An Online Expectation-Maximization Algorithm for Changepoint Models

Changepoint models are widely used to model the heterogeneity of sequential data. We present a novel sequential Monte Carlo (SMC) online Expectation-Maximization (EM) algorithm for estimating the static parameters of such models. The SMC online EM algorithm has a cost per time which is linear in the number of particles and could be particularly important when the data is representable as a long sequence of observations, since it drastically reduces the computational requirements for implementation. We present an asymptotic analysis for the stability of the SMC estimates used in the online EM algorithm and demonstrate the performance of this scheme using both simulated and real data originating from DNA analysis.

An online expectation-maximisation algorithm for nonnegative matrix factorisation models

In this paper we formulate the nonnegative matrix factorisation (NMF) problem as a maximum likelihood estimation problem for hidden Markov models and propose online expectation-maximisation (EM) algorithms to estimate the NMF and the other unknown static parameters. We also propose a sequential Monte Carlo approximation of our online EM algorithm. We show the performance of the proposed method with two numerical examples. © 2012 IFAC.

A Monte Carlo expectation maximisation algorithm for multiple target tracking

In this paper, we present an expectation-maximisation (EM) algorithm for maximum likelihood estimation in multiple target models (MTT) with Gaussian linear state-space dynamics. We show that estimation of sufficient statistics for EM in a single Gaussian linear state-space model can be extended to the MTT case along with a Monte Carlo approximation for inference of unknown associations of targets. The stochastic approximation EM algorithm that we present here can be used along with any Monte Carlo method which has been developed for tracking in MTT models, such as Markov chain Monte Carlo and sequential Monte Carlo methods. We demonstrate the performance of the algorithm with a simulation. © 2012 ISIF (Intl Society of Information Fusi).

Two problems with variational expectation maximisation for time-series models

Variational methods are a key component of the approximate inference and learning toolbox. These methods fill an important middle ground, retaining distributional information about uncertainty in latent variables, unlike maximum a posteriori methods (MAP), and yet generally requiring less computational time than Monte Carlo Markov Chain methods. In particular the variational Expectation Maximisation (vEM) and variational Bayes algorithms, both involving variational optimisation of a free-energy, are widely used in time-series modelling. Here, we investigate the success of vEM in simple probabilistic time-series models. First we consider the inference step of vEM, and show that a consequence of the well-known compactness property of variational inference is a failure to propagate uncertainty in time, thus limiting the usefulness of the retained distributional information. In particular, the uncertainty may appear to be smallest precisely when the approximation is poorest. Second, we consider parameter learning and analytically reveal systematic biases in the parameters found by vEM. Surprisingly, simpler variational approximations (such a mean-field) can lead to less bias than more complicated structured approximations.

Can, and should, behavioural neuroscience influence public policy?

Recent years have seen enormous demand amongst policy makers for new insights from the behavioural sciences, especially neuroscience. This demand is matched by an increasing willingness on behalf of behavioural scientists to translate the policy implications of their work. But can neuroscience really help shape the governance of a nation? Or does this represent growing misuse of neuroscience to attach scientific authority to policy, plus a clutch of neuroscientists trying to overstate their findings for a taste of power?. © 2012.

Modulation of pain ratings by expectation and uncertainty: Behavioral characteristics and anticipatory neural correlates.

Expectations about the magnitude of impending pain exert a substantial effect on subsequent perception. However, the neural mechanisms that underlie the predictive processes that modulate pain are poorly understood. In a combined behavioral and high-density electrophysiological study we measured anticipatory neural responses to heat stimuli to determine how predictions of pain intensity, and certainty about those predictions, modulate brain activity and subjective pain ratings. Prior to receiving randomized laser heat stimuli at different intensities (low, medium or high) subjects (n=15) viewed cues that either accurately informed them of forthcoming intensity (certain expectation) or not (uncertain expectation). Pain ratings were biased towards prior expectations of either high or low intensity. Anticipatory neural responses increased with expectations of painful vs. non-painful heat intensity, suggesting the presence of neural responses that represent predicted heat stimulus intensity. These anticipatory responses also correlated with the amplitude of the Laser-Evoked Potential (LEP) response to painful stimuli when the intensity was predictable. Source analysis (LORETA) revealed that uncertainty about expected heat intensity involves an anticipatory cortical network commonly associated with attention (left dorsolateral prefrontal, posterior cingulate and bilateral inferior parietal cortices). Relative certainty, however, involves cortical areas previously associated with semantic and prospective memory (left inferior frontal and inferior temporal cortex, and right anterior prefrontal cortex). This suggests that biasing of pain reports and LEPs by expectation involves temporally precise activity in specific cortical networks.

Efficient decoding with generative score-spaces using the expectation semiring

State-of-the-art speech recognisers are usually based on hidden Markov models (HMMs). They model a hidden symbol sequence with a Markov process, with the observations independent given that sequence. These assumptions yield efficient algorithms, but limit the power of the model. An alternative model that allows a wide range of features, including word- and phone-level features, is a log-linear model. To handle, for example, word-level variable-length features, the original feature vectors must be segmented into words. Thus, decoding must find the optimal combination of segmentation of the utterance into words and word sequence. Features must therefore be extracted for each possible segment of audio. For many types of features, this becomes slow. In this paper, long-span features are derived from the likelihoods of word HMMs. Derivatives of the log-likelihoods, which break the Markov assumption, are appended. Previously, decoding with this model took cubic time in the length of the sequence, and longer for higher-order derivatives. This paper shows how to decode in quadratic time. © 2013 IEEE.

Weighted least squares with expectation-maximization algorithm for burst detection in U.K. water distribution systems

Flow measurement data at the district meter area (DMA) level has the potential for burst detection in the water distribution systems. This work investigates using a polynomial function fitted to the historic flow measurements based on a weighted least-squares method for automatic burst detection in the U.K. water distribution networks. This approach, when used in conjunction with an expectationmaximization (EM) algorithm, can automatically select useful data from the historic flow measurements, which may contain normal and abnormal operating conditions in the distribution network, e.g., water burst. Thus, the model can estimate the normal water flow (nonburst condition), and hence the burst size on the water distribution system can be calculated from the difference between the measured flow and the estimated flow. The distinguishing feature of this method is that the burst detection is fully unsupervised, and the burst events that have occurred in the historic data do not affect the procedure and bias the burst detection algorithm. Experimental validation of the method has been carried out using a series of flushing events that simulate burst conditions to confirm that the simulated burst sizes are capable of being estimated correctly. This method was also applied to eight DMAs with known real burst events, and the results of burst detections are shown to relate to the water company's records of pipeline reparation work. © 2014 American Society of Civil Engineers.

Radiation effects on the immiscible polymer blend of nylon1010 and high-impact polystyrene (HIPS) I: Gel/dose curves, mathematical expectation theorem and thermal behaviour

This paper studies the radiation properties of the immiscible blend of nylon1010 and HIPS. The gel fraction increased with increasing radiation dose. The network was found mostly in nylon1010, the networks were also found in both nylon1010 and HIPS when the dose reaches 0.85 MGy or more. We used the Charleby-Pinner equation and the modified Zhang-Sun-Qian equation to simulate the relationship with the dose and the sol fraction. The latter equation fits well with these polymer blends and the relationship used by it showed better linearity than the one by the Charleby-Pinner equation. We also studied the conditions of formation of the network by the mathematical expectation theorem for the binary system. Thermal properties of polymer blend were observed by DSC curves. The crystallization temperature decreases with increasing dose because the cross-linking reaction inhibited the crystallization procession and destroyed the crystals. The melting temperature also reduced with increasing radiation dose. The dual melting peak gradually shifted to single peak and the high melting peak disappeared at high radiation dose. However, the radiation-induced crystallization was observed by the heat of fusion increasing at low radiation dose. On the other hand, the crystal will be damaged by radiation. A similar conclusion may be drawn by the DSC traces when the polymer blends were crystallized. When the radiation dose increases, the heat of fusion reduces dramatically and so does the heat of crystallization. (C) 1999 Elsevier Science Ltd. All rights reserved.

Behavioural responses by yaks in different physiological states (lactating, dry or replacement heifers), when grazing natural pasture in the spring (dry and germinating) season on the Qinghai-Tibetan plateau

Using heterogeneous vegetation in alpine grassland through grazing is a necessary component of deintensification of livestock systems and conservation of natural environments. However, better understanding of the dynamics of animal feeding behaviour would improve pasture and livestock grazing managements, particularly in the early part of the spring season when forage is scarce. The changes in behaviour may improve the use of poor pastures. Then, enhancing management practices may conserve pasture and improve animal productivity. Grazing behaviour over 24 In periods by yaks in different physiological states (lactating, dry and replacement heifers) was recorded in the early, dry and later, germinating period of the spring season. Under conditions of inadequate forage, the physiological state of yaks was not the primary factor affecting their grazing and ruminating behaviour. Forage and sward state affected yaks' grazing and ruminating behaviour to a greater extent. Generally, yaks had higher intake and spent more time grazing and ruminating during the later part of the spring season, following germination of forage, than during the earlier dry part of the season. However, the live weight of yaks was less during pasture germination than during the early dry part of the season because the herbage mass is low, and the yaks have to expend much energy to seek feed at this particular time. (c) 2007 Elsevier B.V. All rights reserved.

Behavioural reaction of root vole (Microtus oeconomus pallas) males of different social ranks to familiar and novel odour of conspecific males

In this experiment, we tested the hypothesis that males of root voles (Microtus oeconomus Pallas) of different social ranks display different behavioural strategies. To document behavioural differences between social ranks, we investigated patterns in the behavioural responses to urine cues from familiar and novel individu in a choice maze. Ten pairs of male voles were efectively used in this experiment. All behaviour was recorded with OBSERVER 5.0. When experiment was finished, video tapes were transformed into digital data. Then all data were analyzed by SPSS. The results showed that the approach latency of subordinates was shorter for familiar odours than novel ones, dominant individuals preferentially entered the strange odourant box, subordinates preferred familiar odours over novel ones, subordinates spent more time visiting familiar odours compared to the novel odours, dominants preferred novel odours to familiar ones, subordinates approached familiar odours more frequently than novel ones and self-groomed more often in the familiar odourant box than in the novel box, and dominant and subordinate individuals showed significantly different countermarking behaviours to familiar and novel odours. In conclusion, the dominants and subordinates displayed different behaviour patterns when faced to familiar and novel conspecific males' urine cues. The data support our hypothesis that differences in social rank induce differences in behavioural patterns.

Detecting False Identity through Behavioural Patterns

T. Boongoen and Q. Shen. 'Detecting False Identity through Behavioural Patterns', In Proceedings of International Crime Science Conference, British Library, London UK, 2008. Publisher's online version forthcoming.;The full text is currently unavailable in CADAIR pending approval by the publisher. Sponsorship: UK EPSRC grant EP/D057086