Decision Support Systems have been utilised since 1960, providing physicians with fast and accurate means towards more accurate diagnoses, increased tolerance when handling missing or incomplete data. In this paper, a...
详细信息
Decision Support Systems have been utilised since 1960, providing physicians with fast and accurate means towards more accurate diagnoses, increased tolerance when handling missing or incomplete data. In this paper, an intelligent diagnostic system has been developed for the analysis of Wireless Capsule Endoscopic Images. Wireless Capsule Endoscopy (WCE) constitutes a recent technology in which a capsule with micro-camera attached to it, is swallowed by the patient. Two issues are being addressed, including the extraction of texture features from the texture spectra in the chromatic and achromatic domains from each colour component histogram of WCE images and the concept of a fusion of multiple classifiers. The implementation of an advanced neural network, based on a modified expectationmaximisation scheme that incorporates a dynamic structure methodology has been also adopted in this paper. The high detection accuracy of the proposed system provides thus an indication that such intelligent schemes could be used as a supplementary diagnostic tool in WCE.
In this paper, we propose a novel unsupervised online learning trajectory analysis method based on weighted directed graph. Each trajectory can be represented as a sequence of key points. In the training stage, unsupe...
详细信息
ISBN:
(纸本)9784990644109;9781467322164
In this paper, we propose a novel unsupervised online learning trajectory analysis method based on weighted directed graph. Each trajectory can be represented as a sequence of key points. In the training stage, unsupervised expectation-maximization algorithm (EM) is applied for training data to cluster key points. Each class is a Gaussian distribution. It is considered as a node of the graph. According to the classification of key points, we can build a weighted directed graph to represent the trajectory network in the scene. Each path is a category of trajectories. In the test stage, we adopt online EM algorithm to classify trajectories and update the graph. In the experiments, we test our approach and obtain a good performance compared with state-of-the-art approaches.
Retinal images (RI) are widely used to diagnose a variety of eye conditions and diseases such as myopia and diabetic retinopathy. They are inherently characterised by having nonuniform illumination and low-contrast ho...
详细信息
ISBN:
(纸本)9781479903573
Retinal images (RI) are widely used to diagnose a variety of eye conditions and diseases such as myopia and diabetic retinopathy. They are inherently characterised by having nonuniform illumination and low-contrast homogeneous regions which represent a unique set of challenges for retinal image registration (RIR). This paper investigates using the expectation maximization for principal component analysis based mutual information (EMPCA-MI) algorithm in RIR. It combines spatial features with mutual information to efficiently achieve improved registration performance. Experimental results for mono-modal RI datasets verify that EMPCA-MI together with Powell-Brent optimization affords superior robustness in comparison with existing RIR methods, including the geometrical features method.
The widely used broadband wireless technology enables a novel application of providing high-quality communications between vehicles and traffic control centers, which is collectively referred to as vehicle-to-ground c...
详细信息
ISBN:
(纸本)9789860334074
The widely used broadband wireless technology enables a novel application of providing high-quality communications between vehicles and traffic control centers, which is collectively referred to as vehicle-to-ground communications. Channel modeling is in rapidly increasing demand to design and optimize the vehicle-to-ground communication systems. And practical channel models are only available when accurate estimations of the channel parameters are feasible. By adopting quadrature encoding and spectrum spreading, a novel and low-cost measurement method is proposed in this paper. The method can be implemented to achieve channel matrix accurately and furthermore determinate the parameters of a MIMO channel by using the space-alternating generalized expectation-maximization (SAGE) algorithm. Then the method was carried out in a measurement of a vehicle-mounted 4x4 MIMO system. Both large-scale and small-scale fading are investigated and analyzed. A path loss (PL) model and characteristics of channel parameters including PDP, K-factor, angle of arrival (AOA), angle of departure (AOD) and spatial correlation matrixes for V2G channel modeling are given based on the estimations. These results offer a valuable reference for future studies.
This work concerns the development of field directionality mapping algorithms for short acoustic arrays on mobile maneuverable platforms that avoid the left/right ambiguities and endfire resolution degradation common ...
详细信息
This work concerns the development of field directionality mapping algorithms for short acoustic arrays on mobile maneuverable platforms that avoid the left/right ambiguities and endfire resolution degradation common to longer non-maneuverable line arrays. In this paper, it is shown that short maneuverable arrays can achieve a high fraction of usable bearing space for target detection in interference-dominated scenarios, despite their lower array gain against diffuse background noise. Two narrowband techniques are presented which use the expectation-maximization maximum likelihood algorithm under different models of the time-varying field directionality. The first, derivative based maximum likelihood, uses a deterministic model while the second, recursive Bayes maximum likelihood, uses a stochastic model for the time-varying spatial spectrum. In addition, a broadband extension is introduced that incorporates temporal spectral knowledge to suppress ambiguities when the average sensor array spacing is greater than a half-wavelength. Dynamic multi-source simulations demonstrate the ability of a short, maneuvering array to reduce array ambiguities and spatial grating lobes in an interference dominated environment. Monte Carlo evaluation of receiver operating characteristics is used to evaluate the improvement in source detection achieved by the proposed methods versus conventional broadband beamforming. (C) 2013 Acoustical Society of America. [http://dx. ***/10.1121/1.4770233]
The bivariate distribution of zero-up-crossing wave heights and associated periods is important in the stochastic modelling of ocean waves and is of theoretical and practical interest among scientists and engineers. R...
详细信息
The bivariate distribution of zero-up-crossing wave heights and associated periods is important in the stochastic modelling of ocean waves and is of theoretical and practical interest among scientists and engineers. Recently, joint descriptions in mixed sea states have garnered attention. The present study proposes a mixture bivariate lognormal model to characterise the joint distribution in sea states with two-peaked spectra. A parametric distribution based on conditional modelling is compared with the presented model. To verify the fitted models, secondary waves, which can be formed when waves propagate over marine obstacles, were generated in laboratory conditions and simulated data were obtained by the Ochi-Hubble model. The joint distributions of wave heights and periods, as well as the marginal distributions of these two wave parameters in three types of combined sea states are studied and discussed. Results show that the conditional model is not suitable for fitting the bivariate distribution, which may be primarily owing to its inaccurate description of the wave period distribution. Joint probability density functions of wave heights and periods created using a finite mixture model provide improved performance and can describe the bimodal nature of the distribution relatively well.
This paper addresses the problem of field directionality mapping (FDM) or spatial spectrum estimation in dynamic environments with a maneuverable towed acoustic array. Array processing algorithms for towed arrays are ...
详细信息
This paper addresses the problem of field directionality mapping (FDM) or spatial spectrum estimation in dynamic environments with a maneuverable towed acoustic array. Array processing algorithms for towed arrays are typically designed assuming the array is straight, and are thus degraded during tow-ship maneuvers. In this paper, maneuvering the array is treated as a feature allowing for left and right disambiguation as well as improved resolution toward endfire. The Cramer-Rao lower bound is used to motivate the improvement in source localization which can be theoretically achieved by exploiting array maneuverability. Two methods for estimating time-varying field directionality with a maneuvering array are presented: (1) Maximum likelihood (ML) estimation solved using the expectation maximization algorithm and (2) a non-negative least squares (NNLS) approach. The NNLS method is designed to compute the field directionality from beamformed power outputs, while the ML algorithm uses raw sensor data. A multi-source simulation is used to illustrate both the proposed algorithms' ability to suppress ambiguous towed array backlobes and resolve closely spaced interferers near endfire which pose challenges for conventional beamforming approaches especially during array maneuvers. Receiver operating characteristics are presented to evaluate the algorithms' detection performance versus signal-to-noise ratio. The results indicate that both FDM algorithms offer the potential to provide superior detection performance when compared to conventional beamforming with a maneuverable array. (C) 2010 Acoustical Society of America. [DOI: 10.1121/1.3505121]
A source penumbral image reconstruction method with linear mapping principle for geometrical optics is established. The ideal binary point spread function (PSF) can be obtained using a geometrical optics model. The sy...
详细信息
A source penumbral image reconstruction method with linear mapping principle for geometrical optics is established. The ideal binary point spread function (PSF) can be obtained using a geometrical optics model. The system PSF with certain sharpness was obtained using a Monte Carlo (MC) model. Considering other factors besides the transportation of the x (gamma)-rays or particles (fusion neutrons) in the penumbral encoding aperture in MC model, such as the scattering background and the systematic error, the PSF from MC model "source-image pair matching" experiments with a large area standard oval shape source were processed. A method for correcting and calibrating the PSF by the expectation maximization adaptive algorithm was established and the optimized PSF with 22.30 mu m sharpness was achieved. This is more consistent with the real system PSF despite the increased noise level of the two-dimensional PSF and large irregularity in the PSF profile. (C) 2010 American Institute of Physics. [doi: 10.1063/1.3427208]
Two practical issues are involved in asset life prediction using degradation indicators: (1) identifying uncertain failure thresholds of degradation indicators and (2) fusing multiple degradation indicators extracted ...
详细信息
Two practical issues are involved in asset life prediction using degradation indicators: (1) identifying uncertain failure thresholds of degradation indicators and (2) fusing multiple degradation indicators extracted from condition monitoring data. The state space degradation model provides an effective approach to address these two issues. However, existing research on the state space degradation model largely adopts a discrete time or states assumption which requires equal inspection intervals or discretising continuous degradation indicators. To remove the discrete time and states assumptions, this paper proposes a Gamma-based state space model. The Gamma process has a monotonically increasing property that is consistent with the irreversible degradation processes of engineering assets within a single maintenance cycle. The monotonically increasing property also makes the establishment of the likelihood function more straightforward when failure times are considered In this paper, parameter estimation and lifetime prediction algorithms for the Gamma-based state space model are developed. In addition, an effectiveness evaluation approach for indicators in degradation modelling is established. The proposed Gamma-based state space model and algorithms are validated using both simulated data and afield dataset from a liquefied natural gas company.
Image blur resulting from camera motion is an annoying factor for robotic vision, especially for high-speed applications. This work proposes a sensor fusion model for blind image de-blurring using inertial measurement...
详细信息
ISBN:
(纸本)9781467321273;9781467321259
Image blur resulting from camera motion is an annoying factor for robotic vision, especially for high-speed applications. This work proposes a sensor fusion model for blind image de-blurring using inertial measurement unit. The model attempts to observe the camera motion, estimate the point spread function and de-convolute the image simultaneously. To solve the problem, an iterative estimation procedure using Maximum A-Posteriori expectation-Maximization (MAP-EM) algorithms and Unscented Kalman Filter are proposed. Simulation results show the feasibility of the proposed formulation to blindly de-blurring the image under camera motion.
暂无评论