Anomaly detection during milk processing by autoencoder neural network based on near-infrared spectroscopy

Vasafi, Pegah Sadeghi; Emire, Shimelis Admassu; Brettschneider, Kim Christin; Hinrichs, Jörg; Hitzmann, Bernd

doi:10.1016/j.jfoodeng.2021.110510

Cited by 37 publications

(15 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This process has the added benefit of removing noise in the input during encoding such that the decoded copy is more representative of the true response. In 2021, Vasafi et al [41] made an initial application of an autoencoder in the field of food production process control by using it to detect anomalies such as changes in fat, temperature, added water, and cleaning solution during milk processing. Anomalies were found to result in significantly higher reconstruction error at the autoencoder output layer as compared with the control (i.e., "normal") data.…”

Section: Autoencodersmentioning

confidence: 99%

Advanced Optical Technologies in Food Quality and Waste Management

Chauvin¹,

Duran²,

Ng³

et al. 2021

Innovation in the Food Sector Through the Valorization of Food and Agro-Food by-Products

View full text Add to dashboard Cite

Food waste is a global problem caused in large part by premature food spoilage. Seafood is especially prone to food waste because it spoils easily. Of the annual 4.7 billion pounds of seafood destined for U.S. markets between 2009 and 2013, 40 to 47 percent ended up as waste. This problem is due in large part to a lack of available technologies to enable rapid, accurate, and reliable valorization of food products from boat or farm to table. Fortunately, recent advancements in spectral sensing technologies and spectroscopic analyses show promise for addressing this problem. Not only could these advancements help to solve hunger issues in impoverished regions of the globe, but they could also benefit the average consumer by enabling intelligent pricing of food products based on projected shelf life. Additional technologies that enforce trust and compliance (e.g., blockchain) could further serve to prevent food fraud by maintaining records of spoilage conditions and other quality validation at all points along the food supply chain and provide improved transparency as regards contract performance and attribution of liability. In this chapter we discuss technologies that have enabled the development of hand-held spectroscopic devices for detecting food spoilage. We also discuss some of the analytical methods used to classify and quantify spoilage based on spectral measurements.

show abstract

Section: Autoencodersmentioning

confidence: 99%

Advanced Optical Technologies in Food Quality and Waste Management

Chauvin¹,

Duran²,

Ng³

et al. 2021

Innovation in the Food Sector Through the Valorization of Food and Agro-Food by-Products

View full text Add to dashboard Cite

show abstract

“…Moreover, the temperature is the most important option which has to be controlled, as milk is a heat‐treated product. As a result, controlling these changes is a beneficial task [ 2 , 3 , 4 ]. Therefore, controlling the process online is a vital sector that helps a company avoid suffering.…”

Section: Introductionmentioning

confidence: 99%

“…In this case, not only detecting the abnormal changes would be an advantage but also it is very important to understand what exactly happened in the processing steps. Therefore, a predictive tool based on online measurement data is needed to monitor every stage of production [ 3 ].…”

Section: Introductionmentioning

confidence: 99%

Comparison of various classification techniques for supervision of milk processing

Vasafi

Hitzmann

2021

Engineering in Life Sciences

Self Cite

View full text Add to dashboard Cite

Detecting the types of anomalies that can occur throughout the milk processing process is an important task since it can assist providers in maintaining control over the process. The Raman spectrometer was used in conjunction with several classification approaches-linear discriminant analysis, decision tree, support vector machine, and k nearest neighbor-to establish a viable method for detecting different types of anomalies that may occur during the process-temperature and fat variation and added water or cleaning solution. Milk with 5% fat measured at 10 • C was used as the reference milk for this study. Added water, cleaning solution, milk with various fat contents and different temperatures were used to detect abnormal conditions. While decision trees and linear discriminant analysis were unable to accurately categorize the various type of anomalies, the k nearest neighbor and support vector machine provided promising results. The accuracy of the support vector machine test set and the k nearest neighbor test set were 81.4% and 84.8%, respectively. As a result, it is reasonable to conclude that both algorithms are capable of appropriately classifying the various groups of samples. It can assist milk industries in determining what is wrong during milk processing.

show abstract

“…These innovations include the method of near infrared (NIR) spectroscopy, which has gained wide popularity and recognition over the past 15 years due to its ability to be used in research aimed at determining food quality. In particular, the NIR method was used in order to authenticate agricultural and food products (Yan et al., 2006), to detect milk processing anomalies (Vasafi et al ., 2021), to classify botanical origin of honey (Gan et al ., 2016 ), to detect traces of peanuts in wheat flour (Mishra et al ., 2015), to identify the authenticity of Copaiba oil (Oliveira Moreira and Braga, 2021), to detect high deoxynivalenol content in barley (Caramês et al ., 2020).…”

Section: Introductionmentioning

confidence: 99%

Control of powdery contents and mass rates of the extract in the dry substance of barley malt by photoluminescent method

Belyakov

Куликова

Gerts

2021

Int J of Food Sci Tech

View full text Add to dashboard Cite

In order to adapt the photoluminescent method for controlling the quality indicators of barley malt, experimental studies were carried out on its grains. The spectral characteristics of excitation and luminescence of products of various powdery contents and the mass rate of the extract in dry substance (extractivity) of the malt are qualitatively similar, though with an increase in submitted parameters, the curves shift upward. The dependences of powdery contents and extractivity on photoluminescence fluxes can be statistically reliably approximated by linear regression models. The developed technologies for photoluminescence control include sample preparation, excitation of luminescence at a wavelength of 424 nm, its registration in the range of 450-600 nm and amplification of the obtained electrical signal. Further, on the basis of previously established dependencies, powdery contents and extractivity of the malt are determined, after which a decision is made concerning further actions towards the products.

show abstract

Anomaly detection during milk processing by autoencoder neural network based on near-infrared spectroscopy

Cited by 37 publications

References 27 publications

Advanced Optical Technologies in Food Quality and Waste Management

Advanced Optical Technologies in Food Quality and Waste Management

Comparison of various classification techniques for supervision of milk processing

Control of powdery contents and mass rates of the extract in the dry substance of barley malt by photoluminescent method

Contact Info

Product

Resources

About