Fast Convergence of Regularised Region-based Mixture of Gaussians for Dynamic Background Modelling

The momentum term has long been used in machine learning algorithms, especially back-propagation, to improve their speed of convergence. In this paper, we derive an expression to prove the O(1/k2) convergence rate of the online gradient method, with momentum type updates, when the individual gradients are constrained by a growth condition. We then apply these type of updates to video background modelling by using it in the update equations of the Region-based Mixture of Gaussians algorithm. Extensive evaluations are performed on both simulated data, as well as challenging real world scenarios with dynamic backgrounds, to show that these regularised updates help the mixtures converge faster than the conventional approach and consequently improve the algorithm’s performance.

Electromagnetic Focusing and Imaging in Stratified Media Using Gradient Phase Profiled Conjugating Lens

High-resolution imaging of a dipole source in stratified medium based on negative refraction is presented in this paper. Compensation of the material parameter contrast at the stratified media interface is achieved using a gradient phase profiled conjugating lens (GPCL). It is shown both analytically and numerically that the phase gradient applied across the GPCL positioned at the interface of vertically stratified media enables a high-quality image of a dipole source in a mirror symmetric position with respect to the lens plane. The analytical closed form expression of the phase gradient function is derived using Huygens-Kirchhoff principle. The result is applicable to media with arbitrary stratification and material parameters, including lossy materials. The mechanism for formation of the dipole image in the stratified medium and aberration due to the dielectric contrast at the interface, particularly electromagnetic loss, is discussed in detail. The efficacy of gradient phase and amplitude aberration compensations mechanisms available through the GPCL is articulated. The results of the study are of importance in a wide range of imaging problems in stratified media for medical, civil, and military applications.

Kuznetsov independence for interval-valued expectations and sets of probability distributions: Properties and algorithms

Kuznetsov independence of variables X and Y means that, for any pair of bounded functions f(X) and g(Y), E[f(X)g(Y)]=E[f(X)] *times* E[g(Y)], where E[.] denotes interval-valued expectation and *times* denotes interval multiplication. We present properties of Kuznetsov independence for several variables, and connect it with other concepts of independence in the literature; in particular we show that strong extensions are always included in sets of probability distributions whose lower and upper expectations satisfy Kuznetsov independence. We introduce an algorithm that computes lower expectations subject to judgments of Kuznetsov independence by mixing column generation techniques with nonlinear programming. Finally, we define a concept of conditional Kuznetsov independence, and study its graphoid properties.

Algorithms for Hidden Markov Models With Imprecisely Specified Parameters

Hidden Markov models (HMMs) are widely used models for sequential data. As with other probabilistic graphical models, they require the specification of precise probability values, which can be too restrictive for some domains, especially when data are scarce or costly to acquire. We present a generalized version of HMMs, whose quantification can be done by sets of, instead of single, probability distributions. Our models have the ability to suspend judgment when there is not enough statistical evidence, and can serve as a sensitivity analysis tool for standard non-stationary HMMs. Efficient inference algorithms are developed to address standard HMM usage such as the computation of likelihoods and most probable explanations. Experiments with real data show that the use of imprecise probabilities leads to more reliable inferences without compromising efficiency.

Direct Observation of Density-Gradient Effects in Harmonic Generation from Plasma Mirrors

High-order harmonics and attosecond pulses of light can be generated when ultraintense, ultrashort laser pulses reflect off a solid-density plasma with a sharp vacuum interface, i.e., a plasma mirror. We demonstrate experimentally the key influence of the steepness of the plasma-vacuum interface on the interaction, by measuring the spectral and spatial properties of harmonics generated on a plasma mirror whose initial density gradient scale length L is continuously varied. Time-resolved interferometry is used to separately measure this scale length. 

GRADIENT CORRECTIONS IN DENSITY-FUNCTIONAL THEORY CALCULATIONS FOR SURFACES - CO ON PD(110)

Ab initio total energy calculations have been performed for CO chemisorption on Pd(110). Local density approximation (LDA) calculations yield chemisorption energies which are significantly higher than experimental values but inclusion of the generalised gradient approximation (GGA) gives better agreement. In general, sites with higher coordination of the adsorbate to surface atoms lead to a larger degree of overbinding with LDA, and give larger corrections with GGA. The reason is discussed using a first-order perturbation approximation. It is concluded that this may be a general failure of LDA for chemisorption energy calculations. This conclusion may be extended to many surface calculations, such as potential energy surfaces for diffusion.

Enhanced clinical pharmacy service targeting tools: risk-predictive algorithms

Rationale, aims and objectives: This study aimed to determine the value of using a mix of clinical pharmacy data and routine hospital admission spell data in the development of predictive algorithms. Exploration of risk factors in hospitalized patients, together with the targeting strategies devised, will enable the prioritization of clinical pharmacy services to optimize patient outcomes. 

Methods: Predictive algorithms were developed using a number of detailed steps using a 75% sample of integrated medicines management (IMM) patients, and validated using the remaining 25%. IMM patients receive targeted clinical pharmacy input throughout their hospital stay. The algorithms were applied to the validation sample, and predicted risk probability was generated for each patient from the coefficients. Risk threshold for the algorithms were determined by identifying the cut-off points of risk scores at which the algorithm would have the highest discriminative performance. Clinical pharmacy staffing levels were obtained from the pharmacy department staffing database. 

Results: Numbers of previous emergency admissions and admission medicines together with age-adjusted co-morbidity and diuretic receipt formed a 12-month post-discharge and/or readmission risk algorithm. Age-adjusted co-morbidity proved to be the best index to predict mortality. Increased numbers of clinical pharmacy staff at ward level was correlated with a reduction in risk-adjusted mortality index (RAMI). 

Conclusions: Algorithms created were valid in predicting risk of in-hospital and post-discharge mortality and risk of hospital readmission 3, 6 and 12 months post-discharge. The provision of ward-based clinical pharmacy services is a key component to reducing RAMI and enabling the full benefits of pharmacy input to patient care to be realized.

Co-tape casting fabrication, field assistant sintering and evaluation of a coke resistant La0.2Sr0.7TiO3-Ni/YSZ functional gradient anode supported solid oxide fuel cell

The ability to directly utilize hydrocarbons and other renewable liquid fuels is one of the most important issues affecting the large scale deployment of solid oxide fuel cells (SOFCs). Herein we designed La_0.2Sr_0.7TiO₃-Ni/YSZ functional gradient anode (FGA) supported SOFCs, prepared with a co-tape casting method and sintered using the field assisted sintering technique (FAST). Through SEM observations, it was confirmed that the FGA structure was achieved and well maintained after the FAST process. Distortion and delamination which usually results after conventional sintering was successfully avoided. The La_0.2Sr_0.7TiO₃-Ni/YSZ FGA supported SOFCs showed a maximum power density of 600mWcm^-2 at 750°C, and was stable for 70h in CH₄. No carbon deposition was detected using Raman spectroscopy. These results confirm the potential coke resistance of La_0.2Sr_0.7TiO₃-Ni/YSZ FGA supported SOFCs.

Efficient Algorithms for Answering the m-Closest Keywords Query

As an important type of spatial keyword query, the m-closest keywords (mCK) query finds a group of objects such that they cover all query keywords and have the smallest diameter, which is defined as the largest distance between any pair of objects in the group. The query is useful in many applications such as detecting locations of web resources. However, the existing work does not study the intractability of this problem and only provides exact algorithms, which are computationally expensive.

In this paper, we prove that the problem of answering mCK queries is NP-hard. We first devise a greedy algorithm that has an approximation ratio of 2. Then, we observe that an mCK query can be approximately answered by finding the circle with the smallest diameter that encloses a group of objects together covering all query keywords. We prove that the group enclosed in the circle can answer the mCK query with an approximation ratio of 2 over 3. Based on this, we develop an algorithm for finding such a circle exactly, which has a high time complexity. To improve efficiency, we propose another two algorithms that find such a circle approximately, with a ratio of 2 over √3 + ε. Finally, we propose an exact algorithm that utilizes the group found by the 2 over √3 + ε)-approximation algorithm to obtain the optimal group. We conduct extensive experiments using real-life datasets. The experimental results offer insights into both efficiency and accuracy of the proposed approximation algorithms, and the results also demonstrate that our exact algorithm outperforms the best known algorithm by an order of magnitude.

Changes in epilithic biomasses and invertebrate community structure over a deposit metal concentration gradient in upland headwater streams

Stream bed metal deposits affect the taxon richness, density and taxonomic diversity of primary and secondary producers by a variety of direct or indirect abiotic and biotic processes but little is known about the relative importance of these processes over a deposit metal concentration gradient. Inorganic matter (IM), algal and non-photosynthetic detrital (NPD) dry biomasses were estimated for 10 monthly samples, between 2007 and 2008, from eight sites differing in deposit density. Invertebrate abundance, taxon richness and composition were also determined. Relations between these variables were investigated by canonical correspondence analysis (CCA), generalized estimating equation models and path analysis. The first CCA axis correlates with deposit density and invertebrate abundance, with lumbriculids and chironomids increasing in abundance with deposit density and all other taxa declining. Community structure changes significantly above a deposit density of approximately 8 mg cm, when algal biomass, invertebrate richness and diversity decline. Invertebrate richness and diversity were determined by direct effects of NPD biomass and indirect effects of IM. Algal biomass only had an effect on invertebrate abundance. Possible pH, oxygen, food and ecotoxicological effects of NPD biomass on the biota are discussed.

Anytime Algorithms for Solving Possibilistic MDPs and Hybrid MDPs

The ability of an agent to make quick, rational decisions in an uncertain environment is paramount for its applicability in realistic settings. Markov Decision Processes (MDP) provide such a framework, but can only model uncertainty that can be expressed as probabilities. Possibilistic counterparts of MDPs allow to model imprecise beliefs, yet they cannot accurately represent probabilistic sources of uncertainty and they lack the efficient online solvers found in the probabilistic MDP community. In this paper we advance the state of the art in three important ways. Firstly, we propose the first online planner for possibilistic MDP by adapting the Monte-Carlo Tree Search (MCTS) algorithm. A key component is the development of efficient search structures to sample possibility distributions based on the DPY transformation as introduced by Dubois, Prade, and Yager. Secondly, we introduce a hybrid MDP model that allows us to express both possibilistic and probabilistic uncertainty, where the hybrid model is a proper extension of both probabilistic and possibilistic MDPs. Thirdly, we demonstrate that MCTS algorithms can readily be applied to solve such hybrid models.