Research Article
Enhanced Connectivity Validity Measure Based on Outlier Detection for Multi-Objective Metaheuristic Data Clustering Algorithms
Algorithm 1
Pseudo-code of the proposed LOF-based algorithm.
(i) | //Inputs: | (ii) | C//the nearest neighbours matrix that is generated from the stage (1) | (iii) | L//number of nearest neighbours minPts in LOF algorithm | (iv) | λ//The threshold used in the LOF algorithm | (v) | Clabel//the labels matrix generated by LOF | (vi) | for each Cj in C do | (1) | //stage (2) | (vii) | Compute the L-distance neighbourhood points of Cj; | (2) | //stage (3) | (viii) | Compute the reachability distance for neighbourhood | (3) | points of Cj; | (xi) | //stage (3) | (x) | Compute the LOF of neighbourhood points of Cj; | (4) | //stage (4) | (ix) | for each neighbourhood point, Pi of Cjdo | (5) | If LOF of Pi ≥ λ then | (6) | Label Pi as outlier and store it Clabel; | (7) | Endif | (8) | End for | (9) | //stage (5) | (10) | Compute connectivity of C by excluding outliers in Clabel; | (11) | //stage (6) | (12) | Execute the multi-objective clustering algorithm; |
|