The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
In the paper, a robust and efficient system identification method is proposed for a state-space model with heavy-tailed process and measurement noises by using the maximum likelihood criterion. An expectation maximization algorithm for a state-space model with heavy-tailed process and measurement noises is derived by treating auxiliary random variables as missing data, based on which a new nonlinear...
In the paper, a novel third-degree Student's t spherical-radial cubature rule (SRCR) is proposed, from which a new robust Student's t based cubature filter is developed. The standard third-degree SRCR is a special case of the proposed Student's t SRCR when the degrees of freedom parameter tends to infinity. Moreover, the proposed Student's t SRCR is identical to the unscented transform (UT) when the...
In this paper, we propose a novel approach to track elongated, curved extended targets by representing their shapes with splines. Elongated shapes are forms whose length is much larger than their width, and can be found in many places, such as in connected vehicles like trains, in group targets like a caravan moving along a curved street, or even when estimating the pose of a person. A particular...
Nowadays, user localization in indoor environments is more necessary to build many location-based services. This paper presents a robust audio identification method for enhancing a real-time indoor localization system on a mobile device using the audio signals emitted by nearby loudspeakers. The proposed audio identification method deals with various noise distortions due to different noisy indoor...
The use of Fuzzy Inference System (FIS) in decision making problems has received little attention so far. This may be due to the difficulty in gathering a complete set of fuzzy rules, which is free from noise, and the complexity in constructing an FIS model that is able to satisfy a number of important properties, including the monotonicity property. Previously, we have proposed a single-input Monotone-Interval...
In this paper, we address the problem of impulsive noise reduction in color images through an evolutionary approach. We designed a new hybrid genetic algorithm, called GARIN, which takes as input a noisy image and generates as output a reduced noise version of the same image. As part of its evolutionary process, GARIN integrates the execution of robust and adaptive filters from literature with the...
Class label noise is a data-level difficulty associated with training objects with incorrectly assigned labels. This problem may originate from poorly documented historic data, errors during data generation process or mistakes made by human experts. Inclusion of such examples during the training process will mislead the classifier by presenting a falsified class distribution and consequently lead...
As a nonlinear extension of Kalman filter, the extended Kalman filter (EKF) is also based on the minimum mean square error (MMSE) criterion. In general, the EKF performs well in Gaussian noises. But its performance may deteriorate substantially when the system is disturbed by heavy-tailed impulsive noises. In order to improve the robustness of EKF against impulsive noises, a new filter for nonlinear...
In practical applications like power system, the distribution of the measurement noise is unknown or frequently deviates from the assumed Gaussian model, often being characterized by heavy tails and sometimes generating impulse noise, named outliers. Under these conditions, the performances of the conventional state estimation (SE) methods that assume known and Gaussian noise, will be greatly degraded...
Participation of class-wise noisy patterns may mislead the selection process of relevant patterns for subspace projection. And modelling between-class scatter for each class using the patterns that are nearer to the corresponding class decision boundary may improve the quality of feature generation. In this manuscript, a novel dimensionality reduction method, named Maximum Class Boundary Criterion...
Motivated by the design of distributed observers with good performance and robustness to measurement and communication noise, the problem of obtaining a global estimate, over a graph, of a common process is considered. We propose a global consensus algorithm that satisfies a pre-specified rate of convergence and has optimized robustness to both communication and measurement noise. The convergence...
When collecting samples via crowd-sourcing for semi-supervised learning, often labels that designate events of interest are assigned unreliably, resulting in label noise. In this paper, we propose a robust method for graph-based image classifier learning given noisy labels, leveraging on recent advances in graph signal processing. In particular, we formulate a graph-signal restoration problem, where...
In web topic detection, detecting “hot” topics from enormous User-Generated Content (UGC) on web data poses two main difficulties that conventional approaches can barely handle: 1) poor feature representations from noisy images and short texts; and 2) uncertain roles of modalities where visual content is either highly or weakly relevant to textual cues due to less-constrained data. In this paper,...
In this paper, we develop a dynamic mode decomposition algorithm that is robust to both inlier and outlier noise in the data. One application of our algorithm is the identification of multiple crowd or traffic flows from compressed video streams. Our method uses motion vectors that are readily available in the compressed bitstream, and do not require computationally expensive optical flow. These motion...
A robust diffusion adaptive filtering algorithm, called the diffusion recursive least lp-norm (DRLP), is developed for distributed estimation over network. The new algorithm aims at recursively minimizing the lp-norm of error, and can offer a more stable and robust solution than traditional adaptive filtering schemes based on minimization of the squared error, such as the diffusion recursive least...
Quantum Process Tomography (QPT) is one of the most important task of checking the functionality of quantum information processing devices. However, there is a significant difficulty that the required resources grow scaling exponentially with the number of qubits during the QPT. Recently, a compressed sensing QPT (CS QPT) is proposed that can reduce the required resource significantly. But the work...
This paper deals with the design of guaranteed cost robust modified Covariance Intersection (CI) fusion Kalman filter for time-invariant multi-sensor systems with uncertain noise variances and random missing measurements. The systems are converted into that with only uncertain noise variances by introducing the fictitious noise. According to the mini-max robust estimation principle and Lyapunov equation...
This paper addresses the design of robust measurement fusion Kalman filter for linear discrete-time multisensor systems with multiplicative noises perturbations both on state equation and measurement equations, and with uncertain noise variances. By introducing two fictitious noises, the system is converted into one with only uncertain noise variances. According to the minimax robust estimation principle,...
Detecting spatiotemporal pattern from noisy sequences of events plays a very important role in presence sharing, Internet of Things (IoT) and many other fields. As pointed out in existing literature, the core activities of these applications involve event notifications. However, excessive number of event notifications will lead to user's intolerability. Existing literature proposed a Spatiotemporal...
In this article considered the ways of robust solutions construction based on the method of pseudo-observations and weighted method LS-SVM using Huber's simple and adapted loss function.
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.