ABSTRACT
The Covid-19 pandemic that hit us in 2020 changed our lifestyle in every way. There was tremendous damage to people's lives. It is now predicted that other variants of Coronavirus are affecting people's health throughout the world. We must remain vigilant against upcoming dangers. The Indian health ministry has also advised people to take the necessary precautions. In this paper, we will focus on automating temperature and oxygen monitoring using the Internet of Things. According to our proposed model, data generated by the temperature sensor (MLX90614) and oxygen saturation sensor (MAX30102) will be stored in a relational database. Using this data, future data analyses can be conducted. We are also going to visualize the data by building an interactive dashboard using Power BI. Overall, health monitoring will become much more convenient and speedier. © 2023 IEEE.
ABSTRACT
Data visualization is a very important step in data analysis as it provides insight into the data in a more effective manner that is interesting, simple, and understandable to every-one without any language barrier. It can also represent a huge amount of data in a small space very easily. In the previous two years, the whole world has suffered from a very terrifying nightmare known as COVID-19. Known to be starting from the country of China, the pandemic affected not only the health and well-being of mankind, but also had serious impacts on the economies of various countries. Hence, a visualization of the data set of the pandemic might provide beneficial insights for finding a possible solution and can help in overcoming the impacts of the pandemic. Microsoft Power BI is a very famous tool for analyzing data. Power BI provides a different way to visualize the data. This paper has been analyzed the covid-19 data by using Power BI to understand the trends and patterns of the Pandemic. With the help of visualizing the data, it can be represented in stacked column charts, tables, and maps. These three ways are easy and simple to understand the patterns of the pandemic. It also helps to understand how covid impact the world. This research with power BI dashboard by using a dashboard feature that connects different pieces of visual graphs. © 2023 IEEE.
ABSTRACT
The rise of the Coronavirus pandemic was unanticipated, and it turned into a very serious and catastrophically dangerous scenario especially in terms of financial balance, physical and mental health, population growth, socialization, and globalization. This paper considers Australian COVID-19 data from its beginning on the 25th of January to this date for experimental study. The popular Microsoft Power BI tool and Python coding language were primarily utilized to visualize the data sets and understand the depth of the COVID-19 situation in Australia. More specifically Python is primarily used in this study on the data to generate visualizations and forecasted models for effective interpretation of the ongoing medical peril. The plots and graphs created significantly extract trends for the accumulative infection rates ongoing in Australia from February 2020 to September 2021. Such important comprehensions of the numerical data set allowed for a graphical understanding and representation with data science applications. Statistical forecasting models such as the autoregressive integrated moving average (ARIMA) model and the long short-term memory (LSTM) model were applied to the time series data of Australian COVID-19 infection numbers to predict the future trends of COVID-19 cases in Australia. Finally, we feel this research can help the policymakers and health practitioners to manage such global medical issues more efficiently in the future with the help of data science technology and applications which is the uprising heart of our technological era.
ABSTRACT
Currently the transformation of a city involves the participation of users through all media and especially through communication networks and social networks. Right now, the pandemic waves of COVID-19, and the phases of confinement, oriented users to communicate through social networks specifically Twitter in which they shared their feelings, and the behavior of their situation in the face of the pandemic. When talking about sharing sentiment information on social networks we are talking about a large volume of information that is posted on the networks that can be processed and analyzed using technological tools including RStudio to collect and process;and Power BI to analyze and visualize. The methodology presented has been the result of a process of investigation of related works focused on the participations of the users of a city in Ecuador downloading data from the Social Network Twitter. The methodology is composed of the phases of collecting, storing, transforming, analyzing and visualizing, and the development and execution of the proposal, leaving solid foundations for the implementation of an intelligent campus prototype that combines technological tools and the analysis of information that supports decision making and information analysis. © 2022 IEEE.
ABSTRACT
The construction sector generates large amounts of heterogeneous and dynamic data characterized by their fragmentation throughout the life cycle of a project. Immediate and accurate access to that data is fundamental to the management, decision-making and analysis by construction owners, supervisors, managers, and technicians involved in the different phases of the project life cycle. However, since construction project data are diverse, dispersed, uncorrelated, and difficult to visualize, a reliable basis for decision-making can rarely be established by the management team. Aiming to bridge this gap, a methodology for data management during building construction by means of Data with BIM and Business Intelligence (BI) analysis tools was developed in this study. This methodology works by extracting data from 3D parametric model and integrating it with a BI tool, through which data are visualized and interrelated with the same database, the BIM model. To demonstrate the applicability of the methodology, a study case was carried out. It was shown that this methodology provides a collaborative platform for accurate data analysis to the construction management and supervision teams, allowing project stakeholders to access and update data in real-time, in permanent linkage with the BIM model. Additionally, improving the reliability of the decision-making process and ensuring project deliverability, the developed methodology contributes to a more sustainable management process by decreasing errors and resource consumption, including energy. Therefore, the main goal of this study is to present a methodology for data analysis with BIM models integrated with BI for sustainable construction management.