Modeling energy band gap of doped TiO2 semiconductor using homogeneously hybridized support vector regression with gravitational search algorithm hyper-parameter optimization
Source abstract
Abstract
Titanium dioxide (TiO2) semiconductor is characterized with a wide band gap and attracts a significant attention for several applications that include solar cell carrier transportation and photo-catalysis. The tunable band gap of this semiconductor coupled with low cost, chemical stability and non-toxicity make it indispensable for these applications. Structural distortion always accompany TiO2 band gap tuning through doping and this present work utilizes the resulting structural lattice distortion to estimate band gap of doped TiO2 using support vector regression (SVR) coupled with novel gravitational search algorithm (GSA) for hyper-parameters optimization. In order to fully capture the non-linear relationship between lattice distortion and band gap, two SVR models were homogeneously hybridized and were subsequently optimized using GSA. GSA-HSVR (hybridized SVR) performs better than GSA-SVR model with performance improvement of 57.2% on the basis of root means square error reduction of the testing dataset. Effect of Co doping and Nitrogen-Iodine co-doping on band gap of TiO2 semiconductor was modeled and simulated. The obtained band gap estimates show excellent agreement with the values reported from the experiment. By implementing the models, band gap of doped TiO2 can be estimated with high level of precision and absorption ability of the semiconductor can be extended to visible region of the spectrum for improved properties and efficiency.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Gas Sensing Nanomaterials and Sensors · Chalcogenide Semiconductor Thin Films · Transition Metal Oxide Nanomaterials
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Physics Department, King Fahd University of Petroleum and Minerals 1 , Dhahran Postal code 34464, Kingdom of Saudi Arabia
Physics and Electronics Department, Adekunle Ajasin University 2 , Akungba Akoko Postal code 342111, Ondo State Nigeria
Institute for Digital Communications, School of Engineering, University of Edinburgh 3 , Edinburgh Postal code EH8 9AB, United Kingdom
Computer Science Department, College of Computer Science and Information Technology, Imam Abdulrahman Bin Faisal University 4 , Dammam Postal code 31433, Saudi Arabia
Computer Information System Department, College of Computer Science and Information Technology, Imam Abdulrahman Bin Faisal University 5 , Dammam Postal code 31433, Saudi Arabia
References (44)
Show source-provided references
1. Cobalt and sulfur co-doped nano-size TiO2 for photodegradation of various dyes and phenol10.1016/j.jes.2015.04.024 ↗
2. Preparation of multiple-doped TiO2 nanotube arrays with nitrogen, carbon and nickel with enhanced visible light photoelectrochemical activity via single-step anodization10.1016/j.ijhydene.2015.07.069 ↗
3. Structural phase analysis, band gap tuning and fluorescence properties of Co doped TiO 2 nanoparticles10.1016/j.optmat.2014.10.054 ↗
4. Band gap manipulation of cerium doping TiO2 nanopowders by hydrothermal method10.1016/j.jallcom.2015.12.034 ↗
5. Mg-doped TiO2 thin films deposited by low cost technique for CO gas monitoring
6. Magnetic and optical properties of Al-doped anatase TiO2(101) surface from density functional theory10.1016/j.jmmm.2015.12.013 ↗
7. A facile route to synthesis of S-doped TiO2 nanoparticles for photocatalytic activity10.1016/j.molcata.2015.05.002 ↗
8. Annealing effects on structure and magnetic properties of Mn-doped TiO210.1016/j.jmmm.2015.11.065 ↗
9. Photoluminescence of Cr-doped TiO2 induced by intense UV laser excitation10.1016/j.jlumin.2015.03.034 ↗
10. Physical properties of Zn doped TiO2 thin films with spray pyrolysis technique and its effects in antibacterial activity10.1016/j.saa.2014.11.016 ↗
11. Nb-doped TiO2 thin films for photovoltaic applications10.1016/j.matdes.2015.07.034 ↗
12. Iron doped thin TiO2 films synthesized with the RF PECVD method10.1016/j.ceramint.2015.02.071 ↗
13. The surface science of titanium dioxide10.1016/s0167-5729(02)00100-0 ↗
14. Support vector regression
15. Support vector regression and artificial neural network models for stability indicating analysis of mebeverine hydrochloride and sulpiride mixtures in pharmaceutical preparation: A comparative study10.1016/j.saa.2011.11.003 ↗
16. Lattice constant prediction of cubic and monoclinic perovskites using neural networks and support vector regression10.1016/j.commatsci.2010.08.028 ↗
17. Computational intelligence method of estimating solid- liquid interfacial energy of materials at their melting tem- peratures
18. Estimation of average surface energies of transition metal nitrides using computational intelligence technique
19. Application of computational intelligence technique for estimating superconducting transition temperature of YBCO superconductors10.1016/j.asoc.2016.02.005 ↗
20. Development and validation of surface energies estimator (SEE) using computational intelligence technique10.1016/j.commatsci.2015.01.020 ↗
21. Sliding window-based support vector regression for predicting micrometeorological data10.1016/j.eswa.2016.04.012 ↗
22. Prediction of asphaltene precipitation using support vector regression tuned with genetic algorithms
23. Financial time series forecasting using LPP and SVM optimized by PSO10.1007/s00500-012-0953-y ↗
24. Credit scoring using support vector machines with direct search for parameters selection10.1007/s00500-008-0305-0 ↗
25. Estimation of superconducting transition temperature T C for superconductors of the doped MgB2 system from the crystal lattice parameters using support vector regression
26. GSA: A gravitational search algorithm10.1016/j.ins.2009.03.004 ↗
27. An approach using support vector regression for mobile location in cellular networks10.1016/j.comnet.2015.12.003 ↗
28. Journal of natural gas science and engineering investigating the effect of correlation-based feature selection on the performance of neural network in reservoir characterization10.1016/j.jngse.2015.08.042 ↗
29. Computational intelligence method of determining the energy band gap of doped ZnO semiconductor10.1016/j.matdes.2016.03.116 ↗
30. A robabilistic framepwork for SVM regression and error bar estimation10.1023/a:1012494009640 ↗
31. Estimation of surface energies of hexagonal close packed metals using computational intelligence technique10.1016/j.asoc.2015.03.009 ↗
32. Estimation of melting points of fatty acids using homogeneously 3 hybridized support vector regression
33. A novel homogenous hybridization scheme for performance improvement of support vector machines regression in reservoir characterization10.1155/2016/2580169 ↗
34. A novel hybrid system for feature selection based on an improved gravitational search algorithm and k-NN method10.1016/j.asoc.2015.01.043 ↗
35. Combined heat and power economic dispatch problem using gravitational search algorithm10.1016/j.epsr.2015.10.007 ↗
36. Feature subset selection by gravitational search algorithm optimization10.1016/j.ins.2014.05.030 ↗
37. Optimal capacitor placement in radial distribution system using Gravitational Search Algorithm10.1016/j.ijepes.2014.07.041 ↗
38. Parametric optimization of ultrasonic machining process using gravitational search and fireworks algorithms10.1016/j.asej.2014.10.009 ↗
39. Using gravitational search algorithm in prototype generation for nearest neighbor classification10.1016/j.neucom.2015.01.008 ↗
40. Photocatalytic degradation of 4-chloro-2-methylphenoxyacetic acid using W-doped TiO210.1016/j.jphotochem.2015.07.014 ↗
41. Photocatalytic CO2 reduction with H2 as reductant over copper and indium co-doped TiO2 nanocatalysts in a monolith photoreactor10.1016/j.apcata.2014.12.053 ↗
42. Comparative study of (N, Fe) doped TiO2 photocatalysts10.1016/j.apsusc.2014.11.137 ↗
43. Preparation, characterization of N – I co-doped TiO 2 and catalytic performance toward simultaneous Cr ( VI ) reduction and benzoic acid oxidation10.1016/j.apcatb.2013.04.052 ↗
44. Preparation, characterization of N-I co-doped TiO2 and catalytic performance toward simultaneous Cr(VI) reduction and benzoic acid oxidation10.1016/j.apcatb.2013.04.052 ↗