Explore the vast range of titles available.

Images captured by vision sensors in outdoor environments often suffer from haze-induced degradations, including blurred details, faded colors, and reduced visibility, which severely impair the performance of sensing and perception systems. To address this issue, we propose a haze-removal algorithm for hazy images using multiple variational constraints. Based on the classic atmospheric scattering model, a mixed variational framework is presented that incorporates three regularization terms for the transmission map and scene radiance. Concretely, an ℓp norm and an ℓ2 norm were constructed to jointly enforce the transmissions for smoothing the details and preserving the structures, and a weighted ℓ1 norm was devised to constrain the scene radiance for suppressing the noises. Furthermore, our devised weight function takes into account both the local variances and the gradients of the scene radiance, which adaptively perceives the textures and structures and controls the smoothness in the process of image restoration. To address the mixed variational model, a re-weighted least square strategy was employed to iteratively solve two separated subproblems. Finally, a gamma correction was applied to adjust the overall brightness, yielding the final recovered result. Extensive comparisons with state-of-the-art methods demonstrated that our proposed algorithm produces visually satisfactory results with a superior clarity and vibrant colors. In addition, our proposed algorithm demonstrated a superior generalization to diverse degradation scenarios, including low-light and remote sensing hazy images, and it effectively improved the performance of high-level vision tasks.

This chapter contains sections titled: Unified formulation: refined models Unified formulation: advanced mixed models PVD(u, Φ) for the electromechanical shell case RMVT(u, Φ, σ n ) for the electromechanical shell case RMVT(u, Φ, D n ) for the electromechanical shell case RMVT(u, Φ, σ n , D n ) for the electromechanical shell case Assembly procedure for fundamental nuclei Acronyms for refined and advanced models Pure mechanical problems as particular cases, PVD(u) and RMVT(u, σ n ) Classical shell theories as particular cases of unified formulation Geometry of shells Plate models as particular cases of shell models References

We show how the notion of message passing can be used to streamline the algebra and computer coding for fast approximate inference in large Bayesian semiparametric regression models. In particular, this approach is amenable to handling arbitrarily large models of particular types once a set of primitive operations is established. The approach is founded upon a message passing formulation of mean field variational Bayes that utilizes factor graph representations of statistical models. The underlying principles apply to general Bayesian hierarchical models although we focus on semiparametric regression. The notion of factor graph fragments is introduced and is shown to facilitate compartmentalization of the required algebra and coding. The resultant algorithms have ready-to-implement closed form expressions and allow a broad class of arbitrarily large semiparametric regression models to be handled. Ongoing software projects such as Infer.NET and Stan support variational-type inference for particular model classes. This article is not concerned with software packages per se and focuses on the underlying tenets of scalable variational inference algorithms. Supplementary materials for this article are available online.

In a dynamic social or biological environment, the interactions between the actors can undergo large and systematic changes. In this paper we propose a model-based approach to analyze what we will refer to as the dynamic tomography of such time-evolving networks. Our approach offers an intuitive but powerful tool to infer the semantic underpinnings of each actor, such as its social roles or biological functions, underlying the observed network topologies. Our model builds on earlier work on a mixed membership stochastic blockmodel for static networks, and the state-space model for tracking object trajectory. It overcomes a major limitation of many current network inference techniques, which assume that each actor plays a unique and invariant role that accounts for all its interactions with other actors; instead, our method models the role of each actor as a time-evolving mixed membership vector that allows actors to behave differently over time and carry out different roles/functions when interacting with different peers, which is closer to reality. We present an efficient algorithm for approximate inference and learning using our model; and we applied our model to analyze a social network between monks (i.e., the Sampson's network), a dynamic email communication network between the Enron employees, and a rewiring gene interaction network of fruit fly collected during its full life cycle. In all cases, our model reveals interesting patterns of the dynamic roles of the actors.

Vision transformer (ViTs) models have shown higher accuracy, robustness and large volume data processing ability, creating new baselines and references for perception tasks. However, these advantages require large memory and high-performance processors and computing units, which makes model adaptability and deployment challenging within resource-constrained environments such as memory-restricted and battery-powered edge devices. This paper addresses the model deployment challenges by proposing a model approximation approach VI-ViT , for edge deployment using variational inference with mixed precision for processing multi-modalities, such as point clouds and images. Our experimental evaluation on the nuScenes and Waymo datasets show up to 37% and 31% reduction in model parameters and Flops while maintaining a mean average precision of 70.5 compared to 74.8 of the baseline model. This work presents a practical deployment approach for approximating and optimizing Vision Transformers for edge AI applications by balancing model metrics such as parameters, flops, latency, energy consumption, and accuracy, which can easily be adapted to other transformer models and datasets.

Genomic prediction has become a powerful modelling tool for assessing line performance in plant and livestock breeding programmes. Among the genomic prediction modelling approaches, linear based models have proven to provide accurate predictions even when the number of genetic markers exceeds the number of data samples. However, breeding programmes are now compiling data from large numbers of lines and test environments for analyses, rendering these approaches computationally prohibitive. Machine learning (ML) now offers a solution to this problem through the construction of fully connected deep learning architectures and high parallelisation of the predictive task. However, the fully connected nature of these architectures immediately generates an over-parameterisation of the network that needs addressing for efficient and accurate predictions. In this research we explore the use of an ML architecture governed by variational Bayesian sparsity in its initial layers that we have called VBS-ML. The use of VBS-ML provides a mechanism for feature selection of important markers linked to the trait, immediately reducing the network over-parameterisation. Selected markers then propagate to the remaining fully connected feed-forward components of the ML network to form the final genomic prediction. We illustrated the approach with four large Australian wheat breeding data sets that range from 2665 lines to 10375 lines genotyped across a large set of markers. For all data sets, the use of the VBS-ML architecture improved genomic prediction accuracy over legacy linear based modelling approaches. An ML architecture governed under a variational Bayesian paradigm was shown to improve genomic prediction accuracy over legacy modelling approaches. This VBS-ML approach can be used to dramatically decrease the parameter burden on the network and provide a computationally feasible approach for improving genomic prediction conducted with large breeding population numbers and genetic markers.

Monthly runoff forecasting plays a critically supportive role in water resources planning and management. Various signal decomposition techniques have been widely applied to enhance the accuracy of monthly runoff forecasting. However, the forecasting of different components, generated through the runoff decomposition, often relies on homogeneous models that utilize identical algorithms or similar structures. The use of a homogeneous model to forecast all components may result in low forecasting accuracy for individual components, which, in turn, impacts the overall forecasting performance negatively. To address this issue, we propose a mixed signal processing model for monthly runoff forecasting, which combines signal processing with heterogeneous machine learning methods that employ different algorithms or structures. Specifically, the SVM and LSTM models are utilized to forecast the original monthly runoff and all components of the monthly runoff decomposed by the Variational Mode Decomposition (VMD), or each component individually. We compare the forecasting models without signal processing and those with either homogeneous or heterogeneous forecasting models that incorporate signal processing. For validation, the Pingshi Hydrological Station in the Lechangxia Basin was selected as the target station. The results demonstrate that the optimal hybrid model, based on mixed signal processing, exhibits a superior performance when compared with the optimal SVM, LSTM, VMD-SVM, and VMD-LSTM models. Specifically, its validation R avg values increased by 3.2%, 3.5%, 0.9%, and 1.2%, respectively, while its validation RMSE avg values decreased by 4.7%, 3%, 1%, and 1%, respectively. The input variables of the optimal hybrid model primarily include sea surface temperature and geopotential height at 500 hPa, suggesting that these factors have a more impact on the monthly runoff in the Lechangxia Basin. This study underscores the importance of selecting a suitable forecasting model for the different characteristics of components, which aids in improving the overall performance of monthly runoff forecasting with signal processing. Moreover, it highlights that reliance solely on teleconnection factors as input variables may not be sufficient for ensuring the accuracy of monthly runoff prediction models.

We develop algorithms for performing semiparametric regression analysis in real time, with data processed as it is collected and made immediately available via modern telecommunications technologies. Our definition of semiparametric regression is quite broad and includes, as special cases, generalized linear mixed models, generalized additive models, geostatistical models, wavelet nonparametric regression models and their various combinations. Fast updating of regression fits is achieved by couching semiparametric regression into a Bayesian hierarchical model or, equivalently, graphical model framework and employing online mean field variational ideas. An Internet site attached to this article, realtime-semiparametric-regression.net, illustrates the methodology for continually arriving stock market, real estate, and airline data. Flexible real-time analyses based on increasingly ubiquitous streaming data sources stand to benefit. This article has online supplementary material.

In this paper, we consider stochastic mixed vector variational inequality problems. Firstly, we present an equivalent form for the stochastic mixed vector variational inequality problems. Secondly, we present a deterministic bi-criteria model for giving the reasonable resolution of the stochastic mixed vector variational inequality problems and further propose the approximation problem for solving the given deterministic model by employing the smoothing technique and the sample average approximation method. Thirdly, we obtain the convergence analysis for the proposed approximation problem while the sample space is compact. Finally, we propose a compact approximation method when the sample space is not a compact set and provide the corresponding convergence results.

Variable Angle Tow (VAT) laminates offer a promising alternative to classical straight-fiber composites in terms of design and performance. However, analyzing these structures can be more complex due to the introduction of new design variables. Carrera’s unified formulation (CUF) has been successful in previous works for buckling, vibrational, and stress analysis of VAT plates. Typically, one-dimensional (1D) and two-dimensional (2D) CUF models are used, with a linear law describing the fiber orientation variation in the main plane of the structure. The objective of this article is to expand the CUF 2D plate finite elements family to perform free vibration analysis of composite laminated plate structures with curvilinear fibers. The primary contribution is the application of Reissner’s mixed variational theorem (RMVT) to a CUF finite element model. The principle of virtual displacements (PVD) and RMVT are both used as variational statements for the study of monolayer and multilayer VAT plate dynamic behavior. The proposed approach is compared to Abaqus three-dimensional (3D) reference solutions, classical theories and literature results to investigate the effectiveness of the developed models. The results demonstrate that mixed theories provide the best approximation of the reference solution in all cases.