Adaptive Diffusion Research Articles

Fault tolerant distributed estimation in wireless sensor networks

In distributed wireless sensor networks (WSNs), each sensor node estimates the global parameter from the local data in distributed manner. An iterative distributed estimation algorithm is used where the diffusion co-operation scheme is incorporated. Presence of faulty sensor node in the network leads to inaccurate estimation in the conventional error squared based distributed algorithms. Therefore, a fault tolerant distributed estimation in WSNs is proposed here when faulty sensor nodes are present in the network and the network is not aware of them. For this, a robust diffusion estimation algorithms using robust function like Huber's cost function and error saturation non linearity are proposed here in order to make the network fault tolerant. Further, to make the robust estimation algorithm energy efficient, the block adaptive diffusion adaptive algorithm is addressed. The proposed algorithms are validated by simulation and the result shows that the fault tolerant distributed estimation method is robust to node failure.

A Comparative Study on Left and Right Endocardium Segmentation using Gradient Vector Field and Adaptive Diffusion Flow Algorithms

The cardiac Magnetic Resonance Imaging (MRI) provides high resolution images of the heart without radiation exposure. It is an excellent noninvasive test used by radiologist for proper detection of heart diseases. The manual segmentation of left ventricle in cine short axis MRI sequences takes an ample amount of time as compared to semi-automated segmentation. In Gradient Vector Flow (GVF) model certain barriers hinder the performance such as weak edge detection, high computational time, limited capture range and its ambiguity with other parameters. In this paper segmentation of Endocardium is carried out on multistage MRI frames Using Adaptive Diffusion flow (ADF) model. This deformable model was tested on large scale number of Cardiac MRI images. We replace the smoothening energy term in GVF with active hyper-surface harmonic minimal function in order to avoid possible leakage at weak edges. The use of harmonic maps is adjusted in accordance with image characteristics. We also assimilate infinite Laplace function to move active contours into narrow concave sections. Experimental results and collation with GVF are presented in this paper which reveals several good results based on extraction of endocardium tissue from left and right ventricle, including less computational time, noise robustness and weak edge preserving on Cardiac MR Images.

Hybrid local diffusion maps and improved cuckoo search algorithm for multiclass dataset analysis

Data clustering is a meaningful tool that can, help people classify mixed data automatically. With rapid technological development, data in modern applications become large scale and high dimensional. Some original clustering methods are not suitable for complicated datasets. To improve the performance of the popular kernel fuzzy C-means (KFCM), this study proposed a local density adaptive diffusion maps (LDM) technique to obtain a reliable similarity description and dimensionality reduction. To find the valid cluster centroids of the dataset, this study also proposed an improved cuckoo search (ICS) to optimize the unknown parameters of the KFCM model. The ICS algorithm utilized quaternions to represent individuals who will be optimized. Variable step length of Lévy flights and discovery probability were also proposed, which were adjusted by the evolutional ratio of the cuckoo search process. To verify the availability of the ICS, 5 benchmark functions were tested. Finally, the proposed hybrid ICS and LDM based on KFCM (ICS-LDM-KFCM) was used to identify 4 standard artificial and 6 real world datasets. Compared with other clustering methods, the proposed method obtained more accurate results. This method is verified to be more suitable for complicated datasets with large number of attributes and clusters.

Metadata-conscious anonymous messaging

Anonymous messaging platforms allow users to spread messages over a network (e.g., a social network) without revealing message authorship to other users. Popular demand for anonymous messaging is evidenced by the success of mobile apps like Whisper and Yik Yak. In such platforms, the spread of messages is typically modeled as a diffusion process. Recent advances in network analysis have revealed that such diffusion processes are vulnerable to author deanonymization by adversaries with access to metadata, such as timing information. In this work, we ask the fundamental question of how to intervene in the propagation of anonymous messages in order to make it difficult to find the source. In particular, we study the performance of a message propagation protocol called adaptive diffusion introduced in [1] . We prove that it achieves asymptotically optimal source-hiding and significantly outperforms standard diffusion. We further demonstrate empirically that adaptive diffusion hides the source effectively on real social graphs.

基于自适应扩散模型的单帧红外条纹非均匀性校正算法

基于自适应扩散模型的单帧红外条纹非均匀性校正算法

Sparse and Adaptive Diffusion Dictionary (SADD) for recovering intra-voxel white matter structure.

On the analysis of the Diffusion-Weighted Magnetic Resonance Images, multi-compartment models overcome the limitations of the well-known Diffusion Tensor model for fitting in vivo brain axonal orientations at voxels with fiber crossings, branching, kissing or bifurcations. Some successful multi-compartment methods are based on diffusion dictionaries. The diffusion dictionary-based methods assume that the observed Magnetic Resonance signal at each voxel is a linear combination of the fixed dictionary elements (dictionary atoms). The atoms are fixed along different orientations and diffusivity profiles. In this work, we present a sparse and adaptive diffusion dictionary method based on the Diffusion Basis Functions Model to estimate in vivo brain axonal fiber populations. Our proposal overcomes the following limitations of the diffusion dictionary-based methods: the limited angular resolution and the fixed shapes for the atom set. We propose to iteratively re-estimate the orientations and the diffusivity profile of the atoms independently at each voxel by using a simplified and easier-to-solve mathematical approach. As a result, we improve the fitting of the Diffusion-Weighted Magnetic Resonance signal. The advantages with respect to the former Diffusion Basis Functions method are demonstrated on the synthetic data-set used on the 2012 HARDI Reconstruction Challenge and in vivo human data. We demonstrate that improvements obtained in the intra-voxel fiber structure estimations benefit brain research allowing to obtain better tractography estimations. Hence, these improvements result in an accurate computation of the brain connectivity patterns.

Construction, Analysis and Application of Coupled Compact Difference Scheme in Computational Acoustics and Fluid Flow Problems

AbstractIn the present work, a new type of coupled compact difference scheme has been proposed for the solution of computational acoustics and flow problems. The proposed scheme evaluates the first, the second and the fourth derivative terms simultaneously. Derived compact difference scheme has a significant spectral resolution and a physical dispersion relation preserving (DRP) ability over a considerable wavenumber range when a fourth order four stage Runge-Kutta scheme is used for the time integration. Central stencil has been used for the present numerical scheme to evaluate spatial derivative terms. Derived scheme has the capability of adding numerical diffusion adaptively to attenuate spurious high wavenumber oscillations responsible for numerical instabilities. The DRP nature of the proposed scheme across a wider wavenumber range provides accurate results for the model wave equations as well as computational acoustic problems. In addition to the attractive feature of adaptive diffusion, present scheme also helps to control spurious reflections from the domain boundaries and is projected as an alternative to the perfectly matched layer (PML) technique.

Towards a partial differential equation remote sensing image method based on adaptive degradation diffusion parameter

For the anisotropy diffusion feature, Partial Differential Equation (PDE) methods keep edge detail characters well in case of denoising, thus being widely applied in remote sense image denoising, smoothing, filtering and reconstruction. A PDE remote sensing image denoising method based on Adaptive Degradation Diffusion Parameter (ADDP) was proposed in the paper to deal with fuzzy detail problem caused by increasing iteration number. The PDE denoising method with ADDP enlarged diffusion size in the plat region of remote sensing image without affecting the remote sensing image edge, thus avoiding loss of remote sensing image detail and intersections caused by Gaussian convolution smoothing in the PDE filtering model based on curvature-based movement (CM) and image denoising model based on total variation (TV). In the region where gradation value changes little, the method executed isotropic diffusion to remove isolated noise. The upwind scheme was applied for model numerical realization. Experimental in remote sensing image denoising results proved its feasibility and effectiveness.

SNR Controlled Anisotropic Diffusion for Rician Noise Reduction in MR Images

To alleviate excessive smoothing of high signal-to-noise ratio (SNR) regions which are correspond to the structural features of MR images by using classical anisotropic diffusion (AD) filter. A novel AD filter called SNR controlled anisotropic diffusion is proposed. In this filter, an adaptive diffusivity function which is based on the correction factor of MR images was constructed. This adaptive diffusivity function of the proposed filter could control smoothing speed in terms of varying of SNR values in space and time scale until smoothing stop. The experimental results verify the effectiveness of novel AD filter.

Spy vs. Spy

Anonymous messaging platforms, such as Secret, Yik Yak and Whisper, have emerged as important social media for sharing one's thoughts without the fear of being judged by friends, family, or the public. Further, such anonymous platforms are crucial in nations with authoritarian governments; the right to free expression and sometimes the personal safety of the author of the message depend on anonymity. Whether for fear of judgment or personal endangerment, it is crucial to keep anonymous the identity of the user who initially posted a sensitive message. In this paper, we consider an adversary who observes a snapshot of the spread of a message at a certain time. Recent advances in rumor source detection shows that the existing messaging protocols are vulnerable against such an adversary. We introduce a novel messaging protocol, which we call adaptive diffusion, and show that it spreads the messages fast and achieves a perfect obfuscation of the source when the underlying contact network is an infinite regular tree: all users with the message are nearly equally likely to have been the origin of the message. Experiments on a sampled Facebook network show that it effectively hides the location of the source even when the graph is finite, irregular and has cycles.

Dual-Matrix Sampling for Scalable Translucent Material Rendering.

This paper introduces a scalable algorithm for rendering translucent materials with complex lighting. We represent the light transport with a diffusion approximation by a dual-matrix representation with the Light-to-Surface and Surface-to-Camera matrices. By exploiting the structures within the matrices, the proposed method can locate surface samples with little contribution by using only subsampled matrices and avoid wasting computation on these samples. The decoupled estimation of irradiance and diffuse BSSRDFs also allows us to have a tight error bound, making the adaptive diffusion approximation more efficient and accurate. Experiments show that our method outperforms previous methods for translucent material rendering, especially in large scenes with massive translucent surfaces shaded by complex illumination.

Active contours driven by localizing region and edge-based intensity fitting energy with application to segmentation of the left ventricle in cardiac CT images

Dual source CT of the heart is a well-known and accepted method for detection of cardiac disease. However, weak edges, touching characters, intensity inhomogeneities and complex background lead LV segmentation to leakage and false boundary, in cardiac CT images. This difficult task is accomplished in this work by establishing a new active contour model in a variational level set formulation. Its external energy functional incorporates an edge-based information fitting term, which is an adaptive diffusion flow (ADF), and responsible for extracting object boundaries, especially segmenting the weak and missing borders, and a localizing region intensity fitting, which localizes the Chan–Vese external energy against intensity inhomogeneity and complex background to improve the robustness of the proposed method. For improving the adaptability of the model, the weighted parameter between them is then designed according to the gradient information of image. Besides, the regularity of the level set function is intrinsically preserved by the length regularization term to ensure the curve smooth. Experimental results demonstrate desirable performance of our extension method for real-world dual source cardiac CT images.

Diffusion Filters for Variational Data Assimilation of Sea Surface Temperature in an Intermediate Climate Model

Sequential, adaptive, and gradient diffusion filters are implemented into spatial multiscale three-dimensional variational data assimilation (3DVAR) as alternative schemes to model background error covariance matrix for the commonly used correction scale method, recursive filter method, and sequential 3DVAR. The gradient diffusion filter (GDF) is verified by a two-dimensional sea surface temperature (SST) assimilation experiment. Compared to the existing DF, the new GDF scheme shows a superior performance in the assimilation experiment due to its success in extracting the spatial multiscale information. The GDF can retrieve successfully the longwave information over the whole analysis domain and the shortwave information over data-dense regions. After that, a perfect twin data assimilation experiment framework is designed to study the effect of the GDF on the state estimation based on an intermediate coupled model. In this framework, the assimilation model is subject to “biased” initial fields from the “truth” model. While the GDF reduces the model bias in general, it can enhance the accuracy of the state estimation in the region that the observations are removed, especially in the South Ocean. In addition, the higher forecast skill can be obtained through the better initial state fields produced by the GDF.

Distributed estimation in diffusion networks using affine least-squares combiners

We propose a diffusion scheme for adaptive networks, where each node obtains an estimate of a common unknown parameter vector by combining a local estimate with the combined estimates received from neighboring nodes. The combination weights are adapted in order to minimize the mean-square error of the network employing a local least-squares (LS) cost function. This adaptive diffusion network with LS combiners (ADN-LS) is analyzed, deriving expressions for its network mean-square deviation that characterize the convergence and steady-state performance of the algorithm. Experiments carried out in stationary and tracking scenarios show that our proposal outperforms a state-of-art scheme for adapting the weights of diffusion networks (ACW algorithm from [10]), both during convergence and in tracking situations. Despite its good convergence behavior, our proposal may present a slightly worse steady-state performance in stationary or slowly-changing scenarios with respect to ACW due to the error inherent to the least-squares adaptation with sliding window. Therefore, to take advantage of these different behaviors, we also propose a hybrid scheme based on a convex combination of the ADN-LS and ACW algorithms.

An ABC Supported Heterogeneous Access Networks Selection Mechanism

The popularity of mobile communications and coexistence of heterogeneous access networks make it possible that the person can achieve the communication business with little restrict, which requires the support of ABC (always best connected) and the guarantee of users’ QoS requirement. For the property that the network status and users’ QoS requirements are difficult to get, this paper proposes an ABC supported heterogeneous access networks selection mechanism based on the particle swarm optimization based on adaptive diffusion and hybrid mutation in view of users’ preference, users’ cost and network providers’ income. The simulation result shows that this mechanism can not only satisfy the users’ requirements, but also maximizes the utility of both sides.

A fast adaptive diffusion wavelet method for Burger’s equation

A fast adaptive diffusion wavelet method is developed for solving the Burger’s equation. The diffusion wavelet is developed in 2006 (Coifman and Maggioni, 2006) and its most important feature is that it can be constructed on any kind of manifold. Classes of operators which can be used for construction of the diffusion wavelet include second order finite difference differentiation matrices. The efficiency of the method is that the same operator is used for the construction of the diffusion wavelet as well as for the discretization of the differential operator involved in the Burger’s equation. The diffusion wavelet is used for the construction of an adaptive grid as well as for the fast computation of the dyadic powers of the finite difference matrices involved in the numerical solution of Burger’s equation. In this paper, we have considered one dimensional and two dimensional Burger’s equation with Dirichlet and periodic boundary conditions. For each test problem the CPU time taken by fast adaptive diffusion wavelet method is compared with the CPU time taken by finite difference method and observed that the proposed method takes lesser CPU time. We have also verified the convergence of the given method.

Noise reduction of welding defect image based on NSCT and anisotropic diffusion

In order to reduce noise effectively in the welding defect image and preserve the minutiae information, a noise reduction method of welding defect image based on nonsubsampled contourlet transform (NSCT) and anisotropic diffusion is proposed. Firstly, an X-ray welding defect image is decomposed by NSCT. Then total variation (TV) model and Catte_PM model are used for the obtained low-pass component and band-pass components, respectively. Finally, the denoised image is synthesized by inverse NSCT. Experimental results show that, compared with the hybrid method of wavelet threshold shrinkage with TV diffusion, the method combining NSCT with P_Laplace diffusion, and the method combining contourlet with TV model and adaptive contrast diffusion, the proposed method has a great improvement in the aspects of subjective visual effect, peak signal-to-noise ratio (PSNR) and mean-square error (MSE). Noise is suppressed more effectively and the minutiae information is preserved better in the image.

Adaptive Penalty-Based Distributed Stochastic Convex Optimization

In this work, we study the task of distributed optimization over a network of learners in which each learner possesses a convex cost function, a set of affine equality constraints, and a set of convex inequality constraints. We propose a fully-distributed adaptive diffusion algorithm based on penalty methods that allows the network to cooperatively optimize the global cost function, which is defined as the sum of the individual costs over the network, subject to all constraints. We show that when small constant step-sizes are employed, the expected distance between the optimal solution vector and that obtained at each node in the network can be made arbitrarily small. Two distinguishing features of the proposed solution relative to other related approaches is that the developed strategy does not require the use of projections and is able to adapt to and track drifts in the location of the minimizer due to changes in the constraints or in the aggregate cost itself. The proposed strategy is also able to cope with changing network topology, is robust to network disruptions, and does not require global information or rely on central processors.

Multiple-step local Wiener filter with proper stopping in wavelet domain

In this paper, we propose an adaptive multiple steps local Wiener filter image denoising algorithm in the wavelet domain. This algorithm can be considered as a discretized implementation of adaptive heat diffusion equation, and is carried out by multiple successive steps. The denoised output from one iteration is taken as the input to the next. The proper iteration number is determined by total denoising amount which is measured by noise variance. The selected local window sizes are also relatively stable. The experimental results show the effectiveness of the proposed method.

Diffusion Information Theoretic Learning for Distributed Estimation Over Network

Distributed estimation over networks has received a lot of attention due to its broad applicability. In diffusion type of distributed estimation, the parameters of interest can be well estimated from noisy measurements through diffusion cooperation between nodes. Meanwhile, the consumption of communication resources is low, since each node exchanges information only with its neighbors. In previous studies, most of the cost functions used in diffusion distributed estimation are based on mean square error (MSE) criterion, which is optimal only when the measurement noise is Gaussian. However, this condition does not always hold in real-world environments. In non-Gaussian cases, the information theoretic learning (ITL) provides a more general framework and has a better performance than the MSE-based method. In this work, we incorporate information theoretic measure into the cost function of diffusion distributed estimation. Moreover, an information theoretic measure based adaptive diffusion strategy is proposed to further promote estimation performance. Simulation results show that the diffusion ITL-based distributed estimation method can achieve superior performance comparing to the standard diffusion least mean square (LMS) algorithm when the noise is modeled to be non-Gaussian.