scispace - formally typeset
Search or ask a question

Showing papers in "Computers in Biology and Medicine in 2013"


Journal ArticleDOI
TL;DR: A novel PSO-SVM model has been proposed that hybridized the particle swarm optimization (PSO) and SVM to improve the EMG signal classification accuracy and validate the superiority of the SVM method compared to conventional machine learning methods.

422 citations


Journal ArticleDOI
TL;DR: This review discusses the available methods of various retinal feature extractions and automated analysis for diagnosis of diabetic retinopathy.

376 citations


Journal ArticleDOI
Shufang Li1, Weidong Zhou1, Qi Yuan1, Shujuan Geng1, Dongmei Cai1 
TL;DR: A novel method for feature extraction and pattern recognition of ictal EEG, based upon empirical mode decomposition (EMD) and support vector machine (SVM), where the EEG signal is decomposed into Intrinsic Mode Functions (IMFs) using EMD, and then the coefficient of variation and fluctuation index of IMFs are extracted as features.

248 citations


Journal ArticleDOI
TL;DR: Four different clustering algorithms are tested and compared in the task of fast nuclei segmentation and it is shown that the presented method ensures accurate and objective data acquisition that could be used to facilitate breast cancer diagnosis.

230 citations


Journal ArticleDOI
TL;DR: A novel method for lung nodule detection, segmentation and recognition using computed tomography (CT) images is presented and compared with other efficient methods through experiments using clinical CT images and two groups of public datasets.

156 citations


Journal ArticleDOI
TL;DR: The proposed scheme introduces a substitution mechanism in the permutation process through a bit-level shuffling algorithm to address the efficiency problem encountered by many existing permutation-substitution type image ciphers.

154 citations


Journal ArticleDOI
TL;DR: A probabilistic classifier based on Bayes' theorem and a supervised learning using a perceptron convergence algorithm to address the emotion recognition problem from electroencephalogram signals.

150 citations


Journal ArticleDOI
TL;DR: A new entropy measure, Fuzzy Measure Entropy (FuzzyMEn), is proposed for the analysis of heart rate variability (HRV) signals and could be considered as a valid and reliable method for a clinical HRV application.

133 citations


Journal ArticleDOI
TL;DR: A non-invasive diagnosis support system for diabetes mellitus is proposed, which determines whether or not diabetes is present by determining the cardiac health of a patient using heart rate variability (HRV) analysis.

129 citations


Journal ArticleDOI
TL;DR: Multi-level basis selection (MLBS) is proposed to preserve the most informative bases of a wavelet packet decomposition tree through removing less informative bases by applying three exclusion criteria: frequency range, noise frequency, and energy threshold.

121 citations


Journal ArticleDOI
TL;DR: Finite element models of the lumbar spine with various degrees of IVD degeneration at the L4-L5 functional spinal unit (FSU) were developed and validated and could provide fundamental information for understanding the mechanism of injuries caused by IVd degeneration.

Journal ArticleDOI
TL;DR: In this investigation, seven levels of workload were induced using an arithmetic task, and the entropy of wavelet coefficients extracted from EEG signals is shown to distinguish all seven levels, suggesting increased synchronization of neural responses for higher load levels.

Journal ArticleDOI
TL;DR: The proposed methods for baseline wander removal and powerline interference removal from electrocardiogram (ECG) signals have been shown to preserve ECG shapes characteristic of heart abnormalities.

Journal ArticleDOI
TL;DR: The proposed algorithm can be used for extracting fetal ECG from abdominal signals based on wavelet analysis, the least mean square (LMS) adaptive filtering algorithm, and the spatially selective noise filtration (SSNF) algorithm and the performance is proven quantitatively by SNR calculation.

Journal ArticleDOI
TL;DR: In this paper, the semi-numerical techniques known as the optimal homotopy analysis method (HAM) and Differential Transform Method (DTM) are applied to study the magneto-hemodynamic laminar viscous flow of a conducting physiological fluid in a semi-porous channel under a transverse magnetic field.

Journal ArticleDOI
TL;DR: The results demonstrate that the proposed scheme LSRG-SWT achieves 96% and 93.59% accuracy in mass/non-mass classification (1st component) and benign/malignant classification (2nd component) respectively when using the I.U. database with k-fold cross validation.

Journal ArticleDOI
TL;DR: A Multi-Gaussian (MG) model is proposed to fit real pulse waveforms using an adaptive number (4 or 5 in this study) of Gaussian waves to decompose single-period pulse waveform into a constant number of individual waves.

Journal ArticleDOI
TL;DR: This paper introduces three novel learning rules called Opposite Weight Back Propagation per Pattern (OWBPP), OWBPP, OWBPE and OWBPI to accelerate the training procedure of an MLP classifier and quantitatively analyzes the accuracy and convergence rate of each system.

Journal ArticleDOI
TL;DR: An automatic ECG signal enhancement technique is proposed to remove noise components from time-frequency domain represented noisyECG signal and shows better signal to noise ratio (SNR) and lower root means square error (RMSE) compared to earlier reported wavelet transform with soft thresholding (WT-Soft) and wave let transform with subband dependent threshold ( WT-Subband) based technique.

Journal ArticleDOI
TL;DR: The use of a custom-made stent-graft to perform a fully endovascular repair of an asymptomatic ascending aortic pseudoaneurysm in a patient, who was a poor candidate for open surgery is described.

Journal ArticleDOI
TL;DR: Defined stimuli transfer parameters demonstrated that stress and SED are transferred distinctively between an implant and bone, indicating that SED should be carefully examined in the context of future bone-screw models.

Journal ArticleDOI
TL;DR: Proposed approach is twice effective than existing Beamlet based features for classifying the mass as round, oval, lobular or irregular, and can be easily implemented and used in fuzzy inference system as if…then…else statements.

Journal ArticleDOI
TL;DR: In this work a simplified model is used to simulate a pulsatile non-Newtonian blood flow past a stenosed artery caused by atherosclerotic plaques of different severity, and the computational results obtained may shed light on the flow and force characteristics of more realistic blood flow through an atherosclerosis vessel.

Journal ArticleDOI
TL;DR: It is concluded that pulse signals taken by familiar SP and PWOF methods are shown in statistical indifferences among seven parameters (Vppmean,Vppmax, HR, LENGTH, WIDTH, AS, and DS).

Journal ArticleDOI
TL;DR: The measurement of feature relevance based on fuzzy entropy is presented, tested with a Radial Basis Function Network classifier for a medical database classification and shows that the proposed method is capable of producing good results with fewer features than the original datasets.

Journal ArticleDOI
TL;DR: The qualitative and quantitative results prove that the rankings generated by the proposed method are closer to the rankings created by radiologists.

Journal ArticleDOI
TL;DR: An erythrokinetic model is described that integrates rates of phlebotomy, erythropoiesis and red cell senescence with patient characteristics to predict the onset of iatrogenic anemia in an objective manner and predicts that adults with average body weight and average blood volume would require 40-70 days to reach 70 g/L of hemoglobin.

Journal ArticleDOI
TL;DR: This paper presents initial cluster prototypes using prototype initialization method to enhance the robustness of the original clustering algorithms to reduce noise and outliers, and the superiority of the proposed methods has been examined through the experimental study on medical images.

Journal ArticleDOI
TL;DR: Among factors influencing the behavioral intentions of using telecare, the strongest factor is attitude, followed by the perceived usefulness, the perceived ease of use, subjective norms, and personal innovativeness, respectively.

Journal ArticleDOI
TL;DR: The most important conclusion obtained from this model is the existence of negative relation between velocity at several inner points of the internal carotid artery and velocity at the inlet of the common carotids artery.