Automated Prototype for Bombyx mori Cocoon Sorting Attempts to Improve Silk Quality and Production Efficiency through Multi-Step Approach and Machine Learning Algorithms
Abstract
:1. Introduction
2. Materials and Methods
2.1. Silkworm Samples
- -
- 100 cocoons with a shape fit for reeling: mixed stained and white, and mixed alive or dead pupae inside;
- -
- 100 cocoons with a shape not fit for reeling: mixed stained and white, and mixed alive or dead pupae inside;
- -
- 100 cocoons with a shape fit for reeling: stained, mixed alive or dead pupae inside;
- -
- 100 cocoons with a shape fit for reeling: white, mixed alive or dead pupae inside;
- -
- 100 cocoons with a shape fit for reeling: mixed stained and white, with alive pupae inside;
- -
- 100 cocoons with a shape fit for reeling: mixed stained and white, with dead pupae inside.
2.2. The Sorting Machine Prototype
- -
- Shape and size, using a camera and imaging algorithms;
- -
- Outside stains, using two opposite-direction-mounted cameras and imaging algorithms;
- -
- Amount of light passing through, using a custom-made light sensor and AI model.
2.3. Sorting for Defective Cocoon Shape and Size
2.4. Sorting for Outside Stained Cocoons
2.5. Sorting for Dead Cocoons
2.6. Integration Model on Main PC
3. Results
4. Discussion
5. Conclusions
Author Contributions
Funding
Informed Consent Statement
Acknowledgments
Conflicts of Interest
References
- Available online: https://www.tradeforum.org/Silk-in-World-Markets/ (accessed on 21 November 2022).
- Tzenov, P.; Cappellozza, S.; Saviane, A. Black, Caspian Seas and Central Asia Silk Association (BACSA) for the Future of Sericulture in Europe and Central Asia. Insects 2021, 13, 44. [Google Scholar] [CrossRef]
- Cappellozza, S.; Saviane, A. Gelsibachicoltura: Luci ed ombre sulla ripresa di quest’attività in Europa. Riv. Divulg. Cult. Agrar. 2022, 5, 59–76. [Google Scholar]
- Tao, H.; Kaplan, D.L.; Omenetto, F.G. Silk Materials—A Road to Sustainable High Technology. Adv. Mater. 2012, 24, 2824–2837. [Google Scholar] [CrossRef]
- De Ponti, P. European Silk Forum. Per quanto tempo ancora la Cina fornirà seta all’Europa? La Seta 2011, 63, 12–14. [Google Scholar]
- Lee, Y.W. Silk reeling and testing manual. In FAO Agricultural Services Bulletin n.136; FAO: Rome, Italy, 1999. [Google Scholar]
- Trestini, S.; Cappellozza, S.; Penone, C.; Saviane, A. Allevamento del baco da seta, opportunità e produzioni. L’informatore Agrario 2018, 44, 37–40. Available online: https://serinnovation.it/linformatore-agrario-n-44-2018/ (accessed on 22 December 2022).
- Available online: https://www.panorama.it/news/cronaca/seta-italiana (accessed on 21 November 2022).
- Nadaf, H.A.; Vishaka, G.V.; Chandrashekharaiah, M.; Rathore, M.S.; Srinivas, C. Scope and potential applications of artificial intelligence in tropical tasar silkworm Antheraea mylitta D. seed production. J. Entomol. Zool. Stud. 2021, 9, 899–903. [Google Scholar]
- Xiong, H.; Cai, J.; Zhang, W.; Hu, J.; Deng, Y.; Miao, J.; Tan, Z.; Li, H.; Cao, J.; Wu, X. Deep learning enhanced terahertz imaging of silkworm eggs development. iScience 2021, 24, 103316. [Google Scholar] [CrossRef] [PubMed]
- Kiratiratanapruk, K.; Sinthupinyo, W. Silkworm egg image analysis using different color information for improving quality inspection. In Proceedings of the 2016 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS), Phuket, Thailand, 24–27 October 2016; pp. 1–6. [Google Scholar]
- Kanjanawanishkul, K. An Image-based Eri Silkworm Pupa Grading Method Using Shape, Color, and Size. Int. J. Intell. Eng. Syst. 2022, 15, 2. [Google Scholar] [CrossRef]
- Dai, F.; Wang, X.; Zhong, Y.; Zhong, S.; Chen, C. Convolution Neural Network Application in the Simultaneous Detection of Gender and Variety of Silkworm (Bombyx mori) Cocoons. J. Phys. Conf. Ser. 2021, 1769, 012017. [Google Scholar] [CrossRef]
- Lee, A.; Kim, G.; Kim, S.W.; Kim, G. A discrimination model for dead cocoons using near-infrared transmission spectra analyses. Sens. Actuator A Phys. 2022, 346, 113857. [Google Scholar] [CrossRef]
- Zhu, Z.; Yuan, H.; Song, C.; Li, X.; Fang, D.; Guo, Z.; Zhu, X.; Liu, W.; Yan, G. High-speed sex identification and sorting of living silkworm pupae using near-infrared spectroscopy combined with chemometrics. Sens. Actuators B Chem. 2018, 268, 299–309. [Google Scholar] [CrossRef]
- Assirelli, A.; Cabassi, G.; Cappellozza, S.; Costa, C.; Figorilli, S.; Marinoni, L.; Pallottino, F.; Saviane, A. Procedimento e Apparecchiatura per la Cernita Automatizzata di Insetti. Patent No. IT201900016208A1, 12 September 2019. [Google Scholar]
- Otsu, N. A Threshold Selection Method from Gray-Level Histograms. IEEE Trans. Syst. Man Cybern. 1979, 9, 62–66. [Google Scholar] [CrossRef] [Green Version]
- Bookstein, F. Morphometric Tools for Landmark Data: Geometry and Biology; Cambridge University Press: Cambridge, UK, 1997. [Google Scholar] [CrossRef]
- Rohlf, F.J.; Archie, J.W. A comparison of Fourier methods for the description of wing shape in mosquitoes (Diptera: Culicidae). Syst. Zool. 1984, 3, 302–317. [Google Scholar] [CrossRef]
- Crampton, J.S. Elliptic Fourier shape analysis of fossil bivalves: Some practical considerations. Lethaia 1995, 28, 179–186. [Google Scholar] [CrossRef]
- Antonucci, F.; Costa, C.; Pallottino, F.; Paglia, G.; Rimatori, V.; De Giorgio, D.; Menesatti, P. Quantitative method for shape description of almond cultivars (Prunus amygdalus Batsch). Food Bioprocess Technol. 2012, 5, 768–785. [Google Scholar] [CrossRef]
- Assirelli, A.; Cabassi, G.; Cappellozza, S.; Costa, C.; Figorilli, S.; Marinoni, L.; Pallottino, F.; Saviane, A. Deposito della domanda di brevetto per Invenzione Industriale dal titolo: “Procedimento e apparecchiatura per la cernita automatizzata di insetti”. Patent No. 102019000016208, 12 September 2019. [Google Scholar]
- Costa, C.; Menesatti, P.; Antonucci, F.; Pallottino, F. Deposito della domanda di brevetto per Invenzione Industriale dal Titolo: “Sistema e metodo per Identificazione e Selezione di Molluschi”. Patent No. 1424804, 1 July 2014. [Google Scholar]
Cameras | H | S | B |
---|---|---|---|
Camera 1 Top | 0–80 | 60–255 | 0–255 |
Camera 2 Bottom | 0–255 | 220–255 | 0–255 |
Parameters | True Positive Percentage (%) |
---|---|
Oversized cocoons (larger than 450 mm2) | 87.8 |
Undersized cocoons (smaller than 300 mm2) | 29.6 |
Undersized cocoons with no vertically positioned ones | 90.0 |
Target Class | |||
---|---|---|---|
Unstained | Stained | ||
Output class | Unstained | 785 | 85 |
Stained | 67 | 287 |
Target Class | |||
---|---|---|---|
Unstained | Stained | ||
Output class | Unstained | 808 | 77 |
Stained | 51 | 294 |
Parameters | Threshold | Recall | Overall Accuracy (%) |
---|---|---|---|
Size | 81,900 px2 < Size < 124,500 px2 | 0.57 | 90.0 |
Shape training set | - | 0.65 | 56.6 |
Shape test set | - | 0.57 | 59.8 |
Stained top | 144 px2 | 0.77 | 87.6 |
Stained bottom | 144 px2 | 0.79 | 89.6 |
Alive–dead training set | - | 0.84 | 81.5 |
Alive–dead test set | - | 0.82 | 78.4 |
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. |
© 2023 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
Vasta, S.; Figorilli, S.; Ortenzi, L.; Violino, S.; Costa, C.; Moscovini, L.; Tocci, F.; Pallottino, F.; Assirelli, A.; Saviane, A.; et al. Automated Prototype for Bombyx mori Cocoon Sorting Attempts to Improve Silk Quality and Production Efficiency through Multi-Step Approach and Machine Learning Algorithms. Sensors 2023, 23, 868. https://doi.org/10.3390/s23020868
Vasta S, Figorilli S, Ortenzi L, Violino S, Costa C, Moscovini L, Tocci F, Pallottino F, Assirelli A, Saviane A, et al. Automated Prototype for Bombyx mori Cocoon Sorting Attempts to Improve Silk Quality and Production Efficiency through Multi-Step Approach and Machine Learning Algorithms. Sensors. 2023; 23(2):868. https://doi.org/10.3390/s23020868
Chicago/Turabian StyleVasta, Simone, Simone Figorilli, Luciano Ortenzi, Simona Violino, Corrado Costa, Lavinia Moscovini, Francesco Tocci, Federico Pallottino, Alberto Assirelli, Alessio Saviane, and et al. 2023. "Automated Prototype for Bombyx mori Cocoon Sorting Attempts to Improve Silk Quality and Production Efficiency through Multi-Step Approach and Machine Learning Algorithms" Sensors 23, no. 2: 868. https://doi.org/10.3390/s23020868
APA StyleVasta, S., Figorilli, S., Ortenzi, L., Violino, S., Costa, C., Moscovini, L., Tocci, F., Pallottino, F., Assirelli, A., Saviane, A., & Cappellozza, S. (2023). Automated Prototype for Bombyx mori Cocoon Sorting Attempts to Improve Silk Quality and Production Efficiency through Multi-Step Approach and Machine Learning Algorithms. Sensors, 23(2), 868. https://doi.org/10.3390/s23020868