Search

The automatic analysis and detection of audio signals is an important field of research with promising applications in various biomedical engineering problems such as speech, heart murmur, and lung sound analysis and classification. In this regard, automatic classification of infant vocalizations is becoming an appealing research area for medical diagnosis in clinical milieu. Indeed, the analysis and classification of infant cry records is a conventional non-inva-sive technique to distinguish between healthy and unhealthy infants. [ABSTRACT FROM AUTHOR]

Gait and posture are regular activities which are fully controlled by the sensorimotor cortex. In this paper, the complexity of fluctuations in human walking stride records is analyzed to assess gait in healthy young, healthy older adults, and patients affected with Parkinson’s disease (PD). In this regard, a nonlinear analysis of gait reliability is performed by measuring long-range dependence, chaos, and information content in walking stride records. We seek to test if changes in these measures of gait nonlinear patterns occur with age and pathology. The inferential analyses were conducted by employing various statistical tests. The obtained results show a strong evidence of significant group differences in the measured gait nonlinear patterns. More importantly, values of all the three complexity measures increase with age and occurrence of pathology. In addition, age and PD significantly affect gait nonlinear dynamics. In particular, age shapes randomness, while PD alters regularity and stability. Complexity measures considered in this paper provide new insights to better understand the biomechanics of walk due to aging. In addition, they appear to be valuable tools that can highlight differences in gait nonlinear dynamics with respect to PD patients. In this regard, the measurement of gait nonlinear patterns may possibly afford pertinent clinical information on neuromotor conditions, characterization of some neurological disorders, and rehabilitation. [ABSTRACT FROM AUTHOR]

Electroencephalogram (EEG) signals are widely used to detect epileptic seizures in a patient’s neuronal activity. Since visual inspection and interpretation of EEG signal are time-consuming and prone to errors, various computer-aided diagnostic (CAD) tools have been proposed. In this paper, we present a novel automated detection system to distinguish between intracranial EEG time courses with seizures and those that are seizure-free based on complexity measures. Specifically, the features used to characterize the EEG signals are estimates of multiscaling properties over a large spectrum measured by using the generalized Hurst exponent. We tested the capacity of these estimates to correctly classify seizure intervals using a publicly available data set. Using the k-nearest neighbor classifier and testing with tenfold cross validation, we achieved 100% accurate classification. Our proposed CAD system outperformed the existing state-of-the-art models. Moreover, our CAD system is not only accurate but also fast and simple to implement. Therefore, it can be used as an expert system to support a decision in clinical applications. [ABSTRACT FROM AUTHOR]

Recently, variational mode decomposition (VMD) has been proposed as an advanced multiresolution technique for signal processing. This study presents a VMD-based generalized regression neural network ensemble learning model to predict California electricity and Brent crude oil prices. Its performance is compared to that of the empirical mode decomposition (EMD) based generalized regression neural network (GRNN) ensemble model. Particle swarm optimization is used to optimize each GRNN initial weight within the ensemble system. Experimental results showed that the VMD-based ensemble outperformed EMD-based ensemble forecasting system in terms of mean absolute error, mean absolute percentage error, and root mean-squared error. It also outperformed the conventional auto-regressive moving average model used for comparison purpose. As a result, the VMD-based GRNN ensemble forecasting paradigm could be a promising methodology for California electricity and Brent crude oil price prediction. [ABSTRACT FROM PUBLISHER]