Electronic nose dataset for pork adulteration in beef

Recently, the issue of food authentication has gained attention, especially halal authentication, because of cases of pork adulteration in beef. Many studies have developed rapid detection for adulterated meat. However, these studies are not yet practical and economical methods and instruments and a faster analysis process. In this context, this paper proposes the Optimized Electronic Nose System (OENS) for more accurately detecting pork adulteration in beef. OENS has advantages such as proper noise filtering, an optimized sensor array, and optimized support vector machine (SVM) parameters. Noise filtering is carried out by cross-validation with different mother wavelets, i.e., Haar, dmey, coiflet, symlet, and Daubechies. The sensor array was optimized by dimension reduction using principal component analysis (PCA). An algorithm is proposed for the optimization of the SVM parameters. An experiment was conducted by analyzing seven classes of meat, comprising seven different mixtures of beef and pork. The first and seventh classes were 100% beef and 100% pork, respectively, while the second, third, fourth, fifth, and sixth classes contained 10%, 25%, 50%, 75%, and 90% of beef in a sample of 100 grams, respectively. Sample testing was carried out for 15 minutes for each sample. The classification test results to detect beef and pork had an accuracy of 98.10% using the optimized support vector machine. Thus, OENS has a favorable performance to detect pork adulteration in beef for halal authentication.

show abstract

“…The data of all 7 classes are shown in TABLE 3. For interested readers, our dataset has also been uploaded here [43], [44].…”

Section: A Materialsmentioning

confidence: 99%

Detecting Pork Adulteration in Beef for Halal Authentication Using an Optimized Electronic Nose System

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…The meat samples were separately minced and artificially adulterated to four adulteration levels: 100% 97%, 95% and 90% w / w of turkey to have a total of 20 g per sample (meat mixture concentration). The concentration levels for this study were determined based on the commonly reported ranges in literature [ 7 , 8 , 9 ] but the extra lower level of 97% w / w turkey (3% w / w of chicken in turkey) was included to study the feasibility of e-tongue in discriminating lower concentrations than those reported in literature.…”

Section: Methodsmentioning

confidence: 99%

“…This type of adulteration be done at varying concentration levels of meat types depending on the meat type and market demand. Concentration levels with increasing scales of 5% w / w [ 7 ], 10% w / w [ 8 ], and 20% w / w [ 9 ] of meat adulteration are among the most common in literature.…”

Section: Introductionmentioning

confidence: 99%

“…Common examples are mass spectrometry [ 10 ], polymerase chain reaction (PCR) [ 11 , 12 ] and enzyme-linked immunosorbent assay (ELISA) [ 13 ]. Due to cost, accuracy, reliability, less sophistication, and speed of the analytical process, other methods such as spectroscopy [ 7 , 14 , 15 , 16 , 17 ] and machine learning-enabled smart sensor systems [ 18 ], such as the electronic nose (e-nose) [ 8 , 9 , 19 , 20 ] and electronic tongue [ 19 ], have become more preferred methods for detecting meat adulteration. Both spectroscopy and e-nose are non-invasive techniques but spectroscopy operates on the principle of how the meat sample reacts with electromagnetic waves in a defined wavelength whereas, e-nose operates on the principle assessing odor signatures from the meat sample through high sensitivity sensors [ 20 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Standardized Extraction Techniques for Meat Analysis with the Electronic Tongue: A Case Study of Poultry and Red Meat Adulteration

Zaukuu

Gillay

Kovács

2021

Sensors

View full text Add to dashboard Cite

The electronic tongue (e-tongue) is an advanced sensor-based device capable of detecting low concentration differences in solutions. It could have unparalleled advantages for meat quality control, but the challenges of standardized meat extraction methods represent a backdrop that has led to its scanty application in the meat industry. This study aimed to determine the optimal dilution level of meat extract for e-tongue evaluations and also to develop three standardized meat extraction methods. For practicality, the developed methods were applied to detect low levels of meat adulteration using beef and pork mixtures and turkey and chicken mixtures as case studies. Dilution factor of 1% w/v of liquid meat extract was determined to be the optimum for discriminating 1% w/w, 3% w/w, 5% w/w, 10% w/w, and 20% w/w chicken in turkey and pork in beef with linear discriminant analysis accuracies (LDA) of 78.13% (recognition) and 64.73% (validation). Even higher LDA accuracies of 89.62% (recognition) and 68.77% (validation) were achieved for discriminating 1% w/w, 3% w/w, 5% w/w, 10% w/w, and 20% w/w of pork in beef. Partial least square models could predict both sets of meat mixtures with good accuracies. Extraction by cooking was the best method for discriminating meat mixtures and can be applied for meat quality evaluations with the e-tongue.

show abstract

“…Essentially, we can describe GD optimization as a hiker (the weight coefficient) who wants to climb down a mountain (cost function) into valley (cost minimum) and each step is determined by the steepness of the slope (gradient) and the leg length of the hiker (learning rate). Commonly, in deep learning, stochastic GD is used as a learning algorithm (Hinton et al, 2012;Hua et al, 2015;Sarno et al, 2020). Furthermore, gradient value can be obtained by curve fitting.…”

Section: Related Workmentioning

confidence: 99%

First-Degree Polynomial Gradient Approach to Reveal the Severity of COVID-19 Pandemic in Affected Countries

Wijaya¹,

Agung²,

Fahrudin³

et al. 2021

Journal of Computer Science

Self Cite

View full text Add to dashboard Cite

COVID-19 is a new type of Coronavirus (2019-nCoV) which originated from Wuhan in China. Since 11 March 2020, WHO has declared COVID-19 as a pandemic. Currently, it has spread to 175 countries or regions around the world. From day to day, confirmed, recovered and death cases have been reported. This data rapidly changes that indicates an uncertain situation. This uncertain situation might affect many social-economic activities. However, until now, there is no approach to categorize these countries in conjunction with the latest situation. The typical measure, for example, the Case Fatality Rate (CFR) is used to measure the proportion of deaths compared to the total number of confirmed from a certain disease. It utilizes for diseases with discrete, limited-time courses, such as outbreaks of acute infections. The major drawback of CFR is it can only be considered as a final result when all the cases have been accomplished (either died or recovered). According to this gap, we proposed the first-degree polynomial or linear gradient approach to categorize the COVID-19 severity status of areas or countries based on the rate of confirmed, recovered and death cases. The status categorization is necessary information for all parties to be aware of the situation. It can be used for consideration to determine policies related to COVID-19 pandemic such as travel warning, self-isolation, work from home, lock-down, etc.

show abstract

Electronic nose dataset for pork adulteration in beef

Cited by 28 publications

References 3 publications

Detecting Pork Adulteration in Beef for Halal Authentication Using an Optimized Electronic Nose System

Detecting Pork Adulteration in Beef for Halal Authentication Using an Optimized Electronic Nose System

Standardized Extraction Techniques for Meat Analysis with the Electronic Tongue: A Case Study of Poultry and Red Meat Adulteration

First-Degree Polynomial Gradient Approach to Reveal the Severity of COVID-19 Pandemic in Affected Countries

Contact Info

Product

Resources

About