnusamy 2021). Thus, methods of data analysis, mostly methods of multivariate statistics, are necessary to extract the latent information contents of data sets from food adulteration.…”