ridm@nrct.go.th   ระบบคลังข้อมูลงานวิจัยไทย   รายการโปรดที่คุณเลือกไว้

Intelligent methods for solving inverse problems of backscattering spectra with noise : a comparison between neural networks and simulated annealing

หน่วยงาน Central Queensland University, Australia

รายละเอียด

ชื่อเรื่อง : Intelligent methods for solving inverse problems of backscattering spectra with noise : a comparison between neural networks and simulated annealing
นักวิจัย : Li, Michael M. , Guo, Wanwu. , Verma, Brijesh. , Tickle, Kevin. , O'Connor, John.
คำค้น : Simulated annealing (Mathematics) , Neural networks (Computer science) , Inverse problems (Differential equations) , Artificial intelligence. , Applied research. , 890205 Information Processing Services (incl. Data Entry and Capture) , 080108 Neural, Evolutionary and Fuzzy Computation. , 080199 Artificial Intelligence and Image Processing not elsewhere classified. , 080110 Simulation and Modelling. , Inverse problems -- Neural networks -- Simulated annealing
หน่วยงาน : Central Queensland University, Australia
ผู้ร่วมงาน : -
ปีพิมพ์ : 2552
อ้างอิง : http://hdl.cqu.edu.au/10018/38255 , cqu:5018
ที่มา : Li, M, Guo, W, Verma, B, Tickle, K & O'Connor, J 2009, 'Intelligent methods for solving inverse problems of backscattering spectra with noise: A comparison between neural networks and simulated annealing', Neural Computing & Applications, Vol 18, No. 5, 2009, pp.423-430. http://dx.doi.org/10.1007/s00521-008-0219-x (viewed 11/11/09)
ความเชี่ยวชาญ : -
ความสัมพันธ์ : Neural computing and applications. London. : Springer, 2009. Vol. 18, no. 5 (2009), p. 423-430 8 pages Refereed 0941-0643 1433-3058 (online) , ACQUIRE [electronic resource] : Central Queensland University Institutional Repository.
ขอบเขตของเนื้อหา : -
บทคัดย่อ/คำอธิบาย :

This paper investigates two different intelligent techniques - the neural network (NN) method and the simulated annealing (SA) algorithm for solving the inverse problem of Rutherford Backscattering (RBS) with noisy data. The RBS inverse problem is to determine the sample structure information from measured spectra, which can be defined as either a function approximation or a non-linear optimization problem. Early studies emphasized on numerical methods and empirical fitting. In this work, we have applied intelligent techniques and compared their performance and effectiveness for spectral data analysis by solving the inverse problem. Since each RBS spectrum may contain up to 512 data points, principal component analysis is used to make the feature extraction so as to ease the complexity of constructing the network. The innovative aspects of our work include introducing dimensionality reduction and noise modeling. Experiments on RBS spectra from SiGe thin films on a silicon substrate show that the SA is more accurate but the NN is faster, though both methods produce satisfactory results. Both methods are resilient to 10% Poisson noise in the input. These new findings indicate that in RBS data analysis the NN approach should be preferred when fast processing is required; whereas the SA method becomes the first choice should the analysis accuracy be targeted.

บรรณานุกรม :
Li, Michael M. , Guo, Wanwu. , Verma, Brijesh. , Tickle, Kevin. , O'Connor, John. . (2552). Intelligent methods for solving inverse problems of backscattering spectra with noise : a comparison between neural networks and simulated annealing.
    กรุงเทพมหานคร : Central Queensland University, Australia.
Li, Michael M. , Guo, Wanwu. , Verma, Brijesh. , Tickle, Kevin. , O'Connor, John. . 2552. "Intelligent methods for solving inverse problems of backscattering spectra with noise : a comparison between neural networks and simulated annealing".
    กรุงเทพมหานคร : Central Queensland University, Australia.
Li, Michael M. , Guo, Wanwu. , Verma, Brijesh. , Tickle, Kevin. , O'Connor, John. . "Intelligent methods for solving inverse problems of backscattering spectra with noise : a comparison between neural networks and simulated annealing."
    กรุงเทพมหานคร : Central Queensland University, Australia, 2552. Print.
Li, Michael M. , Guo, Wanwu. , Verma, Brijesh. , Tickle, Kevin. , O'Connor, John. . Intelligent methods for solving inverse problems of backscattering spectra with noise : a comparison between neural networks and simulated annealing. กรุงเทพมหานคร : Central Queensland University, Australia; 2552.