Pattern Mining—FTISPAM Using Hybrid Genetic Algorithm

An innovative approach is elegantly launched to effectively identify the medical behavioural changes of the patients. With this end in view, the sequential change patterns are extracted at two diverse time intervals, with the help of the fuzzy time interval sequential change pattern mining employing the HGA technique. However, the pattern mining at two diverse time intervals is likely to yield further superfluous data. With an eye on averting the generation of the corresponding superfluous data, an optimized method such as the hybrid genetic algorithm (HGA) based fuzzy time interval sequential pattern mining is envisaged for the purpose of attaining the patterns. The sequential pattern detection algorithm effectively segments the located change patterns into four diverse types such as the perished patterns, added patterns, unexpected changes, and the emerging patterns. When the pattern categorization comes to an end, the changed patterns are harmonized by means of the Similarity Computation Index (SCI) values. At last, the significant patterns are estimated and employed to categorize the change in the conduct of the patient. The imaginative system is performed in the working stage of the MATLAB and its execution is surveyed and appeared differently in relation to that of the advanced strategy like the genetic algorithm. © The Author(s).