Parametric statistics

About: Parametric statistics is a research topic. Over the lifetime, 39200 publications have been published within this topic receiving 765761 citations.

Estimation of Sparse MIMO Channels with Common Support

Abstract: We consider the problem of estimating sparse communication channels in the MIMO context. In small to medium bandwidth communications, as in the current standards for OFDM and CDMA communication systems (with bandwidth up to 20 MHz), such channels are individually sparse and at the same time share a common support set. Since the underlying physical channels are inherently continuous-time, we propose a parametric sparse estimation technique based on finite rate of innovation (FRI) principles. Parametric estimation is especially relevant to MIMO communications as it allows for a robust estimation and concise description of the channels. The core of the algorithm is a generalization of conventional spectral estimation methods to multiple input signals with common support. We show the application of our technique for channel estimation in OFDM (uniformly/contiguous DFT pilots) and CDMA downlink (Walsh-Hadamard coded schemes). In the presence of additive white Gaussian noise, theoretical lower bounds on the estimation of sparse common support (SCS) channel parameters in Rayleigh fading conditions are derived. Finally, an analytical spatial channel model is derived, and simulations on this model in the OFDM setting show the symbol error rate (SER) is reduced by a factor 2 (0 dB of SNR) to 5 (high SNR) compared to standard non-parametric methods - e.g. lowpass interpolation.

Passivity analysis of neural networks with time delay

Abstract: The passivity conditions for delayed neural networks (DNNs) are considered in this paper. We firstly derive the passivity condition for DNNs without uncertainties, and then extend the result to the case with time-varying parametric uncertainties. The proposed approach is based on a Lyapunov-Krasovskii functional construction. The passivity conditions are presented in terms of linear matrix inequalities, which can be easily solved by using the effective interior-point algorithm. Numerical examples are also given to demonstrate the effectiveness of the theoretical results.

Adaptive Control of Electrostatic Microactuators With Bidirectional Drive

Abstract: In this paper, adaptive control is presented for a class of single-degree-of-freedom (1DOF) electrostatic microactuator systems which can be actively driven bidirectionally. The control objective is to track a reference trajectory within the air gap without knowledge of the plant parameters. Both full-state feedback and output feedback schemes are developed, the latter being motivated by practical difficulties in measuring velocity of the moving plate. For the full-state feedback scheme, the system is transformed to the parametric strict feedback form, for which adaptive backstepping is performed to achieve asymptotic output tracking. Analogously, the output feedback design involved transformation to the parametric output feedback form, followed by the use of adaptive observer backstepping to achieve asymptotic output tracking. To prevent contact between the movable and fixed electrodes, special barrier functions are employed in Lyapunov synthesis. All closed-loop signals are ensured to be bounded. Extensive simulation studies illustrate the performance of the proposed control.

Strong optimality of the normalized ML models as universal codes and information in data

Abstract: We show that the normalized maximum-likelihood (NML) distribution as a universal code for a parametric class of models is closest to the negative logarithm of the maximized likelihood in the mean code length distance, where the mean is taken with respect to the worst case model inside or outside the parametric class. We strengthen this result by showing that, when the data generating models are restricted to be the most "benevolent" ones in that they incorporate all the constraints in the data and no more, the bound cannot be beaten in essence by any code except when the mean is taken with respect to the data generating models in a set of vanishing size. These results allow us to decompose the code of the data into two parts, the first having all the useful information in the data that can be extracted with the family in question and the rest which has none, and we obtain a measure for the (useful) information in data.