Similarity-aware data aggregation using fuzzy c-means approach for wireless sensor networks

Abstract

For resource-constrained IoT systems, data collection is one of the fundamental operations to reduce the energy dissipation of sensor nodes and improve the network lifetime. However, an anomaly or deviation will exert a great influence on the quality of data collected, especially for a data aggregation scheme. By taking into account dataaware clustering and detection of anomalous events, a similarity-aware data aggregation using a fuzzy c-means approach for wireless sensor networks is proposed. Firstly, by using a fuzzy c-means approach, the clustering process can be performed to organize sensors into clusters based on data similarity. Next, an effective support degree function is defined for further outlier diagnosis. Afterwards, the appropriate weight of valid data can be obtained by taking advantage of the probability distribution characteristics of normal samples within a certain period. Finally, the aggregation result in the cluster can be estimated. Practical database-based simulations have confirmed that the proposed data aggregation method can achieve better performance than traditional methods in terms of data outlier detection accuracy and relative recovery error.

Local Aggregation Scheme for Data Collection in Periodic Sensor Network

“…Jacques M. Bahi [5] define a data aggregation method for a tree based periodic sensors network that works in two level, at the node level aggregation called local aggregation and at the aggregator level. At every period p, sensor nodes send its aggregated data set to its appropriate aggregator.…”

“…He also implemented In-network data aggregation algorithm [7] which is an effective technique to remove redundant data that preserve communication energy in sensor networks. Same local level aggregation is used, which he applied in their prior algorithm [5] but proposed a new frequency filtering approach which is applied on aggregator node to find similar set. Hassan Harb [6] proposed a cluster-based periodic sensor network (CPSN), in which sensor node periodically collect the data and sends its aggregated dataset to its Cluster head.…”

Error-Aware Data Clustering for In-Network Data Reduction in Wireless Sensor Networks

“…In particular, several data clustering techniques have been explored including principal component analysis based aggregation (PCAg) [10], multiple-PCA [11], candid covariance-free incremental PCA (CCIPCA) [5], data aggregative window function (DAWF) [12], projection basis PCA [13], distributed PCA [14], K-means [15], enhanced K-means [9], K-medoids [16], singular value decomposition (SVD) [17], auto-regressive moving average (ARMA) [18], and least mean square (LMS) [19]. Various applications of these techniques are available in existing literature [20][21][22][23][24][25][26][27][28]. However, current data clustering techniques lead to a myriad of problems including error-control for in-network data reduction, time-intensiveness and complex computation.…”

Energy-efficient privacy-preserving data aggregation protocols based on slicing

“…It is almost impractical and uneconomical for each node to send its sensing data directly to base station (BS) [6][7][8], because the energy of the node will be exhausted in the process of data transmission and the battery capacity of the sensor node cannot meet the requirement of network application. The energy issue has become a major concern in both industrial practice and academic world [9][10][11]. Data aggregation (DA) [12][13][14][15] technique which is one of the essential techniques in assuring the effectiveness of WSNs can effectively overcome the energy obstacle by fusing data and decreasing redundancy in many critical applications.…”