Dealing with air pollution presents a major environmental challenge in smart city environments. Real-time monitoring of pollution data enables local authorities to analyze the current traffic situation of the city and make decisions accordingly. Deployment of the Internet of Things-based sensors has considerably changed the dynamics of predicting air quality. Existing research has used different machine learning tools for pollution prediction; however, comparative analysis of these techniques is required to have a better understanding of their processing time for multiple datasets. In this paper, we have performed pollution prediction using four advanced regression techniques and present a comparative study to determine the best model for accurately predicting air quality with reference to data size and processing time. We have conducted experiments using Apache Spark and performed pollution estimation using multiple datasets. The Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) have been used as evaluation criteria for the comparison of these regression models. Furthermore, the processing time of each technique through standalone learning and through fitting the hyperparameter tuning on Apache Spark has also been calculated to find the best-fit model in terms of processing time and lowest error rate.INDEX TERMS IoT, smart city, air quality index (AQI), data mining, Apache Spark.
This study is based on positivism research philosophy and utilizes deductive approach. The study uses a dataset of 117 firms listed on KSE-100 Index from 2005 to 2012 to analyze the predictability of capital asset pricing model (CAPM) under different data frequencies and time frames. Six months daily data, in contradiction to the recommended five years monthly data, provides the best estimates. However, the performance of model can be regarded poor as it only explains 7.39% difference in returns.
This study examines the response of the BRICS and MSCI emerging stock market indices to the COVID-19 outbreak. For this purpose, this study uses a multifractal detrended fluctuation analysis (MF-DFA) to investigate the market efficiency dynamics of these indices and then ranks them based on their market efficiency. Overall, our results indicate that the returns from all the stock indices exhibit long-range correlations, implying that these markets are not weak-form efficient. Specifically, China showed the highest level of multifractality (i.e., inefficiency), which can be attributed to its highly volatile market structure. Using a subsample analysis, we further explore the impact of COVID-19 on these markets’ efficiency by dividing the dataset into pre- and post-COVID periods. The findings indicate that COVID-19 adversely affected the efficiency of all the indices. Surprisingly, improvement in the Chinese market’s inefficiency was witnessed, which can be attributed to the prompt and effective measures (i.e., timely imposition of health-related measures such as lockdowns and resident quarantines to contain COVID-19 and financial packages designed to curtail the economic meltdown) introduced by the Chinese government. The findings of this study may help investors, policymakers and regulators in refining their financial and policy decisions according to the new efficiency levels of these markets.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.