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.
This paper proposes a robust fault detection method based on interval observer design. This method offers the advantage of being robust against disturbances, measurement noises, uncertain parameters and unknown inputs. The optimization framework is used to reduce the conservatism of the interval-based approach. The design of the observer parameters is formulated using the Linear Matrix Inequality...
This paper aims to propose a new robust state-estimation and fault-detection method by combining the unknown input observer (UIO) and the set-membership estimator (SME). It is known that both the SUIO and the SME can be used to estimate the states of a system. The former aims to obtain a particular value by actively decoupling the effect of unknown inputs, while the latter can obtain state-estimation...
Two usually distinct paradigms exist to model uncertainties. The stochastic one deals with random uncertainties. Strong assumptions about their probability distributions are often made, especially when online computation is required. For instance, assuming independent Gaussian distributions is common practice when using standard versions of the famous Kalman Filter. Though efficient to deal with measurement...
We investigate recovery of nonnegative vectors from nonadaptive compressive measurements in the presence of noise of unknown power. It is known in the literature that under additional assumptions on the measurement design recovery of such vectors is possible with nonnegative least squares without any regularization. We show that uniqueness results known for the noiseless case carry over to robust...
Sub-band speech processing is well-known in robust speech recognition. On the other hand, in recent years, deep neural networks (DNNs) have been widely used in speech recognition for acoustic modeling and also feature extraction and transformation. In this paper, we propose to use deep belief network (DBN) as a post-processing method for de-noising in Mel sub-band level where we enhance logarithm...
In this paper, we propose a novel approach to track extended objects by incorporating negative information. While traditional techniques to track extended targets use only positive measurements, assumed to stem from the target, the proposed estimator is also capable of incorporating negative measurements, which tell us where the target cannot be. To achieve this, we introduce a simple, robust, and...
Over the last decade, a lot of research has been done on sound event classification. But a main problem with sound event classification is that the performance sharply degrades in the presence of noise. As spectrogram-based image features and denoising auto encoder reportedly have superior performance in noisy conditions, this paper proposes a new robust feature called denoising auto encoder image...
Extracting meaningful structures from an image is an important task and benefits a wide range of image application tasks. However, it is typically very challenging to distinguish between noisy or textural patterns from image structures, especially when such patterns do not exhibit regularity (e.g., irregular textural patterns or those with varying scales). While existing edge-preserving image filters...
In this work we study the problem of weakly supervised human body detection under difficult poses (e.g., multiview and/or arbitrary poses) within the framework of multi-instance learning (MIL). We first point out the existence of the so-called “vanishing gradient” problem in MIL with a noisy-or rule as its bagging model. This is mainly due to the independence assumption of the noisy-or rule, which...
In this paper we describe a straightforward, yet effective method of recovering angles from a set of tomographic projections when the view-angles are completely unknown. Existing works on this problem have consistently assumed availability of projections from a large number of angles as well as made assumptions on the underlying distribution of angles to aid reconstruction. We make no such assumptions,...
Multiple Instance Learning (MIL) recently provides an appealing way to alleviate the drifting problem in visual tracking. Following the tracking-by-detection framework, an online MILBoost approach is developed that sequentially chooses weak classifiers by maximizing the bag likelihood. In this paper, we extend this idea towards incorporating the instance significance estimation into the online MILBoost...
In this paper, we propose a new guided depth upsampling method denoted as Robust Weighted Least Squares (RWLS). Our work is inspired by the connection between the Weighted Least Squares (WLS) and the Auto Regressive (AR) model. By adopting a new robust penalty function to model the smoothness of the proposed model, we show that the proposed method performs much better in preserving sharp depth discontinuities...
We propose a non-iterative image deconvolution algorithm for data corrupted by Poisson noise. Many applications involve such a problem, ranging from astronomical to biological imaging. We parametrize the deconvolution process as a linear combination of elementary functions, termed as linear expansion of thresholds (LET). This parametrization is then optimized by minimizing a robust estimate of the...
In this paper, we address the problem of sparse signal recovery, from multi-bit scalar quantized compressed sensing measurements, where the saturation issue is taken into account. We propose a convex optimization approach, where saturation errors are jointly estimated with the sparse signal to be recovered. In the proposed approach, saturated measurements, even though over-identified, are considered...
Robust phonetic segmentation is extremely important for several speech processing tasks such as phone level articulation analysis and error detection, speech synthesis, and annotation. In this paper, we present an unsupervised phonetic segmentation approach and its application to noisy and clipped speech such as mobile phone recordings. We propose a multi-taper-based Perceptual Linear Prediction (PLP)...
Positional binding specifies feature positions for an image (or for text). We show how to incorporate position into a fully distributed vector formed from Vector Quantization, or add position to a vector formed from a Vector Symbolic Architecture. The method guarantees that small shifts in position result in small changes to the representation vector, and does not require an increase in vector size...
Speaker recognition plays an important role in speech processing and classification. In this paper, we propose a features extraction method using Perception Auditory Factor to improve the performance of speaker recognition in noisy environment. After the speech enhancement based on auditory perception characteristic and the 2-dimension enhancement for spectrogram, speech distribution is obtained from...
The information fusion estimation problems are investigated for uncertain systems with cross-correlated noises and data transmission delays. Based on Kalman filtering theory, a distributed fusion estimation scheme is proposed by distributed information perception and centralized fusion. To alleviate the communication burden and computational cost with network-induced transmission delays, the measurement...
Recently, steganography is frequently used for providing covert channel. There are two types of steganography, noisy and noiseless. Noisy steganography approach hides the message by altering the bit of cover. The alteration process produce noise such that it will raise suspicion. Desoky and Younis proposed a noiseless steganography method namely Graphstega that conceal the message as plotted data...
This paper presents a yaw control problem for ship steering using a complex fourth order Nomoto model. A linear matrix iinequality (LMI) based H robust control to deal with poles on imaginary axis is applied to solve the yaw control problem for ship steering. The model uncertainty of ship steering problem is tackled using μ-synthesis control approach. The tracking ability and robust stability of H...
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.