Distributed state estimation and data fusion in wireless sensor networks using multi-level quantized innovation

Abstract

Low energy consumption and limited power supply are significant factors for wireless sensor networks (WSNs); thus, distributed state estimation and data fusion with quantized innovation are explored. The universal features of practical WSNs are investigated, and a dynamic transmission strategy is introduced. Furthermore, quantization state estimation based on Bayesian theory is derived. Unlike previous algorithms suitable for processing scalar measurement, the proposed distributed data fusion algorithm is applicable to general vector measurement. Furthermore, the efficiency of the proposed dynamic transmission strategy is analyzed. It is concluded that the proposed algorithm is more efficient than previous methods, and its estimation accuracy comparable to that of the standard Kalman filtering, which is based on analog-amplitude vector measurement.

Joint Data Compression and Parameter Estimation for Kronecker Product Structure

“…Remark 1: Obviously, the solutions of K and L in (9) are not unique because L = LQ and K = Q −1 K also satisfy L Q = G, where Q is an arbitrary invertible matrix with proper dimensions. In other words, one future topic is to design Q so as to readjust the data range for more effective data buffering in the finite-bit case.…”

“…Up to now, the existing methods for parameter estimation based on high-dimensional data can be classified into four methods. The first well-known method is to quantize the raw data into multi-bit [8], [9] or even one-bit [10] data for subsequent parameter estimation. Such compact coding methods that represent the original data using fixed-length codes have also been used in hashing-based [11]- [14] or quantizationbased [15] cross-modal similarity measurement in recent years.…”

Distributed Robust Dimensionality Reduction Fusion Estimation Under DoS Attacks and Uncertain Covariances

“…Therefore, information loss is inevitable, which may lead to the estimated performance degradation of the fusion estimation. To overcome the problem of bandwidth constraints, several methods have been developed, including quantification method [20] - [22] and dimensionality reduction method [23] - [28]. As the literature in [25] - [28] pointed out, the dimensionality reduction method shows more advantages in solving the bandwidth constraints problem for high-dimensional state.…”

Analysis of Distributed Wireless Sensor Systems with a Switched Quantizer

“…e study in [24] proposes a new descriptor sliding mode observer method to solve the problem that signal quantization will reduce the estimation performance. In [25], the quantization state estimation suitable for general vector measurement is derived based on Bayesian theory. e work in [26] studies a recursive filtering algorithm to deal with state estimation problems in power systems with quantized nonlinear measurements.…”