Stability and convergence analysis of transform-domain LMS adaptive filters with second-order autoregressive process

In this paper, the stability and convergence properties of the class of transform-domain least mean square (LMS) adaptive filters with second-order autoregressive (AR) process are investigated. It is well known that this class of adaptive filters improve convergence property of the standard LMS adaptive filters by applying the fixed data-independent orthogonal transforms and power normalization. However, the convergence performance of this class of adaptive filters can be quite different for various input processes, and it has not been fully explored. In this paper, we first discuss the mean-square stability and steady-state performance of this class of adaptive filters. We then analyze the effects of the transforms and power normalization performed in the various adaptive filters for both first-order and second-order AR processes. We derive the input asymptotic eigenvalue distributions and make comparisons on their convergence performance. Finally, computer simulations on AR process as well as moving-average (MA) process and autoregressive-moving-average (ARMA) process are demonstrated for the support of the analytical results.

Laguerre Runge-Kutta-Fehlberg method for simulating laser pulse propagation in biological tissue

An efficient algorithm for solving the transient radiative transfer equation for laser pulse propagation in biological tissue is presented. A Laguerre expansion is used to represent the time dependency of the incident short pulse. The Runge–Kutta– Fehlberg method is used to solve the intensity. The discrete ordinates method is used to discretize with respect to azimuthal and zenith angles. This method offers the advantages of representing the intensity with a high accuracy using only a few Laguerre polynomials, and straightforward extension to inhomogeneous media. Also, this formulation can be easily extended for solving the 2-D and 3-D transient radiative transfer equations.

New variable step-sizes minimizing mean-square deviation for the lms-type algorithms

The least-mean-square-type (LMS-type) algorithms are known as simple and effective adaptation algorithms. However, the LMS-type algorithms have a trade-off between the convergence rate and steady-state performance. In this paper, we investigate a new variable step-size approach to achieve fast convergence rate and low steady-state misadjustment. By approximating the optimal step-size that minimizes the mean-square deviation, we derive variable step-sizes for both the time-domain normalized LMS (NLMS) algorithm and the transform-domain LMS (TDLMS) algorithm. The proposed variable step-sizes are simple quotient forms of the filtered versions of the quadratic error and very effective for the NLMS and TDLMS algorithms. The computer simulations are demonstrated in the framework of adaptive system modeling. Superior performance is obtained compared to the existing popular variable step-size approaches of the NLMS and TDLMS algorithms. © 2014 Springer Science+Business Media New York.

Exponential stability for markovian jumping stochastic BAM neural networks with mode-dependent probabilistic time-varying delays and impulse control

Abstract
In this article, an exponential stability analysis of Markovian jumping stochastic bidirectional associative memory (BAM) neural networks with mode-dependent probabilistic time-varying delays and impulsive control is investigated. By establishment of a stochastic variable with Bernoulli distribution, the information of probabilistic time-varying delay is considered and transformed into one with deterministic time-varying delay and stochastic parameters. By fully taking the inherent characteristic of such kind of stochastic BAM neural networks into account, a novel Lyapunov-Krasovskii functional is constructed with as many as possible positive definite matrices which depends on the system mode and a triple-integral term is introduced for deriving the delay-dependent stability conditions. Furthermore, mode-dependent mean square exponential stability criteria are derived by constructing a new Lyapunov-Krasovskii functional with modes in the integral terms and using some stochastic analysis techniques. The criteria are formulated in terms of a set of linear matrix inequalities, which can be checked efficiently by use of some standard numerical packages. Finally, numerical examples and its simulations are given to demonstrate the usefulness and effectiveness of the proposed results.

Improving the performance of equalization in communication systems

In this paper, research on exploring the potential of several popular equalization techniques while overcoming their disadvantages has been conducted. First, extensive literature survey on equalization is conducted. The focus has been placed on several popular linear equalization algorithm such as the conventional least-mean-square (LMS) algorithm, the recursive least squares (RLS) algorithm, the fi1tered-X LMS algorithm and their development. The approach in analysing the performance of the filtered-X LMS Algorithm, a heuristic method based on linear time-invariant operator theory is provided to analyse the robust perfonnance of the filtered-X structure. It indicates that the extra filter could enhance the stability margin of the corresponding non filtered X structure. To overcome the slow convergence problem while keeping the simplicity of the LMS based algorithms, an H2 optimal initialization is proposed.

Rapid determination of protein contents in microencapsulated fish oil supplements by ATR-FTIR spectroscopy and partial least square regression (PLSR) analysis

Following the recent success in quantitative analysis of essential fatty acid compositions in a commercial microencapsulated fish oil (?EFO) supplement, we extended the application of portable attenuated total reflection Fourier transform infrared (ATR-FTIR) spectroscopic technique and partial least square regression (PLSR) analysis for rapid determination of total protein contents-the other major component in most commercial ?EFO powders. In contrast to the traditional chromatographic methodology used in a routine amino acid analysis (AAA), the ATR-FTIR spectra of the ?EFO powder can be acquired directly from its original powder form with no requirement of any sample preparation, making the technique exceptionally fast, noninvasive, and environmentally friendly as well as being cost effective and hence eminently suitable for routine use by industry. By optimizing the spectral region of interest and number of latent factors through the developed PLSR strategy, a good linear calibration model was produced as indicated by an excellent value of coefficient of determination R2 = 0.9975, using standard ?EFO powders with total protein contents in the range of 140-450 mg/g. The prediction of the protein contents acquired from an independent validation set through the optimized PLSR model was highly accurate as evidenced through (1) a good linear fitting (R2 = 0.9759) in the plot of predicted versus reference values, which were obtained from a standard AAA method, (2) lowest root mean square error of prediction (11.64 mg/g), and (3) high residual predictive deviation (6.83) ranked in very good level of predictive quality indicating high robustness and good predictive performance of the achieved PLSR calibration model. The study therefore demonstrated the potential application of the portable ATR-FTIR technique when used together with PLSR analysis for rapid online monitoring of the two major components (i.e., oil and protein contents) in finished ?EFO powders in the actual manufacturing setting.

Dynamical analysis of neural networks with time-varying delays using the LMI approach

This study is concerned with the delay-range-dependent stability analysis for neural networks with time-varying delay and Markovian jumping parameters. The time-varying delay is assumed to lie in an interval of lower and upper bounds. The Markovian jumping parameters are introduced in delayed neural networks, which are modeled in a continuous-time along with finite-state Markov chain. Moreover, the sufficient condition is derived in terms of linear matrix inequalities based on appropriate Lyapunov-Krasovskii functionals and stochastic stability theory, which guarantees the globally asymptotic stable condition in the mean square. Finally, a numerical example is provided to validate the effectiveness of the proposed conditions.

Equilibration strategies in molecular dynamics simulation of polyethers

A comparison of the NVT and NVE ensemble simulations of tetraglyme showed that, in terms of energy, temperature and most of the structural features the results were very similar. However, major differences were observed in dynamic properties, ie in the mean square displacement and in the O--O distances. A fast equilibration method suitable for amorphous polymer systems is also detailed. This was accomplished by the reassignment of the velocity distribution to the particles, after the interruption of an NVE simulation.

Low complexity MMSE based channel estimation technique for LTE OFDMA systems

Long term evolution (LTE) is designed for high speed data rate, higher spectral efficiency, and lower latency as well as high-capacity voice support. LTE uses single carrierfrequency division multiple access (SC-FDMA) scheme for the uplink transmission and orthogonal frequency division multiple access (OFDMA) in downlink. The one of the most important challenges for a terminal implementation are channel estimation (CE) and equalization. In this paper, a minimum mean square error (MMSE) based channel estimator is proposed for an OFDMA systems that can avoid the ill-conditioned least square (LS) problem with lower computational complexity. This channel estimation technique uses knowledge of channel properties to estimate the unknown channel transfer function at non-pilot subcarriers.

Missing value estimation for mixed-attribute data sets

Missing data imputation is a key issue in learning from incomplete data. Various techniques have been developed with great successes on dealing with missing values in data sets with homogeneous attributes (their independent attributes are all either continuous or discrete). This paper studies a new setting of missing data imputation, i.e., imputing missing data in data sets with heterogeneous attributes (their independent attributes are of different types), referred to as imputing mixed-attribute data sets. Although many real applications are in this setting, there is no estimator designed for imputing mixed-attribute data sets. This paper first proposes two consistent estimators for discrete and continuous missing target values, respectively. And then, a mixture-kernel-based iterative estimator is advocated to impute mixed-attribute data sets. The proposed method is evaluated with extensive experiments compared with some typical algorithms, and the result demonstrates that the proposed approach is better than these existing imputation methods in terms of classification accuracy and root mean square error (RMSE) at different missing ratios.

Optimal hedge ration with moving least squares - an empirical study using Indian single stock futures data

The use of commodity, currency and stock index futures to hedge risky exposures in the underlying assets is well documented in financial literature. However single stock futures are a relatively new addition to the family of futures and as such, academic research on its use as a hedging tool is relatively thin. In this study we have explored the efficacy of two different methodological approaches that may be applied when hedging a long position in the underlying stock with a single stock future. We use daily trading data covering years 2002 to 2007 from the Indian market, where single stock futures have been really thriving in terms of volume of trade, to extract the optimal hedge ratios using both static OLS as well as 30-day, 60-day and 90-day moving least squares. The method of moving least squares has been in use by market practitioners for some time primarily as a trend analysis and charting tool. Our results indicate that the moving least squares approach outperforms the static OLS in terms of the hedging efficiency, which has been measured by the root mean square hedging error.

Continuous finite-time state feedback stabilizers for some nonlinear stochastic systems

This paper is concerned with the problem of finite-time stabilization for some nonlinear stochastic systems. Based on the stochastic Lyapunov theorem on finite-time stability that has been established by the authors in the paper, it is proven that Euler-type stochastic nonlinear systems can be finite-time stabilized via a family of continuous feedback controllers. Using the technique of adding a power integrator, a continuous, global state feedback controller is constructed to stabilize in finite time a large class of two-dimensional lower-triangular stochastic nonlinear systems. Also, for a class of three-dimensional lower-triangular stochastic nonlinear systems, a recursive design scheme of finite-time stabilization is given by developing the technique of adding a power integrator and constructing a continuous feedback controller. Finally, a simulation example is given to illustrate the theoretical results. © 2014 John Wiley & Sons, Ltd.

Correlated differential privacy: hiding information in non-IID data set

Privacy preserving on data mining and data release has attracted an increasing research interest over a number of decades. Differential privacy is one influential privacy notion that offers a rigorous and provable privacy guarantee for data mining and data release. Existing studies on differential privacy assume that in a data set, records are sampled independently. However, in real-world applications, records in a data set are rarely independent. The relationships among records are referred to as correlated information and the data set is defined as correlated data set. A differential privacy technique performed on a correlated data set will disclose more information than expected, and this is a serious privacy violation. Although recent research was concerned with this new privacy violation, it still calls for a solid solution for the correlated data set. Moreover, how to decrease the large amount of noise incurred via differential privacy in correlated data set is yet to be explored. To fill the gap, this paper proposes an effective correlated differential privacy solution by defining the correlated sensitivity and designing a correlated data releasing mechanism. With consideration of the correlated levels between records, the proposed correlated sensitivity can significantly decrease the noise compared with traditional global sensitivity. The correlated data releasing mechanism correlated iteration mechanism is designed based on an iterative method to answer a large number of queries. Compared with the traditional method, the proposed correlated differential privacy solution enhances the privacy guarantee for a correlated data set with less accuracy cost. Experimental results show that the proposed solution outperforms traditional differential privacy in terms of mean square error on large group of queries. This also suggests the correlated differential privacy can successfully retain the utility while preserving the privacy.

Novel criteria for exponential stability of linear neutral time-varying differential systems

Using a novel approach, we get explicit criteria for exponential stability of linear neutral time-varying differential systems. A brief discussion to the obtained results is given. To the best of our knowledge, the results of this paper are new.