A Comparative Study on Fuzzy Clustering for Cloud Computing. Taking Web Service as a case
Choukri Djellali, Mehdi Adda, Mohamed Tarik Moutacalli · Procedia Computer Science · 2021
This study addresses the increasingly encountered challenge of data clustering. We present a comparative study to data clustering for cloud computing using Fuzzy C-MEANS and Adaptive Resonance Theory. To reduce variance and improve generalization ability, we used a resampling method based on 10-fold cross-validation. The typical initialization scheme is applied to improve the convergence speed of training and thus, reach the optimal solution. Experimental results on cloud computing datasets showed that the typical initialization-based Fuzzy Adaptive Resonance Theory model is effective and achieves improved accuracy for pattern recognition task compared to Fuzzy C-MEANS.