Identification of Beef Odors under Different Storage Day and Processing Temperature Conditions Using an Odor Sensing System
Abstract
:1. Introduction
2. Materials and Methods
2.1. Beef Samples
2.2. GC-MS Analysis
2.3. Odor Sensing System
2.4. Experimental System
2.5. Measurement Conditions
2.6. Data Analysis
2.6.1. Preprocessing Techniques
2.6.2. Dimensionality Reduction
2.6.3. Machine Learning
3. Results and Discussion
3.1. Detection of Beef Odorant Substance Composition Using GC-MS
3.2. Identification of Beef Odor Using Artificial Olfactory System
3.2.1. Response of Sensor Arrays to Beef Samples
3.2.2. Visualization Using Dimensionality Reduction Methods
- PCA Visualization
- Unsupervised UMAP
- Supervised UMAP
3.2.3. Beef Odor Recognition by Classifiers
4. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Rathnayaka, S.D.; Selvanathan, S.; Selvanathan, E.A.; Shashika Rathnayaka, C.D.; Busi, G. Demand for animal-derived food in selected Asian countries: A system-wide analysis. Agric. Econ. 2021, 52, 97–122. [Google Scholar] [CrossRef]
- Sasaki, K.; Motoyama, M.; Watanabe, G.; Nakajima, I. Meat consumption and consumer attitudes in Japan: An overview. Meat Sci. 2022, 192, 108879. [Google Scholar] [CrossRef] [PubMed]
- Herring, A.D. North American beef production. In Beef Cattle Production and Trade; CSIRO Publishing: Collingwood, VIC, Australia, 2014; p. 574. [Google Scholar]
- Smith, S.B.; Gotoh, T.; Greenwood, P.L. Current situation and future prospects for global beef production: Overview of special issue. Asian-Australas. J. Anim. Sci. 2018, 31, 927. [Google Scholar] [CrossRef]
- Grunert, K.G. Future trends and consumer lifestyles with regard to meat consumption. Meat Sci. 2006, 74, 149–160. [Google Scholar] [CrossRef]
- Ghaly, A.E.; Dave, D.; Ghaly, A.E. Meat Spoilage Mechanisms and Preservation Techniques: A Critical Review. Am. J. Agric. Biol. Sci. 2011, 6, 486–510. [Google Scholar]
- Nollet, L.M.L.; Boylston, T. Handbook of Meat, Poultry and Seafood Quality; Blackwell Publishing: Hoboken, NJ, USA, 2007; p. 719. [Google Scholar]
- Song, S.; Zhang, X.; Hayat, K.; Huang, M.; Liu, P.; Karangwa, E.; Gu, F.; Jia, C.; Xia, S.; Xiao, Z.; et al. Contribution of beef base to aroma characteristics of beeflike process flavour assessed by descriptive sensory analysis and gas chromatography olfactometry and partial least squares regression. J. Chromatogr. A 2010, 1217, 7788–7799. [Google Scholar] [CrossRef] [PubMed]
- Júnior, P.O.V.; de Cassia Vieira Cardoso, R.; Nunes, I.L.; da Silva Lima, W.K. Quality and Safety of Fresh Beef in Retail: A Review. J. Food Prot. 2022, 85, 435–447. [Google Scholar]
- Kukhtyn, M.; Salata, V.; Berhilevych, O.; Malimon, Z.; Tsvihun, A.; Gutyj, B.; Horiuk, Y. Evaluation of storage methods of beef by microbiological and chemical indicators. Potravin. Slovak J. Food Sci. 2020, 14, 602–611. [Google Scholar] [CrossRef]
- Ercolini, D.; Ferrocino, I.; Nasi, A.; Ndagijimana, M.; Vernocchi, P.; La Storia, A.; Laghi, L.; Mauriello, G.; Guerzoni, M.E.; Villani, F. Monitoring of microbial metabolites and bacterial diversity in beef stored under different packaging londitions. Appl. Environ. Microbiol. 2011, 77, 7372–7381. [Google Scholar] [CrossRef]
- Chai, C.; Lee, S.Y.; Oh, S.W. Shelf-life charts of beef according to level of bacterial contamination and storage temperature. LWT Food Sci. Technol. 2017, 81, 50–57. [Google Scholar] [CrossRef]
- Conte-Junior, C.A.; Monteiro, M.L.G.; Patrícia, R.; Mársico, E.T.; Lopes, M.M.; Alvares, T.S.; Mano, S.B. The Effect of Different Packaging Systems on the Shelf Life of Refrigerated Ground Beef. Foods 2020, 9, 495. [Google Scholar] [CrossRef] [PubMed]
- Sanchez, P.D.C.; Arogancia, H.B.T.; Boyles, K.M.; Pontillo, A.J.B.; Ali, M.M. Emerging nondestructive techniques for the quality and safety evaluation of pork and beef: Recent advances, challenges, and future perspectives. Appl. Food Res. 2022, 2, 100147. [Google Scholar] [CrossRef]
- Wu, X.; Liang, X.; Wang, Y.; Wu, B.; Sun, J. Non-Destructive Techniques for the Analysis and Evaluation of Meat Quality and Safety: A Review. Foods 2022, 11, 3713. [Google Scholar] [CrossRef]
- Shi, Y.; Wang, X.; Borhan, M.S.; Young, J.; Newman, D.; Berg, E.; Sun, X. A Review on Meat Quality Evaluation Methods Based on Non-Destructive Computer Vision and Artificial Intelligence Technologies. Food Sci. Anim. Resour. 2021, 41, 563. [Google Scholar] [CrossRef]
- Xu, W.; He, Y.; Li, J.; Deng, Y.; Xu, E.; Feng, J.; Ding, T.; Liu, D.; Wang, W. Non-destructive determination of beef freshness based on colorimetric sensor array and multivariate analysis. Sens. Actuators B Chem. 2022, 369, 132282. [Google Scholar] [CrossRef]
- Gao, S.; Liu, Y.; Yatabe, R.; Onodera, T.; Nishimura, M.; Nogi, T.; Oe, T.; Toko, K. Measurement of Glycogen Content in Wagyu Beef Using Near-infrared Spectroscopy with Multiple-reflection Attenuated Total Reflectance. Sens. Mater. 2023, 35, 2159–2174. [Google Scholar] [CrossRef]
- Mansur, A.R.; Seo, D.H.; Song, E.J.; Song, N.E.; Hwang, S.H.; Yoo, M.; Nam, T.G. Identifying potential spoilage markers in beef stored in chilled air or vacuum packaging by HS-SPME-GC-TOF/MS coupled with multivariate analysis. LWT 2019, 112, 108256. [Google Scholar] [CrossRef]
- Argyri, A.A.; Mallouchos, A.; Panagou, E.Z.; Nychas, G.J.E. The dynamics of the HS/SPME–GC/MS as a tool to assess the spoilage of minced beef stored under different packaging and temperature conditions. Int. J. Food Microbiol. 2015, 193, 51–58. [Google Scholar] [CrossRef]
- Niinomi, T.; Nakao, A.; Hanai, Y.; Ushio, H.; Hayashi, T.; Nakatani, M. A Compact 16-Channel Input Thermally Adsorption-/Desorption-Controlled Intelligent Odor Sensing System. IEEE Sens. J. 2024, 24, 9334–9340. [Google Scholar] [CrossRef]
- Nakamoto, T.; Muthadi, M. Odor Sensing System. In Smart Sensors for Environmental and Medical Applications; Wiley-IEEE Press: New York, NY, USA, 2020; pp. 173–192. [Google Scholar]
- Qin, C.; Wang, Y.; Hu, J.; Wang, T.; Liu, D.; Dong, J.; Lu, Y. Artificial Olfactory Biohybrid System: An Evolving Sense of Smell. Adv. Sci. 2023, 10, 2204726. [Google Scholar] [CrossRef]
- Yue, X.; Wang, J.; Zhao, F.; Zhang, P.; Yang, H.; Tao, T.H.; Qin, N. Electronic Nose Based on the Integration of MEMS Multi-Sensor and CMOS Circuit. In Proceedings of the 2024 IEEE 37th International Conference on Micro Electro Mechanical Systems (MEMS), Austin, TX, USA, 21–25 January 2024; pp. 592–595. [Google Scholar]
- Ollé, E.P.; Farré-Lladós, J.; Casals-Terré, J. Advancements in Microfabricated Gas Sensors and Microanalytical Tools for the Sensitive and Selective Detection of Odors. Sensors 2020, 20, 5478. [Google Scholar] [CrossRef]
- Zhao, Z.; Lei, C.; Liang, T.; Zhang, J.; Liu, Y.; Ghaffar, A.; Xiong, J. Multi-Channel MEMS-FAIMS Gas Sensor for VOCs Detection. Micromachines 2023, 14, 608. [Google Scholar] [CrossRef]
- Gong, N.; Aleixandre, M.; Nakamoto, T. Odor Recorder Based on an Array of QCM Sensors Using Frequency Shifts and Resistance Changes of Multiple Harmonics. In Proceedings of the 2022 IEEE Sensors, Dallas, TX, USA, 30 October–2 November 2022. [Google Scholar]
- Zhang, J.; Xue, Y.; Sun, Q.; Zhang, T.; Chen, Y.; Yu, W.; Xiong, Y.; Wei, X.; Yu, G.; Wan, H.; et al. A miniaturized electronic nose with artificial neural network for anti-interference detection of mixed indoor hazardous gases. Sens. Actuators B Chem. 2021, 326, 128822. [Google Scholar] [CrossRef]
- Rath, R.J.; Farajikhah, S.; Oveissi, F.; Dehghani, F.; Naficy, S. Chemiresistive Sensor Arrays for Gas/Volatile Organic Compounds Monitoring: A Review. Adv. Eng. Mater. 2023, 25, 2200830. [Google Scholar] [CrossRef]
- Qiao, Y.; Luo, J.; Cui, T.; Liu, H.; Tang, H.; Zeng, Y.; Liu, C.; Li, Y.; Jian, J.; Wu, J.; et al. Soft Electronics for Health Monitoring Assisted by Machine Learning. Nano-Micro Lett. 2023, 15, 66. [Google Scholar] [CrossRef]
- Mei, H.; Peng, J.; Wang, T.; Zhou, T.; Zhao, H.; Zhang, T.; Yang, Z. Overcoming the Limits of Cross-Sensitivity: Pattern Recognition Methods for Chemiresistive Gas Sensor Array. Nano-Micro Lett. 2024, 16, 269. [Google Scholar] [CrossRef]
- Liu, L.; Li, W.; He, Z. Development of compact electronic noses: A review. Meas. Sci. Technol. 2021, 32, 062002. [Google Scholar]
- Lin, H.; Wei, Z.; Chen, C.; Huang, Y.; Zhu, J. Early Identification of Rotten Potatoes Using an Electronic Nose Based on Feature Discretization and Ensemble Convolutional Neural Network. Sensors 2024, 24, 3105. [Google Scholar] [CrossRef] [PubMed]
- Kim, C.; Lee, K.K.; Kang, M.S.; Shin, D.M.; Oh, J.W.; Lee, C.S.; Han, D.W. Artificial olfactory sensor technology that mimics the olfactory mechanism: A comprehensive review. Biomater. Res. 2022, 26, 40. [Google Scholar] [CrossRef] [PubMed]
- Srisongkram, N.; Fongnet, P.; Sisuwan, N.; Srisai, S.; Kongkeaw, P.; Harnsoongnoen, S. Differentiating Analysis of Beef, Pork, Bovine Blood, and Porcine Blood via Electronic Olfaction Technology. In Proceedings of the 2024 12th International Electrical Engineering Congress (iEECON), Pattaya, Thailand, 6–8 March 2024. [Google Scholar]
- Wijaya, D.R.; Sarno, R.; Zulaika, E. DWTLSTM for electronic nose signal processing in beef quality monitoring. Sens. Actuators B Chem. 2021, 326, 128931. [Google Scholar] [CrossRef]
- Yatabe, R.; Shunori, A.; Wyszynski, B.; Hanai, Y.; Nakao, A.; Nakatani, M.; Oki, A.; Oka, H.; Washio, T.; Toko, K. Odor Sensor System Using Chemosensitive Resistor Array and Machine Learning. IEEE Sens. J. 2021, 21, 2077–2083. [Google Scholar] [CrossRef]
- Shunori, A.; Yatabe, R.; Wyszynski, B.; Hanai, Y.; Nakao, A.; Nakatani, M.; Oki, A.; Oka, H.; Washio, T.; Toko, K. Multichannel Odor Sensor System using Chemosensitive Resistors and Machine Learning. In Proceedings of the 2019 IEEE International Symposium on Olfaction and Electronic Nose (ISOEN), Fukuoka, Japan, 26–29 May 2019; Institute of Electrical and Electronics Engineers Inc.: Piscataway, NJ, USA, 2019; pp. 1–3. [Google Scholar]
- Wyszynski, B.; Yatabe, R.; Nakao, A.; Nakatani, M.; Oki, A.; Oka, H.; Toko, K. Array of chemosensitive resistors with composites of gas chromatography (GC) materials and carbon black for detection and recognition of VOCs: A basic study. Sensors 2017, 17, 1606. [Google Scholar] [CrossRef] [PubMed]
- Llobet, E. Gas sensors using carbon nanomaterials: A review. Sens. Actuators B Chem. 2013, 179, 32–45. [Google Scholar] [CrossRef]
- Liu, Y.; Furuno, S.; Akagawa, S.; Yatabe, R.; Onodera, T.; Fujiwara, N.; Takeda, H.; Uchida, S.; Toko, K. Odor recognition of thermal decomposition products of electric cables using odor sensing arrays. Chemosensors 2021, 9, 261. [Google Scholar] [CrossRef]
- Liu, Y.; Akagawa, S.; Yatabe, R.; Onodera, T.; Fujiwara, N.; Takeda, H.; Toko, K. Odor recognition of deteriorated mineral oils using an odor-sensing array. Front. Anal. Sci. 2022, 2, 896092. [Google Scholar] [CrossRef]
- Rohrschneider, L. Explanatory coefficients for stationary phases in gas chromatography from McReynolds phase constants. Chromatographia 1994, 38, 679–688. [Google Scholar] [CrossRef]
- Kersten, B.R.; Poole, C.F.; Furton, K.G. Ambiguities in the determination of McReynolds stationary phase constants. J. Chromatogr. A 1987, 411, 43–59. [Google Scholar] [CrossRef]
- McInnes, L.; Healy, J.; Melville, J. UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction. arXiv 2018, arXiv:1802.03426. [Google Scholar]
Channel | Material | McReynolds Constant | Resistance (KΩ) |
---|---|---|---|
CH 1 | Apiezon L | 143 | 1.32 |
CH 2 | SE-30 | 217 | 1.23 |
CH 3 | OV-1 | 222 | 1.09 |
CH 4 | DC-11 | 276 | 1.05 |
CH 5 | SE-52 | 334 | 2.32 |
CH 6 | OV-3 | 423 | 1.40 |
CH 7 | DC-550 | 620 | 1.56 |
CH 8 | DC-710 | 827 | 1.66 |
CH 9 | OV-17 | 884 | 2.08 |
CH 10 | Tween 80 | 993 | 1.72 |
CH 11 | OV-210 | 1520 | 1.29 |
CH 12 | Siponate DS-10 | 1720 | 1.34 |
CH 13 | PEG 1000 | 2587 | 1.11 |
CH 14 | PEG 600 | 2646 | 0.98 |
CH 15 | OV-275 | 4219 | 0.96 |
CH 16 | PEG 2000 | 2353–2587 | 0.86 |
No. | Time (min) | Component | Odor Type | Peak Intensity (×103) | ||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|
Day 0 | Day 4 | Day 8 | ||||||||||
RT | 100 °C | 180 °C | RT | 100 °C | 180 °C | RT | 100 °C | 180 °C | ||||
Alkanes | ||||||||||||
1 | 1.55 | Heptane | Sweet, ethereal | - | - | 20.2 | - | - | - | - | 56.7 | 20.0 |
2 | 1.84 | Octane | Odorless | - | - | 45.1 | - | - | - | 81.8 | 75.3 | 35.7 |
Alcohols | ||||||||||||
3 | 3.04 | Ethanol | Fresh, slightly sweet | 13.5 | 11.6 | - | - | - | - | 61.9 | 39.4 | 20.2 |
4 | 6.55 | 1-Penten-3-ol | Herbal, floral | - | - | - | - | - | - | 20.0 | 29.4 | |
5 | 6.55 | 1-Butanol | Alcohol-like | - | - | - | - | - | - | 25.4 | 26.8 | |
6 | 7.61 | 1-Butanol, 3-methyl- | Strong, fusel oil-like | - | - | - | - | - | - | 110.8 | 19.8 | 13.6 |
7 | 8.30 | 1-Pentanol | Pungent, fusel oil-like | 49.1 | 37.2 | 29.6 | 17.9 | 21.0 | 12.5 | 187.1 | 221.8 | 79.4 |
8 | 9.87 | 1-Hexanol | Fresh, sweet, fruity | 12.2 | - | 14.3 | 25.5 | 24.1 | 15.3 | 280.0 | 384.0 | 114.3 |
9 | 10.53 | 2-Nonen-1-ol | Green, cucumber-like | - | - | 24.5 | - | - | - | - | - | - |
10 | 11.23 | 1-Octen-3-ol | Mushroom-like | 19.9 | 15.7 | 18.8 | - | - | - | 86.2 | 101.2 | 52.2 |
11 | 11.30 | 1-Heptanol | Musty, herbal, sweet | - | - | - | - | - | - | 21.3 | 20.2 | - |
12 | 12.64 | 1-Octanol | Fatty, citrus | - | - | - | - | - | - | 13.1 | 11.7 | - |
13 | 13.38 | 2-Octen-1-ol, (Z)- | Fresh, green | - | - | - | - | - | - | - | 13.9 | - |
14 | 13.82 | 1-Nonen-4-ol | Green, cucumber-like | - | - | - | - | - | - | 16.6 | 27.9 | - |
Aldehydes | ||||||||||||
15 | 2.74 | Butanal, 2-methyl- | Fruity | - | - | 43.4 | - | - | 15.2 | 11.2 | - | 167.0 |
16 | 2.88 | Butanal, 3-methyl- | Fruity | - | - | 132.1 | - | - | 51.0 | - | 23.0 | 473.6 |
17 | 3.73 | Pentanal | Pungent, penetrating | - | 14.7 | - | - | - | - | - | - | - |
18 | 6.20 | Hexanal | Fresh, green, grassy | 127.9 | 178.5 | 87.6 | - | 31.9 | 28.8 | - | 365.5 | 242.1 |
19 | 7.29 | Heptanal | Fruity, oily | - | 11.1 | 24.2 | - | - | - | - | 30.3 | 51.5 |
20 | 8.99 | Octanal | Fatty, citrus-like | - | - | 30.2 | - | - | - | - | - | - |
21 | 10.50 | Nonanal | Waxy, citrus | - | - | - | - | - | - | - | 14.2 | 17.2 |
22 | 11.53 | Furfural | Sweet, almond-like | - | - | - | - | - | - | - | - | 30.1 |
23 | 12.36 | Benzaldehyde | Bitter almond | - | - | - | - | - | - | - | - | 48.3 |
Ketones | ||||||||||||
24 | 1.95 | Acetone | Sweet, fruity | - | - | - | - | - | - | 51.1 | 59.4 | - |
25 | 2.65 | 2-Butanone | Sweet, acetone-like | - | - | 14.2 | - | - | - | - | - | 60.1 |
26 | 5.11 | Acetylpropionyl | Butter-like | - | - | - | - | - | - | - | - | 25.9 |
27 | 5.13 | 2,3-Pentanedione | Buttery | 13.9 | - | 14.5 | - | - | - | - | - | - |
28 | 3.72 | 2,3-Butanedione | Strong, buttery | - | - | - | - | - | - | - | 22.0 | 33.6 |
29 | 6.91 | Heptan-2-one | Fruity, banana-like | - | - | - | - | - | - | 15.7 | 29.7 | - |
30 | 7.21 | 2-Heptanone | Fruity, banana-like | - | - | 30.1 | - | - | 11.5 | - | - | 131.0 |
31 | 8.92 | Acetoin | Butter-like | 15.4 | 11.5 | - | 61.8 | 80.2 | 48.4 | 202.4 | 736.6 | 699.2 |
32 | 9.02 | 2-Propanone, 1-methoxy- | Mild, sweet | - | - | 19.0 | - | - | - | - | - | - |
33 | 9.47 | 2-Propanone, 1-hydroxy- | Mild, sweet | - | - | 30.7 | - | - | - | - | - | 136.4 |
34 | 9.50 | 2,5-Octanedione | Sweet, buttery | - | - | - | - | - | - | - | 26.7 | 43.9 |
35 | 9.52 | 2,3-Octanedione | Sweet, buttery | 44.8 | - | - | - | - | - | - | - | - |
36 | 11.53 | 2-Propanone, 1-(acetyloxy)- | Mild, sweet | - | - | 12.5 | - | - | - | - | - | 27.5 |
Acids | ||||||||||||
37 | 13.56 | Butanoic acid | Unpleasant, rancid, buttery | - | - | - | - | - | - | 13.7 | - | - |
38 | 16.04 | Hexanoic acid | Fatty, cheesy | - | - | - | - | - | - | 41.2 | 15.7 | - |
Esters | ||||||||||||
39 | 1.95 | Allyl acetate | Fruity | - | - | - | - | - | 11.7 | - | - | - |
40 | 2.00 | 1-Propen-2-ol, acetate | Fruity, floral | - | - | 27.3 | - | - | - | - | - | 108.9 |
41 | 11.30 | Ammonium acetate | Ammonia-like | - | - | - | - | - | - | 216.0 | - | - |
42 | 21.25 | Diethyl phthalate | Odorless | 47.1 | - | - | - | - | - | 165.3 | - | 15.2 |
Hydrocarbons | ||||||||||||
43 | 2.08 | 1-Octene | Mild, waxy | - | - | - | - | - | - | - | 11.9 | - |
44 | 8.25 | Styrene | Sweet, balsamic | - | - | - | - | - | - | 14.0 | - | - |
Pyrazines | ||||||||||||
45 | 7.74 | Pyrazine | Nutty, roasted | - | - | 17.3 | - | - | - | - | - | 64.1 |
46 | 8.56 | Pyrazine, methyl- | Nutty, roasted | - | - | - | - | - | - | - | - | 175.6 |
47 | 9.55 | Pyrazine, 2,5-dimethyl- | Nutty, roasted | - | - | 26.1 | - | - | - | - | - | 50.5 |
48 | 9.61 | Pyrazine, ethyl- | Nutty, roasted | - | - | - | - | - | - | - | - | 80.1 |
49 | 9.78 | Pyrazine, 2,3-dimethyl- | Nutty, roasted | - | - | - | - | - | - | - | - | 19.4 |
50 | 10.35 | Pyrazine, 2-ethyl-5-methyl- | Nutty, roasted | - | - | - | - | - | - | - | - | 38.5 |
51 | 10.64 | Pyrazine, trimethyl- | Nutty, roasted | - | - | 15.5 | - | - | - | - | - | 30.3 |
Furans | ||||||||||||
52 | 2.41 | Furan, 2-methyl- | Sweet, woody | - | - | 11.6 | - | - | - | - | - | 43.6 |
53 | 3.34 | Furan, 2-ethyl- | Sweet, woody | - | - | 29.0 | - | - | 18.1 | - | 31.7 | 198.3 |
54 | 6.33 | Furan <2-butyl-> | Sweet, woody | - | - | - | - | - | - | - | - | 17.4 |
55 | 8.06 | Furan, 2-pentyl- | Sweet, woody | - | - | 65.5 | - | - | 27.3 | 26.6 | 45.7 | 430.1 |
56 | 13.69 | Furan, tetrahydro-2-methyl- | Sweet, nutty | - | - | - | - | - | - | 35.6 | 43.1 | 47.9 |
57 | 13.95 | 2-Furanmethanol | Sweet, almond-like | - | - | 78.8 | - | - | 12.7 | - | - | 164.5 |
Others | ||||||||||||
58 | 4.40 | Thiophene | Unpleasant, garlic-like | - | - | - | - | - | - | - | - | 13.3 |
59 | 5.58 | Thiophene, 2-methyl- | Unpleasant, garlic-like | - | - | - | - | - | - | - | - | 16.2 |
60 | 8.60 | Pyrimidine, 2-methyl- | Unpleasant, garlic-like | - | - | 49.0 | - | - | 19.9 | - | - | - |
61 | 12.24 | Pyrrole | Sweet, caramel-like | - | - | 14.2 | - | - | - | - | - | 82.0 |
Abbreviation | Classifier | Parameter |
---|---|---|
SVM | Support Vector Machine | kernel = “linear”, C = 100 |
KNN | K-Nearest Neighbors | n_neighbors = 15, weights = “distance”, metric = “minkowski” |
DT | Decision Tree | max_depth = 8, criterion = “log_loss”, splitter = “random” |
RF | Random Forest | max_depth = 8, criterion = “log_loss”, n_estimators = 100 |
MLP | Multilayer Perceptron | hidden_layer_sizes = 6, activation = “tanh”, solver = “lbfgs” |
LR | Logistic Regression | C = 100 |
Dim | Accuracy of Classifiers [%] | CEV [%] | ||||||
---|---|---|---|---|---|---|---|---|
SVM | KNN | DT | RF | MLP | LR | |||
PCA | 2 | 45.3 | 44.6 | 40.0 | 44.9 | 43.5 | 42.1 | 69.7 |
3 | 49.1 | 47.0 | 44.9 | 48.1 | 46.0 | 49.1 | 73.7 | |
4 | 56.1 | 44.2 | 42.5 | 48.8 | 52.6 | 52.6 | 77.2 | |
5 | 55.1 | 44.9 | 36.1 | 48.4 | 50.2 | 53.7 | 80.3 | |
6 | 57.2 | 46.0 | 39.7 | 46.0 | 50.5 | 57.2 | 82.9 | |
9 | 55.1 | 48.4 | 40.4 | 48.8 | 41.1 | 55.8 | 88.7 | |
12 | 55.1 | 44.9 | 40.0 | 46.0 | 40.4 | 53.7 | 92.4 | |
Unsupervised UMAP | 2 | 39.7 | 41.1 | 37.5 | 37.9 | 40.0 | 36.1 | - |
3 | 43.9 | 40.4 | 24.9 | 35.8 | 40.7 | 43.2 | - | |
4 | 49.1 | 42.8 | 28.4 | 42.1 | 44.2 | 44.6 | - | |
5 | 44.6 | 37.5 | 34.7 | 39.0 | 38.3 | 42.1 | - | |
6 | 43.5 | 39.3 | 30.5 | 40.7 | 37.5 | 41.1 | - | |
9 | 45.6 | 39.0 | 33.3 | 39.0 | 40.4 | 44.2 | - | |
12 | 41.4 | 40.7 | 32.3 | 44.9 | 37.5 | 41.8 | - | |
Supervised UMAP | 2 | 92.3 | 99.0 | 93.0 | 99.3 | 99.3 | 83.9 | - |
3 | 99.7 | 98.3 | 94.0 | 100.0 | 99.7 | 97.5 | - | |
4 | 99.0 | 98.6 | 93.0 | 98.6 | 96.5 | 97.9 | - | |
5 | 100.0 | 99.7 | 90.9 | 99.7 | 99.3 | 100.0 | - | |
6 | 100.0 | 98.6 | 91.6 | 100.0 | 98.6 | 99.3 | - | |
9 | 100.0 | 99.7 | 97.9 | 99.7 | 99.0 | 100.0 | - | |
12 | 100.0 | 99.0 | 96.8 | 99.7 | 96.1 | 100.0 | - |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Liu, Y.; Peng, N.; Kang, J.; Onodera, T.; Yatabe, R. Identification of Beef Odors under Different Storage Day and Processing Temperature Conditions Using an Odor Sensing System. Sensors 2024, 24, 5590. https://doi.org/10.3390/s24175590
Liu Y, Peng N, Kang J, Onodera T, Yatabe R. Identification of Beef Odors under Different Storage Day and Processing Temperature Conditions Using an Odor Sensing System. Sensors. 2024; 24(17):5590. https://doi.org/10.3390/s24175590
Chicago/Turabian StyleLiu, Yuanchang, Nan Peng, Jinlong Kang, Takeshi Onodera, and Rui Yatabe. 2024. "Identification of Beef Odors under Different Storage Day and Processing Temperature Conditions Using an Odor Sensing System" Sensors 24, no. 17: 5590. https://doi.org/10.3390/s24175590