Detection of cardiac arrhythmia in electrocardiograms using adaptive feature extraction and modified support vector machines

The electrocardiogram (ECG) analysis is one of the most important approaches to cardiac arrhythmia detection. Many algorithms have been proposed, however, the recognition rate is still unsatisfactory due to unreliable feature extraction in signal characteristic analysis or poor generalization capability of the classifier. In this paper, we propose a system for cardiac arrhythmia detection in ECGs with adaptive feature selection and modified support vector machines (SVMs). Wavelet transform-based coefficients and signal amplitude/interval parameters are first enumerated as candidates, but only a few specific ones are adaptively selected for the classification of each class pair. A new classifier, which integrates k-means clustering, one-against-one SVMs, and a modified majority voting mechanism, is proposed to further improve the recognition rate for extremely similar classes. The experimental results show that the proposed ECG analysis approach can obtain a higher recognition rate than the published approaches. By testing the system with more than 100,000 samples in MIT-BIH arrhythmia database, the average recognition rate is 98.92%, and the recognition rate for each class is kept above 92%.     

Speech based automatic personality perception using spectral features

Automatic personality perception is the prediction of personality that others attribute to a person in a given situation. The aim of automatic personality perception is to forecast the behaviour of the speaker perceived by the listener from nonverbal behavior. Extroversion, Conscientiousness, Agreeableness, Neuroticism, and Openness are the speaker traits used for personality assessment. In this work, a speaker trait prediction approach for automatic personality assessment is proposed. This approach is based on modeling the relationship between speech signal and personality traits using spectral features. The experiments are achieved over the SSPNet Personality Corpus. The Frequency Domain Linear Prediction and Mel Frequency Cepstral Coefficient features are extracted for the prediction of speaker traits. The classification is done using Instance based k-Nearest neighbor and Support Vector Machine (SVM) classifiers. The experimental results show that k-Nearest Neighbor classifier outperforms SVM classifier. The classification accuracy is between 90 and 100%.     

Domain decomposition techniques using spectral methods

The main domain decomposition techniques currently in use in connection with approximation by spectral methods are reviewed. Their most relevant features concerning both the theoretical and the computational aspects are analyzed. Some applications to the Helmholtz problem, to the convection-diffusion equation and to the transport equation are shown.     

Rational spectral factorization using state-space methods

We describe a state-space-based algorithm to find the minimum phase spectral factor of any rational spectral density, whether it be proper, improper, or polynomial.     

Examination of simulation output using spectral methods

Spectral procedures that have been developed to estimate the variance of the sample mean of simulation output are presented and evaluated. The evaluation is performed using a single server queueing situation with exponential interarrival and service times. This process is employed because theoretical values are available for use in the evaluation. In addition, the assumptions necessary to apply spectral methods are valid for this process. The results of the evaluation indicate that spectral methods produce unreliable estimates of the variance of the sample mean. Thus, it is concluded that spectral methods will not produce reliable estimates of the variance of the sample mean for general simulation output.     

Remote detection of bottleneck links using spectral and statistical methods

Persistently saturated links are abnormal conditions that indicate bottlenecks in Internet traffic. Network operators are interested in detecting such links for troubleshooting, to improve capacity planning and traffic estimation, and to detect denial-of-service attacks. Currently bottleneck links can be detected either locally, through SNMP information, or remotely, through active probing or passive flow-based analysis. However, local SNMP information may not be available due to administrative restrictions, and existing remote approaches are not used systematically because of their network or computation overhead. This paper proposes a new approach to remotely detect the presence of bottleneck links using spectral and statistical analysis of traffic. Our approach is passive, operates on aggregate traffic without flow separation, and supports remote detection of bottlenecks, addressing some of the major limitations of existing approaches. Our technique assumes that traffic through the bottleneck is dominated by packets with a common size (typically the maximum transfer unit, for reasons discussed in Section 5.1). With this assumption, we observe that bottlenecks imprint periodicities on packet transmissions based on the packet size and link bandwidth. Such periodicities manifest themselves as strong frequencies in the spectral representation of the aggregate traffic observed at a downstream monitoring point. We propose a detection algorithm based on rigorous statistical methods to detect the presence of bottleneck links by examining strong frequencies in aggregate traffic. We use data from live Internet traces to evaluate the performance of our algorithm under various network conditions. Results show that with proper parameters our algorithm can provide excellent accuracy (up to 95%) even if the traffic through the bottleneck link accounts for less than 10% of the aggregate traffic.     

Machine learning and IoT-based cardiac arrhythmia diagnosis using statistical and dynamic features of ECG

The Journal of Supercomputing - Cardiac arrhythmia is a life-threatening disease which causes severe health problems in patients. A timely diagnosis of arrhythmia diseases will be useful to save...     

A spectral matching quality indicator for material mapping using spectral library search methods

Spectral library search methods are being used increasingly as an efficient approach for exploiting hyperspectral remotely sensed data in material identification and mapping applications. The aim of this study was to develop a quantitative method, using an indicator called the Quality factor (Q-factor), for providing quantitative information on the reliability of spectral identifications in the interpretation (classification) of unknown spectra by library search methods. This was achieved by summing the two main requirements of a typical reflectance spectral library search for material mapping: (1) a reliable correlation between spectral matching scores and material similarity, and (2) a reliable separation ability between the relevant and non-relevant parts of the candidate reference spectra. These form a metric whose values reflect the closeness of the output reference spectra to the input unknown spectra for a chosen library search method. The Q-factor was tested as an indicator of the reliability of the material identifications by the library search for a range of unknown reflectance spectra of various types of vegetation, soils and minerals collected from the US Geological Survey (USGS) Spectral Library and from our in-house spectral database. The results indicate that this approach has the potential to separate correct and incorrect spectral identifications resulting from a particular spectral library search method using a reference similarity logic. The method may be applied to any combination of deterministic spectral matching alternatives using reflectance spectra. Spectrum-level quality information provided by the Q-factor is useful for optimizing a particular search method or for choosing the most appropriate method for distinct identification and classification problems.     

Viscoelastic flow in an undulating tube using spectral methods

The flow of a viscoelastic fluid through an undulating tube is considered. The fluid is modelled using the UCM constitutive equation. The governing set of equations is solved using a time-splitting technique. This is based on separate treatments of the convection and generalised Stokes operators. The spatial discretisation is based on a spectral discretisation in which the radial basis functions satisfy the conditions along the axis of symmetry of the tube explicitly. Compatible approximation spaces are chosen for velocity, pressure and extra-stress. The convection problem is solved in a type-sensitive manner using a high-order Runge-Kutta method. The weak formulation of the generalised Stokes problem is discretised and solved using a nested conjugate gradient technique. The effect of elasticity on flow resistance is investigated and comparisons made with other results in the literature.     

Modeling of first-order photobleaching kinetics using Krylov subspace spectral methods

We solve the first order 2-D reaction–diffusion equations which describe binding-diffusion kinetics using the photobleaching scanning profile of a confocal laser scanning microscope, approximated by a Gaussian laser profile. We show how to solve the first-order photobleaching kinetics partial differential equations (PDEs) using a time-stepping method known as a Krylov subspace spectral (KSS) method. KSS methods are explicit methods for solving time-dependent variable-coefficient partial differential equations. They approximate Fourier coefficients of the solution using Gaussian quadrature rules in the spectral domain. In this paper, we show how a KSS method can be used to obtain not only an approximate numerical solution, but also an approximate analytical solution when using initial conditions that come from pre-bleach steady states and also general initial conditions, to facilitate asymptotic analysis. Analytical and numerical results are presented. It is observed that although KSS methods are explicit, it is possible to use a time step that is far greater than what the CFL condition would indicate.     

Iterative methods for domain decomposition using spectral tau and collocation approximation

In this paper we consider the numerical approximation of elliptic problems by spectral methods in domains subdivided into substructures. We review an iterative procedure with interface relaxation, reducing the given differential problem to a sequence of Dirichlet and mixed Neumann-Dirichlet problems on each subdomain. The iterative procedure is applied to both tau and collocation spectral approximations. Two optimal strategies for the automatic selection of the relaxation parameter are indicated. We present several numerical experiments showing the convergence properties of the iterative scheme with respect to the decomposition. A multilevel technique for domain decomposition methods is proposed.     

Wearable ECG signal processing for automated cardiac arrhythmia classification using CFASE-based feature selection

Classification of electrocardiogram (ECG) signals is obligatory for the automatic diagnosis of cardiovascular disease. With the recent advancement of low-cost wearable ECG device, it becomes more feasible to utilize ECG for cardiac arrhythmia classification in daily life. In this paper, we propose a lightweight approach to classify five types of cardiac arrhythmia, namely, normal beat (N), atrial premature contraction (A), premature ventricular contraction (V), left bundle branch block beat (L), and right bundle branch block beat (R). The combined method of frequency analysis and Shannon entropy is applied to extract appropriate statistical features. Information gain criterion is employed to select features that the results show that 10 highly effective features can obtain performance measures comparable to those obtained by using the complete features. The selected features are then fed to the input of Random Forest, K-Nearest Neighbour, and J48 for classification. To evaluate classification performance, tenfold cross validation is used to verify the effectiveness of our method. Experimental results show that Random Forest classifier demonstrates significant performance with the highest sensitivity of 98.1%, the specificity of 99.5%, the precision of 98.1%, and the accuracy of 98.08%, outperforming other representative approaches for automated cardiac arrhythmia classification.     

Dual transmission model and related spectral content of the fetal heart sounds

A dual transmission model of the fetal heart sounds is presented in which the properties of the signals received on a sensor, installed on the maternal abdominal surface, depend upon the position of the fetus. For a fetus in the occiput anterior position, the predominant spectral content lies in the frequency band 16-50Hz ("impact" mode), but for a fetus in the occiput posterior position, it lies in the frequency band 80-110Hz ("acoustic" mode). Signal processing comprises digital bandpass filtering, matched filtering, Teager energy operator, autocorrelation, and figure of merit algorithms. The digital filter permits the user to select the frequency band that best conforms to the prevailing signal mode. Clinical tests on twelve patients, with some in the occiput anterior and some in the occiput posterior fetal positions, support the validity of the dual transmission model.     

An automatic initialization of interactive segmentation methods using shortest path basins

Image segmentation is one of many fundamental problems in computer vision. The need to divide an image to a number of classes is often a part of a system that uses image processing methods. Therefore, lots of methods were developed that are based on different approaches. The image segmentation could be classified with respect to many criteria. One such a criterion is based on the degree of allowed interactivity. The interactivity could be of several types—interactive initialization, interaction while the computation is running or manual refinement of achieved results, for example. Especially the precise initialization plays an important role in many methods. Therefore the possibility to initialize the method manually is often invaluable advantage and information obtained this way could be the difference between good and poor results. Unfortunately, in many cases it is not possible to initialize a method manually and the process needs to be automated. In this paper, an approach for such an automation is presented. It is based on shortest paths in a graph and deriving an area of influence for each obtained seed point. This method is called shortest path basins.     

Quantum search in structured database using local adiabatic evolution and spectral methods

Since Grover’s seminal work which provides a way to speed up combinatorial search, quantum search has been studied in great detail. We propose a new method for designing quantum search algorithms for finding a marked element in the state space of a graph. The algorithm is based on a local adiabatic evolution of the Hamiltonian associated with the graph. The main new idea is to apply some techniques such as Krylov subspace projection methods, Lanczos algorithm and spectral distribution methods. Indeed, using these techniques together with the second-order perturbation theory, we give a systematic method for calculating the approximate search time at which the marked state can be reached. That is, for any undirected regular connected graph which is considered as the state space of the database, the introduced algorithm provides a systematic and programmable way for evaluation of the search time, in terms of the corresponding graph polynomials.     

Comparison of automatic thresholding methods for snow-cover mapping using Landsat TM imagery

Knowledge of snow cover is essential to understanding the global water and energy cycle. Thresholding the normalized difference snow index (NDSI) image is a method frequently used to map snow cover from remotely sensed data. However, the threshold is dependent on the scenario and needs to be determined accordingly. In this study, nine automatic thresholding methods were tested on the NDSI. Comparisons of the automatic thresholding methods, optimal threshold, and support vector machine (SVM) classification show that Otsu's and Nie's methods appear to be the most robust among the nine automatic thresholding methods, achieving comparable accuracies with the latter two approaches. In addition, NDSI from the digital number (DN) can be an efficient substitution for NDSI obtained from atmospherically or topographically corrected data, with similar accuracy.     

Computational haemodynamics: geometry and non-newtonian modelling using spectral/hp element methods

The increased availability of large scale computational facilities is enabling the use of computational modelling for the treatment of complex problems of industrial interest. Computational haemodynamics is an area where improved computational power and algorithmic development have permitted the application in biomechanics of techniques originally devised for direct numerical simulations in others areas of scientific interest. In this paper we present a highly accurate algorithm for the numerical solution of the incompressible Navier–Stokes equations which employs a spectral/hp element spatial discretisation and a high-order time splitting. Two important developments discussed in this paper are the coupling of these techniques with unstructured mesh generation, used in many everyday engineering applications, and the introduction of a non-Newtonian viscosity model to account for the shear thinning properties of blood. The proposed method will be applied to the analysis of shear stress distributions in flows of interest in haemodynamics. Received: 5 May 1999 / Accepted: 21 september 1999     

Detection of cloaked web spam by using tag-based methods

Web spam attempts to influence search engine ranking algorithm in order to boost the rankings of specific web pages in search engine results. Cloaking is a widely adopted technique of concealing web spam by replying different content to search engines’ crawlers from that displayed in a web browser. Previous work on cloaking detection is mainly based on the differences in terms and/or links between multiple copies of a URL retrieved from web browser and search engine crawler perspectives. This work presents three methods of using difference in tags to determine whether a URL is cloaked. Since the tags of a web page generally do not change as frequently and significantly as the terms and links of the web page, tag-based cloaking detection methods can work more effectively than the term- or link-based methods. The proposed methods are tested with a dataset of URLs covering short-, medium- and long-term users’ interest. Experimental results indicate that the tag-based methods outperform term- or link-based methods in both precision and recall. Moreover, a Weka J4.8 classifier using a combination of term and tag features yields an accuracy rate of 90.48%.     

Asymptotic analysis of spectral methods

A detailed asymptotic analysis of spectral methods for prototype problems is presented. Asymptotic error behavior throughout the solution regime is given. A number of surprising results are presented, including theO(N) boundedness of the eigenvalues of collocation on Legendre points.     

Detection of mines and minelike targets using principal componentand neural-network methods

Introduces a system for real-time detection and classification of arbitrarily scattered surface-laid mines from multispectral imagery data of a minefield. The system consists of six channels which use various neural-network structures for feature extraction, detection, and classification of targets in six different optical bands ranging from near UV to near IR. A single-layer autoassociative network trained using the recursive least square (RLS) learning rule was employed in each channel to perform feature extraction. Based upon the extracted features, two different neural-network architectures were used and their performance was compared against the standard maximum likelihood (ML) classification scheme. The outputs of the detector/classifier network in all the channels were fused together in a final decision-making system. Two different final decision making schemes using the majority voting and weighted combination based on consensual theory were considered. Simulations were performed on real data for six bands and on several images in order to account for the variations in size, shape, and contrast of the targets and also the signal-to-clutter ratio. The overall results showed the promise of the proposed system for detection and classification of mines and minelike tagets.