Intelligent surveillance lifecycle architecture for epidemiological data clustering using Twitter and novel genetic algorithm

Abstract

Social media has spread globally. Over the past few years, Twitter has climbed to over one billion active users. On average, they send out 340 million tweets per day. That produces a massive amount of information, calculated to be in excess of 150 gigabytes of data per year. This research, as reported in this paper, focuses on creating an Intelligent surveillance lifecycle architecture for epidemiological data clustering using Twitter and novel genetic algorithm (ISLA/EDC). The purpose of the architecture is to develop concepts and techniques such that epidemiologists can be able to more efficiently and effectively determine the locations of disease outbreaks as they occur. They do not have to rely on the illnesses being directly reported to them. The technical solution of the architecture provides medical tasks that support strategic decision making and operational business processes. The design of the architecture is based on Service-Oriented Architecture (SOA). In a SOA environment, the technical solution develops new intelligent concepts of integrating approaches of search methodologies, information extraction, data clustering, genetic algorithm, and intelligent agents. A prototype is created and examined in order to validate the concepts.