Sequential Estimation Method Research Articles

Orientation in Manhattan: equiprojective classes and sequential estimation

The problem of inferring 3D orientation of a camera from video sequences has been mostly addressed by first computing correspondences of image features. This intermediate step is now seen as the main bottleneck of those approaches. In this paper, we propose a new 3D orientation estimation method for urban (indoor and outdoor) environments, which avoids correspondences between frames. The scene property exploited by our method is that many edges are oriented along three orthogonal directions; this is the recently introduced Manhattan world (MW) assumption. The main contributions of this paper are: the definition of equivalence classes of equiprojective orientations, the introduction of a new small rotation model, formalizing the fact that the camera moves smoothly, and the decoupling of elevation and twist angle estimation from that of the compass angle. We build a probabilistic sequential orientation estimation method, based on an MW likelihood model, with the above-listed contributions allowing a drastic reduction of the search space for each orientation estimate. We demonstrate the performance of our method using real video sequences.

Detection of Dynamic Stability Deficits in Subjects with Functional Ankle Instability

To determine which combination of landing protocol and analysis technique would be the most effective at detecting differences in dynamic stability between healthy subjects and subjects with functional ankle instability (FAI). Fifty-eight subjects participated in this investigation: 29 healthy individuals and 29 individuals with FAI. Subjects were assessed during a single test session for time to stabilization (TTS) in the anterior/posterior, medial/lateral, and vertical directions from two protocols: a step down and jump protocol. The step down protocol started with each subject atop a 20-cm-high platform, and the jump protocol started with subjects in a standing position 70 cm from the center of a force plate and required each subject to jump off both legs and touch a designated marker placed at a position equivalent to 50% of the subject's maximum vertical leap. TTS scores in the anterior/posterior, medial/lateral, and vertical direction were compared between group, protocol, and type of analysis. A significant protocol by analysis by group interaction (F(1,56) = 6.9, P = 0.011) was observed for anterior/posterior TTS. Likewise, protocol by group (F(1,56) = 4.4, P = 0.042) and protocol by analysis (F(1,56) = 14.1, P < 0.001) interactions were also noted in anterior/posterior TTS. The jump protocol (2381.7 +/- 36.5 ms) produced significantly greater TTS scores in the vertical direction than the step protocol (1533.5 +/- 71.8 ms), whereas the unbounded third order polynomial (UTOP) method (2554.4 +/- 68.7 ms) produced significant greater TTS scores as compared with the sequential estimation (SE) method (1360.8 +/- 52.1 ms). The jump protocol and UTOP method of analysis are the most effective TTS combination in detecting differences between healthy and FAI groups.

Differential acquisition of m-sequences using recursive soft sequential estimation

A novel sequential estimation method is proposed for the acquisition of m-sequences. This sequential estimation method exploits the principle of iterative soft-in-soft-out (SISO) decoding for enhancing the acquisition performance, and that of differential preprocessing for the sake of achieving an enhanced acquisition performance, when communicating over various communication environments. Hence, the advocated acquisition arrangement is referred to as the differential recursive soft sequential estimation (DRSSE) acquisition scheme. The DRSSE acquisition scheme exhibits a low complexity, which is similar to that of an m-sequence generator, while achieving an acquisition time that is linearly dependent on the number of stages in the m-sequence generator. A low acquisition time is achieved with the advent of the property that the proposed DRSSE scheme is capable of determining the real-time reliabilities associated with the decision concerning a set of, say, S consecutive chips. This set of consecutive chips constitutes the sufficient initial condition for enabling the local m-sequence generator to produce a synchronized local despreading m-sequence replica. Owing to these attractive characteristics, the DRSSE acquisition scheme constitutes a promising initial synchronization scheme for acquisition of long m-sequences, when communicating over various propagation environments.

Formulation of dynamics, actuation, and inversion of a three-dimensional two-link rigid body system

In this paper, three issues related to three-dimensional multilink rigid body systems are considered: dynamics, actuation, and inversion. Based on the Newton-Euler equations, a state space formulation of the dynamics is discussed that renders itself to inclusion of actuators, and allows systematic ways of stabilization and construction of inverse systems. The development here is relevant to robotic systems, biological modeling, humanoid studies, and collaborating man-machine systems. The recursive dynamic formulation involves a method for sequential measurement and estimation of joint forces and couples for an open chain system. The sequence can start from top downwards or from the ground upwards. Three-dimensional actuators that produce couples at the joints are included in the dynamics. Inverse methods that allow estimation of these couples from the kinematic trajectories and physical parameters of the system are developed. The formulation and derivations are carried out for a two-link system. Digital computer simulations of a two-rigid body system are presented to demonstrate the feasibility and effectiveness of the methods. © 2005 Wiley Periodicals, Inc.

Time-Varying Noise Estimation for Speech Enhancement and Recognition Using Sequential Monte Carlo Method

We present a method for sequentially estimating time-varying noise parameters. Noise parameters are sequences of time-varying mean vectors representing the noise power in the log-spectral domain. The proposed sequential Monte Carlo method generates a set of particles in compliance with the prior distribution given by clean speech models. The noise parameters in this model evolve according to random walk functions and the model uses extended Kalman filters to update the weight of each particle as a function of observed noisy speech signals, speech model parameters, and the evolved noise parameters in each particle. Finally, the updated noise parameter is obtained by means of minimum mean square error (MMSE) estimation on these particles. For efficient computations, the residual resampling and Metropolis-Hastings smoothing are used. The proposed sequential estimation method is applied to noisy speech recognition and speech enhancement under strongly time-varying noise conditions. In both scenarios, this method outperforms some alternative methods.

A MIMO System with Backward Compatibility for OFDM-Based WLANs

Orthogonal frequency division multiplexing (OFDM) has been selected as the basis for the new IEEE 802.11a standard for high-speed wireless local area networks (WLANs). We consider doubling the transmission data rate of the IEEE 802.11a system by using two transmit and two receive antennas. We propose a preamble design for this multi-input multi-output (MIMO) system that is backward compatible with its single-input single-output (SISO) counterpart as specified by the IEEE 802.11a standard. Based on this preamble design, we devise a sequential method for the estimation of the carrier frequency offset (CFO), symbol timing, and MIMO channel response. We also provide a simple soft detector based on the unstructured least square approach to obtain the soft information for the Viterbi decoder. This soft detector is very simple since it decouples the multidimensional QAM symbol detection into multiple one-dimensional QAM symbol-and further PAM symbol-detections. Both the sequential parameter estimation method and the soft detector can provide excellent overall system performance and are ideally suited for real-time implementations. The effectiveness of our methods is demonstrated via numerical examples.

Acquisition of&amp;lt;tex&amp;gt;$m$&amp;lt;/tex&amp;gt;-Sequences Using Recursive Soft Sequential Estimation

A novel sequential estimation method is proposed for the initial synchronization of pseudonoise (PN) signals derived from m-sequences. This sequential estimation method is designed based on the principle of recursive soft-in/soft-out (SISO) decoding, and we refer to it as the recursive soft sequential estimation (RSSE) acquisition scheme. The RSSE acquisition scheme exhibits a complexity similar to that of a conventional m-sequence generator, which increases only linearly with the number of stages in the m-sequence generator. Our simulation results also show that the acquisition time of the proposed RSSE acquisition scheme is also linearly dependent on the number of stages in the m-sequence generator. Owing to the above properties, the employment of the proposed RSSE acquisition scheme is beneficial for the acquisition of long m-sequences.

An Ensemble Kalman Filter with a complex marine ecosystem model: hindcasting phytoplankton in the Cretan Sea

Abstract. The purpose of this paper is to examine the use of a complex ecosystem model along with near real-time in situ data and a sequential data assimilation method for state estimation. The ecosystem model used is the European Regional Seas Ecosystem Model (ERSEM; Baretta et al., 1995) and the assimilation method chosen is the Ensemble Kalman Filer (EnKF). Previously, it has been shown that this method captures the nonlinear error evolution in time and is capable of both tracking the observations and providing realistic error estimates for the estimated state. This system has been used to assimilate long time series of in situ chlorophyll taken from a data buoy in the Cretan Sea. The assimilation of this data using the EnKF method results in a marked improvement in the ability of ERSEM to hindcast chlorophyll. The sensitivity of this system to the type of data used for assimilation, the frequency of assimilation, ensemble size and model errors is discussed. The predictability window of the EnKF appears to be at least 2 days. This is an indication that the methodology might be suitable for future operational data assimilation systems using more complex three-dimensional models. Key words. Oceanography: general (numerical modelling; ocean prediction) – Oceanography: biological and chemical (plankton)

Seed accumulating sequential estimation for PN sequence acquisition at low signal-to-noise ratio

The sequential estimation (SE) proposed by Ward for rapid acquisition of pseudo-noise (PN) sequences performs well only at moderate chip signal-to-noise ratios (SNRs). In this paper, a seed accumulating sequential estimation (SASE) method based on accumulated seeds of the received PN sequence is proposed, which performs well at low chip SNR also. The mean acquisition time performance of the SASE method is investigated. Numerical results show that the SASE performs dramatically better than the SE at low chip SNR and the improvement becomes larger as the period of PN sequence increases.

An Ensemble Kalman filter with a 1-D marine ecosystem model

The Ensemble Kalman Filter (EnKF) has been examined in a data assimilation experiment with a one-dimensional three-component ecosystem model. The model is an extension of the zero-dimensional model developed by Evans and Parslow [Biol. Oceanogr. 3 (1985) 327.]. The purpose of this paper is to examine the possibilities of using a sequential data assimilation method for state estimation in a biological model, an approach which differs from the more traditional parameter estimation studies. The method chosen is the Ensemble Kalman Filer (EnKF), and it has been shown that this method captures the nonlinear error evolution in time and is capable of both tracking the reference solution and to provide realistic error estimates for the estimated state. This is an indication that the methodology might be suitable for future operational data assimilation systems using more complex three-dimensional models.

A sequential method of solving inverse natural convection problems

A sequential algorithm is developed to solve an inverse natural convectionproblem of estimating the time-varying strength of a heat source from theknowledge of temperature readings taken inside the domain. The Boussinesqequation is used to model the natural convection induced by the heat source. Thesequential algorithm is based on the Kalman filtering technique. Although thedirect implementation of the Kalman filter for nonlinear partial differentialequations such as the Boussinesq equation is never feasible due to thetremendous requirements of computer time and memory, a practical method ofsequential estimation is devised in the present investigation—by reducing theBoussinesq equation to a minimal set of ordinary differential equations bymeans of the Karhunen–Loève Galerkin procedure. The performance of thepresent technique of inverse analysis is evaluated by means of severalnumerical experiments, and is found to be very accurate as well as efficient.

Estimating the locations and number of change points by the sample-splitting method

This paper derives a sequential testing and estimation method for the number of change points in structural-change models. In the first step, the parameters are estimated by a one-change model. The null hypothesis that there is no structural change against the alternative of one change is tested. If the null is rejected, then the whole sample is split into two subsamples by using the estimated change point in the previous step as a cutoff point. The same procedure is repeated until the null in each subsample is accepted. We argue that this method can consistently estimate the number, locations and magnitudes of changes. Situations in which the sample splitting method fails are also discussed.

Non-linear regression analysis: new approach to traditional implementations

Non-linear regression (NLR) analysis in chemometric applications is the main subject of the paper. The following novel items of NLR procedure are reported. The modification of gradient method is considered. For inversion of the Fisher matrix the recurrence algorithm based on the matrix exponential is used. A new method of sequential Bayesian estimation allows processing of the data successively for every response. Each data set is fitted individually, but taking into account the information about common parameters estimated on previous data sets. A posterior Bayesian distribution is built after every set processing. A new method of confidence estimation is suggested. Unlike bootstrap, not initial data but parameter estimates are simulated. This method has the same accuracy as bootstrap but is about 1000 times faster. A new coefficient of non-linearity is introduced. It is calculated by the Monte Carlo procedure and accounts for the model structure as well as the experimental design features. All new ideas were implemented in the software FITTER, a new Excel Add-In. Its main capabilities are reported. The paper is illustrated with a number of practical examples in DSC, TMA and TGA data analysis. Copyright  2000 John Wiley & Sons, Ltd.

Automating parallel simulation using parallel time streams

This paper describes a package for parallel steady-state stochastic simulation that was designed to overcome problems caused by long simulation times experienced in our ongoing research in performance evaluation of high-speed and integrated-services communication networks, while maintaining basic statistical rigors of proper analysis of simulation output data. The package, named AKAROA, accepts ordinary (nonparallel) simulation programs, and alll further stages of stochastic simulation should be transparent for users. The package employs a new method of sequential estimation for the Multiple-Replications-in-Parallel scenario. All basic functions, including the transformation of originally nonparallel simulators into ones suitable for parallel execution, control of the precision of estimates, and stopping of parallel simulation processes when the required precision of the overall steady-state estimates is achieved, are automated. The package can be used on multiprocessor systems and/or heterogeneous computer networks, involving an arbitrary number of processors. The design issues, architecture, and implementation of AKAROA, as well as the results of its preliminary performance studies are presented

New sequential method to process noisy temperature response from flash experiment measured by infrared camera

The estimation of a thermal diffusivity map of a surface can be performed with an infrared camera by processing thermal images in response to a pulse of radiant energy. Indirectly, it is then possible to map other properties (humidity, density, etc.). One of the first requirements of this kind of device is to take into account the thermal measurement noise. When the thermal diffusivity varies by a small amount around a nominal value, a new method of sequential estimation based on an asymptotic expansion is proposed. The confidence interval of this method has been analytically compared with success, to the moment method and the method of logarithmic transformation. An experiment demonstrated that thickness variations of 50 μm can be detected on a plate 5 mm thick for a sample of polyvinyl chloride.

Sequential parameter estimation of a simplified induction motor load model

The load model used in power system analysis, computation and control should be both accurate and simple. However, the accuracy and simplicity often contradict each other, so that compromises have to be made between them. This paper describes a simplified practical model for composite loads. It is recognized that the simultaneous parameter estimation of the model is difficult. Therefore, a sequential parameter estimation method is developed. The estimation results of both theoretical simulations and tests are reported.

Power estimation methods for sequential logic circuits

Recently developed methods for power estimation have primarily focused on combinational logic. We present a framework for the efficient and accurate estimation of average power dissipation in sequential circuits. Switching activity is the primary cause of power dissipation in CMOS circuits. Accurate switching activity estimation for sequential circuits is considerably more difficult than that for combinational circuits, because the probability of the circuit being in each of its possible states has to be calculated. The Chapman-Kolmogorov equations can be used to compute the exact state probabilities in steady state. However, this method requires the solution of a linear system of equations of size 2/sup N/ where N is the number of flip-flops in the machine. We describe a comprehensive framework for exact and approximate switching activity estimation in a sequential circuit. The basic computation step is the solution of a nonlinear system of equations which is derived directly from a logic realization of the sequential machine. Increasing the number of variables or the number of equations in the system results in increased accuracy. For a wide variety of examples, we show that the approximation scheme is within 1-3% of the exact method, but is orders of magnitude faster for large circuits. Previous sequential switching activity estimation methods can have significantly greater inaccuracies.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

A Loss Bound Model for On-Line Stochastic Prediction Algorithms

In this paper, we consider the problem of on-line prediction in which at each time an unlabeled instance is given and then a prediction algorithm outputs a probability distribution over the set of labels rather than {0, 1}-values before it sees the correct label. For this setting, we propose a weighted-average-type on-line stochastic prediction algorithm WA, which can be regarded as a hybrid of the Bayes algorithm and a sequential real-valued parameter estimation method. We derive upper bounds on the instantaneous logarithmic loss and cumulative logarithmic loss for WA in both the example-dependent form and the expected form (the expectation is taken with respect to the fixed target distribution of sequences). Specifically, under some specific parametric assumptions for target rules, we prove that WA is optimal in the sense that the upper bound on the expected cumulative logarithmic loss for WA asymptotically matches Rissanen′s coding-theoretic lower bound. Further, we derive an upper bound on the expected cumulative quadratic loss by making use of relationships between the quadratic loss and the logarithmic loss. Throughout the paper, we relate computational learning theory to information theory, most specifically, Rissanen′s predictive minimum description length principle, by giving noiseless coding theoretic interpretations to the loss bounds.

On the Robust Control of Seam Tracking Applied Observing System of Weld Line Position and Direction in Welding Robot with Visual Sensor.

In order to improve the robustness of the visual sensing system of on intelligent welding robot against noise, a new control system is constructed. In this paper, some robust control systems to track a weld line with disappeared portion are proposed. One of them is the sequential linear estimation (SLE) method, in which the weld line positions are estimated on the assumption that the weld line is linear. Another method is the position detecting observer (PDO) method, in which a scanning line is set at a front position of the image and the positions of the weld line are estimated. Furthermore, the direction detecting observer (DDO) method, in which two scanning lines to detect the weld line direction are set at a front position of the image, is proposed. As the result of tracking experiments, the effectiveness of these systems are confirmed.

Sequential estimation of survival functions with a neutral to the right process prior

In this work, a parametric sequential estimation method of survival functions is proposed in the Bayesian nonparametric context when neutral to the right processes are used. It is proved that the mentioned method is an 1-SLA rule when Dirichlet processes are used; furthermore, asymptotically pointwise optimal procedures are obtained. Finally, an example is given.