DEVELOPING A LOW COST ELECTRONIC NOSE FOR SPOILAGE ANALYSIS OF GROUND BEEF

Öz

A low-cost, easy-to-use e-nose is developed to detect the spoilage of ground meat. E-nose consists of hardware, software and data processing components. The main elements of hardware component are gas sensors sensitive to hydrogen sulfide (H2S) and ammonia (NH3). Using MIT App Inventor 2 an Android application is developed to run the hardware component, retrieve the data, preprocess and send it to Google Sheets. Classification model is developed, and data management is carried out in Google Colab and Google Script. Logistic regression method is used to develop classification models from the collected signals. The model classified the samples as "spoiled" and "fresh" based on the gas concentrations. The Nessler solution is used to determine the actual spoilage state. Ground beef samples stored in the refrigerator and at room temperature are used to obtain spoiled and fresh samples to develop a logistic regression model. A total of 36 samples are used to develop model. Another set of 24 samples is used to test model and prototype device performance. It is observed that all samples used in the testing phase were classified correctly. The cost of the system has been determined as approximately $100 considering January 2021 exchange rates.

Anahtar Kelimeler

• Food safety
• Artificial intelligence
• Machine learning
• Logistic regression
• Electronic nose

Kıyma Kokuşma Analizi İçin Düşük Maliyetli Elektronik Burun Geliştirilmesi

Öz

Kıyma örneklerinin bozulmasını belirlemek için düşük maliyetli, kullanımı kolay bir elektronik burun geliştirilmiştir. E-burun donanım, yazılım ve veri işleme bileşenlerinden oluşmaktadır. Donanım bileşeninin ana unsurları, hidrojen sülfür (H2S) ve amonyağa (NH3) duyarlı yarı iletken gaz sensörleridir. MIT App Inventor 2 kullanılarak, donanım bileşenini çalıştırmak, verileri almak, ön işlemeye tabi tutmak ve Google Sheets'e göndermek için bir Android uygulaması geliştirilmiştir. Google Colab ve Google Script kullanılarak sınıflandırma modeli geliştirilmiş ve veri yönetimi gerçekleştirilmiştir. Toplanan sensör sinyallerinden sınıflandırma modelleri geliştirmek için lojistik regresyon metodu kullanılmıştır. Model, gaz konsantrasyonlarına dayalı olarak kıyma örneklerini "bozulmuş" ve "taze" olarak sınıflandırmıştır. Nessler çözeltisi gerçek bozulma durumunu belirlemek için kullanılmıştır. Buzdolabında ve oda sıcaklığında saklanan dana kıyma örnekleri, lojistik regresyon modeli geliştirmek için bozulmuş ve taze örneklerin elde edilmesi için kullanılmıştır. Model geliştirmek için toplam 36 örnek kullanılmıştır. Model ve prototip cihaz performansını test etmek için başka bir 24 numune seti kullanılmıştır. Test aşamasında kullanılan tüm örneklerin doğru bir şekilde sınıflandırıldığı görülmüştür. Sistemin maliyeti Ocak 2021 kur değerleri dikkate alındığında yaklaşık 100 $ olarak belirlenmiştir.

Anahtar Kelimeler

• Gıda güvenliği
• yapay zeka
• makine öğrenmesi
• lojistik regresyon
• elektronik burun

Kaynakça

1. 1. Adiono, T., Anindya, S.F., Fuada, S., Afifah, K. and Purwanda, I.G. (2019) Efficient Android software development using MIT App Inventor 2 for bluetooth-based smart home. Wireless Personal Communications, 105, 233–256. doi:10.1007/s11277-018-6110-x
2. 2. Albayrak, N. and Yousef, A.E. (1997) A spectrophotometric assay to determine bacteriocin activity. IFT Annual Meeting, Book of Abstracts, New Orleans, Louisiana, USA, 240 pp.
3. 3. Balasubramanian, S., Panigrahi, S., Louge, C.M., Marchello, M., Doetkott, C., Gu, H., Sherwood, J. and Nolan, L. (2005) Spoilage identification of beef using an electronic nose system. Transactions of the ASAE, 47(5), 1625-1633. . doi: 10.13031/2013.17593
4. 4. Barisci, J., Andrew, M., Harris, P., Patridge, A. and Wallace, G. (1997) Development of an electronic nose. Proceedings of Smart Electronic Nose, 3242, 164-171.
5. 5. Baumler, A.J., Heffron, F. and Reissbrodt, R. (1997) Rapid detection of Salmonella enterica with primers specific for iroB. Journal of Clinical Microbiology, 35(5), 1224–1230. doi:10.1128/jcm.35.5.1224-1230.1997
6. 6. Bautista, D., Vaillancourt, J., Clarke, R., Renwick, S. and Griffiths, M. (1995). Rapid assessment of the microbiological quality of poultry carcasses using ATP Bioluminescence. Journal of Food Protection, 58(5), 551-554. doi: 10.4315/0362-028X-58.5.551
7. 7. Carneiro, T., Da Nóbrega, R.V.M., Nepomuceno, T., Bian, G-B., De Albuquerque, V.H.C. and Filho, P.D.R. (2018) Performance analysis of Google Colaboratory as a tool for accelerating deep learning applications. IEEE Access, 6(2018), 61677-61685. doi: 10.1109/ACCESS.2018.2874767
8. 8. Dalcin, L. D., Paz, R.R., Kler, P.A. and Cosimo, A. (2011) Parallel distributed computing using Python. Advances in Water Resources, 34, 1124–1139. doi: 10.1016/j.advwatres.2011.04.013

9. 9. Doty, A.C., Wilson, A.D., Forse, L.B. and Risch, T.S. (2020). Assessment of the portable C-320 electronic nose for discrimination of nine insectivorous bat species: implications for monitoring white-nose syndrome. Biosensors (Basel), 2020, 10, 2. doi: 10.3390/bios10020012
10. 10. Ferrández, D., Yedra, E., Atanes-Sánchez, E. and Moron, C. (2022) Arduino based monitoring system for materials used in façade rehabilitation- Experimental study with lime mortars. Case Studies in Construction Materials, 16(2022), e00985. doi:10.1016/j.cscm.2022.e00985
11. 11. Hong, X., Wang, J. and Hai, Z. (2012) Discrimination and prediction of multiple beef freshness indexes based on electronic nose. Sensors and Actuators B: Chemical, 161(2012), 381-389. doi: 10.1016/j.snb.2011.10.048
12. 12. Huang, C. and Gu, Y. (2022) A machine learning method for the quantitative detection of adulterated meat using a MOS-based e-Nose. Foods, 2022,11, 602. doi: 10.3390/foods11040602
13. 13. Jay, J. (2000) Modern Food Microbiology. 6th ed. Aspen Publication. Maryland, 789 pp.
14. 14. Kızıl, Ü., Lindley, J.A. and Panigrahi, S. (2001) Determination of manure characteristics using gas sensors. 2001 ASAE Annual International Meeting, Paper No: 01-1024, Sacramento, California, USA.
15. 15. Kızıl, Ü., Genç, L., Rahman, S., Khaitsa, M.L. and Genç, T.T. (2015) Design and test of a low-cost electronic nose system for identification of Salmonella Enterica in poultry manure. Transactions of the ASABE, 58(3), 819-826. doi: 10.13031/trans.58.11023
16. 16. Kong, B.H. and Ma, L.Z. (2003) Meat Science and Technology, Chinese Light Industry Press, Beijing, China, 2003.
17. 17. Lazuardi, R.A.F., Karlita, T., Yuniarno, E.M., Purnama, I.K.E. and Purnomo, M.H. (2019) Human bone localization in ultrasound image using YOLOv3 CNN architecture. Computer Engineering Network and Intelligent Multimedia (CENIM) 2019 International Conference on, 1-6. doi:10.1109/CENIM48368.2019.8973372
18. 18. Limbo, S., Torri, L., Sinelli, N., Franzetti, L. and Casiraghi, E. (2010) Evaluation and predictive modeling of shelf life of minced beef stored in high-oxygen modified atmosphere packaging at different temperatures. Meat Science, 84(2010), 129–136. doi: 10.1016/j.meatsci.2009.08.035
19. 19. MEB. (2013) Gıda Teknolojisi: Et ve Et Ürünleri Analizi. (Web sayfası: https://betalab.com.tr/wp-content/uploads/2019/11/MEB-G%C4%B1da-Teknolojisi.pdf) (Erişim tarihi: Ocak 2021)
20. 20. Miyaomoto, T., Kuaramitsu, Y., Ookuma, A., Trevanich, S., Honjoh, K. and Hotano, S. (1998) Rapid detection and counting of viable bacteria in vegetables and environmental water using a photon counting T.V. camera. Journal of Food Protection, 61(10),1312-1316. doi: 10.4315/0362-028x-61.10.1312
21. 21. Ouellette, J. (1999) Electronic noses sniff out new markets. The Industrial Physicist, 5(1), 26-9.
22. 22. Pérez, F., Granger, B. and Hunter, J. (2011) Python: an ecosystem for scientific computing. Computing in Science and Engineering, 13 (2), 13-21. doi:10.1109/MCSE.2010.119
23. 23. Stussi, E., Cella, S., Serra, G. and Verier, G. (1996) Fabrication of conducting polymer patterns for gas sensing by a dry technique. Materials Science and Engineering, 1996, 27-33. doi: 10.1016/0928-4931(95)00122-0
24. 24. Tan, W. and Shelef, L.A. (1997) Rapid detection of Salmonella enteritidis in foods using an automated system and immunomagnetic beads. IFT Annual Meeting, Book of Abstracts, New Orleans, Louisiana, USA.
25. 25. Wijaya D. R., Sarno, R., Zulaika, E. and Sabila, S. I. (2017a) Development of mobile electronic nose for beef quality monitoring. Procedia Computer Science, 124 (2017), 728–735. doi: 10.1016/j.procs.2017.12.211
26. 26. Wijaya D. R., Sarno, R., Daiva, A. F. (2017b) Electronic nose for classifying beef and pork using Naïve Bayes. 2017 International Seminar on Sensor, Instrumentation, Measurement and Metrology (ISSIMM), Surabaya, Indonesia. doi: 10.1109/ISSIMM.2017.8124272
27. 27. Wijaya D. R., Sarno, R. and Zulaika, E. (2021) DWTLSTM for electronic nose signal processing in beef quality monitoring. Sensors and Actuators B: Chemical, 326 (2021), 128931. doi: 10.1016/j.snb.2020.128931
28. 28. Winters, D.K., O’Leary, A.E. and Slavik, M.F. (1997) Rapid detection of Campylobacter jejuni in contaminated food products by PCR. IFT Annual Meeting, Book of Abstract, New Orleans, Louisiana, USA.
29. 29. Xiao, Y., Jiaojiao, J., Guohua H., Fangyuan Y., Minmin W., Jie H., Xiaoguo Y. and Shanggui, D. (2014) Determination of the freshness of beef strip loins (M. longissimus lumborum) using electronic nose. Food Anal. Methods, (2014) 7, 1612–1618. doi: 10.1007/s12161-014-9796-8