Application of BP neural networks in non-linearity correction of optical tweezers

Abstract

The back-propagation (BP) neural network is proposed to correct nonlinearity and optimize the force measurement and calibration of an optical tweezer system. Considering the low convergence rate of the BP algorithm, the Levenberg-Marquardt (LM) algorithm is used to improve the BP network. The proposed method is experimentally studied for force calibration in a typical optical tweezer system using hydromechanics. The result shows that with the nonlinear correction using BP networks, the range of force measurement of an optical tweezer system is enlarged by 30% and the precision is also improved compared with the polynomial fitting method. It is demonstrated that nonlinear correction by the neural network method effectively improves the performance of optical tweezers without adding or changing the measuring system.

References

1. Brouhard G J, Schek H T, Hunt A J, et al.. Advanced optical tweezers for the study of cellularand molecular biomechanics. IEEE Transactionson Biomedical Engineering. 2003, 50(1): 121–125. doi:10.1109/TBME.2002.805463
2. Huang C C, Wang C F, Mehta D S, et al.. Optical tweezers as sub-pico-newton force transducers. Optics Communications, 2001, 195(1–4): 41–48. doi:10.1016/S0030-4018(01)01329-3
3. Xu S H, Li Y M, Lou L R . Systematical study of the trapping forces of opticaltweezers formed by different types of optical ring beams. Chinese Physics, 2006, 15(6): 1391–1397. doi:10.1088/1009-1963/15/6/044
4. Merenda F, Boer G, Rohner J, et al.. Escape trajectories of single-beam opticallytrapped micro-particles in a transverse fluid flow. Optics Express, 2006, 14(4): 1685–1699. doi:10.1364/OE.14.001685
5. Greulich K O . Micromanipulation by light in biology and medicine. Berlin: Birkhauser Verlag, 1999 : 90–96
6. Ranaweera A, Bamieh B . Modeling, identification,and control of a spherical particle trapped in an optical tweezer. International Journal of Robust and Nonlinear Control, 2004, 00: 1–19
7. Ranaweera A, Bamieh B, Teel A R . Nonlinear stabilization of a spherical particle trappedin an optical tweezer. In: Proceedingsof the 42nd IEEE Conference on Decision and Control, 2003, 4: 3431–3436
8. Hagan M T, Demuth H B, Beale M H . Neural Network Design (in Chinese, trans. Dai Kui). Beijing: China Machine Press, 2002, 227–255
9. Tian S P, Zhao Y, Wei H Y, et al.. Nonlinear correction of sensors based on neuralnetwork model. Optics and Precision Engineering, 2006, 14(5): 896–902
10. Shi Z L, Kang J, Sun R . BP NN-based method for lens distortion correction oflarge-field imaging. Optics and PrecisionEngineering, 2005, 13(3): 348–353 (in Chinese)
11. Chen H T, Li Y M, Lou L R, et al.. Detection of nanometer displacement in optical-tweezersand its related measuring errors. ChineseJournal of Lasers, 2004, 31(6): 729–734 (in Chinese)
12. Huisstede J H G, van der Werg K O, Bennink M L et al.. Force detection inoptical tweezers using backscattered light. Optics Express, 2005, 13(4): 1113–1123. doi:10.1364/OPEX.13.001113