Cough-based COVID-19 Detection with Multi-head Deep Neural Network

Clinicians have long used audio signals created by the human body as indications to diagnose sickness or track disease progression. Preliminary research indicates promise in detecting COVID-19 from voice and coughing acoustic signals. In this paper, various popular convolutional neural networks (CNN) are employed to detect COVID-19 from cough sounds available in the Coughvid opensource dataset. The CNN models are given input in the form of hand-crafted features or raw signals represented using spectrograms. The CNN architectures for both the types of inputs has been optimized to enhance performance. COVID-19 could be detected from cough sounds with an accuracy of 77.5% using CNN on handcrafted features, and 72.5% using VGG16 on spectrograms. However, result show that the concatenation of the two in a multi-head deep neural network yield higher accuracy as compared to just using hand-extracted features or spectrograms of raw signals as input. The classification improved to 81.25% when ResNet50 was employed in the multi-head deep neural network, which was higher than that obtained with VGG16 and MobileNet. © 2022 IEEE.

Digital financial literacy among adults in India: measurement and validation

The ongoing COVID-19 pandemic has considerably promoted the usage of Digital Financial Services (DFS) in India. Therefore, exploring the various determinants influencing the DFS users is crucial for the DFS providers to understand their customers better. This study aims to identify, measure, and validate the determinants of Digital Financial Literacy (DFL) from the Indian adults who use Digital Financial Services. A sample of 384 adult DFS users from India was surveyed using a self-administered questionnaire in 2021. A multidimensional scale was developed to measure the Digital Financial Literacy in this study. The results exhibit that Digital Knowledge, Financial Knowledge, Knowledge of DFS, Awareness of Digital Finance Risk, Digital Finance Risk Control, Knowledge of Customer Right, Product Suitability, Product Quality, Gendered Social Norm, Practical Application of Knowledge and Skill, Self-determination to use the Knowledge and Skill and Decision Making are the determinants of DFL among the adults in India. Further, the users of DFS without DFL will face numerous challenges such as inability to complete the transaction, financial loss and privacy breach, etc. Hence, the study concludes that DFL is prerequisite to use DFS effectively.

Changing customer mindset in adopting digital financial services during the COVID-19 pandemic: Evidence from India

Digital Financial Services (DFS) have been growing steadily all over the world. The COVID-19 crisis has reinforced the need for DFS. This study aims to examine the growth of DFS in the global and Indian markets and to analyze the factors that change the mindsets and attitudes of adults towards the adoption of DFS during the pandemic. The growth of DFS is analyzed using secondary data. The changing customer mindset is studied and analyzed through primary data collected by a survey approach. The unit of analysis includes adults who use or prefer to use DFS. A total of 384 respondents, determined by Krejcie and Morgan formula, were personally interviewed. 384 is taken as sample size as this sample size avoids type II errors in the data analysis. The collected data were processed in SPSS21 software. The study results found that technological benefits (67.9%) have the most significant positive effect on changing people's mindsets and attitudes towards DFS followed by the pandemic forces (50.7%). Peer influences (33.2%) and perceived trust (38.3%) have also affected the change in mindsets and attitudes of adults regarding DFS. But the change in mindset is significantly and positively influenced by perceived risk (50.1%) rather than affecting negatively. So, the factors are confirmed again. The factors that drive changes in mindsets and attitudes of adults towards the adoption of DFS are Pandemic Forces & Convenience, Perceived Safety and Security, User Benefits and Experiences, Peer Influences, and Perceived Trust during the pandemic. © Ravikumar T, Rajesh R, Krishna T A, Haresh R, Arjun B S, 2022.

Cough Sound based COVID-19 Detection with Stacked Ensemble Model

COVID-19 pandeamic has affected people all over the world. COVID-19 may manifest with different severity in different people, however, it predominantly affects respiratory system. Symptoms may vary from sore throat and cough to shortness of breath and damaged lungs. This work focusses on developing a smart system for early detection of COVID-19 based on cough sounds and machine learning algorithms. Such a system would be easily accessible and may provide initial screening for detection of COVID-19. Moreover, cough sounds may be recorded by the person on smartphone avoiding the need for visiting a hospital or testing facility and getting exposed to the disease during the pandeamic. First, the duration of cough sound is determined in the recorded audio signal using thresholding. Then, statistical features are extracted for cough sound and normalized. Finally, the performance of 10 different machine learning algorithms are compared for automatic detection of COVID-19. The proposed stacked ensemble of machine learning models yields the best performance, with an accuracy of 79.86% and area under region of convergence curve of 0.797 for cough sounds of new patients. © 2022 IEEE