Higher Order Statistical Features Research Articles

A physiological measures-based method for detecting inattention in drivers using machine learning approach

BackgroundIn recent years, as a result of the usage of electronic gadgets in vehicles, driver inattention has become one of the major causes of road accidents that lead to severe physical injuries, deaths and significant economic losses. Statistics ensure the need of a reliable driver inattention detection system that can alert the driver before a mishap happens. MethodsIn this work, we aimed to develop a system that can detect inattention using electrocardiogram (ECG) and surface electromyogram (sEMG) signals. Cognitive and visual inattention was manipulated by asking the driver to respond to phone calls and short messaging services, respectively. A total of 15 male subjects participated in the data collection process. The subjects were asked to drive for two hours in a simulated environment at three different times of the day. ECG, sEMG and video were obtained throughout the experiment. The gathered physiological signals were preprocessed to remove noises and artefacts. The inattention features were extracted from the preprocessed signals using conventional statistical, higher-order statistical and higher-order spectral features. The features were classified using k-nearest neighbour analysis, linear discriminant analysis and quadratic discriminant analysis. ResultsThe bispectral features gave overall maximum accuracies of 98.12% and 90.97% for the ECG and EMG signals, respectively. ConclusionWe conclude that ECG and EMG signals can be explored further to develop a robust and reliable inattention detection system.

Quantitative ultrasound characterization of locally advanced breast cancer by estimation of its scatterer properties

Tumor grading is an important part of breast cancer diagnosis and currently requires biopsy as its standard. Here, the authors investigate quantitative ultrasound parameters in locally advanced breast cancers that can potentially separate tumors from normal breast tissue and differentiate tumor grades. Ultrasound images and radiofrequency data from 42 locally advanced breast cancer patients were acquired and analyzed. Parameters related to the linear regression of the power spectrum--midband fit, slope, and 0-MHz-intercept--were determined from breast tumors and normal breast tissues. Mean scatterer spacing was estimated from the spectral autocorrelation, and the effective scatterer diameter and effective acoustic concentration were estimated from the Gaussian form factor. Parametric maps of each quantitative ultrasound parameter were constructed from the gated radiofrequency segments in tumor and normal tissue regions of interest. In addition to the mean values of the parametric maps, higher order statistical features, computed from gray-level co-occurrence matrices were also determined and used for characterization. Finally, linear and quadratic discriminant analyses were performed using combinations of quantitative ultrasound parameters to classify breast tissues. Quantitative ultrasound parameters were found to be statistically different between tumor and normal tissue (p < 0.05). The combination of effective acoustic concentration and mean scatterer spacing could separate tumor from normal tissue with 82% accuracy, while the addition of effective scatterer diameter to the combination did not provide significant improvement (83% accuracy). Furthermore, the two advanced parameters, including effective scatterer diameter and mean scatterer spacing, were found to be statistically differentiating among grade I, II, and III tumors (p = 0.014 for scatterer spacing, p = 0.035 for effective scatterer diameter). The separation of the tumor grades further improved when the textural features of the effective scatterer diameter parametric map were combined with the mean value of the map (p = 0.004). Overall, the binary classification results (tumor versus normal tissue) were more promising than tumor grade assessment. Combinations of advanced parameters can further improve the separation of tumors from normal tissue compared to the use of linear regression parameters. While the linear regression parameters were sufficient for characterizing breast tumors and normal breast tissues, advanced parameters and their textural features were required to better characterize tumor subtypes.

Multiple Physiological Signal-Based Human Stress Identification Using Non-Linear Classifiers

This paper describes the human stress identification using multiple physiological signals. The Electrocardiogram (ECG), Electromyogram (EMG), Heart Rate Variability (HRV), Galvanic Skin Response (GSR), and Skin Temperature (ST) are the multiple physiological signals acquired and derived from the 40 subjects using mental arithmetic task -based stress-inducing stimuli. To compute the stress induced in the participated subjects, the wavelet denoising, digital elliptic filtering, ectopic beat removal algorithm, Lomb-Scargle (LS) periodogram, Fast Fourier Transform (FFT), and startle detection algorithms are the signal processing methods used to extract the various features of five physiological signals. K Nearest Neighbour (KNN) and Probabilistic Neural Network (PNN) are the nonlinear classifiers used to discriminate the normal and stress states of of the subjects. In order to strengthen the multiple evidence-based stress identification system, we investigated the Higher-Order Statistical (HOS) features in HRV signals that successfully in various applications in cardiac fault detection. Similarly, to evaluate the efficacy of the electromyogram (EMG), galvanic skin response (GSR), and skin temperature (ST), the existing statistical features are considered with a large number of data samples in stress research. The results indicate that the proposed HOS of HRV performed well, with accuracy up to 93.75 %. In other extreme, 76.25 %, 71.25 %, 70.32 %, and 75.32 % were obtained in ECG, EMG, GSR, and ST, respectively. Finally, this study concludes that multiple physiological signal-based subject-independent analyses incorporated and its algorithm gives the reasonably improved detection rate. DOI: http://dx.doi.org/10.5755/j01.eee.19.7.2232

We now know what fly photoreceptors compute

It has been known for some time that photoreceptors transmit more information when driven by stimuli which have 'naturalistic' statistical properties and that processing of naturalistic visual stimuli involves nonlinear transformations of the input signals. Until now it was not clear which statistical features of the stimuli the neurons are selectively 'tuned' to respond to. Another major difficulty was to elucidate the computational mechanisms which explain differences in coding naturalistic and Gaussian stimuli. Here we used a functional model of Drosophila photoreceptor to fully characterize their underlying computational capabilities. The model was derived based on photoreceptor responses measured in vivo using naturalistic input stimuli, which the system experiences in its natural environment. In order to characterize the nonlinear transformations performed by photoreceptors we analytically computed the higher-order or generalized frequency response functions (GFRFs) of the identified nonlinear photoreceptor model. Using this approach, we demonstrate, for the first time that the observed increase in power of photoreceptor response, and shift towards higher frequencies as the mean light intensity increases, is the result of changes in the operating point of the photoreceptor, which produces a change in the shape of the magnitude of the frequency response functions. This suggests that the photoreceptor adaptation mechanisms are not tuned to fully compensate for the drop in intensity in order to achieve, in an efficient way - by exploiting the photoreceptor nonlinearity - a change in the shape of the magnitude transfer functions, which are optimal for the given mean intensity level. Furthermore, we examined the significance of both local and non-local high-order phase correlations for fly vision. We simulated the photoreceptor model using synthetic stimuli sequences incorporating local phase correlations (edges) and non-local phase correlations (quadratic phase coupling) superimposed with Gaussian white noise. By decomposing voltage output of photoreceptor somata into linear second- and higher-order responses, we explain the nonlinear mechanisms responsible for coding the local and non-local higher-order statistical features in the stimuli as well as improving their signal-to-noise ratio. To validate the results, we carried out electrophysiological experiments using a specially designed stimuli sequence, which allows extracting the nonlinear component of the photoreceptor response directly from data, without a model.

Spectral features for the classification of partial discharge signals from selected insulation defect models

Time-domain features of partial discharge (PD) signals are often used to classify PD patterns. This paper proposes spectral features that are extracted using a filter bank, consisting of band-pass filters. By applying the fast Fourier transform to the PD signal, the resulting frequency bins are grouped into L octave frequency sub-bands. Two new features called the octave frequency moment coefficients (OFMC) and octave frequency Cepstral coefficients (OFCC) are defined in this paper. In addition, time-frequency domain coefficients (TFDC) obtained via wavelet analysis are also analysed. A PD signal can now be represented as an L -dimensional feature vector of OFMC, OFCC or TFDC. These features are compared with discrete wavelet transform-based higher-order statistical features (HOSF) using three different classifiers: probabilistic neural network, support vector machine and the recently emerged sparse representation classifier. Results show that the proposed spectral features are robust and provide a better classification accuracy of PD signals, compared with HOSF.

Improvement of Liver Segmentation by Combining High Order Statistical Texture Features with Anatomical Structural Features

Automatic segmentation of liver in medical images is challenging on the aspects of accuracy, automation and robustness. A crucial stage of the liver segmentation is the selection of the image features for the segmentation. This paper presents an accurate liver segmentation algorithm. The approach starts with a texture analysis which results in an optimal set of texture features including high order statistical texture features and anatomical structural features. Then, it creates liver distribution image by classifying the original image pixelwisely using support vector machines. Lastly, it uses a group of morphological operations to locate the liver organ accurately in the image. The novelty of the approach is resided in the fact that the features are so selected that both local and global texture distributions are considered, which is important in liver organ segmentation where neighbouring tissues and organs have similar greyscale distributions. Experiment results of liver segmentation on CT images using the proposed method are presented with performance validation and discussion.

Internal Representations of Temporal Statistics and Feedback Calibrate Motor-Sensory Interval Timing

Humans have been shown to adapt to the temporal statistics of timing tasks so as to optimize the accuracy of their responses, in agreement with the predictions of Bayesian integration. This suggests that they build an internal representation of both the experimentally imposed distribution of time intervals (the prior) and of the error (the loss function). The responses of a Bayesian ideal observer depend crucially on these internal representations, which have only been previously studied for simple distributions. To study the nature of these representations we asked subjects to reproduce time intervals drawn from underlying temporal distributions of varying complexity, from uniform to highly skewed or bimodal while also varying the error mapping that determined the performance feedback. Interval reproduction times were affected by both the distribution and feedback, in good agreement with a performance-optimizing Bayesian observer and actor model. Bayesian model comparison highlighted that subjects were integrating the provided feedback and represented the experimental distribution with a smoothed approximation. A nonparametric reconstruction of the subjective priors from the data shows that they are generally in agreement with the true distributions up to third-order moments, but with systematically heavier tails. In particular, higher-order statistical features (kurtosis, multimodality) seem much harder to acquire. Our findings suggest that humans have only minor constraints on learning lower-order statistical properties of unimodal (including peaked and skewed) distributions of time intervals under the guidance of corrective feedback, and that their behavior is well explained by Bayesian decision theory.

Forestry in the Republic of Ireland: Government Policy, Grant Incentives and Carbon Sequestration Value

Recent decades have seen a rapid increase in the area of privately owned forest plantations in Ireland. This has been largely driven by grant aid from the government. These forests are significant carbon sinks and as such are delivering added benefit to the country by contributing to greenhouse gas reductions under the Kyoto Protocol. The direct impact of government subvention on the net present value (NPV) for a defined forestry plantation is investigated. The added value of carbon sequestration to forestry investment is also examined using the UK Forestry Commission carbon model. Extending the typical assumption of a constant carbon price for project appraisal purposes, this paper allows carbon prices to evolve randomly according to a flexible stochastic price process. The model chosen is an extended mean-reverting jump-diffusion, with the flexibility to capture the higher-order statistical features (i.e. skewness and kurtosis) of the carbon markets. This allows for an analysis of the risk and uncertainty around the NPV from exposure to stochastic carbon prices. It is shown that government funded grants for afforestation significantly improve the NPV on forestry investment. Carbon sequestration is shown to further add value.

Classification of Multi-User Chirp Modulation Signals Using Wavelet Higher-Order-Statistics Features and Artificial Intelligence Techniques

Higher order statistical features have been recently proved to be very efficient in the classification of wideband communications and radar signals with great accuracy. On the other hand, the denoising properties of the wavelet transform make WT an efficient signal processing tool in noisy environments. A novel technique for the classification of multi-user chirp modulation signals is presented in this paper. A combination of the higher order moments and cumulants of the wavelet coefficients as well as the peaks of the bispectrum and its bi-frequencies are proposed as effective features. Different types of artificial intelligence based classifiers and clustering techniques are used to identify the chirp signals of the different users. In particular, neural networks (NN), maximum likelihood (ML), k-nearest neighbor (KNN) and support vector machine (SVMs) classifiers as well as fuzzy c-means (FCM) and fuzzy k-means (FKM) clustering techniques are tested. The Simulation results show that the proposed technique is able to efficiently classify the different chirp signals in additive white Gaussian noise (AWGN) channels with high accuracy. It is shown that the NN classifier outperforms other classifiers. Also, the simulations prove that the classification based on features extracted from wavelet transform results in more accurate results than that using features directly extracted from the chirp signals, especially at low values of signal-to-noise ratios.

Objective Pathological Voice Quality Assessment Based on HOS Features

This work proposes new features to improve the pathological voice quality classification performance. They are the means, the variances, and the perturbations of the higher-order statistics (HOS) such as the skewness and the kurtosis. The HOS-based features show meaningful differences among normal, grade 1, grade 2, and grade 3 voices classified in the GRBAS scale. The jitter, the shimmer, the harmonic-to-noise ratio (HNR), and the variance of the short-time energy are utilized as the conventional features. The performances are measured by the classification and regression tree (CART) method. Specifically, the CART-based method by utilizing both the conventional features and the HOS-based ones shows its effectiveness in the pathological voice quality measurement, with the classification accuracy of 87.8%.

RESPONSE PROPERTIES OF A SINGLE CHAOTIC NEURON TO STOCHASTIC INPUTS

Response properties of a single chaotic neuron to stochastic inputs are investigated by means of numerical simulations in the context of a nonlinear dynamical approach to analyzing chaotic behaviors of a neuron. We apply six kinds of stochastic inputs with the same mean rate but different correlations of interspike intervals, whose timings are determined by a stochastic process, namely, Markovian processes and Gaussian/Poisson random processes. From numerical evaluations of entropy and conditional entropies with respect to interspike intervals of outputs, it is shown that interspike intervals of outputs represent dynamical structures of each input. Numerical calculations of Lyapunov exponents, trajectories of dynamics and return plots of internal states make meaningful difference in dynamical properties of the model depending on inputs even if mean interspike intervals of outputs are almost the same values. In order to extract dynamical features of outputs, we calculate a time-delayed space representation of output responses to inputs, and the results provide different trajectories in a time-delayed phase space, which reflect a higher order statistical feature of inputs, amplifying their feature differences. For signals containing noise, the behaviors of the model do not suffer degradation, showing robustness to noise in the inputs. As conclusion, our results show that dynamical properties of inputs can be extracted with clear difference of response properties of the model, that is, the model gives a variety of the amplitude and the interspike intervals of outputs depending on inputs. In other words, the model can realize dynamical sampling of inputs with sensitivity of response properties to inputs and robustness to inputs with noise.

Hydrogen Stark Broadening by Different Kinds of Model Microfields

The “method of model microfields (MMM)”, which has been employed successfully especially for the calculation of hydrogen Stark profiles, is based on the assumption that reliable line shapes may be obtained from just the probability density of the plasma microfield and its autocorrelation function. To test the influence of higher order statistical features two different model microfields have been used to investigate Stark broadening of hydrogen Lyman lines by either electrons or ions. Corresponding profiles computed in this way lie close together over the full intensity range, but systematic relative deviations of about 20% show up at frequency separations from the unperturbed line of approximately three times the plasma frequency (for electrons or ions, respectively), i.e., in the “transition region” where neither the impact nor the static approximation holds. Though the joint action of electrons and ions as well as Doppler broadening will tend to diminish these deviations, the present form of the MMM cannot be expected to yield an accuracy better than some 10% throughout the line profile.

Two-layer Exchange in an Estuary Basin, with Special Reference to the Baltic Sea

Stationary and transient states of a two-layer fjord-type estuary are discussed analytically. The forcing functions are the outer salinity S0, the fresh-water supply qf, and a meteorologically forced barotropic transport qm. Forced nonlinear, time-dependent cases have been studied numerically. Some associated laboratory experiments are described. The main results obtained are as follows: (i) A single steady state exists; this is approached in an exponential-like way. (ii) The total mixing through the interface must vary with depth (decrease for increasing interface depth) to allow a stable steady state. (iii) The static stability increases with increasing fresh-water supply, up to a critical value where the two-layer model breaks down. (iv) An added oscillatory component in S0 increases and in qf decreases the esturay salinity and the static stability. The effect of an oscillatory qm may go in either direction. (v) The statistical steady state is sensitive to certain high-order statistical features of the forcing functions. It is suggested that changes in such statistical features, rather than changes in mean forcing conditions, may explain observed physical-chemical secular variations in the Baltic, in particular the drop of oxygen concentrations of the deep water.