Showing papers in "Biomedical Signal Processing and Control in 2021"

TL;DR: This paper proposes a DL assisted automated method using X-ray images for early diagnosis of COVID-19 infection and evaluates the effectiveness of eight pre-trained Convolutional Neural Network models such as AlexNet, VGG-16, GoogleNet, MobileNet-V2, SqueezeNet, ResNet-34, Res net-50 and Inception-V3 for classification of CO VID-19 from normal cases.

TL;DR: A systematic review of the published articles in the last five years aims to help in choosing the appropriate deep neural network architecture and other hyperparameters for developing MI EEG-based BCI systems.

TL;DR: In this article, the authors proposed a high-speed and accurate fully-automated method to detect COVID-19 from the patient's chest CT scan images, which achieved 98.49% accuracy on more than 7996 test images.

TL;DR: A novel hybrid neural model utilizing focal loss, an improved version of cross-entropy loss, to deal with training data imbalance is proposed, which can aid clinicians to detect common atrial fibrillation in real-time on routine screening ECG.

TL;DR: A convolution neural network (CNN) is used to train the classifier for performing classification and experimental results show that the proposed algorithm provides improved results, when compared to traditional schemes.

TL;DR: In this article, a multi-modality algorithm for medical image fusion based on the Adolescent Identity Search Algorithm (AISA) for the Non-Subsampled Shearlet Transform is proposed to obtain image optimization and to reduce the computational cost and time.

TL;DR: In this article, a fusion of convolutional neural network (CNN), support vector machine (SVM), and Sobel filter is proposed to detect COVID-19 using X-ray images.

TL;DR: Clinicians are provided with an advanced methodology for detecting and discriminating between different arrhythmia types by using 2-second segments of 2D recurrence plot images of ECG signals.

TL;DR: The results obtained by verification with two different metaheuristic algorithms proved that the approach proposed can help experts during COVID-19 diagnostic studies.

TL;DR: A novel EEG based computer-aided (CAD) Hybrid Neural Network that can be identified as DepHNN (Depression Hybrid Neural network) for depression screening is presented, which has attained an accuracy of 99.10% with mean absolute error (MAE) of 0.2040.

TL;DR: The experimental results of MD and MI binary and eight-class classifications on the publicly available BreaKHis dataset demonstrate that the proposed transfer learning-based approach is promising and effective, outperforming recent state-of-the-artMD and MI counterparts by a fair margin.

TL;DR: In this paper, a two-phase approach for classifying chest X-ray images is introduced, where the first phase is to train a deep CNN working as a feature extractor, and the second phase comes to use Extreme Learning Machines (ELMs) for real-time detection.

TL;DR: Comparison experiments show that the improved finite element-based particle spring model can better consider the timeliness and accuracy and simulate the soft tissue more accurately.

TL;DR: The results clearly show that the proposed TQWT and RFE based emotion recognition framework is an effective approach for emotion recognition using EEG signals.

TL;DR: The proposed method FE-BkCapsNet, a novel structure with dual channels which can extract convolution features and capsule features simultaneously, integrate sematic features and spatial features into new capsules to obtain more discriminative information is designed.

TL;DR: This study proposes several systolic and diastolic blood pressure estimation models using recurrent neural networks with bidirectional connections and attention mechanism utilising only PPG signals that could capture the non-linear relationship between the PPG features and blood pressure with high accuracy and outperformed the conventional machine learning methods on both datasets.

TL;DR: In this article, a new approach for extension of univariate iterative filtering (IF) for decomposing a signal into intrinsic mode functions (IMFs) or oscillatory modes is proposed for multivariate multi-component signals.

TL;DR: A “brain-ID” framework based on the hybrid deep neural network with transfer learning (HDNN-TL) is proposed to deal with individual differences of 4-class MI task and the experimental results demonstrate that the proposed method can get a satisfying result for new subjects with less time and fewer training data in MI task.

TL;DR: The newly proposed convolutional neural network (CNN) model utilizes image fusion and CNN approaches to classify brain computed tomography scan images into hemorrhagic stroke, ischemic stroke and normal.

TL;DR: Fundus imaging is a retinal image modality for capturing anatomical structures and abnormalities in the human eye and it is observed that VGG16 pre-trained architecture with SGD optimizer performs better for multi-class multi-label fundus images classification on ODIR database.

TL;DR: Experimental results shows that the proposed methods maintain a high quality watermarked images and are very robust against several conventional attacks.

TL;DR: Two dimensional Fourier-Bessel series expansion based empirical wavelet transform (2D-FBSE-EWT), which uses the FBSE spectrum of order zero and order one for boundaries detection and has outperformed all the compared methods used for glaucoma detection.

TL;DR: TCNet-Fusion is proposed, a fixed hyperparameter-based CNN model that utilizes multiple techniques, such as temporal convolutional networks (TCNs), separable convolution, depth-wise convolution; and the fusion of layers, which outperforms other fixed hyper parameter- based CNN models while remaining similar to those that utilize variable hyperparameters.

TL;DR: The experimental results not only could provide strong support for the modularity theory about the brain cognitive function, but show the superiority of the proposed Bi-LSTM model with attention mechanism again.

TL;DR: In this paper, a novel approach is introduced to overcome the aforementioned drawbacks, and it includes the following main steps: Firstly, the three-scale decomposition (TSD) technique was introduced to obtain the base and detail components, and a rule base on local energy function using the Kirsch compass operator was applied to fusing detail layers, which helps the output image preserve important information.

TL;DR: This paper focused on inter-patient heartbeat classification, in which the model is trained over several patients and then used to infer that for patients not used in training, and a two-steps convolutional neural network testing method is proposed for saving power and energy-saving.

TL;DR: Qualitative and quantitative evaluation testify that the proposed MLEPF decomposition model is superior to some excellent algorithms and can achieve close result to some state-of-the-art algorithms.

TL;DR: In this paper, a deep learning strategy based on the Convolutional Neural Network (CNN) was used to automatically detect and identify the Covid-19 disease in X-ray images and computed tomography (CT) images.

TL;DR: A new ECG diagnosis algorithm that combines Convolutional Neural Network (CNN) with the Constant-Q Non-Stationary Gabor Transform (CQ-NSGT) is introduced, for the first time, and experimental results show the superior performance of the proposed approach over other existing techniques.

TL;DR: The evaluation results of cross-patient experiments indicate that, the proposed attention mechanism and bidirectional long short-term memory approach has better performance compared with the current state-of-the-art methods and is more robust across patients.