Transfer deep learning approach for detecting coronavirus disease in X-ray images

<p><span lang="EN-US">Currently, the whole world is fighting a very dangerous and infectious disease caused by the novel coronavirus, called COVID-19. The COVID-19 is rapidly spreading around the world due to its high infection rate. Therefore, early discovery of COVID-19 is crucial to better treat the infected person as well as to slow down the spread of this virus. However, the current solution for detecting COVID-19 cases including the PCR test, CT images, epidemiologically history, and clinical symptoms suffer from high false positive. To overcome this problem, we have developed a novel transfer deep learning approach for detecting COVID-19 based on x-ray images. Our approach helps medical staff in determining if a patient is normal, has COVID-19, or other pneumonia. Our approach relies on pre-trained models including Inception-V3, Xception, and MobileNet to perform two tasks: i) binary classification to determine if a person infected with COVID-19 or not and ii) a multi-task classification problem to distinguish normal, COVID-19, and pneumonia cases. Our experimental results on a large dataset show that the F1-score is 100% in the first task and 97.66 in the second task.</span></p>

A GENERAL OVERVIEW ON THE EFFECT OF BILINGUALISM ON EXECUTIVE FUNCTION SKILLS IN CHILDREN: INCONSISTENT RESULTS AND MODERATOR FACTORS

In this study, we reviewed recent studies comparing executive function performance of bi and monolingual children. In that respect, we came across 27 studies. Most of these studies report “partial” executive function advantage for bilingual children (i.e., a bilingual advantage is reported only for some tasks within the same study). In this regard, we examined in detail whether the executive function advantage in bilingual children is general or this advantage appears only in specific executive function tasks. Upon this evaluation, we observed that the bilingual advantage is not specific to a particular executive function paradigm or executive function task classification. To better explain these inconsistencies, we assessed and discussed the moderator factors (i.e., second language age of acquisition, language proficiency, language exposure, language interactional context, minority status, and socioeconomic status) that potentially could affect the outcome of studies examining the executive function skills of bilingual children. We concluded that the bilingual advantage on executive functions is linked to the general executive function system rather than a single executive function task; however, these effects cannot consistently be demonstrated due to the ignored moderator factors. Thus, to obtain more precise results, we offered suggestions for future studies that will compare bi and monolingual children on executive function performance. Keywords Bilingualism, childhood period, executive functions

Investigating Feature Ranking Methods for Sub-Band and Relative Power Features in Motor Imagery Task Classification

Interpreting the brain commands is now easier using brain-computer interface (BCI) technologies. Motor imagery (MI) signal detection is one of the BCI applications, where the movements of the hand and feet can be recognized via brain commands that can be further used to handle emergency situations. Design of BCI techniques encountered challenges of BCI illiteracy, poor signal to noise ratio, intersubject variability, complexity, and performance. The automated models designed for emergency should have lesser complexity and higher performance. To deal with the challenges related to the complexity performance tradeoff, the frequency features of brain signal are utilized in this study. Feature matrix is created from the power of brain frequencies, and newly proposed relative power features are used. Analysis of the relative power of alpha sub-band to beta, gamma, and theta sub-band has been done. These proposed relative features are evaluated with the help of different classifiers. For motor imagery classification, the proposed approach resulted in a maximum accuracy of 93.51% compared to other existing approaches. To check the significance of newly added features, feature ranking approaches, namely, mutual information, chi-square, and correlation, are used. The ranking of features shows that the relative power features are significant for MI task classification. The chi-square provides the best tradeoff between accuracy and feature space. We found that the addition of relative power features improves the overall performance. The proposed models could also provide quick response having reduced complexity.

Multi-Task Classification and Segmentation for Explicable Capsule Endoscopy Diagnostics

Capsule endoscopy is a leading diagnostic tool for small bowel lesions which faces certain challenges such as time-consuming interpretation and harsh optical environment inside the small intestine. Specialists unavoidably waste lots of time on searching for a high clearness degree image for accurate diagnostics. However, current clearness degree classification methods are based on either traditional attributes or an unexplainable deep neural network. In this paper, we propose a multi-task framework, called the multi-task classification and segmentation network (MTCSN), to achieve joint learning of clearness degree (CD) and tissue semantic segmentation (TSS) for the first time. In the MTCSN, the CD helps to generate better refined TSS, while TSS provides an explicable semantic map to better classify the CD. In addition, we present a new benchmark, named the Capsule-Endoscopy Crohn’s Disease dataset, which introduces the challenges faced in the real world including motion blur, excreta occlusion, reflection, and various complex alimentary scenes that are widely acknowledged in endoscopy examination. Extensive experiments and ablation studies report the significant performance gains of the MTCSN over state-of-the-art methods.

Conditional-GAN Based Data Augmentation for Deep Learning Task Classifier Improvement Using fNIRS Data

Functional near-infrared spectroscopy (fNIRS) is a neuroimaging technique used for mapping the functioning human cortex. fNIRS can be widely used in population studies due to the technology’s economic, non-invasive, and portable nature. fNIRS can be used for task classification, a crucial part of functioning with Brain-Computer Interfaces (BCIs). fNIRS data are multidimensional and complex, making them ideal for deep learning algorithms for classification. Deep Learning classifiers typically need a large amount of data to be appropriately trained without over-fitting. Generative networks can be used in such cases where a substantial amount of data is required. Still, the collection is complex due to various constraints. Conditional Generative Adversarial Networks (CGAN) can generate artificial samples of a specific category to improve the accuracy of the deep learning classifier when the sample size is insufficient. The proposed system uses a CGAN with a CNN classifier to enhance the accuracy through data augmentation. The system can determine whether the subject’s task is a Left Finger Tap, Right Finger Tap, or Foot Tap based on the fNIRS data patterns. The authors obtained a task classification accuracy of 96.67% for the CGAN-CNN combination.

A Time-Series-Based New Behavior Trace Model for Crowd Workers That Ensures Quality Annotation

Crowdsourcing is a new mode of value creation in which organizations leverage numerous Internet users to accomplish tasks. However, because these workers have different backgrounds and intentions, crowdsourcing suffers from quality concerns. In the literature, tracing the behavior of workers is preferred over other methodologies such as consensus methods and gold standard approaches. This paper proposes two novel models based on workers’ behavior for task classification. These models newly benefit from time-series features and characteristics. The first model uses multiple time-series features with a machine learning classifier. The second model converts time series into images using the recurrent characteristic and applies a convolutional neural network classifier. The proposed models surpass the current state of-the-art baselines in terms of performance. In terms of accuracy, our feature-based model achieved 83.8%, whereas our convolutional neural network model achieved 76.6%.