| تعداد نشریات | 286 |
| تعداد نشریات سازمان | 84 |
| تعداد شماره‌ها | 3,020 |
| تعداد مقالات | 33,746 |
| تعداد مشاهده مقاله | 45,000,768 |
| تعداد دریافت فایل اصل مقاله | 48,366,196 |
ارزیابی معماریهای مختلف شبکۀ یادگیری عمیق در تشخیص تازگی تخممرغ بر اساس سیگنالهای صدا | ||
| تحقیقات مهندسی صنایع غذایی | ||
| دوره 20، شماره 1 - شماره پیاپی 70، شهریور 1400، صفحه 183-194 اصل مقاله (844.99 K) | ||
| نوع مقاله: مقاله پژوهشی | ||
| شناسه دیجیتال (DOI): 10.22092/fooder.2020.341923.1258 | ||
| نویسندگان | ||
| مجید لشگری* 1؛ حامد توکلی2؛ رضا محمدی گل3؛ ولی اله لطفی4 | ||
| 1گروه مهندسی مکانیک بیوسیستم، دانشکده کشاورزی و محیط زیست، دانشگاه اراک | ||
| 2استادیار دانشگاه اراک | ||
| 3دانشکده کشاورزی. دانشگاه اراک | ||
| 4گروه مهندسی مکانیک بیوسیستم | ||
| چکیده | ||
| امنیت مواد غذایی که به طور مستقیم با سلامت افراد جامعه در ارتباط است همواره مورد توجه تمامی کشورها بوده است. با توجه به اینکه تخممرغ در بسیاری از صنایع غذایی مصرف می شود و در برنامه غذایی روزانه بسیاری از مردم نیز قرار دارد، تشخیص تازگی آن نیز اهمیت بالایی خواهد داشت . در این تحقیق، قابلیت سامانه آکوستیک به عنوان روشی غیرمخرب برای تشخیص تازگی تخم مرغ بررسی شده است. نمونه ها در دمای محیط به مدت 1، 4، 7، 10، 13 و 16 روز نگهداری شدند. پس از دادهبرداری، تمامی سیگنالهای صدا با استفاده از طیف اسپکتروگرام به تصویر تبدیل شدند. در این تحقیق با استفاده از آزمون مخرب و با در نظر گرفتن دو معیار واحدِ هاو و ارتفاع کیسۀ هوا، میزان تازگی نمونه ها ارزیابی شد. نتایج آزمون مخرب نشان داد که تمامی نمونه های مربوط به روزهای 16و 13 و همچنین 80 درصد نمونه های مربوط به روز 10 با افت کیفیت همراه بودهاند که از نظر معیار درجه بندی، جزو گروه غیرتازه و به عبارتی بی کیفیت به شمار می آیند. بنابراین، نمونه ها به دو گروه تازه (روزهای 1، 4 و 7) و غیرتازه (روزهای 10، 13 و 16) تقسیم شدند. از چهار شبکۀ یادگیری عمیق از پیش آموزش دیده AlexNet، VGGNet، GoogLeNet و ResNet در این تحقیق استفاده شد. در بین این شبکه ها، شبکۀ ResNet با میانگین دقت طبقه بندی 71.5 درصد بهترین دقت را داشته است. | ||
| کلیدواژه‌ها | ||
| آکوستیک؛ تازگی؛ شبکه عصبی کانولوشن؛ طبقه بندی | ||
| عنوان مقاله [English] | ||
| Evaluation of Different Deep Learning Network Architectures in Egg Freshness Detection Based On Sound Signals | ||
| چکیده [English] | ||
| Food security, which is directly related to the health of people, has always been a concern of all nations. Eggs are consumed in many food industries and are in the daily diet of many people, so detection their freshness is very important. In this study, the capability of the acoustic system as a non-destructive method for egg freshness detection was investigated. Samples were stored at room temperature for 1, 4, 7, 10, 13 and 16 days. After data collection, all audio signals were converted to images, using spectrogram. In this study, the freshness of samples was evaluated using two criteria; Haugh unit and air cell height as a destructive test. The results of destructive test showed that all samples stored for 16 and 13 days and also 80% of samples stored for 10 days faced with quality lossaes during storage. According to grading criteria, these samples were considered as unfresh eggs. Therefore, the samples were divided into two groups: fresh eggs (stored for 1, 4 and 7 days) and unfresh (stored for 10, 13 and 16 days). Four pre-trained deep learning networks AlexNet, VGGNet, GoogLeNet and ResNet were used in this study among which ResNet had the best classification accuracy with an average of 71.5%. | ||
| کلیدواژه‌ها [English] | ||
| acoustic, freshness, convolutional neural network, classification | ||
| مراجع | ||
|
Aboonajmi, M., Akram, A., Nishizu, T., Kondo, N., Setarehdan, S.K. & Rajabipour, A. (2010). An ultrasound based technique for the determination of poultry egg quality. Research in Agricultural Engineering, 56(1), pp.26-32. Aboonajmi, M. & Najafabadi, T.A. (2012). Quality assessment poultry egg using spectroscopy and maximum liklihood(ml) classifier. In NABEC-CSBE/SCGAB 2012 Joint Meeting and Technical Conference. Jul. 15-18. Ontario, Canada. Amiriparian, S., Gerczuk, M., Ottl, S., Cummins, N., Freitag, M., Pugachevskiy, S., Baird, A. & Schuller, B.W. (2017). Snore Sound Classification Using Image-Based Deep Spectrum Features. In INTERSPEECH. Aug, 3512-3516. Boddapati, V., Petef, A., Rasmusson, J., & Lundberg, L. (2017). Classifying environmental sounds using image recognition networks. Procedia computer science, 112, pp.2048-2056. Chamberlain, D., Kodgule, R., Ganelin, D., Miglani, V., & Fletcher, R. R. (2016). Application of semi-supervised deep learning to lung sound analysis. In 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Aug, 804-807. Deshpande, H., Singh, R. & Nam, U. (2001). Classification of music signals in the visual domain. In COST-G6 conference on digital audio effects. Dec. 7-9. Verona, Italy. Dutta, R., Hines, E.L., Gardner, J.W., Udrea, D.D. & Boilot, P. (2003). Non-destructive egg freshness determination: an electronic nose based approach. Measurement Science and Technology, 14(2), pp.190. Guo, Y., Liu, Y., Oerlemans, A., Lao, S., Wu, S., & Lew, M. S. (2016). Deep learning for visual understanding: A review. Neurocomputing, 187, pp.27-48. He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770-778. Kamilaris, A. & Prenafeta-Boldu´, F.X. (2018). Deep learning in agriculture: a survey. Computer and Electronics in Agriculture, 147, pp.70–90. Karoui, R., Kemps, B., Bamelis, F., De Ketelaere, B., Decuypere, E. & De Baerdemaeker, J. (2006). Methods to evaluate egg freshness in research and industry: A review. European Food Research and Technology, 222(5-6), pp.727-732. Karoui, R., Nicolaï, B. & De Baerdemaeker, J. (2008). Monitoring the egg freshness during storage under modified atmosphere by fluorescence spectroscopy. Food and Bioprocess Technology, 1(4), pp.346-356. Kemps, B.J., De Ketelaere, B., Bamelis, F.R., Mertens, K., Decuypere, E.M., De Baerdemaeker, J.G. & Schwägele, F. (2007). Albumen freshness assessment by combining visible near-infrared transmission and low-resolution proton nuclear magnetic resonance spectroscopy. Poultry science, 86(4), pp.752-759. Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems, 1097-1105. Lin, H., Zhao, J., Sun, L., Chen, Q. & Zhou, F. (2011). Freshness measurement of eggs using near infrared (NIR) spectroscopy and multivariate data analysis. Innovative Food Science & Emerging Technologies, 12(2), pp.182-186. Liu, Y., Ying, Y., Ouyang, A. & Li, Y. (2007). Measurement of internal quality in chicken eggs using visible transmittance spectroscopy technology. Food control, 18(1), pp.18-22. Omid, M., Soltani, M., Dehrouyeh, M. H., Mohtasebi, S. S., & Ahmadi, H. (2013). An expert egg grading system based on machine vision and artificial intelligence techniques. Journal of food engineering, 118(1), pp.70-77. Pan, L. Q., Zhan, G., Tu, K., Tu, S. C. & Liu, P. (2011). Eggshell crack detection based on computer vision and acoustic response by means of back-propagation artificial neural network. European Food Research Technology, 233 (3), pp.457–463. Ragni, L., Al-Shami, A., Berardinelli, A., Mikhaylenko, G. & Tang, J. (2007). Quality evaluation of shell eggs during storage using a dielectric technique. Transactions of the ASABE, 50(4), pp.1331-1340. Ragni, L., Cevoli, C. & Berardinelli, A. (2010). A waveguide technique for non-destructive determination of egg quality parameters. Journal of Food Engineering, 100, pp.343-348. Raji, A.O., Aliyu, J., Igwebuike, J.U. & Chiroma, S. (2009). Effect of storage methods and time on egg quality traits of laying hens in a hot dry climate. Journal of Agricultural and Biological Science, 4(4), pp.1-7. Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv, 1409.1556. Suktanarak, S. & Teerachaichayut, S. (2017). Non-destructive quality assessment of hens’ eggs using hyperspectral images. Journal of Food Engineering, 215, pp.97-103. Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V. & Rabinovich, A. (2015). Going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition, 1-9. Yalcin, H. (2017). Plant phenology recognition using deep learning: Deep-Pheno. In 6th International Conference on Agro-Geoinformatics, Fairfax VA, USA. Yongwei, W., Wang, J., Zhou, B. & Lu, Q. (2009). Monitoring storage time and quality attribute of egg based on electronic nose. Analytica Chimica Acta, 650(2), pp.183-188. Zhang, W., Cui, D. & Ying, Y. (2014). Nondestructive measurement of pear texture by acoustic vibration method. Postharvest Biology Technology, 96, pp.99–105. Zhang, W., Pan, L., Tu, S., Zhan, G. & Tu, K. (2015). Non-destructive internal quality assessment of eggs using a synthesis of hyperspectral imaging and multivariate analysis. Journal of Food Engineering, 157, pp.41-48. Zhao, J., Lin, H., Chen, Q., Huang, X., Sun, Z. & Zhou, F. (2010). Identification of egg’s freshness using NIR and support vector data description. Journal of food Engineering, 98(4), pp.408-414. | ||
|
آمار تعداد مشاهده مقاله: 757 تعداد دریافت فایل اصل مقاله: 243 |
||