Generalised Wishart Processes

We introduce a stochastic process with Wishart marginals: the generalised Wishart process (GWP). It is a collection of positive semi-definite random matrices indexed by any arbitrary dependent variable. We use it to model dynamic (e.g. time varying) covariance matrices. Unlike existing models, it can capture a diverse class of covariance structures, it can easily handle missing data, the dependent variable can readily include covariates other than time, and it scales well with dimension; there is no need for free parameters, and optional parameters are easy to interpret. We describe how to construct the GWP, introduce general procedures for inference and predictions, and show that it outperforms its main competitor, multivariate GARCH, even on financial data that especially suits GARCH. We also show how to predict the mean of a multivariate process while accounting for dynamic correlations.

Competitive training in hidden Markov models

The use of hidden Markov models is placed in a connectionist framework, and an alternative approach to improving their ability to discriminate between classes is described. Using a network style of training, a measure of discrimination based on the a posteriori probability of state occupation is proposed, and the theory for its optimization using error back-propagation and gradient ascent is presented. The method is shown to be numerically well behaved, and results are presented which demonstrate that when using a simple threshold test on the probability of state occupation, the proposed optimization scheme leads to improved recognition performance.

Recurrent input transformations for Hidden Markov models

This paper presents a new architecture which integrates recurrent input transformations (RIT) and continuous density HMMs. The basic HMM structure is extended to accommodate recurrent neural networks which transform the input observations before they enter the Gaussian output distributions associated with the states of the HMM. During training the parameters of both HMM and RIT are simultaneously optimized according to the Maximum Mutual Information (MMI) criterion. Results are presented for the E-set recognition task which demonstrate the ability of recurrent input transformations to exploit longer term correlations in the speech signal and to give improved discrimination.

The effect of work processes on the casing heat transfer of a transonic turbine

This paper considers the effect of the rotor tip on the casing heat load of a transonic axial flow turbine. The aim of the research is to understand the dominant causes of casing heat-transfer. Experimental measurements were conducted at engine-representative Mach number, Reynolds number and stage inlet to casing wall temperature ratio. Time-resolved heat-transfer coefficient and gas recovery temperature on the casing were measured using an array of heat-transfer gauges. Time-resolved static pressure on the casing wall was measured using Kulite pressure transducers. Time-resolved numerical simulations were undertaken to aid understanding of the mechanism responsible for casing heat load. The results show that between 35% and 60% axial chord the rotor tip-leakage flow is responsible for more than 50% of casing heat transfer. The effects of both gas recovery temperature and heat transfer coefficient were investigated separately and it is shown that an increased stagnation temperature in the rotor tip gap dominates casing heat-transfer. In the tip gap the stagnation temperature is shown to rise above that found at stage inlet (combustor exit) by as much as 35% of stage total temperature drop. The rise in stagnation temperature is caused by an isentropic work input to the tip-leakage fluid by the rotor. The size of this mechanism is investigated by computationally tracking fluid path-lines through the rotor tip gap to understand the unsteady work processes that occur. Copyright © 2005 by ASME.

Blind equalization and sequence estimation using Markov chain Monte Carlo methods

This paper discusses the problem of restoring a digital input signal that has been degraded by an unknown FIR filter in noise, using the Gibbs sampler. A method for drawing a random sample of a sequence of bits is presented; this is shown to have faster convergence than a scheme by Chen and Li, which draws bits independently. ©1998 IEEE.

Scaling POMDPs for dialog management with composite summary point-based value iteration (CSPBVI)

Although partially observable Markov decision processes (POMDPs) have shown great promise as a framework for dialog management in spoken dialog systems, important scalability issues remain. This paper tackles the problem of scaling slot-filling POMDP-based dialog managers to many slots with a novel technique called composite point-based value iteration (CSPBVI). CSPBVI creates a "local" POMDP policy for each slot; at runtime, each slot nominates an action and a heuristic chooses which action to take. Experiments in dialog simulation show that CSPBVI successfully scales POMDP-based dialog managers without compromising performance gains over baseline techniques and preserving robustness to errors in user model estimation. Copyright © 2006, American Association for Artificial Intelligence (www.aaai.org). All rights reserved.

Analysis of basic processes inside the keyhole during deep penetration ND-YAG CW laser welding

During laser welding, the keyhole is generated by the recoil pressure induced by the evaporation processes occurring mainly on the front keyhole wall (KW). In order to characterize the evaporation process, we have measured this recoil pressure by using a plume deflection technique, where the plume generated for static conditions (i. e. with no sample displacement) is deflected by a transverse side gas jet. From the measurement of the plume deflection angle, the recoil pressure can be determined as a function of incident intensity and sample material. From these data one can estimate the pressure generated on the front KW, during laser welding. Therefore, the corresponding dynamic pressure exerted by the vapor plume expansion on the rear KW, in contact with the melt pool, can be also estimated. These pressures appear to be in close agreement with those generated by an additional side jet that has been used in previous experiments, for stabilizing the observed melt pool oscillations or fluctuations.

Gender integration in aquaculture research and technology adoption processes: lessons learned in Bangladesh

This working paper is part of a review of aquaculture technologies and gender in Bangladesh in the period 1990 to 2014. It assesses how gender has been integrated within past aquaculture technology interventions, before exploring the gender dimensions associated with current approaches to transferring knowledge about homestead aquaculture technology. It draws out existing knowledge, identifies research gaps, and selects practices to build upon--as well as practices to move away from. The review examines the research and practice of WorldFish and other development partners in Bangladesh through consultations, a review of gray and published literature, and fieldwork. It aims to contribute to the development of aquaculture technology dissemination methodologies that strengthen and underpin women’s participation in aquaculture.

On the relationship between hidden Markov Models and convex functional transforms for simulating scanning probe Microscopy

Models for simulating Scanning Probe Microscopy (SPM) may serve as a reference point for validating experimental data and practice. Generally, simulations use a microscopic model of the sample-probe interaction based on a first-principles approach, or a geometric model of macroscopic distortions due to the probe geometry. Examples of the latter include use of neural networks, the Legendre Transform, and dilation/erosion transforms from mathematical morphology. Dilation and the Legendre Transform fall within a general family of functional transforms, which distort a function by imposing a convex solution.In earlier work, the authors proposed a generalized approach to modeling SPM using a hidden Markov model, wherein both the sample-probe interaction and probe geometry may be taken into account. We present a discussion of the hidden Markov model and its relationship to these convex functional transforms for simulating and restoring SPM images.©2009 SPIE.

A markov chain Monte Carlo method for estimating population mixing using Y-chromosome markers: Mixing of the Han people in China

We present a new approach for estimating mixing between populations based on non-recombining markers, specifically Y-chromosome microsatellites. A Markov chain Monte Carlo (MCMC) Bayesian statistical approach is used to calculate the posterior probability

Natural actor and belief critic: Reinforcement algorithm for learning parameters of dialogue systems modelled as POMDPs

This article presents a novel algorithm for learning parameters in statistical dialogue systems which are modeled as Partially Observable Markov Decision Processes (POMDPs). The three main components of a POMDP dialogue manager are a dialogue model representing dialogue state information; a policy that selects the system's responses based on the inferred state; and a reward function that specifies the desired behavior of the system. Ideally both the model parameters and the policy would be designed to maximize the cumulative reward. However, while there are many techniques available for learning the optimal policy, no good ways of learning the optimal model parameters that scale to real-world dialogue systems have been found yet. The presented algorithm, called the Natural Actor and Belief Critic (NABC), is a policy gradient method that offers a solution to this problem. Based on observed rewards, the algorithm estimates the natural gradient of the expected cumulative reward. The resulting gradient is then used to adapt both the prior distribution of the dialogue model parameters and the policy parameters. In addition, the article presents a variant of the NABC algorithm, called the Natural Belief Critic (NBC), which assumes that the policy is fixed and only the model parameters need to be estimated. The algorithms are evaluated on a spoken dialogue system in the tourist information domain. The experiments show that model parameters estimated to maximize the expected cumulative reward result in significantly improved performance compared to the baseline hand-crafted model parameters. The algorithms are also compared to optimization techniques using plain gradients and state-of-the-art random search algorithms. In all cases, the algorithms based on the natural gradient work significantly better. © 2011 ACM.

Engineering change impact on product development processes

This paper presents a method to manage Engineering Changes (EC) during the product development process, which is seen to be a complex system. The ability to manage engineering changes efficiently reflects the agility of an enterprise. Although there are unnecessary ECs that should be avoided, many of the ECs are actually beneficial. The proposed method explores the linkages between the product development process features and product specifications dependencies. It suggests ways of identifying and managing specification dependencies to support the Engineering Change Management process. Furthermore, the impacts of an EC on the product specifications as well as on the process organization are studied. © 2009 World Scientific Publishing Company.

Simulating intertwined design processes that have similar structures: A case study of a small company that creates made-to-order fashion products

The authors use simulation to analyse the resource-driven dependencies between concurrent processes used to create customised products in a company. Such processes are uncertain and unique according to the design changes required. However, they have similar structures. For simulation, a level of abstraction is chosen such that all possible processes are represented by the same activity network. Differences between processes are determined by the customisations that they implement. The approach is illustrated through application to a small business that creates customised fashion products. We suggest that similar techniques could be applied to study intertwined design processes in more complex domains. Copyright © 2011 Inderscience Enterprises Ltd.