Laser induced breakdown spectroscopy (LIBS) is an excellent technique for analysis of solid and liquid samples. However there are inherent problems with concentration determination of elements present in the test sample with better accuracy. In order to address this challenge, hybrid fusion of extreme learning machine (ELM) and support vector regression (SVR) is proposed for the first time. Extreme learning machine (ELM) is a non-linear chemo-metric method which has inherent capacity to approximate any non-linear relation describing the laser induced plasma. However, ELM surfers from over-fitting which affects its accuracy for spectroscopic regression. On the other hand, SVR is a non-linear chemo-metric tool based on statistical learning theory and overcomes the problem of over-fitting by proper tuning of its hyper-parameters. The merits of both chemo-metrics are harnessed in this work and implemented for quantitative analysis of LIBS spectra of seven standard bronze samples. The performance of ELM-SVR model which uses the output of ELM as its input is compared to that of SVR-ELM model which takes the output of SVR as its input. The hyper-parameters of the proposed models are optimized using gravitational search algorithm (GSA). On the bases of root mean square error (RMSE) as a measure of model performance, ELM-SVR performs better than SVR, ELM and SVR-ELM model with performance improvement of 95.76%, 89.33% and 52.71%, respectively. The accuracy of the proposed hybrid models would be of immense significance for quick quantitative analysis in LIBS and eventually promotes wide applicability of the technique.
T.Zhang, et al., A novel approach for quantitative analysis of multi-elements in steels based on laser-induced breakdown spectroscopy (LIBS) and random forest regression (RFR), J Anal At Spectrom29 (2014), 2323–2329.
2.
T.X.Phuoc, P.Wang and D.McIntyre, Detection of rare earth elements in Powder River Basin sub-bituminous coal ash using laser-induced breakdown spectroscopy (LIBS), Fuel163 (2016), 129–132.
3.
M.A.Gondal, Y.B.Habibullah, U.Baig and L.E.Oloore, Direct spectral analysis of tea samples using 266nm UV pulsed laser-induced breakdown spectroscopy and cross validation of LIBS results with ICP-MS, Talanta152 (2016), 341–352.
4.
G.S.Senesi, Laser-Induced Breakdown Spectroscopy (LIBS) applied to terrestrial and extraterrestrial analogue geomaterials with emphasis to minerals and rocks, Earth-Science Rev139 (2014), 231–267.
5.
N.Khajehzadeh, O.Haavisto and L.Koresaar, On-stream and quantitative mineral identification of tailing slurries using LIBS technique, Miner Eng98 (2016), 101–109.
6.
S.Natarajan and H.C.Bajaj, Recovered materials from spent lithium-ion batteries (LIBs) as adsorbents for dye removal: Equilibrium, kinetics and mechanism, J Environ Chem Eng4(4) (2016), 4631–4643.
7.
C.Chen, Q.Shi, S.Wang, Q.Lin and Y.Duan, A novel method for metallic element analysis in particle samples using a laser-induced breakdown spectroscopy technique, J Anal At Spectrom31 (2016), 1527–1533.
8.
X.Chen, X.Li, S.Yang, X.Yu and A.Liu, Discrimination of lymphoma using laserinduced breakdown spectroscopy conducted on whole blood samples, Biomed Opt Express9(3) (2018), 1057–1068.
9.
J.Yang, C.Yi, J.Xu and X.Ma, Laser-induced breakdown spectroscopy quantitative analysis method via adaptive analytical line selection and relevance vector machine regression model, Spectrochim Acta - Part B At Spectrosc107 (2015), 45–55.
10.
T.Zhang, D.Xia, H.Tang, X.Yang and H.Li, Classification of steel samples by laser-induced breakdown spectroscopy and random forest, Chemom Intell Lab Syst157 (2016), 196–201.
11.
A.Safi, et al., Multivariate calibration in Laser-Induced Breakdown Spectroscopy quantitative analysis: The dangers of a 'black box' approach and how to avoid them, Spectrochim Acta Part B At Spectrosc (2018), p. #pagerange#.
12.
G.G.Arantes de Carvalho, J.Moros, D.Santos, F.J.Krug and J.J.Laserna, Direct determination of the nutrient profile in plant materials by femtosecond laser-induced breakdown spectroscopy, Anal Chim Acta876 (2015), 26–38.
13.
T.Takahashi and B.Thornton, Quantitative methods for compensation of matrix effects and self-absorption in LIBS signals of solids, Spectrochim Acta - Part B At Spectrosc138 (2017), 31–42.
14.
E.Tognoni, G.Cristoforetti, S.Legnaioli and V.Palleschi, Calibration-free laser-induced breakdown spectroscopy: State of the art, Spectrochim Acta - Part B At Spectrosc65(1) (2010), 1–14.
15.
I.B.Gornushkin, S.V.Shabanov, S.Merk, E.Tognoni and U.Panne, Effects of non-uniformity of laser induced plasma on plasma temperature and concentrations determined by the Boltzmann plot method: Implications from plasma modeling, J Anal At Spectrom25(10) (2010), 1643–1653.
16.
K.K.Herrera, E.Tognoni, I.B.Gornushkin, N.Omenetto, B.W.Smith and J.D.Winefordner, Comparative study of two standard-free approaches in laser-induced breakdown spectroscopy as applied to the quantitative analysis of aluminum alloy standards under vacuum conditions, J Anal At Spectrom24(4) (2009), 426.
17.
Q.Shi, G.Niu, Q.Lin, T.Xu, F.Li and Y.Duan, Quantitative analysis of sedimentary rocks using laser-induced breakdown spectroscopy: Comparison of support vector regression and partial least squares regression chemometric methods, J Anal At Spectrom30(12) (2015), 2384–2393.
18.
U.Thissen, M.Pepers, B.Üstiin, W.J.Melssen and L.M.C.Buydens, Comparing support vector machines to PLS for spectral regression applications, Chemom Intell Lab Syst73(2) (2004), 169–179.
19.
M.Markiewicz-Keszycka, et al., Laser-induced breakdown spectroscopy (LIBS) for food analysis: A review, Trends Food Sci Technol65 (2017), 80–93.
20.
M.Suchoňová, J.Krištof, M.Pribula, M.Veis, F.L.Tabarés and P.Veis, Analysis of LiSn alloy at several depths using LIBS, Fusion Eng Des117 (2017), 175–179.
21.
M.Burger and J.Hermann, Stark broadening measurements in plasmas produced by laser ablation of hydrogen containing compounds, Spectrochim Acta - Part B At Spectrosc122 (2016), 118–126.
22.
C.Chaleard, P.Mauchien, N.Andre, J.Uebbing, J.L.Lacour and C.Geertsen, Correction of matrix effects in quantitative elemental analysis with laser ablation optical emission spectrometry, J Anal At Spectrom12(2) (1997), 183–188.
23.
V.Lazic, et al., Corrections for variable plasma parameters in laser induced breakdown spectroscopy: Application on archeological samples, Spectrochim. Acta - Part B At Spectrosc122 (2016), 103–113.
24.
A.Ciucci, M.Corsi, V.Palleschi, S.Rastelli, A.Salvetti and E.Tognoni, New procedure for quantitative elemental analysis by laser-induced plasma spectroscopy, Appl Spectrosc53(8) (1999), 960–964.
25.
J.Dong, et al., A method for improving the accuracy of calibration-free laser-induced breakdown spectroscopy (CF-LIBS) using determined plasma temperature by genetic algorithm (GA), J Anal At Spectrom30(6) (2015), 1336–1344.
26.
M.B.Xu, et al., A single-beam-splitting technique combined with a calibration-free method for field-deployable applications using laser-induced breakdown spectroscopy, RSC Adv5(6) (2015), 4537–4546.
27.
E.Axente, et al., Accurate analysis of indium-zinc oxide thin films via laser-induced breakdown spectroscopy based on plasma modeling, J Anal At Spectrom29(3) (2014), 553.
28.
Z.Wang, C.Yan, J.Dong, T.Zhang, J.Wei and H.Li, Acidity analysis of iron ore based on calibration-free laser-induced breakdown spectroscopy (CF-LIBS) combined with a binary search algorithm (BSA), RSCAdv6(80) (2016), 76813–76823.
29.
E.Hywel Evans, C.D.Palmer and C.M.M.Smith, Atomic spectrometry update. Advances in atomic spectrometry and related techniques, J Anal At Spectrom27(6) (2012), 909.
30.
D.Bulajic, et al., A procedure for correcting self-absorption in calibration free-laser induced breakdown spectroscopy, Spectrochim Acta - Part B At Spectrosc57(2) (2002), 339–353.
31.
E.Tognoni, et al., A numerical study of expected accuracy and precision in Calibration-Free Laser-Induced Breakdown Spectroscopy in the assumption of ideal analytical plasma, Spectrochim Acta - Part B At Spectrosc62(12) (2007), 1287–1302.
32.
N.Kumar, A.Bansal, G.S.Sarma and R.K.Rawal, Chemo-metrics tools used in analytical chemistry: An overview, Talanta123 (2014), 186–199.
33.
T.O.Owolabi and M.A.Gondal, Development of hybrid extreme learning machine based chemo-metrics for precise quantitative analysis of LIBS spectra using internal reference pre-processing method, Anal Chim Acta1030(7) (2018), 33–41.
34.
G.Bin Huang, Q.Y.Zhu and C.K.Siew, Extreme learning machine: Theory and applications, Neurocomputing70(1-3) (2006), 489–501.
35.
Y.Wang, F.Cao and Y.Yuan, A study on effectiveness of extreme learning machine, Neurocomputing74(16) (2011), 2483–2490.
S.O.Olatunji, Comparison of extreme learning machines and support vector machines on premium and regular gasoline classification for arson and oil spill investigation, ASIAN J Eng Sci Technol1(1) (2010).
38.
S.O.Olatunji, A.Selamat and A.Abdulraheem, A hybrid model through the fusion of type-2 fuzzy logic systems and extreme learning machines for modelling permeability prediction, Inf Fusion16 (2014), 29–45.
I.Barman, C.-R.Kong, N.C.Dingari, R.R.Dasari and M.S.Feld, Development of robust calibration models using support vector machines for spectroscopic monitoring of blood glucose, Anal Chem82(23) (2010), 9719–9726.
41.
U.Thissen, B.Ustiin, W.J.Melssen and L.M.C.Buydens, Multivariate calibration with least-squares support vector machines, Anal Chem76(11) (2004), 3099–3105.
42.
B.Malik, K.Chaitanya and M.Benaissa, Support vector regression with digital band pass filtering for the quantitative analysis of near-infrared spectra, J Chemom28(2) (2014), 116–122.
43.
J.Peng and L.Li, Support vector regression in sum space for multivariate calibration, Chemom Intell Lab Syst130 (2014), 14–19.
44.
P.R.Filgueiras, J.C.L.Alves and R.J.Poppi, Quantification of animal fat biodiesel in soybean biodiesel and B20 diesel blends using near infrared spectroscopy and synergy interval support vector regression, Talanta119 (2014), 582–589.
45.
E.Rashedi, H.Nezamabadi-Pour and S.Saryazdi, GSA: A gravitational search algorithm, Inf Sci (Ny)179(13) (2009), 2232–2248.
46.
V.N.Vapnik, The Nature of Statistical Learning Theory, Springer-VerlagNew York, Inc, 1995.
47.
A.J.Smola, B.Sch and B.Scholkopf, A tutorial on support vector regression, Stat Comput14(3) (2004), 199–222.
48.
T.O.Owolabi, K.O.Akande and S.O.Olatunji, Estimation of surface energies of hexagonal close packed metals using computational intelligence technique, Appl Soft Comput31 (2015), 360–368.
49.
A.Majid, A.Khan, G.Javed and A.M.Mirza, Lattice constant prediction of cubic and monoclinic perovskites using neural networks and support vector regression, Comput Mater Sci50(2) (2010), 363–372.
50.
T.O.Owolabi, K.O.Akande, S.O.Olatunji, A.Alqahtani and N.Aldhafferid, Modeling of Curie temperature of man-ganite for magnetic refrigeration application using manual search and hybrid gravitational-based support vector regression, Soft Comput22(9) (2017), 3023–3032.
51.
A.A.Adewunmi, S.Ismail, T.O.Owolabi, A.S.Sultan and S.O.Olatunji, Modeling the thermal behavior of coal fl y ash based polymer gel system for water reduction in oil and gas wells, J Pet Sci Eng157 (2017), 430–440.
52.
T.O.Owolabi, K.O.Akande and S.O.Olatunji, Estimation of average surface energies of transition metal nitrides using computational intelligence technique, Soft Comput21(20) (2017), 6175–6182.
53.
T.O.Owolabi and M.A.Gondal, A hybrid intelligent scheme for estimating band gap of doped titanium dioxide semicon-ductorusing crystal lattice distortion, Comput Mater Sci137 (2017), 249–256.
54.
T.O.Owolabi, K.O.Akande, S.O.Olatunji, N.Aldhafferi and A.Alqahtani, Modeling energy band gap of doped TiO2 semiconductor using homogeneously hybridized support vector regression with gravitational search algorithm hyper- parameter optimization, AIP Adv115225 (2017), 1–13.
55.
T.O.Owolabi, L.E.Oloore, K.O.Akande and S.O.Olatunji, Modeling of magnetic cooling power of manganite-based materials using computational intelligence approach, Neural Comput Appl (2017), 1–8.
56.
T.O.Owolabi, K.O.Akande and S.O.Olatunji, Computational intelligence method of estimating solid-liquid interfacial energy of materials at their melting temperatures, J Intell Fuzzy Syst31 (2016), 519–527.
57.
T.O.Owolabi, K.O.Akande, S.O.Olatunji, A.Alqahtani and N.Aldhafferi, Incorporation of GSA in SBLLM-based neural network for enhanced estimation of magnetic ordering temperature of manganite, J Intell Fuzzy Syst33(2) (2017), 1225–1233.
58.
T.O.Owolabi, K.O.Akande and S.O.Olatunji, Development and validation of surface energies estimator (SEE) using computational intelligence technique, Comput Mater Sci101 (2015), 143–151.
59.
T.O.Owolabi, K.O.Akande, S.O.Olatunji, A.Alqahtani and N.Aldhafferi, Estimation of Curie temperature of manganite-based materials for magnetic refrigeration application using hybrid gravitational based support vector regression, AIP Adv6(10) (2016), 105009.
60.
F.-Y.Ju and W.-C.Hong, Application of seasonal SVR with chaotic gravitational search algorithm in electricity forecasting, Appl Math Model37(23) (2013), 9643–9651.
61.
D.Goswami and S.Chakraborty, Parametric optimization of ultrasonic machining process using gravitational search and fireworks algorithms, Ain Shams Eng J6(1) (2015), 315–331.
62.
Y.Mohamed Shuaib, M.Surya Kalavathi and C.Christober Asir Rajan, Optimal capacitor placement in radial distribution system using Gravitational Search Algorithm, Int J Electr Power Energy Syst64(2015) (2015), 384–397.
63.
J.Xiang, et al., A novel hybrid system for feature selection based on an improved gravitational search algorithm and k-NN method, Appl Soft Comput31(2015) (2015), 293–307.
64.
F.Y.Ju and W.C.Hong, Application of seasonal SVR with chaotic gravitational search algorithm in electricity forecasting, Appl Math Model37(23) (2013), 9643–9651.
65.
X.Han, et al., Feature subset selection by gravitational search algorithm optimization, Inf Sci (Ny)281 (2014), 128–146.
66.
M.A.Gondal, Y.B.Habibullah, L.E.Oloore and M.A.Iqbal, Determination of carcinogenic fluorine in cigarettes using pulsed UV laser-induced breakdown spectroscopy, Appl Opt54(17) (2015), 5560.
67.
M.A.Gondal, M.A.Shemis, A.A.I.C.Khalil, M.M.Nasr and B.Gondal, Laser produced plasma diagnosis of carcinogenic heavy metals in gallstones, J Anal At Spectrom31(2) (2016), 506–514.
68.
M.A.Gondal, M.A.Dastageer, F.F.Al-Adel, A.A.Naqvi and Y.B.Habibullah, Detection of highly toxic elements (lead and chromium) in commercially available eyeliner (kohl) using laser induced break down spectroscopy, Opt Laser Technol75 (2015), 99–104.
L.Sun and H.Yu, Correction of self-absorption effect in calibration-free laser-induced breakdown spectroscopy by an internal reference method, Talanta79(2) (2009), 388–395.
