Comparison of Machine Learning Models on Performance of Single- and Dual-Type Electrochromic Devices

This study shows that the model fitting based on machine learning (ML) from experimental data can successfully predict the electrochromic characteristics of single- and dual-type flexible electrochromic devices (ECDs) by using tungsten trioxide (WO3) and WO3/vanadium pentoxide (V2O5), respectively. Seven different regression methods were used for experimental observations, which belong to single and dual ECDs where 80% percent was used as training data and the remaining was taken as testing data. Among the seven different regression methods, K-nearest neighbor (KNN) achieves the best results with higher coefficient of determination (R2) score and lower root-mean-squared error (RMSE) for the bleaching state of ECDs. Furthermore, higher R2 score and lower RMSE for the coloration state of ECDs were achieved with Gaussian process regressor. The robustness result of the ML modeling demonstrates the reliability of prediction outcomes. These results can be proposed as promising models for different energy-saving flexible electronic systems.

[1]  Z R Li,et al.  Quantitative structure-pharmacokinetic relationships for drug clearance by using statistical learning methods. , 2006, Journal of molecular graphics & modelling.

[2]  Sudhir A. Kulkarni,et al.  Three-Dimensional QSAR Using the k-Nearest Neighbor Method and Its Interpretation , 2006, J. Chem. Inf. Model..

[3]  Yung‐Sen Lin,et al.  Flexible electrochromic tungsten/iron mixed oxide films synthesized by an atmospheric pressure plasma jet , 2019, Thin Solid Films.

[4]  Göran Lindbergh,et al.  Methodology for measuring current distribution effects in electrochromic smart windows. , 2011, Applied optics.

[5]  Se Hyun Kim,et al.  Non-volatile, Li-doped ion gel electrolytes for flexible WO3-based electrochromic devices , 2019, Materials & Design.

[6]  Tânia Cova,et al.  Deep Learning for Deep Chemistry: Optimizing the Prediction of Chemical Patterns , 2019, Front. Chem..

[7]  Jianhua Yao,et al.  Prediction of mutagenic toxicity by combination of Recursive Partitioning and Support Vector Machines , 2007, Molecular Diversity.

[8]  Harshinder Singh,et al.  Application of the Random Forest Method in Studies of Local Lymph Node Assay Based Skin Sensitization Data , 2005, J. Chem. Inf. Model..

[9]  X. W. Sun,et al.  Electrochromic properties of nanostructured tungsten trioxide (hydrate) films and their applications in a complementary electrochromic device , 2012 .

[10]  Rui Yu,et al.  Ultraflexible, stretchable and fast-switching electrochromic devices with enhanced cycling stability , 2018, RSC advances.

[11]  K. Gasem,et al.  An Improved Structure−Property Model for Predicting Melting-Point Temperatures , 2006 .

[12]  Li Li,et al.  Optimization of Molecules via Deep Reinforcement Learning , 2018, Scientific Reports.

[13]  Thomas Sander,et al.  Toxicity-Indicating Structural Patterns , 2006, J. Chem. Inf. Model..

[14]  Haekyoung Kim,et al.  Sol-gel fabrication of NiO and NiO/WO3 based electrochromic device on ITO and flexible substrate , 2020 .

[15]  O. Bohnké,et al.  Kinetics study and modelling of the electrochromic phenomenon in amorphous tungsten trioxide thin films in acid and lithium electrolytes , 1994 .

[16]  Cigdem Dulgerbaki,et al.  Fabricating polypyrrole/tungsten oxide hybrid based electrochromic devices using different ionic liquids , 2016 .

[17]  Anastasios I. Dounis,et al.  Electrochromic device modeling using an adaptive neuro-fuzzy inference system: A model-free approach , 2016 .

[18]  Hongbo Zeng,et al.  Constructing spraying-processed complementary smart windows via electrochromic materials with hierarchical nanostructures , 2019, Journal of Materials Chemistry C.

[19]  Robert C. Glen,et al.  Predicting Phospholipidosis Using Machine Learning , 2010, Molecular pharmaceutics.

[20]  P. Patil,et al.  Electrochromic performance of the mixed V2O5–WO3 thin films synthesized by pulsed spray pyrolysis technique , 2014 .

[21]  Andreas Bender,et al.  Chemoinformatics-Based Classification of Prohibited Substances Employed for Doping in Sport , 2006, J. Chem. Inf. Model..

[22]  E. Stathatos,et al.  Flexible electrochromic tape using steel foil with WO3 thin film , 2020 .

[23]  Daniel W. Davies,et al.  Machine learning for molecular and materials science , 2018, Nature.

[24]  A. Oksuz,et al.  Electrochromic characteristics of radio frequency plasma sputtered WO 3 thin films onto flexible polyethylene terephthalate substrates , 2017 .

[25]  Linsen Chen,et al.  Highly flexible electrochromic devices enabled by electroplated nickel grid electrodes and multifunctional hydrogels. , 2019, Optics express.

[26]  Hans Briem,et al.  Classifying “Kinase Inhibitor‐Likeness” by Using Machine‐Learning Methods , 2005, Chembiochem : a European journal of chemical biology.

[27]  Wen Chen,et al.  Flexible electrochromic thin films with ultrafast responsion based on exfoliated V2O5 nanosheets/graphene oxide via layer-by-layer assembly , 2020, Applied Surface Science.

[28]  J. Kleperis,et al.  Model of electrochromic and related phenomena in tungsten oxide thin films , 2003 .

[29]  A. Oksuz,et al.  Enhanced electrochromic characteristics induced by Au/PEDOT/Pt microtubes in WO3 based electrochromic devices , 2019, Optical Materials.

[30]  Bruce R. Kowalski,et al.  Pattern Recognition in Chemical Research , 1974 .

[31]  Hongzhi Wang,et al.  Hierarchical NiO microflake films with high coloration efficiency, cyclic stability and low power consumption for applications in a complementary electrochromic device. , 2013, Nanoscale.

[32]  M. Deepa,et al.  A WO3–poly(butyl viologen) layer-by-layer film/ruthenium purple film based electrochromic device switching by 1 volt application , 2015 .

[33]  Arthur L. Samuel,et al.  Some Studies in Machine Learning Using the Game of Checkers , 1967, IBM J. Res. Dev..

[34]  John B. O. Mitchell,et al.  Development and Comparison of hERG Blocker Classifiers: Assessment on Different Datasets Yields Markedly Different Results , 2011, Molecular informatics.

[35]  A. Oksuz,et al.  Enhanced electrochromic performance of WO3 hybrids using polymer plasma hybridization process , 2018 .

[36]  J. Nagai,et al.  Modeling of electrochromic processes , 1999 .

[37]  Xi Chen,et al.  Preparation and performance of fast-response ITO/Li-NiO/Li-WO3/ITO all-solid-state electrochromic devices by evaporation method , 2020, Materials Letters.

[38]  A. Oksuz,et al.  High-performance Flexible Complementary Electrochromic Device Based on Plasma Modified WO3 Nano Hybrids and V2 O5 Nanofilm with Low Operation Voltages , 2018, Electroanalysis.

[39]  Sunil S. Bhagwat,et al.  Prediction of Melting Points of Organic Compounds Using Extreme Learning Machines , 2008 .

[40]  Alice Lee-Sie Eh,et al.  Recent Advances in Flexible Electrochromic Devices: Prerequisites, Challenges, and Prospects , 2018 .

[41]  Xiaomin Li,et al.  Bi-functional flexible electrodes based on tungsten trioxide/zinc oxide nanocomposites for electrochromic and energy storage applications , 2017 .

[42]  Kevin M. Ryan,et al.  Crystal Structure Prediction via Deep Learning. , 2018, Journal of the American Chemical Society.

[43]  Z. R. Li,et al.  Prediction of estrogen receptor agonists and characterization of associated molecular descriptors by statistical learning methods. , 2006, Journal of molecular graphics & modelling.

[44]  Emmanuel Koudoumas,et al.  Oxygen and temperature effects on the electrochemical and electrochromic properties of rf-sputtered V2O5 thin films , 2017 .

[45]  Hang Lei,et al.  Hyperparameter Optimization for Machine Learning Models Based on Bayesian Optimization , 2019 .

[46]  Clayton Springer,et al.  An investigation into pharmaceutically relevant mutagenicity data and the influence on Ames predictive potential , 2011, J. Cheminformatics.

[47]  David W. Opitz,et al.  Use of Statistical and Neural Net Approaches in Predicting Toxicity of Chemicals , 2000, J. Chem. Inf. Comput. Sci..

[48]  Y. Liu,et al.  2-D mathematical modeling for a large electrochromic window—Part I , 2014 .

[49]  Gerhard F. Ecker,et al.  Classification Models for hERG Inhibitors by Counter‐Propagation Neural Networks , 2008, Chemical biology & drug design.

[50]  Paul L. A. Popelier,et al.  pKa Prediction from "Quantum Chemical Topology" Descriptors , 2009, J. Chem. Inf. Model..