Fast identification algorithms for Gaussian process model

A class identification algorithms is introduced for Gaussian process(GP)models.The fundamental approach is to propose a new kernel function which leads to a covariance matrix with low rank,a property that is consequently exploited for computational efficiency for both model parameter estimation and model predictions.The objective of either maximizing the marginal likelihood or the Kullback–Leibler (K–L) divergence between the estimated output probability density function(pdf)and the true pdf has been used as respective cost functions.For each cost function,an efficient coordinate descent algorithm is proposed to estimate the kernel parameters using a one dimensional derivative free search, and noise variance using a fast gradient descent algorithm. Numerical examples are included to demonstrate the effectiveness of the new identification approaches.

Optimization algorithms in FMRF model-based segmentation for LIDAR data and co-registered bands

In this paper, a fuzzy Markov random field (FMRF) model is used to segment land-objects into free, grass, building, and road regions by fusing remotely, sensed LIDAR data and co-registered color bands, i.e. scanned aerial color (RGB) photo and near infra-red (NIR) photo. An FMRF model is defined as a Markov random field (MRF) model in a fuzzy domain. Three optimization algorithms in the FMRF model, i.e. Lagrange multiplier (LM), iterated conditional mode (ICM), and simulated annealing (SA), are compared with respect to the computational cost and segmentation accuracy. The results have shown that the FMRF model-based ICM algorithm balances the computational cost and segmentation accuracy in land-cover segmentation from LIDAR data and co-registered bands.

Electron spin resonance study of puff-resolved free radical formation in mainstream cigarette smoke

Puff-by-puff resolved gas phase free radicals were measured in mainstream smoke from Kentucky 2R4F reference cigarettes using ESR spectroscopy. Three spin-trapping reagents were evaluated: PBN, DMPO and DEPMPO. Two procedures were used to collect gas phase smoke on a puff-resolved basis: i) the accumulative mode, in which all the gas phase smoke up to a particular puff was bubbled into the trap (i.e., the 5th puff corresponded to the total smoke from the 1st to 5th puffs). In this case, after a specified puff, an aliquot of the spin trap was taken and analysed; or, ii) the individual mode, in which the spin trap was analysed and then replaced after each puff. Spin concentrations were determined by double-integration of the first derivative of the ESR signal. This was compared with the integrals of known standards using the TEMPO free radical. The radicals trapped with PBN were mainly carbon-centred, whilst the oxygen-centred radicals were identified with DMPO and DEPMPO. With each spin trap, the puff-resolved radical concentrations showed a characteristic pattern as a function of the puff number. Based on the spin concentrations, the DMPO and DEPMPO spin traps showed better trapping efficiencies than PBN. The implication for gas phase free radical analysis is that a range of different spin traps should be used to probe complex free radical reactions in cigarette smoke.