ABSTRACT
In this paper, we propose a new novel coronavirus pneumonia image classification model based on the combination of Transformer and convolutional network(VQ-ViCNet), and present a vector quantization feature enhancement module for the inconspicuous characteristics of lung medical image data. This model extracts the local latent layer features of the image through the convolutional network, and learns the deep global features of the image data through the Transformer's multi-head self attention algorithm. After the calculation of convolution and attention, the features learned by the Transformer Encoder are enhanced by the vector quantization feature enhancement module and able to better complete the final downstream tasks. This model performs better than convolutional architectures, pure attention architectures and generative models on all 6 public datasets. © 2022 IEEE.
ABSTRACT
Collaborative virtual environment (CVE) is a set of technologies that enable collaborative activities in virtual scenarios while users can participate in such activities remotely via various interfaces. The unique features of CVE make it a promising tool for distant and blended learning, especially when considering the impact of COVID-19 pandemic on conventional face-to-face learning and the much-improved accessibility of the relevant technologies nowadays. This paper reports a systematic review on this emerging area and aims to answer four research questions related to the subject areas being covered, instructional and pedagogical methods, interface technology and virtual world design, and learning outcomes and effectiveness. After applying the selection criteria, a total number of 11 studies, which were published between 1 January 2017 and 31 December 2021, were included in our analysis and discussion. Our findings support the use of CVE in the higher education setting and suggest further investigating the underlying mechanism of learning in CVE, exploring the potential and unique benefits of CVE in practicing distant and blended learning, studying the roles of teachers in CVEs, and evaluating the learning effectiveness on larger samples and through longitudinal studies. © 2022, Springer Nature Switzerland AG.
ABSTRACT
In this project, a low-cost voice operated vending machine (VOVM) is designed using a V3 voice recognition module which is a touchless base vending system. The basic vending machine represents an automatic seller machine where the buyer puts the money in terms of coin or banknote into the vending machine. Then, the required product will be vending out from the machine after selecting the item which is store inside the system. After analysing several vending machines, it is found that the proposed VOVM is more advanced than the other existing vending machine as it can select the items without any contact with the system. This VOVM may also be useful to this current pandemic situation of COVID-19 because of its unique features. The main objective is to upgrade the touchbased vending machine to voice operated system as one can select any items in the vending machine using voice command. This system will make it easier for the user to interact with the machine for everyone and also it can be deployed in every corner of the workplace, hospital, airport, schools, railway station, etc. for selling different kinds of products efficiently. © 2021 IEEE.
ABSTRACT
In a very less time from its advent, blockchain technology has entered into mainstream research all over the world. The Bitcoin cryptocurrency is the first open-source implementation of blockchain technology. The application of blockchain technology is not restricted to financial services only;several other sectors especially healthcare is increasingly focusing their attention to grab potential and unique features of blockchain technology like immutability, security, and trust. This paper aims to review the exploration of blockchain technology in the healthcare domain in recent years and study how these emerging technologies help healthcare to speed up treatment procedures and mitigate the effects of the COVID-19 pandemic. © 2021 IEEE.
ABSTRACT
As the first pandemic wave of Covid-19 hit India and the Indian Government announced a nationwide lockdown in March 2020, [1] it left millions of interstate migrant workers/daily-wage earners without a source of livelihood. Many of them had to return to their hometowns, often hundreds of kilometers away, with many walking a major part or the entirety of the distance [2]. This situation called for a design that could empower migrant workers to thrive in the new normal. An app was designed to enable migrant workers to search for jobs, learn about micro-entrepreneurship, get mental health assistance and develop skills. In terms of usage and interaction, this app proposes several unique features - a result of researching about and understanding our target demographic. At the core of the interaction is a chatbot. It asks questions to the user through text and audio, but the user replies through clickable buttons only. This makes it easy, even for those who may not be literate. The keyboard has been removed from this app. Another unique feature is the usage of interactive videos to explain various things, such as micro-entrepreneurship, skill training, etc. These videos make use of buttons for the users to make choices. In this paper, we discuss these two new interactions that will introduce a visual input method and an interactive video interface which will be inclusive of those less-privileged in terms of literacy in our ever-expanding tech world. The contents of the paper are targeted toward helping the next billion users. However, some of the things proposed may go on to improve interactions for all. © 2021, Springer Nature Switzerland AG.