RamanNet: a generalized neural network architecture for Raman spectrum analysis
<p dir="ltr">Raman spectroscopy provides a vibrational profile of the molecules and thus can be used to uniquely identify different kinds of materials. This sort of molecule fingerprinting has thus led to the widespread application of Raman spectrum in various fields like medical dia...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | , , , , |
| Published: |
2023
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1864513521169989632 |
|---|---|
| author | Nabil Ibtehaz (16888773) |
| author2 | Muhammad E. H. Chowdhury (14150526) Amith Khandakar (14151981) Serkan Kiranyaz (3762058) M. Sohel Rahman (12056885) Susu M. Zughaier (14151987) |
| author2_role | author author author author author |
| author_facet | Nabil Ibtehaz (16888773) Muhammad E. H. Chowdhury (14150526) Amith Khandakar (14151981) Serkan Kiranyaz (3762058) M. Sohel Rahman (12056885) Susu M. Zughaier (14151987) |
| author_role | author |
| dc.creator.none.fl_str_mv | Nabil Ibtehaz (16888773) Muhammad E. H. Chowdhury (14150526) Amith Khandakar (14151981) Serkan Kiranyaz (3762058) M. Sohel Rahman (12056885) Susu M. Zughaier (14151987) |
| dc.date.none.fl_str_mv | 2023-06-21T03:00:00Z |
| dc.identifier.none.fl_str_mv | 10.1007/s00521-023-08700-z |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/journal_contribution/RamanNet_a_generalized_neural_network_architecture_for_Raman_spectrum_analysis/24980826 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Engineering Biomedical engineering Information and computing sciences Data management and data science Machine learning Raman spectrum analysis Convolutional Neural Networks Multilayer perceptron Deep learning Neural network |
| dc.title.none.fl_str_mv | RamanNet: a generalized neural network architecture for Raman spectrum analysis |
| dc.type.none.fl_str_mv | Text Journal contribution info:eu-repo/semantics/publishedVersion text contribution to journal |
| description | <p dir="ltr">Raman spectroscopy provides a vibrational profile of the molecules and thus can be used to uniquely identify different kinds of materials. This sort of molecule fingerprinting has thus led to the widespread application of Raman spectrum in various fields like medical diagnosis, forensics, mineralogy, bacteriology, virology, etc. Despite the recent rise in Raman spectra data volume, there has not been any significant effort in developing generalized machine learning methods targeted toward Raman spectra analysis. We examine, experiment, and evaluate existing methods and conjecture that neither current sequential models nor traditional machine learning models are satisfactorily sufficient to analyze Raman spectra. Both have their perks and pitfalls; therefore, we attempt to mix the best of both worlds and propose a novel network architecture RamanNet. RamanNet is immune to the invariance property in convolutional neural networks (CNNs) and at the same time better than traditional machine learning models for the inclusion of sparse connectivity. This has been achieved by incorporating shifted multi-layer perceptrons (MLP) at the earlier levels of the network to extract significant features across the entire spectrum, which are further refined by the inclusion of triplet loss in the hidden layers. Our experiments on 4 public datasets demonstrate superior performance over the much more complex state-of-the-art methods, and thus, RamanNet has the potential to become the de facto standard in Raman spectra data analysis.</p><h2>Other Information</h2><p dir="ltr">Published in: Neural Computing and Applications<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1007/s00521-023-08700-z" target="_blank">https://dx.doi.org/10.1007/s00521-023-08700-z</a></p> |
| eu_rights_str_mv | openAccess |
| id | Manara2_9041cce21fd9b7101ebf119b9b5c6727 |
| identifier_str_mv | 10.1007/s00521-023-08700-z |
| network_acronym_str | Manara2 |
| network_name_str | Manara2 |
| oai_identifier_str | oai:figshare.com:article/24980826 |
| publishDate | 2023 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | RamanNet: a generalized neural network architecture for Raman spectrum analysisNabil Ibtehaz (16888773)Muhammad E. H. Chowdhury (14150526)Amith Khandakar (14151981)Serkan Kiranyaz (3762058)M. Sohel Rahman (12056885)Susu M. Zughaier (14151987)EngineeringBiomedical engineeringInformation and computing sciencesData management and data scienceMachine learningRaman spectrum analysisConvolutional Neural NetworksMultilayer perceptronDeep learningNeural network<p dir="ltr">Raman spectroscopy provides a vibrational profile of the molecules and thus can be used to uniquely identify different kinds of materials. This sort of molecule fingerprinting has thus led to the widespread application of Raman spectrum in various fields like medical diagnosis, forensics, mineralogy, bacteriology, virology, etc. Despite the recent rise in Raman spectra data volume, there has not been any significant effort in developing generalized machine learning methods targeted toward Raman spectra analysis. We examine, experiment, and evaluate existing methods and conjecture that neither current sequential models nor traditional machine learning models are satisfactorily sufficient to analyze Raman spectra. Both have their perks and pitfalls; therefore, we attempt to mix the best of both worlds and propose a novel network architecture RamanNet. RamanNet is immune to the invariance property in convolutional neural networks (CNNs) and at the same time better than traditional machine learning models for the inclusion of sparse connectivity. This has been achieved by incorporating shifted multi-layer perceptrons (MLP) at the earlier levels of the network to extract significant features across the entire spectrum, which are further refined by the inclusion of triplet loss in the hidden layers. Our experiments on 4 public datasets demonstrate superior performance over the much more complex state-of-the-art methods, and thus, RamanNet has the potential to become the de facto standard in Raman spectra data analysis.</p><h2>Other Information</h2><p dir="ltr">Published in: Neural Computing and Applications<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1007/s00521-023-08700-z" target="_blank">https://dx.doi.org/10.1007/s00521-023-08700-z</a></p>2023-06-21T03:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1007/s00521-023-08700-zhttps://figshare.com/articles/journal_contribution/RamanNet_a_generalized_neural_network_architecture_for_Raman_spectrum_analysis/24980826CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/249808262023-06-21T03:00:00Z |
| spellingShingle | RamanNet: a generalized neural network architecture for Raman spectrum analysis Nabil Ibtehaz (16888773) Engineering Biomedical engineering Information and computing sciences Data management and data science Machine learning Raman spectrum analysis Convolutional Neural Networks Multilayer perceptron Deep learning Neural network |
| status_str | publishedVersion |
| title | RamanNet: a generalized neural network architecture for Raman spectrum analysis |
| title_full | RamanNet: a generalized neural network architecture for Raman spectrum analysis |
| title_fullStr | RamanNet: a generalized neural network architecture for Raman spectrum analysis |
| title_full_unstemmed | RamanNet: a generalized neural network architecture for Raman spectrum analysis |
| title_short | RamanNet: a generalized neural network architecture for Raman spectrum analysis |
| title_sort | RamanNet: a generalized neural network architecture for Raman spectrum analysis |
| topic | Engineering Biomedical engineering Information and computing sciences Data management and data science Machine learning Raman spectrum analysis Convolutional Neural Networks Multilayer perceptron Deep learning Neural network |