By Topic

Signal Processing, IET

Issue 4 • Date June 2012

Filter Results

Displaying Results 1 - 13 of 13
  • Optimal finite impulse response estimation of linear models in receiver channels with imbedded digital signal processing units

    Page(s): 281 - 287
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (394 KB)  

    Two finite impulse response (FIR) estimators (optimal and unbiased) are addressed for filtering, smoothing and predicting linear time-invariant state-space signal models perturbed by white Gaussian noise in receiver channels with imbedded digital signal processing units. The FIR estimators are efficient in estimating oversampled and highly oversampled signals, respectively. Special attention is paid to the unbiased FIR (UFIR), owing to its ability of becoming optimal when the processing memory is large. An iterative UFIR algorithm is discussed in detail and compared with the Kalman filter. The optimal memory and errors are also discussed for such kind of estimators. Examples of applications are given for one-dimensional tracking of a two-state polynomial model and state estimation in a harmonic one. Based on this study, the authors show that the UFIR estimator is more efficient than the Kalman filter in blindly estimating receiver channels under the model temporary uncertainties. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Electroencephalogram signals classification for sleepstate decision - A riemannian geometry approach

    Page(s): 288 - 299
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (393 KB)  

    In this work, the authors study the classification of electroencephalogram (EEG) signals for the determination of the state of sleep of a patient. They employ the power spectral density (PSD) matrices as the feature for the distinction between different classes of EEG signals. This not only allows us to examine the power spectrum contents of each signal as well as the correlation between the multi-channel signals, but also complies with what clinical experts use in their visual judgement of EEG signals. To establish a metric facilitating the classification, the authors exploit the specific geometric properties, and develop, with the aid of fibre bundle theory, an appropriate metric in the Riemannian manifold described by the PSD matrices. To use this new metric effectively for the EEG signal classification, the authors further need to find a weighting for the PSD matrices so that the distances of similar features are minimised whereas those for dissimilar features are maximised. A closed form of this weighting matrix is obtained by solving an equivalent convex optimisation problem. The effectiveness of using these new metrics is examined by applying them to a collection of recorded EEG signals for sleep pattern classification based on the k-nearest neighbour decision algorithm with excellent outcome. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Energy-based feature ranking for assessing the dysphonia measurements in Parkinson detection

    Page(s): 300 - 305
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (227 KB)  

    The Parkinson's disease (PD) detection based on dysphonia has been drawn significant attention. However, all dysphonia measurements differ in the uncontrolled acoustic environments. In order to gain as much reliability as possible, measurements should be assessed and the robust ones are chosen. In this study, motivated by statistical learning theory, the problem of PD detection is addressed to classify the participant as healthy or PD using support vector machine (SVM) with the dysphonia measurements as the input feature vector. Therefore an energy-based feature-ranking algorithm is adopted to assess the dysphonia measurements. Moreover, in order to improve the stability of the proposed algorithm, an ensemble version is also presented where multiple feature-ranking results are aggregated. The experimental results on PD data sets have shown the proposed algorithm outperforms other classic ones, and the ensemble version obtain the higher stability than single one. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Likelihood ratio sign test for voice activity detection

    Page(s): 306 - 312
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (390 KB)  

    Voice activity detection (VAD) plays an important role on the performance of speech processing systems in adverse environments. Recently, statistical model-based VADs have demonstrated impressive performance. The study presents a novel decision test (named likelihood ratio sign test, LRST) for VAD by using sign test and Neyman-Pearson criterion to improve the performance of statistical model-based VAD. The proposed LRST is derived based on the likelihood ratios (LRs) calculated from multiple independent observations by incorporating the long-term speech information into the decision rule. An implementation of the LRST VAD is introduced by defining the LRST over a sliding window and calculating the LRs based on complex Gaussian distribution for an input signal. For experiments, the multiple-observation LRT (MO-LRT) VAD based on multiple observations is used as a reference owing to its outstanding performance compared with conventional VADs. The experimental results show that the proposed approach outperforms the MO-LRT VAD in various noise environments. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Model-based estimation pursuit for sparse decomposition of ultrasonic echoes

    Page(s): 313 - 325
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (1057 KB)  

    Sparse signal decomposition techniques used for ultrasonic signal analysis are mainly based on the matching pursuit (MP) method using generic time-frequency dictionaries or more specific dictionaries designed for ultrasound measurements. These dictionary-based MP (DBMP) methods often perform inadequately in extracting meaningful echo components because of the rigid structure of pre-defined dictionaries. More recently emerged model-based signal decomposition methods decompose an ultrasonic signal in terms of parametric model echoes using successive echo partitioning, parameter estimation and echo subtraction. Although these techniques offer more flexibility in signal decomposition, they still use correlation in matching parametric model echoes to partitioned signal components. This study presents a model-based estimation pursuit (MBEP) method that utilises statistical estimation principles in echo matching, as a result provides a greater flexibility and control in signal decomposition. In particular MBEP algorithm utilises maximum a posteriori estimation and incorporates prior knowledge into signal decomposition. Unlike DBMP methods, MBEP obtains physically meaningful decompositions that have direct interpretations for ultrasonic testing. The superior performance of MBEP has been demonstrated using simulated and experimental ultrasonic signals. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Cardiac disorder classification by heart sound signals using murmur likelihood and hidden markov model state likelihood

    Page(s): 326 - 334
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (596 KB)  

    This study proposes a new algorithm for cardiac disorder classification by heart sound signals. The algorithm consists of three steps: segmentation, likelihood computation and classification. In the segmentation step, the authors convert heart sound signals into mel-frequency cepstral coefficient features and then partition input signals into S1/S2 intervals by using a hidden Markov model (HMM). In the likelihood computation step, using only a period of heart sound signals, the authors compute the HMM `state` likelihood and murmur likelihood. The `state` likelihood is computed for each state of HMM-based cardiac disorder models, and the murmur likelihood is obtained by probabilistically modelling the energies of band-pass filtered signals for the heart pulse and murmur classes. In the classification step, the authors decided the final cardiac disorder by combining the state likelihood and the murmur likelihood by using a support vector machine. In computer experiments, the authors show that the proposed algorithm greatly improve classification accuracy by effectively reducing the classification errors for the cardiac disorder categories where the temporal murmur position plays an important role in detecting disorders. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Enhancing support vector machine-based speech/music classification using conditional maximum a posteriori criterion

    Page(s): 335 - 340
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (126 KB)  

    Support vector machines (SVMs) have been recognised as a promising technique in the field of pattern recognition, and one of the interesting applications of this technique is speech/music classification. In this study, the authors propose a novel approach to improve the SVM-based speech/music classification using the second-order conditional maximum a posteriori (CMAP). To do this, the authors first devise a method to estimate a posteriori probability to select between speech and music from the SVM output. This is achieved by employing the sigmoid function, obtained by optimised data training. A final speech/music classification is then acquired using the second-order CMAP with a maximum a posteriori probability depending not only on the current observation, but also on the classification results of two previous frames, incorporating substantial inter-frame correlations. While conventional SVM optimisation techniques are used during the training phase, the proposed technique can be inherently adopted in the classification phase. In this regard, the proposed approach can be developed and employed in parallel with other optimisation techniques. Experimental results show that the proposed algorithm yields better results than the speech/music classification rule in SVM. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robust set-membership filtering for systems with missing measurement: A linear matrix inequality approach

    Page(s): 341 - 347
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (403 KB)  

    This study addresses the robust set-membership finite-horizon filtering problem for a class of discrete time-varying systems with missing measurement and polytopic uncertainties in the presence of unknown-but-bounded process and measurement noises. A robust set-membership filter is developed and a recursive algorithm is derived for computing the state estimate ellipsoid that is guaranteed to contain the true state. An optimal possible estimate set is computed recursively by solving the semi-definite programming problem. Simulation results are provided to demonstrate the effectiveness of the proposed method. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • New system to fingerprint extensible markup language documents using winnowing theory

    Page(s): 348 - 357
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (750 KB)  

    Today, with the fast development of extensible markup language (XML) and increasing amount of data that is published in the form of XML, copyright protection of these data is becoming an important requirement for numerous applications. This study is proposing a system that uses fingerprinting to trace illegal copies and detect any modification made to an XML data. However, the flexible construction of XML data poses a number of challenges to fingerprinting, such as reorganisation and alteration. To overcome these challenges, the proposed system has to be based on the winnowing theory, which selects fingerprint from hashes of XML elements. This system is distortion free since it does not introduce any deformation to the XML data and also preserves usability constraint that is not optimised by the current fingerprinting systems. Experimental results show that the probability of missing fingerprint matching is very low and the chance to detect and locate changes in the XML data is very high. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Estimating spreading waveform of long-code direct sequence spread spectrum signals at a low signal-to-noise ratio

    Page(s): 358 - 363
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (286 KB)  

    In this study, the problem of estimating the spreading waveform of long-code direct sequence spread spectrum (DSSS) signals is considered. A novel spreading waveform estimation method based on a missing data model is proposed. By showing that the long-code DSSS signal can be equivalently represented as a short-code DSSS signal with missing data, the spreading waveform estimation problem can be viewed as a low-rank matrix approximation problem with missing data that can be approximately solved by the existing optimisation methods. To evaluate the performance of the author's proposed estimator, the authors also derive the Cramer'Rao lower bound (CRB) on the mean square error of spreading waveform estimators. The simulation results demonstrate that the proposed estimator approaches the CRB and provides significant performance improvement compared with the existing estimators in the case of low signal-to-noise ratio situations. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Non-linear active noise cancellation using a bacterial foraging optimisation algorithm

    Page(s): 364 - 373
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (1141 KB)  

    This study presents a new scheme for non-linear active noise control (ANC) systems. In the proposed ANC system, a new evolutionary algorithm known as bacterial foraging (BF) is used for optimising the adaptive controller. The proposed ANC system using bacterial foraging optimisation (BFO) has the ability to prevent falling into local minima. Moreover, using the BF algorithm to adapt the ANC filter coefficients removes the need for the preliminary identification of the secondary path. Several computer simulations are developed in order to analyse the performance of the proposed BFO-based ANC system (BFO-ANC). The experiments are carried out in two major groups including a linear and a non-linear secondary path, along with a non-linear primary path. In each group, the effect of different parameters of the BFO algorithm is investigated on the performance and robustness of the proposed ANC system. The authors also compare the results obtained by three ANC systems; the proposed BFO-based ANC, the GA-based ANC and the filtered-X LMS-based ANC. Simulation results demonstrate the effectiveness of the proposed BFO method in noise cancellation performance under several situations. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • State estimation for a class of slowly switched positive linear systems

    Page(s): 374 - 378
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (174 KB)  

    In this study, the state estimation problem for a class of slowly switched positive linear systems (SPLS) is investigated. A multiple linear copositive Lyapunov function (MLCLF) is preliminarily established, by which the state estimator is designed for the underlying systems with an average dwell-time switching. Then, by reducing MLCLF to the common linear copositive Lyapunov function, the results for the SPLS under arbitrary switching can be easily obtained. Finally, a numerical example is given to show the fesibility of the obtained theoretical findings. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Nonlinear minimum variance estimation for statedependent discrete-time systems

    Page(s): 379 - 391
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (605 KB)  

    A state-dependent model and nonlinear operator-based approach to estimation and filtering is introduced for discrete-time multi-channel systems including time delays. The problem involves a signal entering a communications channel involving nonlinearities and transport delay elements. The measurements are assumed to be corrupted by a coloured noise signal which is correlated with the signal to be estimated. The communications channel may include either static or dynamic nonlinearities represented by a general nonlinear operator and/or a state-dependent model form. The theoretical solution does not involve empirical assumptions or linearisation approximations. The resulting algorithm is relatively simple to derive and to implement and the solution has an estimator block structure that can be justified intuitively. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.

Aims & Scope

IET Signal Processing publishes novel contributions in signal processing.

Full Aims & Scope

Meet Our Editors

IET Research Journals
iet_spr@theiet.org