Masked Facial Recognition Using Deep Metric Learning

Due to the Covid-19 disease, masked faces identification has become the current challenge. This type of identification is difficult because masks cover noses and mouths, obscuring important features for facial recognition. A deep learning-based model for recognizing masked faces is presented in this paper. We tested our system on a dataset of 2113 images collected from 179 people with and without masks. The obtained results are analysed using various metrics and appear to be motivating. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Pre-processing SARS-CoV-2 Sequence Data for Application of Machine Learning Techniques for Visualization and Clustering of Virus Characteristics

SARS-CoV-2, first known as unknown pneumonia on December 31, 2019, has been around the world for more than two years. As the virus has spread for a long time, various types of mutant viruses have occurred, and the sequence data of the virus has been accumulated considerably. Therefore, studies are being conducted on the types of mutations that are divided by analyzing sequence data and what features are found in which variants. Traditionally, this kinds of sequence analysis has been dominated by analysis and visualization using phylogenetic trees. Analysis with these phylogenetic trees can be useful if there is not much data. However, analysis and visualization are not easy when there are hundreds of thousands or millions of data. Thus, in this study, we propose a method to pre-process virus sequence data so that several machine learning techniques can be applied to better analyze and visualize data. In this study, SARS-CoV-2 sequence data is pre-processed by suggesting method and machine learning models such as Auto Encoder and DBSCAN are applied to extract important features and clustering the data. According to the experimental results, important features were extracted by reducing the dimension of the data, and it was confirmed that a numerous amount of viruses were well visualized on 3-dimensional graphs depending on the characteristics of the data, and that they were well clustered according to the virus variation. © 2022 Asia-Pacific of Signal and Information Processing Association (APSIPA).

The development history, important features and future trends of American online master's degree programs

In recent years, due to the impact of the coronavirus "COVID-19"pandemic crisis, obtaining a degree through online learning is attracting more and more people's attention. The research object of this article is the online master's degree program, which is a master-level education based on distance education. The enrollment targets are adults who have obtained a bachelor's degree or above, or are working adults, and the training form is mainly in the form of distance education. The development of the American online master's degree program started early and has gone through three stages of beginning, development and transformation. The development of online master's degree programs has important characteristics: the program provides from closed to open, the main provider from single to multiple, online education and traditional higher education from separation to integration.In the future, American master's degree programs will continue to be unbundled. © 2022 ACM.

Importance of Sequencing the SARS-CoV-2 Genome Using the Nanopore Technique to Understand Its Origin, Evolution and Development of Possible Cures

The sequencing of the genome of new virus, such as the coronavirus type 2 of the acute severe respiratory syndrome (SARS-CoV-2), is essential and of great importance to mitigate new zoonotic outbreaks, which are caused by mutations present in structural and non-structural proteins that make up the viruses. Sequencing allows tracking the behavior of the virus locally and globally, knowing the route of transmission and spread of the virus, and determine the virulence rate. Current studies have been carried out, using first, second or third generation sequencing techniques, which have allowed reading and analyzing the nucleotides that make up the virus genome. Thus, the benefits of effective technologies to know its genetic composition in the shortest possible time become evident. New technologies are able to monitor an epidemic in real time, monitor the evolution and efficacy of a drug, the development of a vaccine as well as epidemiological advances. This work addresses the Oxford Nanopore sequencing, which is considered the most efficient and applied method for sequencing viruses that cause epidemics. Some of the advantages of using this sequencing are highlighted in this work, such as the ability to perform long readings and be able to obtain sample responses in short time. It’s also able to discover as much information as possible about the pathogen, being an important feature to deal with public health emergencies, such is the case of the COVID-19. © 2022, Springer Nature Switzerland AG.

An Automated Model for Booking Appointment in Health Care Sector

This technical paper primarily focuses on requirement of automation in medical sector. As in the current scenario, we can see that from November 2019 to April 2021, more than 15 crores[1] patients were admitted to hospitals and this number is only contributed by Covid-19 without considering other viruses and diseases. Thus, it is the need of hour to introduce a system which can resolve the problems in appointment booking in such a crisis.As of now, world is reaching towards a population of 8 billion[2] but only 164,500[3] hospitals are available worldwide in 2015 which is quite low with respect to population. So our model helps in managing the appointments in such a large extent which will ultimately reduce the load on hospitals. Our model provides the facilities like instant appointment booking with the generation of unique patient ID which will identify any patient worldwide. Thus it will help in tracking any patient's medical reports with the option of online payment, reducing the use of paper and this will be a big step in saving the trees and environment. Our model also gives a comparison feature, enabling the users to get a glance of various prices, ratings of hospitals and doctors. Another important feature which our model provides is locating nearest hospitals from patient's location. © 2021 IEEE.

Face Mask Detection using CNN

Face recognition is an important feature of computer vision. It is used to detect a face and recognize a person and verify the person correctly. Face recognition technology plays an essential role in our everyday lives like in passport checking, smart door, access control, voter verification, criminal investigation, and system to secure public places such as parks, airports, bus stations, and railway stations, etc and many other purposes. While going through the pandemic and the post pandemic situations wearing a mask are compulsory for everyone in order to prevent the transmission of corona virus. This resulted in ineffectiveness of the existing conventional face recognition systems. Hence it is required to improvise the existing systems to get the desired results to detect the masked face at the earliest. This system works in three processes that are image pre-processing, image detection, and image classification. The main aim is to identify that whether a person’s face is covered with mask or not as per the CCTV camera surveillance or a webcam recording. It keeps on checking if a person is wearing mask or not. For classification, feature extraction and detection of the masked faces, Convolutional Neural Network (CNN) and Caffe models are used. These help in easy detection of masked faces with higher accuracy in a very less time and with high security. © 2021 IEEE.

Knowledge Gain in Student's Digital learning: COVID'19 lockdown

This paper is concerned with the problem of students' upgradation of knowledge gained through digital learning. The analysis is carried out with respect to the respondent's attitude in learning classes remotely with the required ambience, bonding between faculty -students' and the relationship with peers and parents' in the advent of COVID'19 lock down period. The important features of the results reported here brings the correlation between respondents' state of mind and online classes. By constructing a predictive data analysis, sufficient conditions are rendered to cope up with their future plans with respect to the current observations. Finally, two simulation examples are given for the effectiveness of the proposed method. © 2021 IEEE.

User Interface/User Experience (UI/UX) Analysis Design of Mobile Banking App for Senior Citizens: A Case Study in Sarawak, Malaysia

Smartphones are having such a huge impact to our society and in our daily lives. However, most smartphone applications are not that user-friendly for a senior-aged person. Due to the COVID-19 pandemic, everything now is done online including mobile banking services. There are seniors who refuse to use mobile banking applications in Malaysia because they are not familiar nor comfortable with the app's interface and flow. This study aims to perform a need analysis on user interface and user experience (UI/UX) design for Malaysian seniors when using a mobile banking app. A questionnaire was used in this research as a quantitative research tool, involving 36 respondents aged 55 years old and above, and currently a resident of Sarawak. The questionnaire is split into 5 sections, i.e., demographic, technology background, task, task rating, and preferences. We observed that 'Fast loading time' is ranked as the most important feature with the highest mean value of 5.0. The least important feature is 'Payment via QR Code' with a mean value of 2.7. Our findings can be used as a basis to prioritize features when designing a mobile banking app to accommodate senior users. © 2021 IEEE.

A SSA-Based Attention-BiLSTM Model for COVID-19 Prediction

The Corona Virus Disease 2019 (COVID-19) has widely spread over the world and comes up with new challenges to the research community. Accurately predicting the number of new infections is essential for optimizing available resources and slowing the progression of such diseases. Long short-term memory network (LSTM) is a typical method for COVID-19 prediction in deep learning, but it is difficult to extract potentially important features in time series effectively. Thus, we proposed a Bidirectional LSTM (BiLSTM) model based on the attention mechanism (ATT) and used the Sparrow Search Algorithm (SSA) for parameter tuning, to predict the daily new cases of COVID-19. We capture the information in the past and future through the BiLSTM network and apply the attention mechanism to assign different weights to the hidden state of BiLSTM, enhance the ability of the model to learn vital information, and use the SSA to optimize the critical parameters of the model for matching the characteristics of COVID-19 data, enhance the interpretability of the model parameters. This study is based on daily confirmed cases collected from six countries: Egypt, Ireland, Iran, Japan, Russia, and the UK. The experimental results show that our proposed model has the best predictive performance among all the comparison models. © 2021, Springer Nature Switzerland AG.