scholarly journals Issues of COVID 19 Screening with Machine Learning Algorithm and Data Sets Availability

2021 ◽  
Author(s):  
G.N. Balaji ◽  
S.V. Suryanarayana ◽  
P. Vijayaragavan
Keyword(s):  
Machine Learning ◽  
Learning Algorithm ◽  
School Management ◽  
Data Sets ◽  
Machine Learning Algorithm ◽  
Shopping Malls ◽  
Railway Stations ◽  
Group Participation ◽  
The Mathematical Model ◽  
Screening Systems

There is a need to wear a mask during the coronavirus outbreak to efficiently deter the transmission of COVID-19 virus. In these instances, traditional facial screening technologies obsolete for monitoring of group entry at Airports, shopping malls, railway stations, etc. It is, therefore, vital to boost the efficiency of screening. This paper addresses the machine learning algorithm for contactless face screening systems in group participation, social interaction, school management, mall entry management, and market resumption scenarios in the case of COVID- 19. A method to screen entry with masks are developed using machine learning, which depends on various face specimens that were discussed here. The second fold discussion in this paper is that previously there are not many freely accessible masked face-databases. To this end, various forms of masked face data sets are identified, namely MFDD, Real MFRD, and Simulated MFRD. Such data sets became widely accessible to businesses and academics, based on which specific apps may be built on masked faces. The mathematical model, with the code was given. The availability and issues of the above data sets were discussed for the benefit of researchers.

scholarly journals Weather Prediction using Machine Learning and IOT

2020 ◽  
Vol 9 (4) ◽  
pp. 2094-2098
Keyword(s):  
Machine Learning ◽  
Weather Forecasting ◽  
Learning Algorithm ◽  
Weather Prediction ◽  
Weather Conditions ◽  
Data Sets ◽  
Machine Learning Algorithm ◽  
Time Data ◽  
Weather Parameters ◽  
Set Up

This project proposes a method for forecasting weather conditions and predicting rainfall by means of machine learning. Here, there are two set ups: one, to measure the weather parameters like temperature, humidity using sensors along with Arduino and another set up, to display the current values(status) and predicted rainfall based on the trained machine learning data sets. The weather forecasting and prediction is done based on the older datasets collected and compared with the current values. The user need not have a backup of huge data to predict the rainfall. Instead a machine learning algorithm can suffice the same. The temperature, humidity sensor modules are used to measure weather parameters and interfaced to an Arduino controller. The proposed setup will compare the forecast value with real-time data, and the predict rainfall based on the dataset fed to the machine learning algorithm.

scholarly journals Testing the classifier adapted to recognize the languages of works based on the Latin alphabet

2021 ◽  
pp. 83-94
Author(s):  
Zafar Usmanov ◽  
◽  
Abdunabi Kosimov ◽  
Keyword(s):  
Machine Learning ◽  
Mathematical Model ◽  
Learning Algorithm ◽  
Automatic Recognition ◽  
Machine Learning Algorithm ◽  
The Third ◽  
Optimal Value ◽  
Minimum Distances ◽  
Homogeneity Hypothesis ◽  
The Mathematical Model

Using the example of a model collection of 10 texts in five languages (English, German, Spanish, Italian, and French) using Latin graphics, the article establishes the applicability of the γ-classifier for automatic recognition of the language of a work based on the frequency of 26 common Latin alphabetic letters. The mathematical model of the γ-classifier is represented as a triad. Its first component is a digital portrait (DP) of the text - the distribution of the frequency of alphabetic unigrams in the text; the second component is formulas for calculating the distances between the DP texts and the third is a machine learning algorithm that implements the hypothesis of “homogeneity” of works written in one language and “heterogeneity” of works written in different languages. The tuning of the algorithm using a table of paired distances between all products of the model collection consisted in determining an optimal value of the real parameter γ, for which the error of violation of the “homogeneity” hypothesis is minimized. The γ-classifier trained on the texts of the model collection showed a high, 100% accuracy in recognizing the languages of the works. For testing the classifier, an additional six random texts were selected, of which five were in the same languages as the texts of the model collection. By the method of the nearest (in terms of distance) neighbor, all new texts confirmed their homogeneity with the corresponding pairs of monolingual works. The sixth text in Romanian showed its heterogeneity in relation to all elements of the collection. At the same time, it showed closeness in minimum distances, first of all, to two texts in Spanish and then to two works in Italian.

Machine Learning Predictions as Regression Covariates

2020 ◽  
pp. 1-18
Author(s):  
Christian Fong ◽  
Matthew Tyler
Keyword(s):  
Machine Learning ◽  
Prediction Error ◽  
Learning Algorithm ◽  
Data Sets ◽  
Machine Learning Algorithm ◽  
Regression Analyses ◽  
Political Dialogue ◽  
Latent Features ◽  
Text Images ◽  
True Values

Abstract In text, images, merged surveys, voter files, and elsewhere, data sets are often missing important covariates, either because they are latent features of observations (such as sentiment in text) or because they are not collected (such as race in voter files). One promising approach for coping with this missing data is to find the true values of the missing covariates for a subset of the observations and then train a machine learning algorithm to predict the values of those covariates for the rest. However, plugging in these predictions without regard for prediction error renders regression analyses biased, inconsistent, and overconfident. We characterize the severity of the problem posed by prediction error, describe a procedure to avoid these inconsistencies under comparatively general assumptions, and demonstrate the performance of our estimators through simulations and a study of hostile political dialogue on the Internet. We provide software implementing our approach.

scholarly journals Aislamiento social obligatorio: un análisis de sentimientos mediante machine learning

2021 ◽  
Vol 12 (26) ◽  
pp. 1-13
Author(s):  
Carlos Alberto Arango Pastrana ◽  
Carlos Fernando Osorio Andrade
Keyword(s):  
Machine Learning ◽  
Social Network ◽  
Social Network Analysis ◽  
Network Analysis ◽  
Learning Algorithm ◽  
Data Sets ◽  
Machine Learning Algorithm ◽  
Economic Problems ◽  
Colombian Government

To reduce the rate of contagion by Covid-19, the Colombian government has adopted, among other measures, for mandatory isolation, with divided opinions, because despite helping to reduce the spread of the virus, it generates mental and economic problems that are difficult to overcome. The objective of this document was to analyze the underlying sentiments in the Twitter comments related to isolation, identifying the topics and words most frequently used in this context. A machine learning algorithm was built to identify sentiments in 72,564 posts and a social network analysis was applied establishing the most frequent topics in the data sets. The results suggest that the algorithm is highly accurate in classifying feelings. Also, as the isolation extends, comments related to the quarantine grow proportionally. Fear was identified as the predominant feeling throughout the period of confinement in Colombia.

Sign in / Sign up

Export Citation Format

Share Document