Showing papers in "Biomedical Signal Processing and Control in 2019"

TL;DR: The experimental results show that the designed networks achieve excellent performance on the task of recognizing speech emotion, especially the 2D CNN LSTM network outperforms the traditional approaches, Deep Belief Network (DBN) and CNN on the selected databases.

TL;DR: A comprehensive review of EMG-based motor intention prediction of continuous human upper limb motion, which will cover the models and approaches used in continuous motion estimation, the kinematic motion parameters estimated from EMG signal, and the performance metrics utilized for system validation.

TL;DR: The approach based on an ensemble of SVMs offered a satisfactory performance, improving the results when compared to a single SVM model using the same features, and showed better results in comparison with previous machine learning approaches of the state-of-the-art.

TL;DR: A new method for estimating the Mean Arterial Pressure (MAP), Diastolic Blood Pressure (DBP) and Systolic Blood pressure (SBP) is proposed using only the PPG signal regardless of its shape (appropriate or inappropriate).

TL;DR: In this paper, a waveform-based hierarchical Artificial Neural Network (ANN-LSTM) model was proposed for continuous BP estimation, which consists of two hierarchy levels, where the lower hierarchy level uses ANNs to extract necessary morphological features from ECG and PPG waveforms and the upper hierarchy layer uses LSTM layers to account for the time domain variation of the features extracted by the lower level.

TL;DR: The obtained results show that the WMRPE with FBSE based rhythms provides better classification accuracies in comparison to the existing rhythms based method and other existing methods.

TL;DR: The results show that the DenseNet-II neural network model has better classification performance than other network models, and improves the accuracy of the benign and malignant classification of mammogram images.

TL;DR: The proposed method to classify multiple heart diseases using one dimensional deep convolutional neural network (CNN) where a modified ECG signal is given as an input signal to the network is found to be superior to other approaches in terms of classification accuracy.

TL;DR: The simulation results based on the five runs of k-fold stratified cross-validation indicate that the proposed method yields superior accuracy (99.66%) as compared to existing schemes.

TL;DR: The proposed segmentation and classification methods can automatically and effectively segment cell nuclei of microscopic images and the feature selection method based on CAGA with Gabor features has the highest classification performance for normal, uninvolved and abnormal images.

TL;DR: This paper proposes a novel automatic epileptic EEG detection method based on convolutional neural network (CNN) with two innovative improvements and treats this task as a big data classification issue.

TL;DR: Assessing the performance of eight different pattern ranking techniques when coupled with nonlinear support vector machine (SVM) to distinguish between PD patients and healthy control subjects shows that the receiver operating characteristic and the Wilcoxon-based ranking techniques provide the highest sensitivity and specificity.

TL;DR: It was observed that Levenberg-Marquardt algorithm with five time domain features performed better than other features with an average percentage of classification accuracy of 87.4%.

TL;DR: The experimental results show that the proposed adaptive multi-scale entropy feature algorithm is effective in the detection of fatigue driving based on using forehead EEG data, and the effectiveness of this feature extraction algorithm is proved.

TL;DR: An end-to-end deep learning framework to realize the training free motor imagery (MI) BCI systems by employing the common space pattern (CSP) extracted from electroencephalography (EEG) as the handcrafted feature and proposing a separated channel convolutional network, here termed SCCN.

TL;DR: A coarse-to-fine deep learning framework on the basis of a classical convolutional neural network, known as the U-net model, to accurately identify the optic disc, and shows reliable and relatively high performance in automated OD segmentation.

TL;DR: Based on the results, the proposed computer-aided automatic cataract detection method proved to be an efficient method that uses pre-trained CNN as transfer learning for the classification of the cataracts.

TL;DR: An automated system based on machine learning algorithms that can predict performance of defibrillators and possible performance failures of the device which can affect performance is developed.

TL;DR: The results demonstrate that the method based on kernel sparse coding from FLAIR (fluid attenuated inversion recovery) contrast-enhanced MRIs (magnetic resonance imaging) has better capacity and higher segmentation accuracy with low computation cost.

TL;DR: An automated psoriasis lesion segmentation method based on a modified U-Net architecture that provides accelerated training by reducing the covariate shift through the implementation of batch normalization and is capable of segmenting the lesion even in challenging cases such as under poor acquisition conditions and in the presence of artifacts.

TL;DR: A novel dual asymmetric feature learning network named DualCheXNet is presented for multi-label thoracic disease classification in CXRs and an iterative training strategy is designed to integrate the loss contribution of the involved classifiers into a unified loss, and optimize the process of complementary features learning in an alternative way.

TL;DR: A novel method for classification of DME and two stages of AMD namely the drusens and the choroidal neo vascularization from healthy optical coherence tomography (OCT) images using convolutional neural network (CNN) for reliable diagnosis.

TL;DR: The results show that a Support Vector Machine (SVM) trained with cortical thickness, gyrification index and ADAS cognitive test scores distinguishes between AD and healthy control subjects better than other machine learning methods and other feature combinations.

TL;DR: The proposed non-invasive CAD system based on brain Magnetic Resonance Imaging (MRIs) is capable of assisting radiologists and clinicians to detect not only the presence, but also the type of glioma tumors.

TL;DR: The feasibility and performance of multivariate wavelet-based synchrosqueezing algorithm was demonstrated on EEG signals obtained from publically available DEAP database by comparing with its univariate version, which resulted in the highest prediction accuracy rates among all emotional states.

TL;DR: Different techniques for MR image classification where different tools are used for features extraction and classification are discussed, and a new scheme is proposed based on these reviewed techniques.

TL;DR: An exhaustive review of the published literature on NLM based MR image denoising techniques to provide a critical review and discussion on the advantages and limitations of these techniques are provided with quantitative result analysis.

TL;DR: Flexible analytical wavelets transform (FAWT) based machine learning models are proposed for automated alcoholism detection and suggest that LS-SVM using polynomial kernel performed best with accuracy 99.17%, Sensitivity as 99.44% using 10-fold cross-validation technique.

TL;DR: Instead of the traditional working mode that used the PC to process the EMG signals, the STM32 microcontroller was used to perform real-time control of the upper limb exoskeleton, which greatly reduced the size of the control equipment and provided convenience for the patients’ rehabilitation training.

TL;DR: The proposed method extracts characteristic units (i.e. codewords) of the EEGs associated with the words of an initial vocabulary, and then a classification algorithm is applied, which shows no statistical difference.