Adaptive estimation of HMM transition probabilities

This paper presents new schemes for recursive estimation of the state transition probabilities for hidden Markov models (HMM's) via extended least squares (ELS) and recursive state prediction error (RSPE) methods. Local convergence analysis for the proposed RSPE algorithm is shown using the ordinary differential equation (ODE) approach developed for the more familiar recursive output prediction error (RPE) methods. The presented scheme converges and is relatively well conditioned compared with the ...

On adaptive HMM state estimation

In this paper new online adaptive hidden Markov model (HMM) state estimation schemes are developed, based on extended least squares (ELS) concepts and recursive prediction error (RPE) methods. The best of the new schemes exploit the idempotent nature of Markov chains and work with a least squares prediction error index, using a posterior estimates, more suited to Markov models then traditionally used in identification of linear systems.

Adaptive estimation of hidden semi-Markov chains with parameterised transition probabilities and exponential decaying states

This paper develops maximum likelihood (ML) estimation schemes for finite-state semi-Markov chains in white Gaussian noise. We assume that the semi-Markov chain is characterised by transition probabilities of known parametric from with unknown parameters. We reformulate this hidden semi-Markov model (HSM) problem in the scalar case as a two-vector homogeneous hidden Markov model (HMM) problem in which the state consist of the signal augmented by the time to last transition. With this reformulation we apply the expectation Maximumisation (EM ) algorithm to obtain ML estimates of the transition probabilities parameters, Markov state levels and noise variance. To demonstrate our proposed schemes, motivated by neuro-biological applications, we use a damped sinusoidal parameterised function for the transition probabilities.

A prospective study of natural recovery from cannabis use in early psychosis

Background and Objectives: Cannabis use is common in early psychosis and has been linked to adverse outcomes. However, factors that influence and maintain change in cannabis use in this population are poorly understood. An existing prospective dataset was used to predict abstinence from cannabis use over the 6 months following inpatient admission for early psychosis. Methods: Participants were 67 inpatients with early psychosis who had used cannabis in the 6 weeks prior to admission. Current diagnoses of psychotic and substance use disorders were confirmed using a clinical checklist and structured diagnostic interview. Measures of clinical, substance use and social and occupational functioning were administered at baseline and at least fortnightly over the 6-month follow up. Results: No substance use or clinical variables were associated with 6-months’ of cannabis abstinence. Only Caucasian ethnicity, living in private accommodation and receiving an income before the admission were predictive. Only private accommodation and receiving an income were significant predictors of abstinence when these variables were entered into a multivariate analysis. Conclusions: While the observed relationships do not necessarily imply causation, they suggest that more optimal substance use outcomes could be achieved by addressing the accommodation and employment needs of patients.

Insurance and transport law : controlling insurance contract terms : Section 54 of the Insurance Contracts Act – compliance, recovery and accountability

Commonwealth legislation covering insurance contracts contains numerous provisions designed to control the operation and effect of terms in life and general insurance contracts. For example, the Life Insurance Act 1995 (Cth) contains provisions regulating the consequences attendant upon incorrect statements in proposals [1] and non-payment of premiums, [2] provides that an insurer may only exclude liability in the case of suicide if it has made express provision for such contingency in its policy, [3] and severely restricts the efficacy of conditions as to war risks. [4] The Insurance Contracts Act 1984 (Cth) is even more intrusive and has a major impact upon contractual provisions in the general insurance field. It is beyond the scope of this note to explore all of these provisions in any detail but examples of controls and constraints imposed upon the operation and effect of contractual provisions include the following. A party is precluded from relying upon a provision in a contract of insurance if such reliance would amount to a failure to act with the utmost good faith. [5] Similarly, a policy provision which requires differences or disputes arising out of the insurance to be submitted to arbitration is void, [6] unless the insurance is a genuine cover for excess of loss over and above another specified insurance. [7] Similarly clause such as conciliation clauses, [8] average clauses, [9] and unusual terms [10] are given qualified operation. [11] However the provision in the Insurance Contracts Act that has the greatest impact upon, and application to, a wide range of insurance clauses and claims is s 54. This section has already generated a significant volume of case law and is the focus of this note. In particular this note examines two recent cases. The first, Johnson v Triple C Furniture and Electrical Pty Ltd [2012] 2 Qd R 337, (hereafter the Triple C case), is a decision of the Queensland Court of Appeal; and the second, Matthew Maxwell v Highway Hauliers Pty Ltd [2013] WASCA 115, (hereafter the Highway Hauliers case), is a decision of the Court of Appeal in Western Australia. This latter decision is on appeal to the High Court of Australia. The note considers too the decision of the New South Wales Court of Appeal in Prepaid Services Pty Ltd v Atradius Credit Insurance NV [2013] NSWCA 252 (hereafter the Prepaid Services case).These cases serve to highlight the complex nature of s 54 and its application, as well as the difficulty in achieving a balance between an insurer and an insured's reasonable expectations.

Cold water immersion enhances recovery of submaximal muscle function after resistance exercise

We investigated the effect of cold water immersion (CWI) on the recovery of muscle function and physiological responses following high-intensity resistance exercise. Using a randomized, cross-over design, 10 physically active men performed high-intensity resistance exercise, followed by one of two recovery interventions: 10 min of cold water immersion at 10°C, or 10 min active recovery (low-intensity cycling). After the recovery interventions, maximal muscle function was assessed after 2 h and 4 h by measuring jump height and isometric squat strength. Submaximal muscle function was assessed after 6 h by measuring the average load lifted during six sets of 10 squats at 80% 1RM. Intramuscular temperature (1 cm) was also recorded, and venous blood samples were analyzed for markers of metabolism, vasoconstriction and muscle damage. CWI did not enhance recovery of maximal muscle function. However, during the final three sets of the submaximal muscle function test, the participants lifted a greater load (p<0.05; 38%; Cohen’s d 1.3) following CWI compared with active recovery. During CWI, muscle temperature decreased 6°C below post-exercise values, and remained below pre-exercise values for another 35 min. Venous blood O2 saturation decreased below pre-exercise values for 1.5 h after CWI. Serum endothelin-1 concentration did not change after CWI, whereas it decreased after active recovery. Plasma myoglobin concentration was lower, whereas plasma interleukin-6 concentration was higher after CWI compared with active recovery. These results suggest that cold water immersion after resistance exercise allow athletes to complete more work during subsequent training sessions, which could enhance long-term training adaptations.

Fouling of waste heat recovery : numerical and experimental results

Numerical results are presented to investigate the performance of a partly-filled porous heat exchanger for waste heat recovery units. A parametric study was conducted to investigate the effects of inlet velocity and porous block height on the pressure drop of the heat exchanger. The focus of this work is on modelling the interface of a porous and non-porous region. As such, numerical simulation of the problem is conducted along with hot-wire measurements to better understand the physics of the problem. Results from the two sources are then compared to existing theoretical predictions available in the literature which are unable to predict the existence of two separation regions before and after the porous block. More interestingly, a non-uniform interface velocity was observed along the streamwise direction based on both numerical and experimental data.

Adaptive finite element analysis of elliptic problems based on bubble-type local mesh generation

A new mesh adaptivity algorithm that combines a posteriori error estimation with bubble-type local mesh generation (BLMG) strategy for elliptic differential equations is proposed. The size function used in the BLMG is defined on each vertex during the adaptive process based on the obtained error estimator. In order to avoid the excessive coarsening and refining in each iterative step, two factor thresholds are introduced in the size function. The advantages of the BLMG-based adaptive finite element method, compared with other known methods, are given as follows: the refining and coarsening are obtained fluently in the same framework; the local a posteriori error estimation is easy to implement through the adjacency list of the BLMG method; at all levels of refinement, the updated triangles remain very well shaped, even if the mesh size at any particular refinement level varies by several orders of magnitude. Several numerical examples with singularities for the elliptic problems, where the explicit error estimators are used, verify the efficiency of the algorithm. The analysis for the parameters introduced in the size function shows that the algorithm has good flexibility.

A comparison between conductive and infrared devices for measuring mean skin temperature at rest, during exercise in the heat, and recovery

Purpose: Skin temperature assessment has historically been undertaken with conductive devices affixed to the skin. With the development of technology, infrared devices are increasingly utilised in the measurement of skin temperature. Therefore, our purpose was to evaluate the agreement between four skin temperature devices at rest, during exercise in the heat, and recovery. Methods: Mean skin temperature (T̅sk) was assessed in thirty healthy males during 30 min rest (24.0± 1.2°C, 56 ± 8%), 30 min cycle in the heat (38.0 ± 0.5°C, 41 ± 2%), and 45 min recovery(24.0 ± 1.3°C, 56 ± 9%). T̅sk was assessed at four sites using two conductive devices(thermistors, iButtons) and two infrared devices (infrared thermometer, infrared camera). Results: Bland–Altman plots demonstrated mean bias ± limits of agreement between the thermistors and iButtons as follows (rest, exercise, recovery): -0.01 ± 0.04, 0.26 ± 0.85, -0.37 ± 0.98°C; thermistors and infrared thermometer: 0.34 ± 0.44, -0.44 ± 1.23, -1.04 ± 1.75°C; thermistors and infrared camera (rest, recovery): 0.83 ± 0.77, 1.88 ± 1.87°C. Pairwise comparisons of T̅sk found significant differences (p < 0.05) between thermistors and both infrared devices during resting conditions, and significant differences between the thermistors and all other devices tested during exercise in the heat and recovery. Conclusions: These results indicate poor agreement between conductive and infrared devices at rest, during exercise in the heat, and subsequent recovery. Infrared devices may not be suitable for monitoring T̅sk in the presence of, or following, metabolic and environmental induced heat stress.

Scale adaptive tracking using mean shift and efficient feature matching

The mean shift tracker has achieved great success in visual object tracking due to its efficiency being nonparametric. However, it is still difficult for the tracker to handle scale changes of the object. In this paper, we associate a scale adaptive approach with the mean shift tracker. Firstly, the target in the current frame is located by the mean shift tracker. Then, a feature point matching procedure is employed to get the matched pairs of the feature point between target regions in the current frame and the previous frame. We employ FAST-9 corner detector and HOG descriptor for the feature matching. Finally, with the acquired matched pairs of the feature point, the affine transformation between target regions in the two frames is solved to obtain the current scale of the target. Experimental results show that the proposed tracker gives satisfying results when the scale of the target changes, with a good performance of efficiency.

Adaptive online gradient descent

We study the rates of growth of the regret in online convex optimization. First, we show that a simple extension of the algorithm of Hazan et al eliminates the need for a priori knowledge of the lower bound on the second derivatives of the observed functions. We then provide an algorithm, Adaptive Online Gradient Descent, which interpolates between the results of Zinkevich for linear functions and of Hazan et al for strongly convex functions, achieving intermediate rates between [square root T] and [log T]. Furthermore, we show strong optimality of the algorithm. Finally, we provide an extension of our results to general norms.