In this paper, we propose a method to mine frequent temporal patterns from medical time series based on fuzzy ranged interval relations. We firstly introduce the concept of ranged interval relations and then extend it to fuzzy relations in order to make it possible to work with fuzziness of duration like days or weeks and to generate pattens associated with abstracted durations. Through the experiments on a synthetic dataset we demonstrate that our approach enables a sequence to simultaneously belong to multiple relations and that it is possible to control the level of concordance for a case to support a pattern by changing the threshold of membership grade.
Data Mining algorithms
• Hardware: Processor: i3 ,i5 RAM: 4GB Hard disk: 16 GB • Software: operating System : Windws2000/XP/7/8/10 Anaconda,jupyter,spyder,flask Frontend :-python Backend:- MYSQL
₹10000 (INR)
2020