Notice of Retraction Anonymising the Sparse Dataset: A New Privacy Preservation Approach while Predicting Diseases

Susan, V. Shyamala; Christopher, Thomas W.

doi:10.11591/ijeei.v4i3.229

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The use of purely traditional means of disease surveillance and the emergence of the WHO as the international instrument for the expediting of intervention programs in the event of unusual and especially tough epidemics and pandemics has led to the disappearance of a number of infectious diseases around the world [18]. But emphasis today keeps shifting towards real-time disease surveillance [19]. The report submitted that the state-of-the-art for real-time disease surveillance depends heavily on social media.…”

Section: Web-based Disease Surveillance and Epidemic Alert System: Stmentioning

confidence: 99%

Epidemic Alert System: A Web-based Grassroots Model

Osaghae

Okokpujie

Ndujiuba

et al. 2018

IJECE

View full text Add to dashboard Cite

Most web-based disease surveillance systems that give epidemic alerts are based on very large and unstructured data from various news sources, social media and online queries that are parsed by complex algorithms. This has the tendency to generate results that are so diverse and non-specific. When considered along with the fact that there are no existing standards for mining and analyzing data from the internet, the results or decisions reached based on internet sources have been classified as low-quality. This paper proposes a web-based grassroots epidemic alert system that is based on data collected specifically from primary health centers, hospitals and registered laboratories. It takes a more traditional approach to indicator-based disease surveillance as a step towards standardizing web-based disease surveillance. It makes use of a threshold value that is based on the third quartile (75th percentile) to determine the need to trigger the alarm for the onset of an epidemic. It also includes, for deeper analysis, demographic information.

show abstract

Section: Web-based Disease Surveillance and Epidemic Alert System: Stmentioning

confidence: 99%