Implementation of a Gas Sensor to Detect Freshness of Meat Using the Neural Network Method
Abstract
Quality and freshness of meat is a critical factor in the food industry to maintain consumer health. This study aims to implement a gas sensor with a Neural Network (NN) approach to detect the freshness level of meat. The NN method has proven capable of recognizing complex patterns in data, which can be applied in gas sensor analysis to obtain important information about the condition of the meat. In this experiment, 5 different gas sensors were used to measure the gases produced during meat degradation. The data from the gas sensor is then processed by the Neural Network to build a predictive model for meat freshness. Experiments were carried out using meat samples at various levels of freshness. The test results were obtained, namely the difference in readings between sensors was 2% and meat that started not being fresh occurred after 10 hours and above
References
Barsan N. “Gas sensing Mechanisms in Thick and Parous SnO2 layers”, Institute for Interface Analysis and Sensors, Tuebingen, Germany.
Bedoui, S., Samet, H. C., & Kachouri, A. (2018). Electronic Nose System and Principal Component Analysis Technique for Gases Identification. Sensors, Circuits & Instrumentation Systems, July, 167–180.
Keller, P.E., Kangas, L.J., Liden, L.H., Hashem, S., & Kouzes, R.T.(1995). Electronic noses and their applications. In IEEE TechnicalApplications Conference (TAC’95) at Northcon’95, Portland, Oregon,10–12 October.
Nasir, M. 2016. Monitoring Perkembangan Bau Tahu Berformalin dan Tanpa Formalin Berbasis E-Nose Menggunakan Metode Principal Component Analysis (PCA). (Skripsi). Universitas Islam Negeri Maulana Malik Ibrahim. Malang
Ozcan, M., Arslan, D., & Ali Ceylan, D. (2006). Effect of inverted saccharose on some properties of honey. Food Chemistry, 99(1), 24–29.
P. Guo and M. Bao, “Research and realization of hand-held mobile bacon detection based on Neural Network Pattern recognition,” in 2016 Chinese Control and Decision Conference (CCDC), 2016, pp. 2018–2021.
G. Peiyuan, B. Man, Q. Shiha, and C. Tianhua, “Detection of Meat Fresh Degree Based on Neural Network,” in 2007 International Conference on Mechatronics and Automation, 2007, pp. 2726–2730.
T. Aguilera, J. Lozano, J. A. Paredes, F. J. Álvarez, and J. I. Suárez, “Electronic Nose Based on Independent Component Analysis Combined with Partial Least Squares and Artificial Neural Networks for Wine Prediction,” Sensors, vol. 12, no. 6, pp. 8055–8072, Jun. 2012
“TGS2602 : Gas Sensors and Modules - Products - Figaro Engineering Inc.” [Online]. Available: http://www.figarosensor.com/products/entry/tgs2602.html. [Accessed: 09-Jan-2017]
P. E. Keller, L. J. Kangas, L. H. Liden, S. Hashem, and R. T. Kouzes, “Electronic Noses And Their Applications,” ResearchGate, Dec. 1995
