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.
We introduce a new algorithm that maps multiple instance data using both positive and negative target concepts into a data representation suitable for standard classification. Multiple instance data are characterized by bags which are in turn characterized by a variable number of feature vectors or instances. Each bag has a known positive or negative label, but the labels of any given instances within...
In CS based data gathering method, a small number of measurements arouse a great deal of improvement in reducing energy consumption, and hold a low reconstruction accuracy. In addition, fixed number of measurements are not always work effectively since signals change over time in actual WSNs. Based on recent theoretical results for L1-L1 minimization, a novel adaptive measurement algorithm for compressed...
In this paper, we propose a cyclostationary noise model for multi-input multi-output (MIMO) narrowband power line communication (NB-PLC) based on frequency-shift (FRESH) filtering. The MIMO FRESH filters are designed to shape a multi-input white noise spectrum to a muti-output cyclic spectrum extracted from experimental noise measurements of three-phase low-voltage power lines. The noise modeling...
Tiny target detections, especially power line detection, have received great attention due to its critical role in ensuring the flight safety of low-flying unmanned aerial vehicles (UAVs). In this paper, an accurate and robust power line detection method is proposed, wherein background noise is mitigated by an embedded convolution neural network (CNN) classifier before conducting the final power line...
We study the problem of remote reconstruction of a continuous signal from its multiple corrupted versions. We are interested in the optimal number of samples and their locations for each corrupted signal to minimize the total reconstruction distortion of the remote signal. The correlation among the corrupted signals can be utilized to reduce the sampling rate. For a class of Gaussian signals, we show...
Matrix completion is the task of recovering a data matrix from a sample of entries, and has received significant attention in theory and practice. Normally, matrix completion considers a single matrix, which can be a noisy image or a rating matrix in recommendation. In practice however, data is often obtained from multiple domains rather than a single domain. For example, in recommendation, multiple...
In this paper, we propose a novel noise masking method based on Computational Auditory Scene Analysis by using an adaptive factor. Although it has succeeded in the field of speech separation and speech enhancement to some extent, the usage of fixed thresholds used for segregation and labeling heavily affects the processing performance. Focusing on this issue, the proposed method utilizes the Normalized...
In this paper we consider the problem of set-membership identification of nonlinear polynomial output error models, where output measurements are affected by bounded additive noise known to enjoy certain peculiar properties like whiteness and uncorrelation with the noiseless output sequence. More precisely, we propose an original approach to compute the so-called parameter uncertainty intervals by...
This paper proposes a new signal-to-noise ratio (SNR) estimation technique on scanning electron microscope (SEM) image, using linear regression. The method is based on the single image approach. Four good quality images are used to compare the proposed method and the existing methods: nearest neighborhood, first order interpolation and piecewise cubic Hermite interpolation. The results are compared...
In subjective evaluation of dysarthric speech, the inter-rater agreement between clinicians can be low. Disagreement among clinicians results from differences in their perceptual assessment abilities, familiarization with a client, clinical experiences, etc. Recently, there has been interest in developing signal processing and machine learning models for objective evaluation of subjective speech quality...
Variational mesh segmentation algorithm is a parametric method that used for optimum segmentation of 3D mesh models. The main disadvantage of this method, which limits its application, is the time-consuming problem and need for user's initial settings. Methods that use for selection of initial proxy elements and where to add new regions after each step of convergence are completely significant in...
Multi-label classification is a common supervised machine learning problem where each instance is associated with multiple classes. The key challenge in this problem is learning the correlations between the classes. An additional challenge arises when the labels of the training instances are provided by noisy, heterogeneous crowd-workers with unknown qualities. We first assume labels from a perfect...
The paper is focused on problems related to proper selection of relatively small number of bands from hyperspectral images ensuring sufficiently accurate classification of pixels into several defined categories. Two approaches to construction of the set of spectral bands are presented. To select the most informative bands, their entropy and mutual correlation characteristics were analyzed. It is recognized...
Object detection is one of the main functions in automated video analysis. However, in reality, when the video was taken in the outdoor environment, noisy obstacles frequently perturb our effort to detect interest objects. This work tried to develop a method for the detection of moving objects under noisy environment by analyzing the motion pattern in spatio-temporal domain for large range. Moving...
This paper presents a two-step restoration algorithm for impulse noise detection and removal. In the detection step, the pixel which is most likely corrupted by noise is detected according to its gray values. In the removal step, the proposed algorithm adaptively alters the filtering window size depending on the noise density. For a noisy pixel, if there exist one or more noise-free pixels in its...
In this paper a Photoplethysmography (PPG) based noise robust real time heart rate measurement technique is proposed. It has been developed using Arduino Uno board based on 8-bit AVR core microcontroller and having 16 MHz clock frequency. The basic idea of the proposed work is to extract the periodic PPG signal contaminated by non-periodic noise and atrifact. The algorithm is based on short term autocorrelation...
High-dimensional classification is a common problem in bio-informatics and medicine science. Usually the number of feature is thousands or more but the sample size is much smaller which presents challenge for pattern recognition in computational biology. In this paper, a statistical sparse independence rule (SSIR) is proposed for high-dimensional disease classification. To make up the weakness of...
We obtained the expressions for estimating the accuracy of information parameters measurement of the signal on correlated, in general, non-Gaussian additive noise under continuous processing. It is demonstrated that taking into account the correlation properties and non-Gaussian nature of the additive noise we can significantly improve the measurement accuracy of the information parameters. It is...
This paper discusses the ambient noise acquired during the period of one week, from May 8 to 15, 2013 over a Posidonia oceanica bed in the Bay of la Revellata, Calvi, Corsica. The acoustic receivers were moored at 3 locations with water depth ranging from 2 to 20 m. Simultaneously with acoustic measurements, the dissolved O2 was measured by an array of optodes. Preliminary results have shown that...
The underwater acoustic noise radiated from the propellers of surface and underwater vehicles is characterized as high-frequency broadband noise modulated by low-frequency narrowband noise. Since the modulation is affected by propeller rotation speed, blade rate, and inception of cavitation, the measured propeller noise can be used to extract the information of propeller system and also to monitor...
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.