Showing papers in "Biocybernetics and Biomedical Engineering in 2016"

TL;DR: The proposed sleep staging algorithm is a data-driven and robust automatic sleep staging scheme that uses single channel EEG signal and its non-REM 1 stage detection accuracy is better than most of the existing works.

TL;DR: Certain applications of the proposed method of ECG signal denoising using the adaptive dual threshold filter (ADTF) and the discrete wavelet transform (DWT) on some of the MIT-BIH Arrhythmia database's signals are presented.

TL;DR: The methodology proposed in this work involves sequential application of image pre-processing, supervised and unsupervised learning and image post-processing techniques and achieves an accuracy comparable with the existing blood vessel segmentation techniques.

TL;DR: Experimental findings backed by statistical and graphical analyses suggest that the proposed method performs better than the existing ones in terms of accuracy, sensitivity, specificity and computational cost.

TL;DR: A new feature extraction method based on empirical mode decomposition (EMD) is proposed, which decomposed the EEG signal into intrinsic mode functions (IMFs) by the EMD algorithm and four statistical parameters are calculated over these IMFs constituting the input feature vector to be fed to a multilayer perceptron neural network (MLPNN) classifier.

TL;DR: An automatic brain hemorrhage detection and classification algorithm on CT images is proposed that obtains the accuracy rate of 96.15%, 95.96% and 94.87% for the segmentation of the EDH, ICH, and SDH types.

TL;DR: A rough set based intuitionistic fuzzy c-means (RIFCM) clustering algorithm is proposed for segmentation of the magnetic resonance (MR) brain images and a new intuitionists fuzzy complement function is proposed to take into account intensity inhomogeneity and noise in brain MR images.

TL;DR: The advantage of the presented method is analysis of the finger skin using a smartphone, which will help to diagnose pathologies of human skin.

TL;DR: An effective approach using wavelet-based non-linear analysis and genetic algorithm optimized support vector machine (GA-SVM) to deal with five challenging classification problems in this study, which attempts to explore the ability of double-density discrete wavelet transform to decompose the original EEG into specific sub-bands.

TL;DR: Results show that the segmentation method identifies the bacilli which retain their shape in-spite of artifacts present in the images and significantly enhanced the SVNN accuracy to 91.3% for object and 92.5% for image level classification than BPNN.

TL;DR: An ensemble schema for cancer diagnosis and classification that has three stages, a hybrid filter-based feature selection method using modified Bayesian logistic regression, Ttest and Fisher ratio is applied for selecting genes and mapped features are classified using SVM classifier.

TL;DR: An automatic voice pathology detection (VPD) system based on voice production theory is developed and features are extracted from vocal tract area, which is connected to the glottis, to indicate that vocal tract irregularity measures can be used effectively in automaticVoice pathology detection.

TL;DR: A new Binary Hausdorff Symmetry (BHS) measure based automatic seed selection, and new edge distance seeded region growing (EDSRG) algorithm for retinal vessel segmentation, both based on point set matching based geometrical interpretation of symmetry are contributed.

TL;DR: Results showed that a spectral parameter – the median frequency was the most promising indicator of the preterm labour risk.

TL;DR: A priori knowledge of knee joint structures and fully automated segmentation methods are adopted to provide reliable detection of bone surfaces from MR imaging sequences specifically designed to evidence the cartilage and not the bone.

TL;DR: Comparison of three methods of spectral analysis of electrohysterographic (EHG) signals: fast Fourier transform (FFT), wavelet transform (WT) and autoregressive modeling (AR) confirmed differences in bioelectrical activity of uterus between patients delivering prematurely within 7 days and after.

TL;DR: In this paper, segmentation of nuclei from breast histopathology images are carried out by Localized Active Contour Model (LACM) utilizing bio-inspired optimization techniques in the detection stage and Krill Herd Algorithm based optimal curve placement provides better initial boundaries compared with other detection techniques.

TL;DR: This paper proposes an automatic speaker recognition approach especially adapted to identify dysarthric speakers and a method for the automatic assessment of the dysarthria severity level, and presents new approaches to improve the analysis and classification of disordered speech.

TL;DR: A method for evaluation of automatically determined baseline in reference to a set of experts, based on ten separate groups of signals comprising typical variability patterns observed in the fetal heart rate, which enabled to evaluate eleven well-known algorithms.

TL;DR: A method based on an improved wavelet neural network (WNN) is proposed for automatic seizure detection in long-term intracranial EEG with high sensitivity and low false detection rate, which demonstrates its potential for clinical usage.

TL;DR: The authors focused on the modeling methodology of balloon angioplasty with minimum possible simplification, i.e.: a full load path, 3D unsymmetrical geometry and discretization, highly nonlinear material models (hyperelasticity, plastic kinematic formulation, crushable foam) and sophisticated contact models (bodies with highly different stiffness).

TL;DR: Numerical investigations demonstrate the utility of one-way-coupled FSI models to compare the haemodynamic conditions for the two LVAD outflow-grafts anastomosis locations and how both affect the aorta and its wall stress.

TL;DR: It is observed from the results that proposed CAD consists of edge based active contour model combined with optimized statistical texture descriptors using DCT along with ANN as classifier achieves the best diagnostic performance of 95.1%.

TL;DR: This experimental setup provides longer time EEG monitoring and drowsiness detection by incorporating the clustering mechanism into the wireless networks.

TL;DR: It was demonstrated that the respiration rate, periodicity of respiration, and presence and length of apnea periods could be reliably estimated from signals recorded using a portable thermal camera.

TL;DR: A robust, accurate and novel method for detecting cell nuclei which can be efficiently used for cell segmentation and compared with other state-of-the-art methods in the literature and software tools to prove its efficiency.

TL;DR: A computer-aided diagnostic system for hierarchical classification of normal, fatty, and heterogeneous liver ultrasound images using feature fusion techniques and both spatial and transform domain based features are used in the classification.

TL;DR: A newly developed algorithm to non-invasive fibrosis stage recognition using machine learning methods – a classification model based on feature projection k -NN classifier based on peripheral blood analysis without using any specialized biomarkers is described.

TL;DR: The customized porous implants satisfies the need of lighter implants with an adequate mechanical strength, restoring better functionality and esthetic outcomes for the patients.

TL;DR: This present preliminary study introduces a simple breast model developed from prone images, which should be built rapidly and by a simple procedure, based only on essential structures, to prove its usefulness in treatment planning.