Machine Learning-Based Heavy Metal Ion Detection Using Surface-Enhanced Raman Spectroscopy
Surface-Enhanced Raman Spectroscopy (SERS) is often used for heavy metal ion detection. However, large variations in signal strength, spectral profile, and nonlinearity of measurements often cause problems that produce varying results. It raises concerns about the reproducibility of the results. Con...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/2/596 |
| _version_ | 1797490462339104768 |
|---|---|
| author | Seongyong Park Jaeseok Lee Shujaat Khan Abdul Wahab Minseok Kim |
| author_facet | Seongyong Park Jaeseok Lee Shujaat Khan Abdul Wahab Minseok Kim |
| author_sort | Seongyong Park |
| collection | DOAJ |
| description | Surface-Enhanced Raman Spectroscopy (SERS) is often used for heavy metal ion detection. However, large variations in signal strength, spectral profile, and nonlinearity of measurements often cause problems that produce varying results. It raises concerns about the reproducibility of the results. Consequently, the manual classification of the SERS spectrum requires carefully controlled experimentation that further hinders the large-scale adaptation. Recent advances in machine learning offer decent opportunities to address these issues. However, well-documented procedures for model development and evaluation, as well as benchmark datasets, are missing. Towards this end, we provide the SERS spectral benchmark dataset of lead(II) nitride (Pb(NO<sub>3</sub>)<sub>2</sub>) for a heavy metal ion detection task and evaluate the classification performance of several machine learning models. We also perform a comparative study to find the best combination between the preprocessing methods and the machine learning models. The proposed model can successfully identify the Pb(NO<sub>3</sub>)<sub>2</sub> molecule from SERS measurements of independent test experiments. In particular, the proposed model shows an <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>84.6</mn><mo>%</mo></mrow></semantics></math></inline-formula> balanced accuracy for the cross-batch testing task. |
| first_indexed | 2024-03-10T00:33:20Z |
| format | Article |
| id | doaj.art-4d806a3e8dfa423eaaed8ea6327ac5bc |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T00:33:20Z |
| publishDate | 2022-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-4d806a3e8dfa423eaaed8ea6327ac5bc2023-11-23T15:21:17ZengMDPI AGSensors1424-82202022-01-0122259610.3390/s22020596Machine Learning-Based Heavy Metal Ion Detection Using Surface-Enhanced Raman SpectroscopySeongyong Park0Jaeseok Lee1Shujaat Khan2Abdul Wahab3Minseok Kim4Department of Bio and Brain Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon 34141, KoreaDepartment of Mechanical System Engineering, Kumoh National Institute of Technology, Gumi 39177, KoreaDepartment of Bio and Brain Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon 34141, KoreaDepartment of Mathematics, Nazarbayev University, Nur-Sultan 010000, KazakhstanDepartment of Mechanical System Engineering, Kumoh National Institute of Technology, Gumi 39177, KoreaSurface-Enhanced Raman Spectroscopy (SERS) is often used for heavy metal ion detection. However, large variations in signal strength, spectral profile, and nonlinearity of measurements often cause problems that produce varying results. It raises concerns about the reproducibility of the results. Consequently, the manual classification of the SERS spectrum requires carefully controlled experimentation that further hinders the large-scale adaptation. Recent advances in machine learning offer decent opportunities to address these issues. However, well-documented procedures for model development and evaluation, as well as benchmark datasets, are missing. Towards this end, we provide the SERS spectral benchmark dataset of lead(II) nitride (Pb(NO<sub>3</sub>)<sub>2</sub>) for a heavy metal ion detection task and evaluate the classification performance of several machine learning models. We also perform a comparative study to find the best combination between the preprocessing methods and the machine learning models. The proposed model can successfully identify the Pb(NO<sub>3</sub>)<sub>2</sub> molecule from SERS measurements of independent test experiments. In particular, the proposed model shows an <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>84.6</mn><mo>%</mo></mrow></semantics></math></inline-formula> balanced accuracy for the cross-batch testing task.https://www.mdpi.com/1424-8220/22/2/596surface-enhanced raman spectroscopy (SERS)machine learningheavy-metal ionneural networkSVMrandom forest |
| spellingShingle | Seongyong Park Jaeseok Lee Shujaat Khan Abdul Wahab Minseok Kim Machine Learning-Based Heavy Metal Ion Detection Using Surface-Enhanced Raman Spectroscopy Sensors surface-enhanced raman spectroscopy (SERS) machine learning heavy-metal ion neural network SVM random forest |
| title | Machine Learning-Based Heavy Metal Ion Detection Using Surface-Enhanced Raman Spectroscopy |
| title_full | Machine Learning-Based Heavy Metal Ion Detection Using Surface-Enhanced Raman Spectroscopy |
| title_fullStr | Machine Learning-Based Heavy Metal Ion Detection Using Surface-Enhanced Raman Spectroscopy |
| title_full_unstemmed | Machine Learning-Based Heavy Metal Ion Detection Using Surface-Enhanced Raman Spectroscopy |
| title_short | Machine Learning-Based Heavy Metal Ion Detection Using Surface-Enhanced Raman Spectroscopy |
| title_sort | machine learning based heavy metal ion detection using surface enhanced raman spectroscopy |
| topic | surface-enhanced raman spectroscopy (SERS) machine learning heavy-metal ion neural network SVM random forest |
| url | https://www.mdpi.com/1424-8220/22/2/596 |
| work_keys_str_mv | AT seongyongpark machinelearningbasedheavymetaliondetectionusingsurfaceenhancedramanspectroscopy AT jaeseoklee machinelearningbasedheavymetaliondetectionusingsurfaceenhancedramanspectroscopy AT shujaatkhan machinelearningbasedheavymetaliondetectionusingsurfaceenhancedramanspectroscopy AT abdulwahab machinelearningbasedheavymetaliondetectionusingsurfaceenhancedramanspectroscopy AT minseokkim machinelearningbasedheavymetaliondetectionusingsurfaceenhancedramanspectroscopy |