Efficient data aggregation with node clustering and extreme learning machine for WSN
- PDF / 3,757,501 Bytes
- 27 Pages / 439.37 x 666.142 pts Page_size
- 101 Downloads / 209 Views
Efficient data aggregation with node clustering and extreme learning machine for WSN Ihsan Ullah1 · Hee Yong Youn2
© Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Wireless sensor network is effective for data aggregation and transmission in IoT environment. Here, the sensor data often contain a significant amount of noises or redundancy exists, and thus, the data are aggregated to extract meaningful information and reduce the transmission cost. In this paper, a novel data aggregation scheme is proposed based on clustering of the nodes and extreme learning machine (ELM) which efficiently reduces redundant and erroneous data. Mahalanobis distancebased radial basis function is applied to the projection stage of the ELM to reduce the instability of the training process. Kalman filter is also used to filter the data at each sensor node before transmitted to the cluster head. Computer simulation with real datasets shows that the proposed scheme consistently outperforms the existing schemes in terms of clustering accuracy of the data and energy efficiency of WSN. Keywords Data aggregation · Kalman filter · Extreme learning machine · Covariance matrix · Clustering · Wireless sensor network
1 Introduction Recently, the networks consisting of a large number of nodes such as wireless sensor network (WSN) are widely used in various applications. Here, the communication range of each node and the network lifetime are usually limited unlike wired network. In order to overcome such limitations, the nodes are clustered to collect the data before transmitted to the base station (BS). Since the sensor nodes in WSN are densely deployed to cover the target area completely [1], a significant
* Hee Yong Youn [email protected] Ihsan Ullah [email protected] 1
Electrical and Computer Engineering, Sungkyunkwan University, Suwon, Korea
2
College of Software, Sungkyunkwan University, Suwon, Korea
13
Vol.:(0123456789)
I. Ullah, H. Y. Youn
amount of redundant data are generated, leading to congestion and resource wastage. Additionally, the data may contain some outliers deviating from normal pattern of data which ultimately reduce the performance of WSN. Data aggregation is a technique combining the data in an energy-efficient way [2]. While sensor data contain noise and uncertainty substantially reducing the performance of WSN, spatial and temporal correlation of the data incurs a huge amount of redundancy [3]. If the impact due to redundant and noisy data can be minimized, the resource utilization and network performance will be significantly enhanced. Therefore, efficient data aggregation is imperative at the cluster head (CH) to reduce the redundancy and send meaningful data to the BS. Filtering of outliers in the collected data will also minimize the energy consumption and as a result increase the network lifetime. Numerous data aggregation and clustering techniques for WSN have been proposed in the literature [4–11]. The effectiveness of data aggregation at the CH can be maximized if similar da
Data Loading...
