Search

Electrocardiography (ECG) is a well-known noninvasive technique in medical science that provides information about the heart's rhythm and current conditions. Automatic ECG arrhythmia diagnosis relieves doctors' workload and improves diagnosis effectiveness and efficiency. This study proposes an automatic end-to-end 2D CNN (two-dimensional convolution neural networks) deep learning method with an effective DenseNet model for addressing arrhythmias recognition. To begin, the proposed model is trained and evaluated on the 97720 and 141404 beat images extracted from the Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) arrhythmia and St. Petersburg Institute of Cardiological Technics (INCART) datasets (both are imbalanced class datasets) using a stratified 5-fold evaluation strategy. The data is classified into four groups: N (normal), V (ventricular ectopic), S (supraventricular ectopic), and F (fusion), based on the Association for the Advancement of Medical Instrumentation® (AAMI). The experimental results show that the proposed model outperforms state-of-the-art models for recognizing arrhythmias, with the accuracy of 99.80% and 99.63%, precision of 98.34% and 98.94%, and F1-score of 98.91% and 98.91% on the MIT-BIH arrhythmia and INCART datasets, respectively. Using a transfer learning mechanism, the proposed model is also evaluated with only five individuals of supraventricular MIT-BIH arrhythmia and five individuals of European ST-T datasets (both of which are also class imbalanced) and achieved satisfactory results. So, the proposed model is more generalized and could be a prosperous solution for arrhythmias recognition from class imbalance datasets in real-life applications. [ABSTRACT FROM AUTHOR]

The aim of this paper is to build a Question-Answering (QA) system considering Bengali and English language whose task is to generate questions along with their answers. There are two different process modules for Bengali and English. In each module, the main part is Question Generator (QG) which generates possible questions from a sentence by choosing a possible phrase as an answer-phrase. After that, the system has to perform some NLP tasks such as main verb decomposition, subjectauxiliary inversion (for English), replace answer-phrase with the question tag. Considering bivokti (িবভি), postfix and singular-plural, we have to choose the proper question tag and their form in Bengali. The selected answer-phrase for a question is used as the answer to that question. Another task of this system is to store the generated questions and their valid answers. Finally, the questions and their answers are displayed on the screen. The performance and accuracy of the system are evaluated on different Bengali and English texts. The performance of the system on question generation is 78.33% compared to the human being and the average percentage of accuracy of the generated questions is 76%. [ABSTRACT FROM AUTHOR]