Adversarial Data Augmentation and Transfer Net for Scrap Metal Identification Using Laser-Induced Breakdown Spectroscopy Measurement of Standard Reference Materials
The DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.
Abstract
In this study, we propose a transfer learning-based classification model for identifying scrap metal using an augmented training dataset consisting of laser-induced breakdown spectroscopy (LIBS) measurement of standard reference material (SRMs) samples, considering varying experimental setups and environmental conditions. LIBS provides unique spectra for identifying unknown samples without complicated sample preparation. Thus, LIBS systems combined with machine learning methods have been actively studied for industrial applications such as scrap metal recycling. However, in machine learning models, a training set of the used samples may not cover the diversity of the scrap metal encountered in field measurements. Moreover, differences in experimental configuration, where laboratory standards and real samples are analyzed in situ, may lead to a wider gap in the distribution of training and test sets, dramatically reducing the performance of the LIBS-based fast classification system for real samples. To address these challenges, we propose a two-step Aug2Tran model. First, we augment the SRM dataset by synthesizing spectra of unobserved types through attenuation of dominant peaks corresponding to sample composition and generating spectra depending on the target sample using a generative adversarial network. Second, we used the augmented SRM dataset to build a robust real-time classification model with a convolutional neural network, which is further customized for the target scrap metal with limited measurements through transfer learning. For evaluation, SRMs of five representative metal types, including aluminum, copper, iron, stainless steel, and brass, are measured with a typical setup to form the SRM dataset. For testing, scrap metal from actual industrial fields is experimented with three different configurations, resulting in eight different test datasets. The experimental results show that the proposed scheme produces an average classification accuracy of 98.25% for the three experimental conditions, as high as the results of the conventional scheme with three separately trained and executed models. Additionally, the proposed model improves the classification accuracy of arbitrarily shaped static or moving samples with various surface contaminations and compositions, and even for differing ranges of charted intensities and wavelengths. Therefore, the proposed Aug2Tran model can be used as a systematic model for scrap metal classification with generalizability and ease of implementation.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Semisupervised hyperspectral image classification based on Generative Adversarial Networks
Zhan, Y., Hu, D., Wang, Y., & Yu, X. (2018) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2017.2780890 · Cited by 283
Campanella, B., Grifoni, E., Legnaioli, S., Lorenzetti, G., Pagnotta, S., Sorrentino, F., & Palleschi, V. (2017) · Spectrochimica Acta Part B: Atomic Spectroscopy · doi:10.1016/j.sab.2017.06.003 · Cited by 78 · cited 1×
“18,19 Building an exhaustive and extensive training set of LIBS measurement with multiple experiments is unsustainable because it can result in sample destruction due to ablation by a laser pulse, which is critical for samples such as skin tissue 8 and archaeological artifacts.”
BackgroundThe Potential for XRF & LIBS Handheld Analyzers to Perform Material Characterization in Scrap Yards
Brooks, L., & Gaustad, G. (2021) · Journal of Sustainable Metallurgy · doi:10.1007/s40831-021-00361-3 · Cited by 23 · cited 1×
“33,34 Mitigating such variations through calibration is based on the well-known and simple linear relationship between the calibrated and test samples.”
Background
Research works printed but not linked: 46
- Anabitarte F. Cobo A. Lopez-Higuera J.M.. “Laser-Induced Breakdown Spectroscopy: Fundamentals Applications and Challenges”. Int. Scholarly Res. Not. 2012. Article no. 285240. doi:10.5402/2012/285240 · DOI · Paper page
- 10.1366/11-06574 · DOI · Paper page
- 10.1021/ac303220r · DOI · Paper page
- 10.1186/s12302-021-00480-4 · doi:10.1186/s12302-021-00480-4
- 10.1080/05704928.2020.1791151 · DOI
- 10.1039/D0AY02089C · doi:10.1039/d0ay02089c
- Nie X.-C.. “Application of Laser-Induced Breakdown Spectroscopy in Deep Space Exploration”. Proc. SPIE 1142 7 Second Target Recognition and Artificial Intelligence Summit Forum. 2020. 114271D. 10.1117/12.2551440 · doi:10.1117/12.2551440
- 10.1088/2058-6272/ab481e · DOI
- Cho M., Park S., Kwon E., Jeong S., et al. “A Waste Metal Sorting System Using LIBS Classification”. Paper presented at: IEEE 28th International Symposium on Industrial Electronics (ISIE). Vancouver, BC, Canada; 12–14 June 2019. Pp. 451-454. 10.1109/ISIE.2019.8781099 · doi:10.1109/isie.2019.8781099
- 10.1007/s40684-021-00364-1 · DOI
- Kim H., Lee L., Srivastava E., Shin S., et al. “Front-End Signal Processing for Metal Scrap Classification Using Online Measurements Based on Laser-Induced Breakdown Spectroscopy”. Spectrochim. Acta, Part B. 2021. 184: 106282. 10.1016/j.sab.2021.106282 · DOI
- 10.1177/00037028198814 · doi:10.1177/00037028198814
- 10.1177/00037028209155 · doi:10.1177/00037028209155
- 10.1039/D1JA00032B · DOI
- 10.1177/00037028221092 · doi:10.1177/00037028221092
- 10.1177/00037028221091 · doi:10.1177/00037028221091
- Li L., Liu X., Yang F., Xu W.-M., et al. “A Review of Artificial Neural Network Based Chemometrics Applied in Laser-Induced Breakdown Spectroscopy Analysis”. Spectrochim. Acta, Part B. 2021. 180: 106183. 10. doi:1016/j.sab.2021.106183
- Grzegorzek M. Schwerbel D. Balthasar D. et al. “Automatic Sorting of Alluminium Alloys Based on Spectroscopy Measures”. In: 35th Annual Workshop of the Austrian Association for Pattern Recognition (OAGM). doi:10.48550/arXiv.1505.01065 · arXiv · doi:10.48550/arxiv.1505.01065
- 10.1177/0003702819861576 · doi:10.1177/0003702819861576
- 10.14429/dsj.67.10690 · doi:10.14429/dsj.67.10690
- 10.1364/OE.402149 · DOI
- 10.1007/978-3-030-68763-2_47 · doi:10.1007/978-3-030-68763-2_47
- 10.1109/ICPR48806.2021.9413119 · DOI
- 10.1039/C8JA00076J · DOI · Paper page
- 10.1016/j.radphyschem.2021.109515 · doi:10.1016/j.radphyschem.2021.109515
- 10.1088/1402-4896/ac1a87 · doi:10.1088/1402-4896/ac1a87
- Cui H., Tang Y., Ma S., Ma Y., et al. “Influence of Laser Wavelength on Self-Absorption Effect in Laser-Induced Breakdown Spectroscopy”. Optik. 2020. 204: 164144. 10.1016/j.ijleo.2019.164144 · doi:10.1016/j.ijleo.2019.164144
- 10.1007/s00216-006-0300-1 · DOI
- 10.1016/j.optlastec.2019.106035 · DOI
- 10.1016/j.sab.2007.10.041 · doi:10.1016/j.sab.2007.10.041
- 10.1016/j.marpolbul.2021.112789 · DOI
- 10.1007/s11467-012-0263-y · doi:10.1007/s11467-012-0263-y
- 10.1186/s41476-021-00164-9 · DOI
- 10.1016/j.trac.2022.116618 · DOI
- 10.1016/j.sab.2022.106478 · DOI
- 10.1038/s41598-021-00647-2 · DOI
- 10.1088/2058-6272/ab7d48 · DOI
- 10.1109/LGRS.2017.2780890 · DOI · Paper page
- 10.1039/C9RA00805E · DOI
- 10.1016/j.sab.2020.105801 · DOI
- 10.1039/C8JA00069G · doi:10.1039/c8ja00069g
- 10.1039/D0JA00334D · DOI
- 10.1039/D1JA00076D · DOI · Paper page
- 10.1186/s40537-017-0089-0 · DOI · Paper page
- 10.1016/j.mex.2021.101408 · DOI
- 10.1109/CSPA48992.2020.9068683 · DOI
Metadata
- Authors
- Srivastava, E., Kim, H., Lee, J., Shin, S., Jeong, S., & Hwang, E.
- Venue
- Applied Spectroscopy
- Publisher
- SAGE Publications
- Published
- 2023-04-25
- Volume
- 77
- Issue
- 6
- Pages
- 603-615
- ISSN
- 0003-7028
- 1943-3530
- Cited by
- 14
- References
- 3
- Language
- en
- Licence
- journals.sagepub.com/page/policies/text-and-data-mining-license (tdm)
- Funders
- Artificial Intelligence Graduate School Program (2019-0-01842)
- Ministry of Environment, Govt. of Republic of Korea (2016002250003)
- Institute of Information & Communications Technology Planning & Evaluation (IITP), Govt. of Korea
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Adversarial Data Augmentation and Transfer Net for Scrap Metal Identification Using Laser-Induced Breakdown Spectroscopy Measurement of Standard Reference Materials. https://app.cochat.ai/papers/10.1177/00037028231170234
- The paper
- Srivastava, E., Kim, H., Lee, J., Shin, S., Jeong, S., & Hwang, E. (2023). Adversarial Data Augmentation and Transfer Net for Scrap Metal Identification Using Laser-Induced Breakdown Spectroscopy Measurement of Standard Reference Materials. Applied Spectroscopy. https://doi.org/10.1177/00037028231170234
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.