Interactive sensor network data retrieval and management using principal components analysis transform

Abstract

With the growing use of large-scale sensor networks, huge volumes of sensor data are being generated from structural health monitoring systems. Vibration sensor data often constitute a large portion of the monitoring data from a structural health monitoring system. Efficient transmission and management of large-size vibration sensor datasets are becoming an increasingly important aspect of structural health monitoring systems. To address this problem of emerging importance, this paper presents a novel method for interactive retrieval and management of sensor network data. Pre-defined features obtained from principal components analysis (PCA) are proposed for the detection of changes in the monitored structure. The PCA transform and linear predictor are also used in the data compression scheme to allow users to retrieve data progressively with significantly reduced data size. The results of a case study involving wireless sensor network data collected from a five-story model building are presented to demonstrate the potential use of the proposed method in the transmission and management of sensor network data. The proposed method is believed to provide data users with the flexibility to select data and retrieve data at multi-resolution levels, reducing raw data size, relaxing the communication bandwidth requirement, and speeding up the data transmission process.

Principal Component Aggregation for Energy-Efficient Information Extraction in Wireless Sensor Networks

“…In [22], authors proposed to rely on principal component scores in order to (i) compress vibration sensor data and…”

“…When sensor measurements are correlated, which is often the case in sensor networks, PC basis allows to represent the sensor measurements variations with a reduced set of coordinates. This feature inspired recent work in the domain of data processing for sensor networks where PCA is used for tasks like approximate monitoring [22], feature prediction [3,10], and event detection [12,20]. However, it is worthy noting that what is common to all these approaches is that the transformation of the sensed data in the PC basis takes place in a centralized manner in the base station.…”

Photo Replication of Birefringent Phase Structures

“…The PCA transform has been widely used in statistical data analysis and pattern recognition [24,25]. Given an observed n s -dimensional vector x, the goal of PCA is to reduce the dimensionality of X.…”

Multivariate reduction in wireless sensor networks

“…Considering multivariate data reduction, there are some proposals that consider discrete wavelet transformation, hierarchical clustering, sampling and singular value decomposition techniques [8]. Specifically, the reduction based on PCA, we can find some contributions that apply PCA with prediction to improve the reduction [6]. Meanwhile, to provide the reduction in WSNs, it is necessary to evaluate some parameters in more details, such as the reduced data quality, energy consumption and delay.…”