Improving Recognition Accuracy of Pesticides in Groundwater by Applying TrAdaBoost Transfer Learning Method
Abstract
:1. Introduction
- The TrAdaBoost algorithm was first applied to the e-nose field.
- The method of PCA, multi-feature extraction algorithms combined with an SVM classifier, were applied to prove that the response signals of source and target domain samples have significant differences.
- Two parameters of the TrAdaBoost algorithm in the pesticide recognition process were optimized: the number of iterations and the number of source domain samples participating in model training.
- The e-nose system applied the TrAdaBoost algorithm to realize qualitative and semi-quantitative identification of pesticides in groundwater under the condition of limited target domain data.
2. Materials and Methods
2.1. Sample Preparation
2.1.1. Soil Sample
2.1.2. Pesticide Reagent
2.1.3. Groundwater Sample Preparation
2.2. E-Nose System and Process
2.3. Data Analysis
2.3.1. Feature Extraction
- Fourier transform (FT): the response signals were used for Fourier transform, and the transform coefficients were applied as the feature values.
- Wavelet transform (WT): the response signals were used for wavelet transform, and the transform coefficients were applied as the feature values.
- Steady-state feature extraction methods:
- Integral value (IV): calculating the area below the sensor response curve.
- Max value (MAX): selecting the maximum voltage value from the e-nose response signal.
- Mean value (Mean): calculating the average voltage value for the e-nose response signal.
2.3.2. Pattern Recognition
3. Results and Discussion
3.1. PCA Analysis
3.2. Selecting an Appropriate Feature Extraction Method
3.3. TrAdaBoost Transfer Learning Method for Qualitative Analysis
3.3.1. Optimizing the Parameters of the TrAdaBoost Method
3.3.2. Comparison of Different Methods
3.4. TrAdaBoost Transfer Learning Method for Semi-Quantitative Analysis
3.4.1. Optimizing the Parameters of the TrAdaBoost Method
3.4.2. Comparison of Different Methods
4. Conclusions
Supplementary Materials
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Alley, W.M.; Healy, R.W.; LaBaugh, J.W.; Reilly, T.E. Hydrology-Flow and Storage in Groundwater Systems. Science 2002, 296, 1985–1990. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Da Silva Sousa, J.; do Nascimento, H.O.; de Oliviera Gomes, H.; do Nascimento, R.F. Pesticide residues in groundwater and surface water: Recent advances in solid-phase extraction and solid-phase microextraction sample preparation methods for multiclass analysis by gas chromatography-mass spectrometry. Microchem. J. 2021, 168, 106359. [Google Scholar] [CrossRef]
- Huang, X.; Liu, G.; Xu, D.; Xu, X.; Li, L.; Zheng, S.; Lin, H.; Gao, H. Novel Zeolitic Imidazolate Frameworks Based on Magnetic Multiwalled Carbon Nanotubes for Magnetic Solid-Phase Extraction of Organochlorine Pesticides from Agricultural Irrigation Water Samples. Appl. Sci. 2018, 8, 959. [Google Scholar] [CrossRef] [Green Version]
- Liu, A.; Kou, W.; Zhang, H.; Xu, J.; Zhu, L.; Kuang, S.; Huang, K.; Chen, H.; Jia, Q. Quantification of Trace Organophosphorus Pesticides in Environmental Water via Enrichment by Magnetic-Zirconia Nanocomposites and Online Extractive Electrospray Ionization Mass Spectrometry. Anal. Chem. 2020, 92, 4137–4145. [Google Scholar] [CrossRef]
- Rodriguez-Cuesta, M.J.; Boque, R.; Rius, F.X.; Vidal, J.L.M.; Frenich, A.G. Development and validation of a method for determining pesticides in groundwater from complex overlapped HPLC signals and multivariate curve resolution. Chemom. Intell. Lab. Syst. 2005, 77, 251–260. [Google Scholar] [CrossRef]
- Novak, J.M.; Watts, D.W.; Stone, K.C.; Johnson, M.H.; Hunt, P.G. Pesticides and metabolites in the shallow groundwater of an eastern Coastal Plain watershed. Trans. Asae 1998, 41, 1383–1390. [Google Scholar] [CrossRef]
- Spurgeon, D.; Wilkinson, H.; Civil, W.; Hutt, L.; Armenise, E.; Kieboom, N.; Sims, K.; Besien, T. Worst-case ranking of organic chemicals detected in groundwaters an surface waters in England. Sci. Total Environ. 2022, 835, 155101. [Google Scholar] [CrossRef]
- Gu, S.; Wang, J.; Wang, Y. Early discrimination and growth tracking of Aspergillus spp. contamination in rice kernels using electronic nose. Food Chem. 2019, 292, 325–335. [Google Scholar] [CrossRef]
- Zhao, R.; Kong, C.; Ren, L.; Sun, Y.; Chang, Z. Real-time monitoring of the oil shale pyrolysis process using a bionic electronic nose. Fuel 2022, 313, 122672. [Google Scholar] [CrossRef]
- Cheng, L.; Meng, Q.H.; Lilienthal, A.J.; Qi, P.F. Development of compact electronic noses: A review. Meas. Sci. Technol. 2021, 32, 062002. [Google Scholar] [CrossRef]
- Al-dayyeni, W.S.; Al-yousif, S.; Taher, M.M. A Review on Electronic Nose: Coherent Taxonomy, Classification, Motivations, Challenges, Recommendations and Datasets. IEEE Access 2021, 9, 88535–88551. [Google Scholar] [CrossRef]
- Gu, S.; Chen, W.; Wang, Z.; Wang, J.; Huo, Y. Rapid detection of Aspergillus spp. infection levels on milled rice by headspace-gas chromatography ion-mobility spectrometry (HS-GC-IMS) and E-nose. LWT—Food Sci. Technol. 2020, 132, 109758. [Google Scholar] [CrossRef]
- Tan, S.L.; Teo, H.S.; Garcia-Guzman, J.; Soc, I.C. E-Nose Screening of Pesticide Residue on Chilli and Double-Checked Analysis through Different Data-Recognition Algorithms. In Proceedings of the 7th IEEE Electronics, Robotics and Automotive Mechanics Conference (CERMA), Cuernavaca, Mexico, 28 September–1 October 2010; pp. 592–596. [Google Scholar]
- Amkor, A.; Maaider, K.; El Barbri, N. Mint treatment day prediction using a multi-sensors system and machine learning algorithms. Sens. Actuators A Phys. 2021, 328, 112787. [Google Scholar] [CrossRef]
- Tang, Y.; Xu, K.; Zhao, B.; Zhang, M.; Gong, C.; Wan, H.; Wang, Y.; Yang, Z. A novel electronic nose for the detection and classification of pesticide residue on apples. RSC Adv. 2021, 11, 20874–20883. [Google Scholar] [CrossRef]
- Nategh, N.A.; Dalvand, M.J.; Anvar, A. Detection of toxic and non-toxic sweet cherries at different degrees of maturity using an electronic nose. J. Food Meas. Charact. 2021, 15, 1213–1224. [Google Scholar] [CrossRef]
- Tang, X.; Xiao, W.; Shang, T.; Zhang, S.; Han, X.; Wang, Y.; Sun, H. An Electronic Nose Technology to Quantify Pyrethroid Pesticide Contamination in Tea. Chemosensors 2020, 8, 30. [Google Scholar] [CrossRef]
- Banning, A.; Banning, H. Pollutants in Groundwater: Current Challenges. Grundwasser 2019, 24, 1. [Google Scholar] [CrossRef] [Green Version]
- Lin, J.; Zhao, L.; Wang, Q.; Ward, R.; Wang, Z.J. DT-LET: Deep transfer learning by exploring where to transfer. Neurocomputing 2020, 390, 99–107. [Google Scholar] [CrossRef] [Green Version]
- Dai, W.; Yang, Q.; Xue, G.; Yu, Y. Boosting for Transfer Learning. ACM Int. Conf. Proc. Ser. 2007, 227, 193–200. [Google Scholar]
- Tang, D.; Yang, X.; Wang, X. Improving the transferability of the crash prediction model using the TrAdaBoost.R2 algorithm. Accid. Anal. Prev. 2020, 141, 105551. [Google Scholar] [CrossRef] [PubMed]
- Fu, Z.; Li, C.; Yao, W. Landslide susceptibility assessment through TrAdaBoost transfer learning models using two landslide inventories. Catena 2023, 222, 106799. [Google Scholar] [CrossRef]
- Jin, X.; Pan, H.; Ying, C.; Kong, Z.; Xu, Z.; Zhang, B. Condition Monitoring of Wind Turbine Generator Based on Transfer Learning and One-Class Classifier. IEEE Sens. J. 2022, 22, 24130–24139. [Google Scholar] [CrossRef]
- Fu, C.; Wu, Z.; Xue, M.; Liu, W. Cross-domain decision making based on TrAdaBoost for diagnosis of breast lesions. Artif. Intell. Rev. 2022. [Google Scholar] [CrossRef]
- Xun, L.; Zhang, J.; Yao, F.; Cao, D. Improved identification of cotton cultivated areas by applying instance-based transfer learning on the time series of MODIS NDVI. Catena 2022, 213, 106130. [Google Scholar] [CrossRef]
- GB/T 14848-2017; Standard for Groundwater Quality. Standards Press of China: Beijing, China, 2017.
- Li, Z. A health-based regulatory chain framework to evaluate international pesticide groundwater regulations integrating soil and drinking water standards. Environ. Int. 2018, 121, 1253–1278. [Google Scholar] [CrossRef]
- Albers, C.N.; Bollmann, U.E.; Badawi, N.; Johnsen, A.R. Leaching of 1,2,4-triazole from commercial barley seeds coated with tebuconazole and prothioconazole. Chemosphere 2022, 286, 131819. [Google Scholar] [CrossRef]
- Aliste, M.; Perez-Lucas, G.; Garrido, I.; Fenoll, J.; Navarro, S. Risk Assessment of 1,2,4-Triazole-Typed Fungicides for Groundwater Pollution Using Leaching Potential Indices. Water Air Soil Pollut. 2021, 232, 469. [Google Scholar] [CrossRef]
- Ionescu, R.; Llobet, E. Wavelet transform-based fast feature extraction from temperature modulated semiconductor gas sensors. Sens. Actuators B—Chem. 2002, 81, 289–295. [Google Scholar] [CrossRef]
- Zhang, S.; Xie, C.; Zeng, D.; Zhang, Q.; Li, H.; Bi, Z. A feature extraction method and a sampling system for fast recognition of flammable liquids with a portable E-nose. Sens. Actuators B—Chem. 2007, 124, 437–443. [Google Scholar] [CrossRef]
- Sanchez, V.D. Advanced support vector machines and kernel methods. Neurocomputing 2003, 55, 5–20. [Google Scholar] [CrossRef]
- Liu, X.; Liu, Z.; Wang, G.; Cai, Z.; Zhang, H. Ensemble Transfer Learning Algorithm. IEEE Access 2018, 6, 2389–2396. [Google Scholar] [CrossRef]
- Moufid, M.; Hofmann, M.; El Bari, N.; Tiebe, C.; Bartholmai, M.; Bouchikhi, B. Wastewater monitoring by means of e-nose, VE-tongue, TD-GC-MS, and SPME-GC-MS. Talanta 2021, 221, 121450. [Google Scholar] [CrossRef]
- Karakaya, D.; Ulucan, O.; Turkan, M. Electronic Nose and Its Applications: A Survey. Int. J. Autom. Comput. 2020, 17, 179–209. [Google Scholar] [CrossRef] [Green Version]
- Wijaya, D.R.; Sarno, R.; Zulaika, E. Noise filtering framework for electronic nose signals: An application for beef quality monitoring. Comput. Electron. Agric. 2019, 157, 305–321. [Google Scholar] [CrossRef]
- Wang, X.; Gu, Y.; Liu, H. A Transfer Learning Method for the Protection of Geographical Indication in China Using an Electronic Nose for the Identification of Xihu Longjing Tea. IEEE Sens. J. 2021, 21, 8065–8077. [Google Scholar] [CrossRef]
- Liu, J.; Wang, Y.; Zhang, Z.; Mo, Y. Multi-view Moving Objects Classification via Transfer Learning. In Proceedings of the First Asian Conference on Pattern Recognition, Beijing, China, 28–28 November 2011; pp. 259–263. [Google Scholar]
- Yu, Y.; Huang, J.; Liu, S.; Zhu, J.; Liang, S. Cross target attributes and sample types quantitative analysis modeling of near-infrared spectroscopy based on instance transfer learning. Measurement 2021, 177, 109340. [Google Scholar] [CrossRef]
Soil Sample | Organic Matter (g/kg) | PH | Cation Exchange Capacity (cmol+/kg) |
---|---|---|---|
location 1 | 10.1 | 6.7 | 7.4 |
location 2 | 47.4 | 7.2 | 14.6 |
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
Chen, D.; Wang, B.; Yang, X.; Weng, X.; Chang, Z. Improving Recognition Accuracy of Pesticides in Groundwater by Applying TrAdaBoost Transfer Learning Method. Sensors 2023, 23, 3856. https://doi.org/10.3390/s23083856
Chen D, Wang B, Yang X, Weng X, Chang Z. Improving Recognition Accuracy of Pesticides in Groundwater by Applying TrAdaBoost Transfer Learning Method. Sensors. 2023; 23(8):3856. https://doi.org/10.3390/s23083856
Chicago/Turabian StyleChen, Donghui, Bingyang Wang, Xiao Yang, Xiaohui Weng, and Zhiyong Chang. 2023. "Improving Recognition Accuracy of Pesticides in Groundwater by Applying TrAdaBoost Transfer Learning Method" Sensors 23, no. 8: 3856. https://doi.org/10.3390/s23083856