Classification of a COVID-19 dataset by using labels created from clustering algorithms

Abstract

<span>Novel coronavirus (COVID-19) is a newly discovered infectious disease that has received much attention in the literature because of its rapid spread and daily global deaths attributable to such disease. The White House, together with a coalition of leading research groups, has published the freely available COVID-19 Open Research Dataset to help the global research community apply the recent advances in natural language processing and other AI techniques in generating novel insights that can support the ongoing fight against this disease. In this paper, the hierarchical and k-means clustering techniques are used to create a tool for identifying similar articles on COVID-19 and filtering them based on their titles. These articles are classified by applying three data mining techniques, namely, random forest (RF), decision tree (DT) and bagging. By using this tool, specialists can limit the number of articles they need to study and pre-process these articles via data framing, tokenisation, normalisation and term frequency-inverse document frequency. Given its 2D nature, the dimensionality of this dataset is reduced by applying t-SNE. The aforementioned data mining techniques are then cross validated to test the accuracy, precision and recall performance of the proposed tool. Results show that the proposed tool effectively extracts the keywords for each cluster, with RF, DT and bagging achieving optimal accuracies of 98.267%, 97.633% and 97.833%, respectively.</span>

Predictions and visualization for confirmed, recovered and deaths COVID-19 cases in Iraq

“…The data-sets has been analysed by the use of a variety of the exploratory approaches of data analysis and these data have been visualized for the purpose of providing an efficient consciousness in regards to COVID-19 outbreak worldwide. Visualization helps in understanding the spread of corona virus from one country to other and for how much [16]. In a response to that ongoing emergency for the public health, an on-line interactive dashboard has been developed, it has been hosted by Johns Hopkins University and CSSE (i.e.…”

A novel predictive model for capturing threats for facilitating effective social distancing in COVID-19

“…Therefore, irrespective of the unlocking process the social distancing is require for a prolonged period to avoid the possibility of re-infection: i) effect of social distancing: the negative trend of the GDP, loss of Jobs, changes environment of society, and scope of entertainment collectively has already impacted the socio-economic balance. The impact of prolonged social distancing will be incalculable from other ill effect on the physical, mental and economic health of the mankind [7]- [10]; ii) rationale of the solutions approach: the use of smart city technology especially mobile crowdsensing could yielded a feasible solution to make the success of the quarantine that does not impact on the decline of the economy. The technology namely mobile crowdsensing works on the data collected from the massive number sensor devices.…”

Applications of artificial intelligence with cloud computing in promoting social distancing to combat COVID-19

“…The principle of work of the Internet of things depends on a large group of devices distributed in the environment that are connected either wired or wirelessly and that interact with each other to achieve the desired goals by providing new services and applications [18], [19]. The internet of things is enabled by artificial intelligence (AI), which is defined as a set of software algorithms that make devices process, make decisions, and perform human tasks [20], [21]. Generally, the aim of technology is to improve the life of humanity and reduce the risks that face the world such as COVID-19.…”