1 |
Comparação entre maquinas de vetores de suporte por minimos quadrados (LS-SVM) e metodos lineares para transferencia de calibração / Comparison between Least-Square support vector machines and linear methods for calibration transferMaretto, Danilo Althmann 27 February 2007 (has links)
Orientador: Ronei Jesus Popi / Dissertação (mestrado) - Universidade Estadual de Campinas, Instituto de Quimica / Made available in DSpace on 2018-08-10T12:11:57Z (GMT). No. of bitstreams: 1
Maretto_DaniloAlthmann_M.pdf: 2490749 bytes, checksum: 2efe474693fb82f366c9c3c06974de92 (MD5)
Previous issue date: 2007 / Resumo: Este trabalho teve como objetivo comparar os métodos lineares de calibração "mínimos quadrados parciais" (PLS) e "padronização direta por partes" (PDS) e um método não-linear "máquina de vetores de suporte por mínimos quadrados" (LS-SVM) na transferência de calibração para modelos de calibração multivariada onde se determinou porcentagem de etanol em cachaça a cinco temperaturas diferentes e para modelos onde se determinou a porcentagem de proteína e gordura em ração para cães em três diferentes granulometrias através de espectroscopia na região do infravermelho próximo. Foram preparadas 50 amostras de cachaça entre 20,86 e 46,48% v/v através de diluição com água Milli-Q ou adição de etanol P.A. (Merck) à cachaça original. A porcentagem alcoólica foi obtida através de um densímetro digital Anton Paar DMA 4500 e os espectros a 5 temperaturas diferentes (15, 20, 25, 30 e 35ºC) foram obtidos na faixa de 850 a 1050 nm em um equipamento Agilent 8453. Um total de 38 amostras de ração moídas foi fornecido pela empresa Nutron Alimentos Ltda a qual realizou testes padrão para determinação de porcentagem de proteína e gordura nas mesmas. As amostras foram então peneiradas, sendo divididas em 3 grupos com tamanhos de partícula diferentes. Os espectros foram obtidos para todos os grupos de partículas de todas as amostras na faixa de 1000 a 2400 nm em um equipamento Varian Cary 5G. Foram feitas quatro propostas diferentes para se fazer a transferência de calibração para cada uma das três aplicações (determinação do teor de etanol em cachaça, e do teor de proteína e gordura em ração). Na grande maioria delas o LS-SVM foi quem apresentou modelos mais bem ajustados / Abstract: The aim of this work was to compare the linear methods of calibration ¿Partial Least Squares¿ (PLS) and ¿Piece-wise Direct Standardization¿ (PDS) and a nonlinear method ¿Least-Squares Support Vector Machines¿ (LS-SVM) on calibration transfer to multivariate calibration models to the determination of alcoholic grade in cachaça in five different temperatures and to determination of protein and fat content in dog food in three different particule sizes by using near infrared spectroscopy. It has been prepared 50 cachaça samples between 20.86 and 46.48% v/v through dilution with Milli-Q water or adding etanol P.A.(Merck) to the original cachaça. The alcoholic grade has been obtained through a Anton Paar DMA 4500 digital densimeter and the spectra in five different temperatures (15, 20, 25, 30 and 35ºC) has been obtained between 850 and 1050 nm in a Agilent 8453 equipament. The 38 grinded dog food samples were supplied by Nutron Alimentos Ltda wich has realized the standard tests to determination of protein and fat mass porcentage in them. The samples have been bolted, been divided in three groups with different particle sizes. The spectra have been obtained to all the particle groups of all samples between 100 and 24000 nm in a Varian Cary 5G equipament. It has been done four different proposals to do the calibration transfer to each one of the three applications (etanol grade in cachaça, and protein and fat in dog food). In the most of them LS-SVM has gotten better adjusted models / Mestrado / Quimica Analitica / Mestre em Química
|
2 |
Application of Least Squares Support Vector Machines in Image CodingChen, Pao-jung 19 July 2006 (has links)
In this thesis, least squares support vector machine for regression (LS-SVR) is applied to image coding. First, we propose five simple algorithms for solving LS-SVR. For linear regression, two simple Widrow-Hoff-like algorithms, in primal form and in dual form, are proposed for LS-SVR problems. The dual form of the algorithm is then generalized to kernel-based nonlinear LS-SVR. The elegant and powerful two-parameter sequential minimization optimization (2PSMO) and three-parameter sequential minimization optimization (3PSMO) algorithms are provided in detail. A predictive function obtained from LS-SVR is utilized to approximate the gray levels of the image. After pruning, only a subset of training data called support vectors is saved. Experimental results on seven image blocks show that the LS-SVR with Gaussian kernel is more appropriate than that with Mahalanobis kernel with a covariance matrix. Two-layer LS-SVR is proposed to choose the machine parameters of the LS-SVR. Before training outer LS-SVR, feature extraction is used to reduce the input dimensionality. Experimental results on three whole images show that the results with two-layer LS-SVR after reducing dimensionality are better than those with two-layer LS-SVR without reducing dimensionality in PSNR for Lena and Baboon images and they are almost the same in PSNR for F16 image.
|
3 |
TOA Wireless Location Algorithm with NLOS Mitigation Based on LS-SVM in UWB SystemsLin, Chien-hung 29 July 2008 (has links)
One of the major problems encountered in wireless location is the effect caused by non-line of sight (NLOS) propagation. When the direct path from the mobile station (MS) to base stations (BSs) is blocked by obstacles or buildings, the signal arrival times will delay. That will make the signal measurements include an error due to the excess path propagation. If we use the NLOS signal measurements for localization, that will make the system localization performance reduce greatly. In the thesis, a time-of-arrival (TOA) based location system with NLOS mitigation algorithm is proposed. The proposed method uses least squares-support vector machine (LS-SVM) with optimal parameters selection by particle swarm optimization (PSO) for establishing regression model, which is used in the estimation of propagation distances and reduction of the NLOS propagation errors. By using a weighted objective function, the estimation results of the distances are combined with suitable weight factors, which are derived from the differences between the estimated measurements and the measured measurements. By applying the optimality of the weighted objection function, the method is capable of mitigating the NLOS effects and reducing the propagation range errors. Computer simulation results in ultra-wideband (UWB) environments show that the proposed NLOS mitigation algorithm can reduce the mean and variance of the NLOS measurements efficiently. The proposed method outperforms other methods in improving localization accuracy under different NLOS conditions.
|
4 |
Analysis, Diagnosis and Design for System-level Signal and Power Integrity in Chip-package-systemsAmbasana, Nikita January 2017 (has links) (PDF)
The Internet of Things (IoT) has ushered in an age where low-power sensors generate data which are communicated to a back-end cloud for massive data computation tasks. From the hardware perspective this implies co-existence of several power-efficient sub-systems working harmoniously at the sensor nodes capable of communication and high-speed processors in the cloud back-end. The package-board system-level design plays a crucial role in determining the performance of such low-power sensors and high-speed computing and communication systems. Although there exist several commercial solutions for electromagnetic and circuit analysis and verification, problem diagnosis and design tools are lacking leading to longer design cycles and non-optimal system designs. This work aims at developing methodologies for faster analysis, sensitivity based diagnosis and multi-objective design towards signal integrity and power integrity of such package-board system layouts.
The first part of this work aims at developing a methodology to enable faster and more exhaustive design space analysis. Electromagnetic analysis of packages and boards can be performed in time domain, resulting in metrics like eye-height/width and in frequency domain resulting in metrics like s-parameters and z-parameters. The generation of eye-height/width at higher bit error rates require longer bit sequences in time domain circuit simulation, which is compute-time intensive. This work explores learning based modelling techniques that rapidly map relevant frequency domain metrics like differential insertion-loss and cross-talk, to eye-height/width therefore facilitating a full-factorial design space sweep. Numerical results performed with artificial neural network as well as least square support vector machine on SATA 3.0 and PCIe Gen 3 interfaces generate less than 2% average error with order of magnitude speed-up in eye-height/width computation.
Accurate power distribution network design is crucial for low-power sensors as well as a cloud sever boards that require multiple power level supplies. Achieving target power-ground noise levels for low power complex power distribution networks require several design and analysis cycles. Although various classes of analysis tools, 2.5D and 3D, are commercially available, the presence of design tools is limited. In the second part of the thesis, a frequency domain mesh-based sensitivity formulation for DC and AC impedance (z-parameters) is proposed. This formulation enables diagnosis of layout for maximum impact in achieving target specifications. This sensitivity information is also used for linear approximation of impedance profile updates for small mesh variations, enabling faster analysis.
To enable designing of power delivery networks for achieving target impedance, a mesh-based decoupling capacitor sensitivity formulation is presented. Such an analytical gradient is used in gradient based optimization techniques to achieve an optimal set of decoupling capacitors with appropriate values and placement information in package/boards, for a given target impedance profile. Gradient based techniques are far less expensive than the state of the art evolutionary optimization techniques used presently for a decoupling capacitor network design. In the last part of this work, the functional similarities between package-board design and radio frequency imaging are explored. Qualitative inverse-solution methods common to the radio frequency imaging community, like Tikhonov regularization and Landweber methods are applied to solve multi-objective, multi-variable signal integrity package design problems. Consequently a novel Hierarchical Search Linear Back Projection algorithm is developed for an efficient solution in the design space using piecewise linear approximations. The presented algorithm is demonstrated to converge to the desired signal integrity specifications with minimum full wave 3D solve iterations.
|
Page generated in 0.0127 seconds