Результаты исследований: Научные публикации в периодических изданиях › статья › Рецензирование
Nonlinear dimensionality reduction methods for potentiometric multisensor systems data analysis. / Selivanovs, Z.; Savosina, J.; Agafonova-Moroz, M.; Kirsanov, D.
в: Electroanalysis, 03.10.2023.Результаты исследований: Научные публикации в периодических изданиях › статья › Рецензирование
}
TY - JOUR
T1 - Nonlinear dimensionality reduction methods for potentiometric multisensor systems data analysis
AU - Selivanovs, Z.
AU - Savosina, J.
AU - Agafonova-Moroz, M.
AU - Kirsanov, D.
N1 - Export Date: 28 November 2023 CODEN: ELANE Адрес для корреспонденции: Kirsanov, D.; Institute of Chemistry, Russian Federation; эл. почта: d.kirsanov@gmail.com Сведения о финансировании: Russian Science Foundation, RSF, RSF 23–23‐00114 Текст о финансировании 1: This research was funded by Russian Science Foundation, grant number RSF 23–23‐00114. Пристатейные ссылки: Lin, L., Zhanqiang, H., Xianqiao, H., Dan, L., Shiyi, T., (2022) Food Res. Int., 162. , https://doi.org/10.1016/j.foodres.2022.112214; Shimizu, F.M., Braunger, M.L., Riul, A., (2019) Chemosensors, 7, p. 36. , https://doi.org/10.3390/chemosensors7030036; Al Ramahi, R., Zaid, A.N., Abu-Khalaf, N., (2019) Infect. Drug. Resist., 12, pp. 2445-2451. , https://doi.org/10.2147/IDR.S213938; Cetó, X., González-Calabuig, A., del Valle, M., (2015) Electroanalysis, 27, pp. 225-233. , https://doi.org/10.1002/elan.201400394; Legin, A., Kirsanov, D., del Valle, M., (2019) TrAC, 121. , https://doi.org/10.1016/j.trac.2019.115675; Oliveri, P., Casolino, M.C., Forina, M., (2010) Adv. Food Nutr. Res., 61, pp. 57-117. , https://doi.org/10.1016/B978-0-12-374468-5.00002-7; del Valle, M., (2010) Electroanalysis, 22, pp. 1539-1555. , https://doi.org/10.1002/elan.201000013; https://doi.org/10.1007/11579427_54, C. Shao, H. Huang, Improvement of Data Visualization Based on ISOMAP. In, MICAI 2005 Advances in Artificial Intelligence, Proceedings of 4, Mexican International Conference on Artifificial Intelligence, Monterrey, Mexico, November 14–18, 2005; A. Gelbukh, Á. De Albornoz, H. Terashima-Marín, Springer Heidelberg, Berlin, 2005; Van Der Maaten, L., Postma, E., Van den Herik, J., (2007) J. Mach. Learn. Res., 10, pp. 66-71; Flach, P., (2012) Machine Learning: The Art and Science of Algorithms that Make Sense of Data, , Cambridge University Press, Cambridge, UK, ISBN 9781107422223; Gajamannage, K., Paffenroth, R., Bollt, E.M., (2017) Pattern Recognit. Lett., 87, pp. 226-236. , https://doi.org/10.48550/arXiv.1707.06757; Tenenbaum, J.B., de Silva, V., Langford, J.C., (2000) Science, 290, pp. 2319-2323; De Backer, S., Naud, A., Scheunders, P., (1998) Pattern Recognit. Lett., 19, pp. 711-720. , https://doi.org/10.1016/S0167-8655(98)00049-X; Trivedi, U., Isomap(D, N_Fcn, N_Size, Options), , https://www.mathworks.com/matlabcentral/fileexchange/62449-isomap-d-n_fcn-n_size-options, accessed on 9 October 2021; Wehrens, R., Chemometrics with R: Multivariate Data Analysis in the Natural Sciences and Life Sciences, , Springer: Berlin Heidelberg, Germany, 2011. ISBN 978–3-642-17840-5; Bro, R., Smilde, A., Rasmus, B., Age, K., (2014) Analitycal Methods, 6, pp. 2812-2283. , https://doi.org/10.1039/C3AY41907J; Brereton, R.G., (2009) Chemometrics for Pattern Recognition, , John Wiley & Sons Ltd: Chichester, UK,, ISBN 978–0-470-98725-4; Wehrens, R., Kruisselbrink, J., (2018) Journal of Statistical Software, 87, pp. 1-18. , https://doi.org/10.18637/jss.v087.i07; Martinez-Murcia, F.J., Ortiz, A., Gorriz, J.M., Ramirez, J., Castillo-Barnes, D., Salas-Gonzalez, D., Segovia, F., Deep Convolutional Autoencoders vs PCA in a Highly-Unbalanced Parkinson's Disease Dataset: A DaTSCAN Study (2018) Proceedings of the International Joint Conference SOCO’18-CISIS’18-ICEUTE’18, pp. 6-8. , https://doi.org/10.1007/978-3-319-94120-2_5, San Sebastián, Spain, June; Alkhayrat, M., Aljnidi, M., Aljoumaa, K., (2020) J Big Data, 7. , https://doi.org/10.1186/s40537-020-0286-0; Lantz, B., Machine Learning with R. Packt Publishing: Birmingham, UK, 2013. ISBN 978–1-78216-8; R: The R Project for Statistical Computing, , https://www.R-project.org/, accessed on 27 December 2022; Kucheryavskiy, S., (2020) Chemom. Intell. Lab. Syst., 198. , https://doi.org/10.1016/j.chemolab.2020.103937; Wehrens, R., Kruisselbrink, J., (2018) Journal of Statistical Software, 87, pp. 1-18. , https://doi.org/10.18637/jss.v087.i07; Wehrens, R., Buydens, L.M.C., (2007) Journal of Statistical Software, 21, pp. 1-19. , https://doi.org/; (2022) Package Keras., , https://tensorflow.rstudio.com, Available online, accessed on 25 December; (2022), https://github.com/rstudio/tensorflow, Available online:, accessed on 25 December; Venables, W.N., Ripley, B.D., (2002) Modern Applied Statistics with S, Fourth Edition, , Springer: New York, USA; Solovieva, S., Karnaukh, M., Panchuk, V., Andreev, E., Kartsova, L., Bessonova, E., Legin, A., Kirsanov, D., (2019) Sens. Actuators B, 289, pp. 42-47; Smirnov, I., Karavan, M., Kenf, E., Tkachenko, L., Timoshenko, V., Brechalov, A., Maltseva, T., Ermolenko, Y., (2022) Solvent Extr. Ion Exch., 40, pp. 756-776; Kravić, N., Savosina, J., Agafonova-Moroz, M., Babain, V., Legin, A., Kirsanov, D., (2022) Chemosensors, 10, p. 90. , https://doi.org/10.3390/chemosensors10030090; Belikova, V., Panchuk, V., Legin, E., Melenteva, A., Kirsanov, D., Legin, A., (2019) Sens. Actuators B, 282, pp. 854-860. , https://doi.org/10.1016/j.snb.2018.11.153; Das, G., Chattopadhyay, M., Gupta, S., (2016) International Journal of Market Research, 58, pp. 815-834. , https://doi.org/10.2501/IJMR-2016-039; Mehrbani, E., Kahaei, M.H., (2022) IET Signal Process, 16, pp. 528-545. , https://doi.org/10.1049/sil2.12124
PY - 2023/10/3
Y1 - 2023/10/3
N2 - Electrochemical multisensor systems were proven to be a very perspective research direction in modern analytical chemistry. The multisensor approach assumes an employment of cross-sensitive chemical sensors in combination with multivariate data processing methods. Dimensionality reduction of the data obtained from multisensor systems is a very important step and it is mostly based on the traditional tools of chemometrics, such as Principal Component Analysis (PCA). In case of chemically complex samples, the response of multisensor systems may have a complex nonlinear nature and the use of linear modelling methods does not seem optimal. However, the potential of nonlinear dimensionality reduction methods in the processing of multisensor data has not yet been systematically studied. In this report we aim to fill this gap and assess the performance of various nonlinear dimensionality reduction tools: Isomap, Self-Organizing Kohonen Maps, and Autoencoder. These methods were explored using three datasets from potentiometric multisensor systems obtained in various real applications. It was shown that nonlinear dimensionality reduction methods give the possibility to obtain additional and more detailed information about the analyzed objects/processes compared to PCA. However, calculation time for nonlinear dimensionality reduction methods essentially exceeds that for PCA, and it can be a limiting factor for application of such algorithms. © 2023 Wiley-VCH GmbH.
AB - Electrochemical multisensor systems were proven to be a very perspective research direction in modern analytical chemistry. The multisensor approach assumes an employment of cross-sensitive chemical sensors in combination with multivariate data processing methods. Dimensionality reduction of the data obtained from multisensor systems is a very important step and it is mostly based on the traditional tools of chemometrics, such as Principal Component Analysis (PCA). In case of chemically complex samples, the response of multisensor systems may have a complex nonlinear nature and the use of linear modelling methods does not seem optimal. However, the potential of nonlinear dimensionality reduction methods in the processing of multisensor data has not yet been systematically studied. In this report we aim to fill this gap and assess the performance of various nonlinear dimensionality reduction tools: Isomap, Self-Organizing Kohonen Maps, and Autoencoder. These methods were explored using three datasets from potentiometric multisensor systems obtained in various real applications. It was shown that nonlinear dimensionality reduction methods give the possibility to obtain additional and more detailed information about the analyzed objects/processes compared to PCA. However, calculation time for nonlinear dimensionality reduction methods essentially exceeds that for PCA, and it can be a limiting factor for application of such algorithms. © 2023 Wiley-VCH GmbH.
KW - autoencoder
KW - chemical analysis
KW - dimensionality reduction
KW - isomap
KW - multisensor systems
KW - principal component analysis (PCA)
KW - self-organizing map (SOM)
KW - Conformal mapping
KW - Learning systems
KW - Nonlinear analysis
KW - Potentiometers (electric measuring instruments)
KW - Self organizing maps
KW - Sensor data fusion
KW - Auto encoders
KW - Dimensionality reduction
KW - Dimensionality reduction method
KW - Isomaps
KW - Nonlinear dimensionality reduction
KW - Potentiometrics
KW - Principal component analyse
KW - Principal-component analysis
KW - Self-organizing map
KW - Self-organizing-maps
KW - Principal component analysis
UR - https://www.mendeley.com/catalogue/848b6c51-7b4b-32d0-a0e1-c4e8a1268f09/
U2 - 10.1002/elan.202300220
DO - 10.1002/elan.202300220
M3 - статья
JO - Electroanalysis
JF - Electroanalysis
SN - 1040-0397
M1 - e202300220
ER -
ID: 114408510