In this paper, we introduce a novel method to define semi-automatically fuzzy partition rules to provide a powerful and accurate insight into cardiac arrhythmia. In particular, we define a text mining approach applied to a large dataset consisting of the freely available scientific papers provided by PubMed. The information extracted is then integrated with expert knowledge, as well as experimental data, to provide a robust, scalable and accurate system, which can successfully address the challenges posed by the management and assessment of big data in the medical sector. The evaluation we carried out shows an accuracy rate of 93% and interopretability of 0.646, which clearly shows that our method provides an excellent balance between accuracy and system transparency. Furthermore, this contributes substantially to the knowledge discovery and offers a powerful tool to facilitate the decision-making process.
|Number of pages||14|
|Journal||Concurrency and Computation: Practice and Experience|
|Early online date||21 Jan 2015|
|Publication status||Published - 28 Jan 2016|
- big data
- cardiac arrhythmia
- data analytics
- fuzzy logic
- knowledge discovery
- text mining
FingerprintDive into the research topics of 'Big Data Based Extraction of Fuzzy Partition Rules for Heart Arrhythmia Detection: a Semi-Automated Approach'. Together they form a unique fingerprint.
Prof MARCELLO TROVATI
- Computer Science - Professor of Computer Science
- Arts & Sciences Faculty Office - Research Fellow, SME Prod. & Innov. Cent