Showing papers in "Pattern Recognition Letters in 2020"

TL;DR: Results based on a dataset of X-ray images show that COVID-CAPS has advantage over previous CNN-based models, being capable of handling small datasets, which is of significant importance due to sudden and rapid emergence of CO VID-19.

TL;DR: This work proposes two different DL techniques to assess the considered problem, and implements a fusion of handcrafted and learned features in the MAN to improve classification accuracy during lung cancer assessment.

TL;DR: This work proposes a light Convolutional Neural Network (CNN) design, based on the model of the SqueezeNet, for the efficient discrimination of COVID-19 CT images with respect to other community-acquired pneumonia and/or healthy CT images.

TL;DR: In this paper, the authors used deep learning pre-trained models, ResNet-50 and DenseNet-161, for the IDC detection task and obtained promising results in classifying magnification independent histopathology images into benign and malignant classes.

TL;DR: A novel visual saliency guided complex image retrieval model is proposed which addresses the complexity of the images and proposes a two-stage definition: Cognitive load based complexity and Cognitive level of complexity classification.

TL;DR: A short review about the general use of IoT solutions in health care, starting from early health monitoring solutions from wearable sensors up to a discussion about the latest trends in fog/edge computing for smart health.

TL;DR: This paper provides a systematic literature survey of techniques for brain tumor segmentation and classification of abnormality and normality from MRI images based on different methods including deep learning techniques, metaheuristic techniques and hybridization of these two.

TL;DR: An active deep learning-based feature selection approach is suggested to segment and recognize brain tumors and shows that the presented method outperforms for both segmentation and classification of brain tumors.

TL;DR: A deep learning-based automated detection and classification model for fundus DR images that offers better classification over the existing models is proposed.

TL;DR: An end-to-end network is designed to conduct future frame prediction and reconstruction sequentially, which makes the reconstruction errors large enough to facilitate the identification of abnormal events, while reconstruction helps enhance the predicted future frames from normal events.

TL;DR: The results demonstrate that the proposed two-layer nested ensemble models outperformance the single classifiers and most of the previous works in terms of accuracy.

TL;DR: A category-wise residual attention learning (CRAL) framework that predicts the presence of multiple pathologies in a class-specific attentive view and yields the average AUC score of 0.816 which is a new state of the art.

TL;DR: A self-paced regularization is added in the sparse feature selection model to reduce the impact of outliers for conducting feature selection and Experimental results show that the proposed method outperforms the comparison methods.

TL;DR: A critical look at the use of ML in CH and why CH has only limited adoption of ML is given, and the dominant divides within ML, Supervised, Semi-supervised and Unsupervised are analysed.

TL;DR: Fusion process to combine structural and texture information of four MRI sequences for the detection of brain tumor provides a more informative tumor region as compared to an individual single sequence of MRI.

TL;DR: The behavior of the proposed approach, based on a continuous reparametrization of the objective function, is illustrated on various datasets showing its efficacy in learning representations for objects while clustering them.

TL;DR: The paper presents Imbalance-XGBoost, a Python package that combines the powerful X GBoost software with weighted and focal losses to tackle binary label-imbalanced classification tasks, and is, to the best of the authors' knowledge, the first of its kind which provides an integrated implementation for the two losses on XGBOost.

TL;DR: Initially the skull is removed through brain surface extraction (BSE) method and the skull removed image is then fed to particle swarm optimization (PSO) to achieve better segmentation and artificial neural network and other classifiers are utilized to classify the tumor grades.

TL;DR: Simulation results reveal that the proposed technique outperforms existing methods with greater accuracy, and time.

TL;DR: A hybrid parallel implementation of FCM for extracting volume objects from medical files is proposed and it is concluded that the parallel implementation is 5X faster than the sequential version of the same operation.

TL;DR: This paper presents a feature representation and fusion model to combine the feature representation of the object in RGB and infrared modalities for object tracking and demonstrates the effectiveness of the proposed method.

TL;DR: A survey of wearable/assistive devices and provides a critical presentation of each system, while emphasizing related strengths and limitations, to inform the research community and the VI people about the capabilities of existing systems, the progress in assistive technologies and provide a glimpse in the possible short/medium term axes of research that can improve existing devices.

TL;DR: A deep learning-based method is presented for ulcer detection and gastrointestinal diseases (ulcer, polyp, bleeding) classification and it is clearly perceived that the proposed method outperforms when compared and analyzed with the existing methods.

TL;DR: This paper proposes to integrate the global and local cues into a three-branch attention guided convolution neural network (AG-CNN) to identify thorax diseases and demonstrates that after integrating the local cues with the global information, the average AUC scores are improved by AG-CNN.

TL;DR: In this paper, the authors proposed a rank-consistent RAnk Logits (CORAL) framework with strong theoretical guarantees for rank-monotonicity and consistent confidence scores, which can extend arbitrary state-of-the-art deep neural network classifiers for ordinal regression tasks.

TL;DR: A novel design of contrast stretching based classical features fusion process for localizing the of lungs cancer classification is proposed, which outperforms in comparison with several existing methods with greater accuracy.

TL;DR: Experimental results and analysis show that MCC is not suitable for classification accuracy measurement on imbalanced datasets.

TL;DR: The proposed methodology focuses on automated detection of epilepsy using a novel stop-band energy (SBE) minimized orthogonal wavelet filter bank and the most substantial EEG data publicly available, which contains an EEG recording of 2130 distinct subjects.

TL;DR: The experimental results confirm the effectiveness of the proposed feature selection algorithm as compared to the existing state-of-the-art techniques which yielded outstanding results for the development of automated CAD systems.

TL;DR: A deep learning convolutional neural network ResNet based on the pyramid dilated convolution for Gliomas classification is proposed, integrated into the bottom of Resnet to increase the receptive field of the original network and improve the classification accuracy.