Asymptotically efficient parameter estimation using quantized output observations

Wang, Le Yi; Yin, George

doi:10.1016/j.automatica.2006.12.030

Cited by 127 publications

(81 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some related results on identification, state estimation, and fault detection using binary or quantized outputs can be found in [17], [31], [33], [34], [35], [36]. In relation to the existing knowledge on observability of sampled systems, we refer the reader to standard textbooks on digital control systems; see, e.g., [7], [18], [24] for classical synchronized sampling schemes on linear systems, and [1], [11] on nonlinear systems.…”

mentioning

confidence: 99%

State Observability and Observers of Linear-Time-Invariant Systems Under Irregular Sampling and Sensor Limitations

Wang

Yin

et al. 2011

IEEE Trans. Automat. Contr.

Self Cite

View full text Add to dashboard Cite

Abstract-State observability and observer designs are investigated for linear-time-invariant systems in continuous time when the outputs are measured only at a set of irregular sampling time sequences. The problem is primarily motivated by systems with limited sensor information in which sensor switching generates irregular sampling sequences. State observability may be lost and the traditional observers may fail in general, even if the system has a full-rank observability matrix. It demonstrates that if the original system is observable, the irregularly sampled system will be observable if the sampling density is higher than some critical frequency, independent of the actual time sequences. This result extends Shannon's sampling theorem for signal reconstruction under periodic sampling to system observability under arbitrary sampling sequences. State observers and recursive algorithms are developed whose convergence properties are derived under potentially dependent measurement noises. Persistent excitation conditions are validated by designing sampling time sequences. By generating suitable switching time sequences, the designed state observers are shown to be convergent in mean square, with probability one, and with exponential convergence rates. Schemes for generating desired sampling sequences are summarized.

show abstract

mentioning

confidence: 99%

State Observability and Observers of Linear-Time-Invariant Systems Under Irregular Sampling and Sensor Limitations

Wang

Yin

et al. 2011

IEEE Trans. Automat. Contr.

Self Cite

View full text Add to dashboard Cite

show abstract

“…More precisely, a maximum likelihood approach for parameter estimation of a static function from binary-valued output data is discussed in [1], while identification of linear dynamical systems which are equipped with only binary-valued sensors is addressed in [2] in the case of stochastic and deterministic description of the disturbances affecting the model. The methodologies discussed in [2] have been extended to system identification with quantized observations [3] and to identification of Wiener models [4]. Identification of linear dynamical systems from quantized output observations is dealt with in [5,6,7,8,9,10,11].…”

Section: Introductionmentioning

confidence: 99%

Fixed-order FIR approximation of linear systems from quantized input and output data

Cerone

Piga²,

Regruto

2013

Systems & Control Letters

View full text Add to dashboard Cite

The problem of identifying a fixed-order FIR approximation of linear systems with unknown structure, assuming that both input and output measurements are subjected to quantization, is dealt with in this paper. A fixed-order FIR model providing the best approximation of the input-output relationship is sought by minimizing the worst-case distance between the output of the true system and the modeled output, for all possible values of the input and output data consistent with their quantized measurements. The considered problem is firstly formulated in terms of robust optimization. Then, two different algorithms to compute the optimum of the formulated problem by means of linear programming techniques are presented. The effectiveness of the proposed approach is illustrated by means of a simulation example.

show abstract

“…There are a few publications in the area of system identification based on quantized sensor data. For instance, Wang et al (2003) studies the problem of binary sensors and Wang and Yin (2007) suggests an algorithm for estimating the gain in dynamic systems with a thorough analysis, and some extensions to other problems than gains are indicated. Still, general results appear to be lacking.…”

Section: Introductionmentioning

confidence: 99%

Statistical results for system identification based on quantized observations

Gustafsson

Karlsson²

2009

Automatica

View full text Add to dashboard Cite

System identification based on quantized observations requires either approximations of the quantization noise, leading to suboptimal algorithms, or dedicated algorithms taylored to the quantization noise properties. This contribution studies fundamental issues in estimation that relate directly to the core methods in system identification. As a first contribution, results from statistical quantization theory are surveyed and applied to both moment calculations (mean, variance etc) and the likelihood function of the measured signal. In particular, the role of adding dithering noise at the sensor is studied. The overall message is that taylored dithering noise can considerably simplify the derivation of optimal estimators. The price for this is a decreased signal to noise ratio, and a second contribution is a detailed study of these effects in terms of the Cramér-Rao lower bound. The common additive uniform noise approximation of quantization is discussed, compared, and interpreted in light of the suggested approaches.

show abstract

Asymptotically efficient parameter estimation using quantized output observations

Cited by 127 publications

References 16 publications

State Observability and Observers of Linear-Time-Invariant Systems Under Irregular Sampling and Sensor Limitations

State Observability and Observers of Linear-Time-Invariant Systems Under Irregular Sampling and Sensor Limitations

Fixed-order FIR approximation of linear systems from quantized input and output data

Statistical results for system identification based on quantized observations

Contact Info

Product

Resources

About