999 resultados para Bayesian fusion
Resumo:
CCTV (Closed-Circuit TeleVision) systems are broadly deployed in the present world. To ensure in-time reaction for intelligent surveillance, it is a fundamental task for real-world applications to determine the gender of people of interest. However, normal video algorithms for gender profiling (usually face profiling) have three drawbacks. First, the profiling result is always uncertain. Second, the profiling result is not stable. The degree of certainty usually varies over time, sometimes even to the extent that a male is classified as a female, and vice versa. Third, for a robust profiling result in cases that a person’s face is not visible, other features, such as body shape, are required. These algorithms may provide different recognition results - at the very least, they will provide different degrees of certainties. To overcome these problems, in this paper, we introduce an Dempster-Shafer (DS) evidential approach that makes use of profiling results from multiple algorithms over a period of time, in particular, Denoeux’s cautious rule is applied for fusing mass functions through time lines. Experiments show that this approach does provide better results than single profiling results and classic fusion results. Furthermore, it is found that if severe mis-classification has occurred at the beginning of the time line, the combination can yield undesirable results. To remedy this weakness, we further propose three extensions to the evidential approach proposed above incorporating notions of time-window, time-attenuation, and time-discounting, respectively. These extensions also applies Denoeux’s rule along with time lines and take the DS approach as a special case. Experiments show that these three extensions do provide better results than their predecessor when mis-classifications occur.
Resumo:
We study the computational complexity of finding maximum a posteriori configurations in Bayesian networks whose probabilities are specified by logical formulas. This approach leads to a fine grained study in which local information such as context-sensitive independence and determinism can be considered. It also allows us to characterize more precisely the jump from tractability to NP-hardness and beyond, and to consider the complexity introduced by evidence alone.
Resumo:
We present a method for learning Bayesian networks from data sets containing thousands of variables without the need for structure constraints. Our approach is made of two parts. The first is a novel algorithm that effectively explores the space of possible parent sets of a node. It guides the exploration towards the most promising parent sets on the basis of an approximated score function that is computed in constant time. The second part is an improvement of an existing ordering-based algorithm for structure optimization. The new algorithm provably achieves a higher score compared to its original formulation. Our novel approach consistently outperforms the state of the art on very large data sets.
Resumo:
Learning Bayesian networks with bounded tree-width has attracted much attention recently, because low tree-width allows exact inference to be performed efficiently. Some existing methods [12, 14] tackle the problem by using k-trees to learn the optimal Bayesian network with tree-width up to k. In this paper, we propose a sampling method to efficiently find representative k-trees by introducing an Informative score function to characterize the quality of a k-tree. The proposed algorithm can efficiently learn a Bayesian network with tree-width at most k. Experiment results indicate that our approach is comparable with exact methods, but is much more computationally efficient.
Resumo:
Tungsten will be employed as a plasma facing material in the ITER fusion reactor under construction in Cadarache, France; therefore, there is a significant need for accurate electron-impact excitation and ionization data for the ions of tungsten. We report on the results of extensive calculations of ionization and excitation for W 3+ that are intended to provide the atomic data needed for the determination of impurity influx diagnostics of tungsten in several existing tokamak reactors. The electron-impact excitation rate coefficients for this study were determined using the relativistic R -matrix method. The contribution to direct electron-impact ionization was determined using the distorted-wave approximation, the accuracy of which was verified by an R -matrix with pseudo states calculation. Contributions to total ionization from excitation autoionization were also generated from the relativistic R -matrix method. These results were then employed to calculate values of ionization per emitted photon, or SXB ratios, for four carefully selected spectral lines; these data will allow the determination of impurity influx from tungsten facing surfaces. For the range of densities of importance in the edge region of a tokamak reactor, these SXB ratios are found to be nearly independent of electron density but vary significantly with electron temperature.
Resumo:
With the focus of ITER on the transport and emission properties of tungsten, generating atomic data for complex species has received much interest. Focusing on impurity influx diagnostics, we discuss recent work on heavy species. Perturbative approaches do not work well for near neutral systems so non-perturbative data are required, presenting a particular challenge for these influx diagnostics. Recent results on Mo+ are given as an illustration of how the diagnostic applications can guide the theoretical calculations for such systems.
Resumo:
Electron-impact excitation collision strengths for transitions between all singly excited levels up to the n = 4 shell of helium-Eke argon and the n = 4 and 5 shells of helium-like iron have been calculated using a radiation-damped R-matrix approach. The theoretical collision strengths have been examined and associated with their infinite-energy limit values to allow the preparation of Maxwell-averaged effective collision strengths. These are conservatively considered to be accurate to within 20% at all temperatures, 3 x 10(5)-3 x 10(8) K forAr(16+) and 10(6)-10(9) K for Fe24+. They have been compared with the results of previous studies, where possible, and we find a broad accord. The corresponding rate coefficients are required for use in the calculation of derived, collisional-radiative, effective emission coefficients for helium-like lines for diagnostic application to fusion and astrophysical plasmas. The uncertainties in the fundamental collision data have been used to provide a critical assessment of the expected resultant uncertainties in such derived data, including redistributive and cascade collisional-radiative effects. The consequential uncertainties in the parts of the effective emission coefficients driven by excitation from the ground levels for the key w, x, y and z lines vary between 5% and 10%. Our results remove an uncertainty in the reaction rates of a key class of atomic processes governing the spectral emission of helium-like ions in plasmas.
Resumo:
Trends and focii of interest in atomic modelling and data are identified in connection with recent observations and experiments in fusion and astrophysics. In the fusion domain, spectral observations are included of core, beam penetrated and divertor plasma. The helium beam experiments at JET and the studies with very heavy species at ASDEX and JET are noted. In the astrophysics domain, illustrations are given from the SOHO and CHANDRA spacecraft which span from the solar upper atmosphere, through soft x-rays from comets to supernovae remnants. It is shown that non-Maxwellian, dynamic and possibly optically thick regimes must be considered. The generalized collisional-radiative model properly describes the collisional regime of most astrophysical and laboratory fusion plasmas and yields self-consistent derived data for spectral emission, power balance and ionization state studies. The tuning of this method to routine analysis of the spectral observations is described. A forward look is taken as to how such atomic modelling, and the atomic data which underpin it, ought to evolve to deal with the extended conditions and novel environments of the illustrations. It is noted that atomic physics influences most aspects of fusion and astrophysical plasma behaviour but the effectiveness of analysis depends on the quality of the bi-directional pathway from fundamental data production through atomic/plasma model development to the confrontation with experiment. The principal atomic data capability at JET, and other fusion and astrophysical laboratories, is supplied via the Atomic Data and Analysis Structure (ADAS) Project. The close ties between the various experiments and ADAS have helped in this path of communication.
Resumo:
We propose and advocate basic principles for the fusion of incomplete or uncertain information items, that should apply regardless of the formalism adopted for representing pieces of information coming from several sources. This formalism can be based on sets, logic, partial orders, possibility theory, belief functions or imprecise probabilities. We propose a general notion of information item representing incomplete or uncertain information about the values of an entity of interest. It is supposed to rank such values in terms of relative plausibility, and explicitly point out impossible values. Basic issues affecting the results of the fusion process, such as relative information content and consistency of information items, as well as their mutual consistency, are discussed. For each representation setting, we present fusion rules that obey our principles, and compare them to postulates specific to the representation proposed in the past. In the crudest (Boolean) representation setting (using a set of possible values), we show that the understanding of the set in terms of most plausible values, or in terms of non-impossible ones matters for choosing a relevant fusion rule. Especially, in the latter case our principles justify the method of maximal consistent subsets, while the former is related to the fusion of logical bases. Then we consider several formal settings for incomplete or uncertain information items, where our postulates are instantiated: plausibility orderings, qualitative and quantitative possibility distributions, belief functions and convex sets of probabilities. The aim of this paper is to provide a unified picture of fusion rules across various uncertainty representation settings.
Resumo:
Bounding the tree-width of a Bayesian network can reduce the chance of overfitting, and allows exact inference to be performed efficiently. Several existing algorithms tackle the problem of learning bounded tree-width Bayesian networks by learning from k-trees as super-structures, but they do not scale to large domains and/or large tree-width. We propose a guided search algorithm to find k-trees with maximum Informative scores, which is a measure of quality for the k-tree in yielding good Bayesian networks. The algorithm achieves close to optimal performance compared to exact solutions in small domains, and can discover better networks than existing approximate methods can in large domains. It also provides an optimal elimination order of variables that guarantees small complexity for later runs of exact inference. Comparisons with well-known approaches in terms of learning and inference accuracy illustrate its capabilities.