Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userOutlier-Detection Based Robust Information Fusion for Networked Systems
91
0
0.0
(
0
)
Added by
Hongwei Wang
Publication date
2019
fields
Mathematical Statistics
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
We consider state estimation for networked systems where measurements from sensor nodes are contaminated by outliers. A new hierarchical measurement model is formulated for outlier detection by integrating the outlier-free measurement model with a binary indicator variable. The binary indicator variable, which is assigned a beta-Bernoulli prior, is utilized to characterize if the sensors measurement is nominal or an outlier. Based on the proposed outlier-detection measurement model, both centralized and decentralized information fusion filters are developed. Specifically, in the centralized approach, all measurements are sent to a fusion center where the state and outlier indicators are jointly estimated by employing the mean-field variational Bayesian inference in an iterative manner. In the decentralized approach, however, every node shares its information, including the prior and likelihood, only with its neighbors based on a hybrid consensus strategy. Then each node independently performs the estimation task based on its own and shared information. In addition, an approximation distributed solution is proposed to reduce the local computational complexity and communication overhead. Simulation results reveal that the proposed algorithms are effective in dealing with outliers compared with several recent robust solutions.
rate research
Read More
The main contribution of this paper is to design an Information Retrieval (IR) technique based on Algorithmic Information Theory (using the Normalized Compression Distance- NCD), statistical techniques (outliers), and novel organization of data base structure. The paper shows how they can be integrated to retrieve information from generic databases using long (text-based) queries. Two important problems are analyzed in the paper. On the one hand, how to detect false positives when the distance among the documents is very low and there is actual similarity. On the other hand, we propose a way to structure a document database which similarities distance estimation depends on the length of the selected text. Finally, the experimental evaluations that have been carried out to study previous problems are shown.
We consider the robust filtering problem for a state-space model with outliers in correlated measurements. We propose a new robust filtering framework to further improve the robustness of conventional robust filters. Specifically, the measurement fitting error is processed separately during the reweighting procedure, which differs from existing solutions where a jointly processed scheme is involved. Simulation results reveal that, under the same setup, the proposed method outperforms the existing robust filter when the outlier-contaminated measurements are correlated, while it has the same performance as the existing one in the presence of uncorrelated measurements since these two types of robust filters are equivalent under such a circumstance.
We propose a novel Bayesian optimisation procedure for outlier detection in the Capital Asset Pricing Model. We use a parametric product partition model to robustly estimate the systematic risk of an asset. We assume that the returns follow independent normal distributions and we impose a partition structure on the parameters of interest. The partition structure imposed on the parameters induces a corresponding clustering of the returns. We identify via an optimisation procedure the partition that best separates standard observations from the atypical ones. The methodology is illustrated with reference to a real data set, for which we also provide a microeconomic interpretation of the detected outliers.
Normalizing flows are prominent deep generative models that provide tractable probability distributions and efficient density estimation. However, they are well known to fail while detecting Out-of-Distribution (OOD) inputs as they directly encode the local features of the input representations in their latent space. In this paper, we solve this overconfidence issue of normalizing flows by demonstrating that flows, if extended by an attention mechanism, can reliably detect outliers including adversarial attacks. Our approach does not require outlier data for training and we showcase the efficiency of our method for OOD detection by reporting state-of-the-art performance in diverse experimental settings. Code available at https://github.com/ComputationalRadiationPhysics/InFlow .
A collection of robust Mahalanobis distances for multivariate outlier detection is proposed, based on the notion of shrinkage. Robust intensity and scaling factors are optimally estimated to define the shrinkage. Some properties are investigated, such as affine equivariance and breakdown value. The performance of the proposal is illustrated through the comparison to other techniques from the literature, in a simulation study and with a real dataset. The behavior when the underlying distribution is heavy-tailed or skewed, shows the appropriateness of the method when we deviate from the common assumption of normality. The resulting high correct detection rates and low false detection rates in the vast majority of cases, as well as the significantly smaller computation time shows the advantages of our proposal.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
