A Weighted Fuzzy c-Means Clustering Algorithm for Incomplete Big Sensor Data

Sensor data processing plays an important role on the development of the wireless sensor networks in the big data era. Owning to the existence of a large number of incomplete data in wireless sensor networks, fuzzy c-means clustering algorithm (FCM) finds it difficult to produce an appropriate cluster result. The paper proposes a distributed weighted fuzzy c-means algorithm based on incomplete data imputation for big sensor data (DWFCM). DWFCM improves Affinity Propagation (AP) clustering algorithm by designing a new similarity metrics for imputing incomplete sensor data, and then proposes a weighted FCM (wFCM) by assigning a lower weighted value to the incomplete data object for improving the cluster accuracy. Finally, we validate the proposed weighted FCM algorithm on the dataset collected from the smart WSN lab. Experiments demonstrate that the weighted FCM algorithm could fill the missing values very accurately and improve the clustering results effectively.