Supervised Gaussian Process Latent Variable Model for Dimensionality Reduction

The Gaussian process latent variable model (GP-LVM) has been identified to be an effective probabilistic approach for dimensionality reduction because it can obtain a low-dimensional manifold of a data set in an unsupervised fashion. Consequently, the GP-LVM is insufficient for supervised learning tasks (e. g., classification and regression) because it ignores the class label information for dimensionality reduction. In this paper, a supervised GP-LVM is developed for supervised learning tasks, and the maximum a posteriori algorithm is introduced to estimate positions of all samples in the latent variable space. We present experimental evidences suggesting that the supervised GP-LVM is able to use the class label information effectively, and thus, it outperforms the GP-LVM and the discriminative extension of the GP-LVM consistently. The comparison with some supervised classification methods, such as Gaussian process classification and support vector machines, is also given to illustrate the advantage of the proposed method.

Peripheries of molecular projection in three-dimensional space and studies of quantitative structure-activity relationships

A new index, i.e., the periphery representation of the projection of a molecule from 3D space to a 2D plane is described. The results, correlation with toxicity of substituted nitrobenzenes, obtained by using periphery descriptors are much better than that obtained by using the areas (i.e., shadows) of projections of the compounds. Even better results were achieved by using the combination of periphery descriptors and the projections areas as well as the indicated variable K reflecting the action of group NO position on the benzene ring.

A Two-Tiered On-Line Server-Side Bandwidth Reservation Framework for the Real-Time Delivery of Multiple Video Streams

The advent of virtualization and cloud computing technologies necessitates the development of effective mechanisms for the estimation and reservation of resources needed by content providers to deliver large numbers of video-on-demand (VOD) streams through the cloud. Unfortunately, capacity planning for the QoS-constrained delivery of a large number of VOD streams is inherently difficult as VBR encoding schemes exhibit significant bandwidth variability. In this paper, we present a novel resource management scheme to make such allocation decisions using a mixture of per-stream reservations and an aggregate reservation, shared across all streams to accommodate peak demands. The shared reservation provides capacity slack that enables statistical multiplexing of peak rates, while assuring analytically bounded frame-drop probabilities, which can be adjusted by trading off buffer space (and consequently delay) and bandwidth. Our two-tiered bandwidth allocation scheme enables the delivery of any set of streams with less bandwidth (or equivalently with higher link utilization) than state-of-the-art deterministic smoothing approaches. The algorithm underlying our proposed frame-work uses three per-stream parameters and is linear in the number of servers, making it particularly well suited for use in an on-line setting. We present results from extensive trace-driven simulations, which confirm the efficiency of our scheme especially for small buffer sizes and delay bounds, and which underscore the significant realizable bandwidth savings, typically yielding losses that are an order of magnitude or more below our analytically derived bounds.

Articulated Pose Estimation in a Learned Smooth Space of Feasible Solutions

A learning based framework is proposed for estimating human body pose from a single image. Given a differentiable function that maps from pose space to image feature space, the goal is to invert the process: estimate the pose given only image features. The inversion is an ill-posed problem as the inverse mapping is a one to many process. Hence multiple solutions exist, and it is desirable to restrict the solution space to a smaller subset of feasible solutions. For example, not all human body poses are feasible due to anthropometric constraints. Since the space of feasible solutions may not admit a closed form description, the proposed framework seeks to exploit machine learning techniques to learn an approximation that is smoothly parameterized over such a space. One such technique is Gaussian Process Latent Variable Modelling. Scaled conjugate gradient is then used find the best matching pose in the space of feasible solutions when given an input image. The formulation allows easy incorporation of various constraints, e.g. temporal consistency and anthropometric constraints. The performance of the proposed approach is evaluated in the task of upper-body pose estimation from silhouettes and compared with the Specialized Mapping Architecture. The estimation accuracy of the Specialized Mapping Architecture is at least one standard deviation worse than the proposed approach in the experiments with synthetic data. In experiments with real video of humans performing gestures, the proposed approach produces qualitatively better estimation results.

Tracking Human Body Pose on a Learned Smooth Space

Particle filtering is a popular method used in systems for tracking human body pose in video. One key difficulty in using particle filtering is caused by the curse of dimensionality: generally a very large number of particles is required to adequately approximate the underlying pose distribution in a high-dimensional state space. Although the number of degrees of freedom in the human body is quite large, in reality, the subset of allowable configurations in state space is generally restricted by human biomechanics, and the trajectories in this allowable subspace tend to be smooth. Therefore, a framework is proposed to learn a low-dimensional representation of the high-dimensional human poses state space. This mapping can be learned using a Gaussian Process Latent Variable Model (GPLVM) framework. One important advantage of the GPLVM framework is that both the mapping to, and mapping from the embedded space are smooth; this facilitates sampling in the low-dimensional space, and samples generated in the low-dimensional embedded space are easily mapped back into the original highdimensional space. Moreover, human body poses that are similar in the original space tend to be mapped close to each other in the embedded space; this property can be exploited when sampling in the embedded space. The proposed framework is tested in tracking 2D human body pose using a Scaled Prismatic Model. Experiments on real life video sequences demonstrate the strength of the approach. In comparison with the Multiple Hypothesis Tracking and the standard Condensation algorithm, the proposed algorithm is able to maintain tracking reliably throughout the long test sequences. It also handles singularity and self occlusion robustly.

A Neural Network Architecture for Autonomous Learning, Recognition, and Prediction in a Nonstationary World

In a constantly changing world, humans are adapted to alternate routinely between attending to familiar objects and testing hypotheses about novel ones. We can rapidly learn to recognize and narne novel objects without unselectively disrupting our memories of familiar ones. We can notice fine details that differentiate nearly identical objects and generalize across broad classes of dissimilar objects. This chapter describes a class of self-organizing neural network architectures--called ARTMAP-- that are capable of fast, yet stable, on-line recognition learning, hypothesis testing, and naming in response to an arbitrary stream of input patterns (Carpenter, Grossberg, Markuzon, Reynolds, and Rosen, 1992; Carpenter, Grossberg, and Reynolds, 1991). The intrinsic stability of ARTMAP allows the system to learn incrementally for an unlimited period of time. System stability properties can be traced to the structure of its learned memories, which encode clusters of attended features into its recognition categories, rather than slow averages of category inputs. The level of detail in the learned attentional focus is determined moment-by-moment, depending on predictive success: an error due to over-generalization automatically focuses attention on additional input details enough of which are learned in a new recognition category so that the predictive error will not be repeated. An ARTMAP system creates an evolving map between a variable number of learned categories that compress one feature space (e.g., visual features) to learned categories of another feature space (e.g., auditory features). Input vectors can be either binary or analog. Computational properties of the networks enable them to perform significantly better in benchmark studies than alternative machine learning, genetic algorithm, or neural network models. Some of the critical problems that challenge and constrain any such autonomous learning system will next be illustrated. Design principles that work together to solve these problems are then outlined. These principles are realized in the ARTMAP architecture, which is specified as an algorithm. Finally, ARTMAP dynamics are illustrated by means of a series of benchmark simulations.

Novel smart modules for imaging, communications, and displays

This dissertation proposes and demonstrates novel smart modules to solve challenging problems in the areas of imaging, communications, and displays. The smartness of the modules is due to their ability to be able to adapt to changes in operating environment and application using programmable devices, specifically, electronically variable focus lenses (ECVFLs) and digital micromirror devices (DMD). The proposed modules include imagers for laser characterization and general purpose imaging which smartly adapt to changes in irradiance, optical wireless communication systems which can adapt to the number of users and to changes in link length, and a smart laser projection display that smartly adjust the pixel size to achieve a high resolution projected image at each screen distance. The first part of the dissertation starts with the proposal of using an ECVFL to create a novel multimode laser beam characterizer for coherent light. This laser beam characterizer uses the ECVFL and a DMD so that no mechanical motion of optical components along the optical axis is required. This reduces the mechanical motion overhead that traditional laser beam characterizers have, making this laser beam characterizer more accurate and reliable. The smart laser beam characterizer is able to account for irradiance fluctuations in the source. Using image processing, the important parameters that describe multimode laser beam propagation have been successfully extracted for a multi-mode laser test source. Specifically, the laser beam analysis parameters measured are the M2 parameter, w0 the minimum beam waist, and zR the Rayleigh range. Next a general purpose incoherent light imager that has a high dynamic range (>100 dB) and automatically adjusts for variations in irradiance in the scene is proposed. Then a data efficient image sensor is demonstrated. The idea of this smart image sensor is to reduce the bandwidth needed for transmitting data from the sensor by only sending the information which is required for the specific application while discarding the unnecessary data. In this case, the imager demonstrated sends only information regarding the boundaries of objects in the image so that after transmission to a remote image viewing location, these boundaries can be used to map out objects in the original image. The second part of the dissertation proposes and demonstrates smart optical communications systems using ECVFLs. This starts with the proposal and demonstration of a zero propagation loss optical wireless link using visible light with experiments covering a 1 to 4 m range. By adjusting the focal length of the ECVFLs for this directed line-of-sight link (LOS) the laser beam propagation parameters are adjusted such that the maximum amount of transmitted optical power is captured by the receiver for each link length. This power budget saving enables a longer achievable link range, a better SNR/BER, or higher power efficiency since more received power means the transmitted power can be reduced. Afterwards, a smart dual mode optical wireless link is proposed and demonstrated using a laser and LED coupled to the ECVFL to provide for the first time features of high bandwidths and wide beam coverage. This optical wireless link combines the capabilities of smart directed LOS link from the previous section with a diffuse optical wireless link, thus achieving high data rates and robustness to blocking. The proposed smart system can switch from LOS mode to Diffuse mode when blocking occurs or operate in both modes simultaneously to accommodate multiple users and operate a high speed link if one of the users requires extra bandwidth. The last part of this section presents the design of fibre optic and free-space optical switches which use ECVFLs to deflect the beams to achieve switching operation. These switching modules can be used in the proposed optical wireless indoor network. The final section of the thesis presents a novel smart laser scanning display. The ECVFL is used to create the smallest beam spot size possible for the system designed at the distance of the screen. The smart laser scanning display increases the spatial resoluti on of the display for any given distance. A basic smart display operation has been tested for red light and a 4X improvement in pixel resolution for the image has been demonstrated.

Bayesian variable selection in structured high-dimensional covariate spaces with applications in genomics

We consider the problem of variable selection in regression modeling in high-dimensional spaces where there is known structure among the covariates. This is an unconventional variable selection problem for two reasons: (1) The dimension of the covariate space is comparable, and often much larger, than the number of subjects in the study, and (2) the covariate space is highly structured, and in some cases it is desirable to incorporate this structural information in to the model building process. We approach this problem through the Bayesian variable selection framework, where we assume that the covariates lie on an undirected graph and formulate an Ising prior on the model space for incorporating structural information. Certain computational and statistical problems arise that are unique to such high-dimensional, structured settings, the most interesting being the phenomenon of phase transitions. We propose theoretical and computational schemes to mitigate these problems. We illustrate our methods on two different graph structures: the linear chain and the regular graph of degree k. Finally, we use our methods to study a specific application in genomics: the modeling of transcription factor binding sites in DNA sequences. © 2010 American Statistical Association.

Enhancement of optically thick to thin line intensities in solar and stellar coronal plasmas through radiative transfer effects: an angularly resolved study.

An analysis of radiative transfer effects present in the Fe XV ion stage of solar and stellar coronal plasmas provides a general explanation of line radiation intensity enhancement above the optically thin limit. Full linearization radiation transfer is compared with the escape factor method and found to be in good agreement at the lower column densities. An angular study of the enhancement shows that symmetry factors are of great importance. This gives a possible reason for the indeterminate status of opacity in relation to coronal lines of distant stellar sources, where only emission integrated across the whole surface is detected.

Energy levels and transition probabilities for nitrogen-like Fe xx

Energies of the 700 lowest levels in Fe XX have been obtained using the multiconfiguration Dirac-Fock method. Configuration interaction method on the basis set of transformed radial orbitals with variable parameters taking into account relativistic corrections in the Breit-Pauli approximation was used to crosscheck our presented results. Transition probabilities, oscillator and line strengths are presented for electric dipole (E1), electric quadrupole (E2) and magnetic dipole (M1) transitions among these levels. The total radiative transition probabilities from each level are also provided. Results are compared with data compiled by NIST and with other theoretical work.

Emission-line ratios for [N II] in gaseous nebulae and a comparison between theory and observation

R-matrix calculations of electron impact excitation rates among the 2s(2)2p(2) P-3, D-1, S-1, and 2s2p(3) S-5 levels of N II are presented. These results are used in conjunction with other recent calculations of electron impact excitation rates and Einstein A-coefficients for N II to derive the emission-line ratio: ratio diagrams and where (R-1, R-2) (R-1, R-3), where R-1 = I(5756.2 Angstrom)/I(6549.9 + 6585.2 Angstrom), R-2 = I(2143.5 Angstrom)/I(6549.9 + 6585.2 Angstrom), and R-3 = I(2139.7 Angstrom)/I(6549.9 + 658.2 Angstrom), for a range of electron temperatures (T-e = 5000-20,000 K) and electron densities (N-e = 10(2)-10(7) cm(-3)) appropriate to gaseous nebulae. These diagrams should, in principle, allow the simultaneous determination of T-e and N-e from measurements of the [N II] lines in a spectrum. Plasma parameters deduced for a sample of gaseous nebulae, using observational data obtained from ground-based telescopes plus the International Ultraviolet Explorer and Hubble Space Telescope satellites, are found to show generally excellent internal consistency and to be in good agreement with the values of T-e and N-e estimated from other line ratios. These results provide observational support for the accuracy of the theoretical ratios and hence the atomic data adopted in their derivation. Theoretical ratios are also presented for the infrared line pair R-4 = I(122 mum)/I(205 mum), and the usefulness of R-4 as an electron density diagnostic is briefly discussed.

A comparison of theoretical Si VIII emission line ratios with observations from SERTS

Recent R-matrix calculations of electron impact excitation rates in N-like Si VIII are used to derive theoretical emission line intensity ratios involving 2s(2)2p(3)-2s2p(4) transitions in the 216 -320 Angstrom wavelength range. A comparison of these with an extensive dataset of solar active region, quiet- Sun, sub-flare and off-limb observations, obtained during rocket flights of the Solar EUV Research Telescope and Spectrograph (SERTS), indicates that the ratio R-1 = I(216.94 Angstrom)/I(319.84 Angstrom) may provide a usable electron density diagnostic for coronal plasmas. The ratio involves two lines of comparable intensity, and varies by a factor of about 5 over the useful density range of 10(8)-10(11) cm(-3). However R-2 = I(276.85 Angstrom)/I(319.84 Angstrom) and R-3 = I(277.05 Angstrom)/I(319.84 Angstrom) show very poor agreement between theory and observation, due to the severe blending of the 276.85 and 277.05 Angstrom lines with Si VII and Mg VII transitions, respectively, making the ratios unsuitable as density diagnostics. The 314.35 Angstrom feature of Si VIII also appears to be blended, with the other species contributing around 20% to the total line flux.

An analytic geometry-variant approach to line ratio enhancement above the optically thin limit

We describe a simple theoretical model to investigate the anomalous effects of opacity on spectral line ratios, as previously studied in elements such as Fe XV and Fe XVII. The model developed is general: it is not specific to a particular atomic system, thus giving applicability to a number of coronal and chromospheric plasmas; furthermore, it may be applied to a variety of astrophysically relevant geometries. The analysis is underpinned by geometrical arguments, and we outline a technique for it to be used as a tool for the explicit diagnosis of plasma geometry in distant astrophysical objects.

Electron densities in the coronae of the Sun and Procyon from extreme-ultraviolet emission line ratios in Fe XI

New R-matrix calculations of electron impact excitation rates for Fe XI are used to determine theoretical emission line ratios applicable to solar and stellar coronal observations. These are subsequently compared to solar spectra of the quiet Sun and an active region made by the Solar EUV Rocket Telescope and Spectrograph (SERTS-95), as well as Skylab observations of two flares. Line blending is identified, and electron densities of 10(9.3), 10(9.7), greater than or equal to 10(10.8), and greater than or equal to 10(11.3) cm(-3) are found for the quiet Sun, active region, and the two flares, respectively. Observations of the F5 IV-V star Procyon, made with the Extreme Ultraviolet Explorer (EUVE) satellite, are compared and contrasted with the solar observations. It is confirmed that Procyon's average coronal conditions are very similar to those seen in the quiet Sun, with N-e = 10(9.4) cm(-3). In addition, although the quiet Sun is the closest solar analog to Procyon, we conclude that Procyon's coronal temperatures are slightly hotter than solar. A filling factor of 25(-12)(+38)% was derived for the corona of Procyon.