Investigating the relationship between COVID-19 shutdown and land surface temperature on the Anatolian side of Istanbul using large architectural impermeable surfaces.

Artificial impermeable surfaces are becoming more prevalent, especially in urban areas, as a result of shifting land use and cover, roads, roofs, etc. The modification of land surface temperature (LST) can also be accomplished through artificially impermeable surfaces. Large artificial impermeable surfaces, such as rooftops, parking lots, and other areas of use, can be found in industrial zones, shopping malls, industrial airports, and other locations. For the Anatolian side of Istanbul, 14 Landsat 8 OLI/TIRS imagery images over the years 2016-2022 were investigated. To evaluate how well the study's images could be utilized, correlation and cosine similarity approaches were employed. A total of 12 images may be employed for research LST studies, it was discovered. We looked at closure dates during the COVID-19 epidemic to find out how human migration affected the LST. In addition, the LST value was estimated using the ordinary least squares (OLS) method employing LST and other biophysical indices. A decrease in LST values was seen as a result of the investigation. High levels of similarity and correlation were found between the images used. Results from the Google Mobility Index also provide support to the study. All of these facts provide support to Istanbul's Anatolian side experiencing lower surface temperature values, which consequently affects the city's massive structures.

A Comparison of the Instructor-Trainee Dance Dataset Using Cosine similarity, Euclidean distance, and Angular difference

The COVID-19 outbreak has restricted most outdoor activities, leads to increasing interest in exercise at home with online trainers. One issue of online exercise technology is the safety since improper motion might result in injury. As a basis to prevent improper motion, methods for evaluating the motion similarity between an instructor and a trainee are essential. Cosine similarity, Angular difference, and Euclidean distance are three general ways for the motion evaluation. This study aimed to determine the most effective way for analyzing the similarity of human motion on the dataset of instructor-led dances. We first experimented with the data to find the appropriate cut-off value for classifying posture into two classes based on the similarity score. Confusion matrix, precision, recall, F1-score, accuracy of the results were then used to compare the efficiency. We discovered that Cosine similarity had the highest accuracy, 82.77 percent at cut-off 93. © 2022 IEEE.

SCS-Net: An efficient and practical approach towards Face Mask Detection.

Much work has been done in the computer vision domain for the problem of facial mask detection to curb the spread of the Coronavirus disease (COVID-19). Preventive measures developed using deep learning-based models have got enormous attention. With the state-of-the-art results touching perfect accuracies on various models and datasets, two very practical problems are still not addressed - the deployability of the model in the real world and the crucial cases of incorrectly worn masks. To this end, our method proposes a lightweight deep learning model with just 0.12M parameters having up to 496 times reduction as compared to some of the existing models. Our novel architecture of the deep learning model is designed for practical implications in the real world. We also augment an existing dataset with a large set of incorrectly masked face images leading to a more balanced three-class classification problem. A large collection of 25296 synthetically designed incorrect face mask images are provided. This is the first of its kind of data to be proposed with equal diversity and quantity. The proposed model achieves a competitive accuracy of 95.41% on two class classification and 95.54% on the extended three class classification with minimum number of parameters in comparison. The performance of the proposed system is assessed with various state-of-the-art literature and experimental results indicate that our solution is more realistic and rational than many existing works which use overly massive models unsuitable for practical deployability.

Mental Health Frequently Asked Questions Chatbot Powered by Machine Learning

Mental health has been a topic of discussion since the COVID-19 pandemic. This article was focused on creating a chatbot app that will answer those frequently asked questions/statements about mental health to educate individuals. Within this project, natural language processing was used to preprocess the data. Term frequency-inverse document frequency vectorization method was used to explore if k-means clusters can categorize the questions/ statements. To reduce the dimensionality of the data vectors principal component analysis (PCA) and ISOMAP algorithm were used. PCA did not perform well for this dataset while ISOMAP did provide reasonable results. Lastly, for the app's design, several similarity measures such as, cosine similarity, Jaccard similarity, and Manhattan distance were experimented with to see which method would work the best to come up with the correct answer for the chatbot. Jaccard similarity was determined to be the best algorithm for the chatbot because it was able to handle questions and statements better than cosine similarity and Manhattan distance. The chatbot was created using the python library Kivy. © 2022 IEEE.

Integration of Content-Based Recommendation System with 360° video player for Virtual Tourism

Nations that rely on tourists visiting their countries as a key source of income have suffered significantly because of the Covid-19 outbreak. As a result, we've chosen to develop a 360° Video Tourism mobile application that will allow users to view the sights of the destination they desire to visit and feel as if they've been transported there. This Android application makes use of 360° video playback technology, which allows users to watch videos in all directions. When the user starts the 360° video, he or she can swipe and move their finger around the screen of their Android device, and the video will appear to shift its orientation and show scenes accordingly. The application uses Firebase as its database to store data, right from the user's personal information to the videos that can be viewed. This application was written in the JAVA programming language and connected with a content-based recommendation system. This algorithm, which is based on Cosine Similarity, suggests similar areas to the user's selected location. If a user chooses 'Taj Mahal,' for example, the application will suggest monuments that are similar to the Taj Mahal. This application serves as a solution, not only for users for exploring unexplored areas from the comfort of their homes but also a chance for the tourism industry to advertise and promote new tourism destinations, leading to increased visitor numbers and higher revenue. © 2022 IEEE.

Essay Test Based E-Testing Using Cosine Similarity Vector Space Model

The covid-19 pandemic has been pushing the development of online learning systems in Indonesia. In online learning, computer-based essay tests and assessments have an essential role. Essay test systems are designed to mimic the concept of essay tests without being computer-based. The answer from the lecturer is compared to the response from the student. The TF-IDF (Term Frequency -Inverse Document Frequency) cosine similarity is used. It is one of the methods of information re-gathering systems. The process in this model consists of two types: 1) creating a corpus/ inverted file, and the second is cosine similarity (CS) for calculating the similarity of the user's answers with the lecturer's. Creating a corpus/inverted file involves several stages like data collection, parsing sentences into terms, stoplist, weighting with IDF, and term weighting using TF-IDF. The cosine similarity process consists of parsing users' answers, weighting users' answers using TF-IDF, and finding cosine similarity values of users' answers with lecturers' answers using the vector space model. The highest cosine similarity value is taken to give the user's answer points. Testing the Essay Test system produces excellent grades. The tests were done Mean Squared Error (MSE) values resulted in an average MSE value of 3.28 from three students. © 2022 IEEE.

Thai Question-Answering System Using Pattem-Matching Approach

Teaching concepts in Thailand's universities have abruptly changed, due to the advancement of the COVID-19 pandemic, including changes in classroom to online formats, as well as administrative difficulties. The research herein, therefore, addresses these concerns, presenting a Thai question-answering system using the pattern-matching approach. Our case study covers course information, teaching timetable, teacher schedule, and course supplements. We classified the questions into six categories according to type and acknowledged typical expressions which matched to question patterns. We use RegEx® to match a defined pattern. When a response did not match, we used word embedding to transform the question into a vector and then calculated the cosine similarity to identify the most similar pattern. The system can then generate a corresponding SQL command to query the answer from the database. We evaluated the accuracy of the proposed system with the collected data resulted in an accuracy rate of 82%. © 2022 IEEE.

Examining the Interplay between Social Media Usage, Happiness, and Academic Performance with Data Science

There are numerous separate studies between social media usage and happiness, or social media and academic performance. However, the triangular relationship hasn't been thoroughly scrutinized. We set out our study wondering about the deep logic behind this interplay and its lessons on helping people make better decisions. We used correlation, linear regression, cosine similarity, random forest prediction, and aided visualization to analyze the data set collected. A strong association was found but the exact model of the trigonal relationship remained a mystery. COVID impacts people's happiness and GPA were also studied. © 2022 IEEE.

Analyzing the Sustainability of Industry Affected in COVID-19 Pandemic Scenario Using Cosine Similarity Measure under SVPNS and PNN Model

COVID-19 outbreak is a reminder of the fact that the pandemics have happened in the past and will also occur in the future. The COVID-19 not only has affected the economy;but also it has affected the livelihood, which leads to the changes in businesses. This study aims to identify the most significant indicator (or parameter) that impacts the sustainability of industries. The study should also develop a real-time monitoring system for the sustainability of industries affected by COVID 19. In this work, the Polynomial Neural Network (PNN) and cosine similarity measure under SVPNS (Single-Valued Pentapartitioned Neutrosophic Set) environment have found their use in analyzing the sustainability of the industry. © 2022, American Scientific Publishing Group (ASPG). All rights reserved.

An Efficient Algorithm to Recommend Covid-19 Related Solutions

With the rise of Covid-19, the open-source community has devoted a huge amount of time into developing technical solutions to stop the spread of the virus. Useful solutions like symptom trackers and extensive analysis on existing datasets are a small drop in the massive number of solutions developed by people. But with the massive number of projects or solutions, it is time consuming for a motivated person to find an appropriate solution to put his time into. Therefore, seeing the inspiring amount of work done by the open source community, we are suggesting an efficient algorithm to recommend projects that are Coronavirus related to which the user can get recommendations for projects according to their preference such as language. © 2022 IEEE.

SATLabel: A Framework for Sentiment and Aspect Terms Based Automatic Topic Labelling

In this paper, we present a framework that automatically labels latent Dirichlet allocation (LDA) generated topics using sentiment and aspect terms from COVID-19 tweets to help the end-users by minimizing the cognitive overhead of identifying key topics labels. Social media platforms, especially Twitter, are considered as one of the most influential sources of information for providing public opinion related to a critical situation like the COVID-19 pandemic. LDA is a popular topic modelling algorithm that extracts hidden themes of documents without assigning a specific label. Thus, automatic labelling of LDA-generated topics from COVID-19 tweets is a great challenge instead of following the manual labelling approach to get an overview of wider public opinion. To overcome this problem, in this paper, we propose a framework named SATLabel that effectively identifies significant topic labels using top unigrams features of sentiment terms and aspect terms clusters from LDA-generated topics of COVID-19-related tweets to uncover various issues related to the COVID-19 pandemic. The experimental results show that our methodology is more effective, simpler, and traces better topic labels compare to the manual topic labelling approach. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Similarity in Sequences of COVID-19 Genetic Codes over Galois Field

The Coronavirus disease 2019 (COVID-19) outbreak has caused the eco- nomic and health problems for all countries. The origin based on genetic codes of its spreading is a signi cant key for identi cation and solution of the outbreak. The purpose of this research is to study the relation- ships based on similarity measurement over Galois eld amongst genetic codes of COVID-19. A Galois eld is an structure for converting genetic codes to binary codes derived from polynomials and then simi- larity is measured by examing the binary codes. The application is the investigation of the relationships amongst the sequences of genetic codes of COVID-19 particles contaminated from waste water in Brazil, Spain, Italy and the sequences of COVID-19 genetic codes in Thailand and China over Galois eld. The nding shows that the similarity of COVID-19 ge- netic code sequences between China and Brazil is the maximum similarity, 99.9746%. In addition, the relationships amongst the sequences' genetic COVID-19 codes from Wuhan markets, SARS and bats are also investi- gated over a Galois eld. The nding found that the similarity of COVID-19 genetic codes sequences between Bat coronavirus RaTG13-MN996532.1 and Wuhan market- LR757995.1 is the maximum similarity, 55.8548%. In conclusion, the sequence of COVID-19 genetic codes in Brazil is possi- bly signi cant and related to the sequence in China, and vice versa. The sequence of COVID-19 genetic codes at Wuhan market- LR757995.1 is pos- sibly transmitted from Bat coronavirus RaTG13 genetic code to humans in China. © 2022, ECTI Association. All rights reserved.

Finding Spatial-Textual Clusters in COVID Tweets

Finding Semantic similarity in text is a vital concept in the fields of information mining, text-based profiling. There have been many approaches to improve information retrieval by mining the semantics of the text. With the pandemic situation prevailing all over the world, we come across many useful posts about the COVID infection that is being tweeted by medical practitioners and people in the health care sector. While we come across such tweets, we also have tweets related to the vaccines, medical facilities, change in economic conditions due to pandemic, etc. But there is no methodology to efficiently study the tweet data and retrieve useful information out of them. Also, we need to utilize the geographical information that comes with each tweet. Though there have been many studies conducted on sentiment analysis, statistical analysis related to twitter data, there has not been much research on finding out the geographical distribution of COVID related tweets combined with query-based textual similarity of COVID related tweets. In this paper, we try to study the semantics of geo-Tagged twitter data related to COVID and segregate the tweets based on their geographical location and according to the content of tweets. We use an improved version of Density-Based Spatial Clustering for clustering the tweets according to geo-spatial information. Then, we apply cosine similarity techniques to do the textural clustering and evaluate the performance of proposed model. The proposed model is able to cluster tweets using the spatial coordinates and classify the tweets based on the textual similarity measure. © 2022 IEEE.

Pilot Recommender System Enabling Students to Indirectly Help Each Other and Foster Belonging Through Reflections

Without a sense of belonging, students may become disheartened and give up when faced with new challenges. Moreover, with the sudden growth of remote learning due to COVID-19, it may be even more difficult for students to feel connected to the course and peers in isolation. Therefore, we propose a recommendation system to build connections between students while recommending solutions to challenges. This pilot system utilizes students' reflections from previous semesters, asking about learning challenges and potential solutions. It then generates sentence embeddings and calculates cosine similarities between the challenges of current and prior students. The possible solutions given by previous students are then recommended to present students with similar challenges. Self-reflection encourages students to think deeply about their learning experiences and benefit both learners and instructors. This system has the potential to allow reflections also to help future learners. By demonstrating that previous students encountered and overcame similar challenges, we could help improve students' sense of belonging. We then perform user studies to evaluate this system's potential and find that participants rated 70% of the recommended solutions as useful. Our findings suggest an increase in students' sense of membership and acceptance, and a decrease in the desire to withdraw. © 2022 ACM.

Semantic Malayalam Dialogue System for Covid-19 Question Answering Using Word Embedding and Cosine Similarity

Covid-19 is a global pandemic, has affected millions of people physically and mentally. The dynamic and rapidly growing situation with COVID-19 made it more difficult to discourse accurate and authoritative information about the disease, in most of the Indian local languages like Malayalam. To resolve this issue, here we propose a semantic Malayalam Dialogue System for COVID-19 related Question Answering. This is a user-friendly knowledge system to automatically deliver relevant answers to COVID-19 related queries in the Malayalam language. The proposed system proceeds in three stages;Document pre-processing, Semantic modelling using word embedding and Answer Retrieval. The NLP techniques are used for document processing, word embedding - CBOW and Skip Gram methods, Neural Network models are used for Semantic Modelling and finally, a cosine similarity measure is used to map and retrieve the answers for the user's queries. The experiment was conducted with our own Malayalam dataset;and compared the performance of two Word2Vec algorithms - CBOW and Skip Gram. The result, with our data set, shows that Skip-Gram is more efficient than CBOW and CBOW is faster than the Skip Gram model. © 2021 IEEE.

A Descriptive Answer Evaluation System Using Cosine Similarity Technique

Use of computer in spite of human in knowledge discovery and engineering is a trend from last decade. In situation of COVID-19, it is need of hour to use such computer assisted assessment tools which will reduce the work of teachers in education domain. In Literature various techniques were developed to assess the answers of objective types questions by using machine learning but very less work carried out on assessment of answer of descriptive type questions. This paper provides a solution for the assessment of answer of descriptive type questions where teacher need not to use any paper or pen but the computer imitates like as teacher and evaluate answer of students. The primary objective is to represent results of subjective answers in the form of pictorial representations using cosine similarity technique. Cosine similarity is one of similarity measures which find similarity between two objects irrespective of their size. The results of web-based application are sufficient enough to withdraw the traditional teacher centric assessment approach and develop a computer-aid solution which is beneficial for educational institutions. © 2021 IEEE.

Using Word2Vec-LDA-Cosine Similarity for Discovering News Dissemination Pattern to Support Government–Citizen Engagement

Evidence of ineffective government–citizen engagement was observed when the Malaysian government decided to make face masks mandatory in public spaces. It is especially critical during a COVID-19 pandemic, where public compliance depends on the speed and clarity at which regulations are announced. Hundreds of arrested cases due to violation were met with confusion and demanded greater clarification. This evidence signifies the need to identify if government-disseminated information is communicated effectively to the citizens through news coverage. Despite this need, current literature has limitations in effectively analysing huge numbers of articles as they mainly employ manual intervention for data news content analysis. Furthermore, there has been no usage of systematic text analytics approaches in government–citizen engagement studies through newspapers. As such, we researched and implemented a modelling framework for discovering how news coverage pattern aligns with government-disseminated information through a case study of COVID-19 in Malaysia during the pandemic. A Word2Vec-LDA-cosine similarity technique was employed in our framework to determine topic similarities as the indication of alignment between news content and government-disseminated information. Our results show that this framework succeeds in capturing the semantics of the corpus to describe news coverage at the same time identified the challenges in general topic comparison tasks. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

COBERT: COVID-19 Question Answering System Using BERT.

In the current situation of worldwide pandemic COVID-19, which has infected 62.5 Million people and caused nearly 1.46 Million deaths worldwide as of Nov 2020. The profoundly powerful and quickly advancing circumstance with COVID-19 has made it hard to get precise, on-request latest data with respect to the virus. Especially, the frontline workers of the battle medical services experts, policymakers, clinical scientists, and so on will require expert specific methods to stay aware of this literature for getting scientific knowledge of the latest research findings. The risks are most certainly not trivial, as decisions made on fallacious, answers may endanger trust or general well being and security of the public. But, with thousands of research papers being dispensed on the topic, making it more difficult to keep track of the latest research. Taking these challenges into account we have proposed COBERT: a retriever-reader dual algorithmic system that answers the complex queries by searching a document of 59K corona virus-related literature made accessible through the Coronavirus Open Research Dataset Challenge (CORD-19). The retriever is composed of a TF-IDF vectorizer capturing the top 500 documents with optimal scores. The reader which is pre-trained Bidirectional Encoder Representations from Transformers (BERT) on SQuAD 1.1 dev dataset built on top of the HuggingFace BERT transformers, refines the sentences from the filtered documents, which are then passed into ranker which compares the logits scores to produce a short answer, title of the paper and source article of extraction. The proposed DistilBERT version has outperformed previous pre-trained models obtaining an Exact Match(EM)/F1 score of 80.6/87.3 respectively.

Quantifying the publication preferences of leading research universities.

Research universities have a strong devotion and advocacy for research in their core academic mission. This is why they are widely recognized for their excellence in research which make them take the most renowned positions in the different worldwide university leagues. In order to examine the uniqueness of this group of universities we analyze the scientific production of a sample of them in a 5 year period of time. On the one hand, we analyze their preferences in research measured with the relative percentage of publications in the different subject areas, and on the other hand, we calculate the similarity between them in research preferences. In order to select a set of research universities, we studied the leading university rankings of Shanghai, QS, Leiden, and Times Higher Education (THE). Although the four rankings own well established and developed methodologies and hold great prestige, we choose to use THE because data were readily available for doing the study we had in mind. Having done that, we selected the twenty academic institutions ranked with the highest score in the last edition of THE World University Rankings 2020 and to contrast their impact, we also, we compared them with the twenty institutions with the lowest score in this ranking. At the same time, we extracted publication data from Scopus database for each university and we applied bibliometrics indicators from Elsevier's SciVal. We applied the statistical techniques cosine similarity and agglomerative hierarchical clustering analysis to examine and compare affinities in research preferences among them. Moreover, a cluster analysis through VOSviewer was done to classify the total scientific production in the four major fields (health sciences, physical sciences, life sciences and social sciences). As expected, the results showed that top universities have strong research profiles, becoming the leaders in the world in those areas and cosine similarity pointed out that some are more affine among them than others. The results provide clues for enhancing existing collaboration, defining and re-directing lines of research, and seeking for new partnerships to face the current pandemic to find was to tackle down the covid-19 outbreak.