We develop computationally fast and storage e cient implementations for the Kalman-Bucy lter (KBf) for data assimilation problems with large time varying multidimensional elds. We refer to them as the block KBf (bKBf) and the localized block KBf (lbKBf). For elds de ned on a 2D lattice of linear dimension I, the bKBf reduces the computational complexity of the KBf by O(I). The lbKBf saves furth...

We propose a novel approximate inference approach for continuous time stochastic dynamical systems observed in both discrete and continuous time with noise. Our expectation-propagation approach generalises the classical Kalman-Bucy smoothing procedure to non-Gaussian observations, enabling continuous-time inference in a variety of models, including spiking neuronal models (state-space models wi...

We study the linear filtering problem for systems driven by continuous Gaussian processes V 1 and V 2 with memory described by two parameters. The processes V j have the virtue that they possess stationary increments and simple semimartingale representations simultaneously. It allows for straightforward parameter estimations. After giving the semimartingale representations of V j by innovation ...

w x C y a x f x , 1 ABSTRACT In this paper, we consider chaotic communication schemes using nonlinear filtering techniques. Two different previously proposed Extended Kalman Filter based chaotic schemes are revisited and implemented using the Unscented Kalman Filter. Also, a recently proposed antipodal chaotic communication scheme is implemented with both the Extended Kalman Filter and the Unsc...

In this paper, we consider chaotic communication using nonlinear filtering techniques. The main contribution of the paper is proposing a novel antipodal chaotic communication scheme, which is implemented with both the Extended Kalman Filter and the Unscented Kalman Filter. Two different previously proposed Extended Kalman Filter based chaotic schemes are also revisited and implemented using the...

This article concerns optimal investment and hedging for agents who must use trading strategies which are adapted to the filtration generated by asset prices, possibly augmented with some inside information related to the future evolution of an asset price. The price evolution and observations are taken to be continuous, so the partial (and, when applicable, inside) information scenario is char...

Despite recent interest in continuous prediction of dimensional emotions, the dynamical aspect of emotions has received less attention in automated systems. This paper investigates how emotion change can be effectively incorporated to improve continuous prediction of arousal and valence from speech. Significant correlations were found between emotion ratings and their dynamics during investigat...

Kalman filtering is a method for estimating state variables of a dynamic systems recursively from noise-contaminated measurements. For systems with nonlinear dynamics, a natural extension of the Linear Kalman Filter (LKF), called Extended Kalman filter (EKF) is used. The Kalman filter represents one of the most popular estimation techniques for integrating signals from navigation systems, like ...

One method to account for parameters errors in the Kalman filter is to consider their effect in the so-called Schmidt-Kalman filter. This work addresses issues that arise when implementing a consider Kalman filter as a real-time, recursive algorithm. A favorite implementation of the Kalman filter as an onboard navigation subsystem is the UDU formulation. A new way to implement a UDU consider fi...

In 1960 Rudolph E. Kalman published his now famous article describing a recursive solution to the discrete-data linear filtering problem (Kalman, “A new approach to linear filtering and prediction problems,” Transactions of the ASME—Journal of Basic Engineering, 82 (D), 35–45, 1960). Since that time, due in large part to advances in digital computing, the Kalman filter has been the subject of e...