Certain investigation on detection of sleep arrhythmia disorders using artificial intelligence methods

Abstract

Discovering the data is one of the main issues with big data sources is newlineveracity. A feature of big data called veracity strongly emphasizes accuracy newlineand dependability. On social media websites and platforms, which have a newlinewealth of information and exceedingly conflicting views, it is difficult to find newlinethe truth about big data. Recent innovations have facilitated enormous newlineamounts of data processing. Researchers in the big data field have begun newlineexploring potential approaches in the form of Crowdsourcing to learn how it newlinecan be useful in boosting the core idea of big data in a productive, relatively newlineinexpensive, and scalable manner since the advent of Crowdsourcing s newlinefundamental idea. But, the collected data is inherently uncertain because of newlinenoise, discrepancy, and incompleteness. To solve this problem, improving newlinedata veracity is crucial. As big data veracity is more critical, it must predict newlinethe veracity of tweets automatically for decision-making. Many techniques newlinehave been developed, such as artificial intelligence and crowdsourcing newlinemodels, to estimate the veracity of tweets from single sources. But, these newlinemodels are ineffective while the amount of crowd labels for tweets from newlinemultiple sources (Facebook, Instagram, and Twitter) is not feasible. Also, newlineanalyzing the sentiment of public opinions has high complexity. As a result, newlinethis article focuses on developing an efficient model to predict the veracity of newlinetweets from multiple sources and analyze the sentiments of the passage. First, newlinedifferent tweets with text labels are collected. Then, a crowdsourcing model is newlineintroduced, which uses the crowdflower dataset to obtain the crowd labels for newlinecollected tweets. Also, the Generative Adversarial Network (GAN) model is newlineapplied to increase the veracity of tweets by handling the low-veracity tweets. newline