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.

Region-based Mixture of Gaussians Modelling for Foreground Detection in Dynamic Scenes

One of the most widely used techniques in computer vision for foreground detection is to model each background pixel as a Mixture of Gaussians (MoG). While this is effective for a static camera with a fixed or a slowly varying background, it fails to handle any fast, dynamic movement in the background. In this paper, we propose a generalised framework, called region-based MoG (RMoG), that takes into consideration neighbouring pixels while generating the model of the observed scene. The model equations are derived from Expectation Maximisation theory for batch mode, and stochastic approximation is used for online mode updates. We evaluate our region-based approach against ten sequences containing dynamic backgrounds, and show that the region-based approach provides a performance improvement over the traditional single pixel MoG. For feature and region sizes that are equal, the effect of increasing the learning rate is to reduce both true and false positives. Comparison with four state-of-the art approaches shows that RMoG outperforms the others in reducing false positives whilst still maintaining reasonable foreground definition. Lastly, using the ChangeDetection (CDNet 2014) benchmark, we evaluated RMoG against numerous surveillance scenes and found it to amongst the leading performers for dynamic background scenes, whilst providing comparable performance for other commonly occurring surveillance scenes.

A Conditional Approach for Modelling Patient Re-admissions in Hospital using a mixture of Coxian phase-type distributions incorporating Bayes Theorem

The number of elderly patients requiring hospitalisation in Europe is rising. With a greater proportion of elderly people in the population comes a greater demand for health services and, in particular, hospital care. Thus, with a growing number of elderly patients requiring hospitalisation competing with non-elderly patients for a fixed (and in some cases, decreasing) number of hospital beds, this results in much longer waiting times for patients, often with a less satisfactory hospital experience. However, if a better understanding of the recurring nature of elderly patient movements between the community and hospital can be developed, then it may be possible for alternative provisions of care in the community to be put in place and thus prevent readmission to hospital. The research in this paper aims to model the multiple patient transitions between hospital and community by utilising a mixture of conditional Coxian phase-type distributions that incorporates Bayes' theorem. For the purpose of demonstration, the results of a simulation study are presented and the model is applied to hospital readmission data from the Lombardy region of Italy.

How much is '5-a-day'? A qualitative investigation into consumer understanding of fruit and vegetable intake guidelines

BACKGROUND: Despite the known health benefits of fruit and vegetables (FV), population intakes remain low. One potential contributing factor may be a lack of understanding surrounding recommended intakes. The present study aimed to explore the understanding of FV intake guidelines among a sample of low FV consumers.

METHODS: Six semi-structured focus groups were held with low FV consumers (n = 28, age range 19-55 years). Focus groups were recorded digitally, transcribed verbatim and analysed thematically using nvivo (QSR International, Melbourne, Australia) to manage the coded data. Participants also completed a short questionnaire assessing knowledge on FV intake guidelines. Descriptive statistics were used to analyse responses.

RESULTS: The discussions highlighted that, although participants were aware of FV intake guidelines, they lacked clarity with regard to the meaning of the '5-a-day' message, including what foods are included in the guideline, as well as what constitutes a portion of FV. There was also a sense of confusion surrounding the concept of achieving variety with regard to FV intake. The sample highlighted a lack of previous education on FV portion sizes and put forward suggestions for improving knowledge, including increased information on food packaging and through health campaigns. Questionnaire findings were generally congruent with the qualitative findings, showing high awareness of the '5-a-day' message but a lack of knowledge surrounding FV portion sizes.

CONCLUSIONS: Future public health campaigns should consider how best to address the gaps in knowledge identified in the present study, and incorporate evaluations that will allow the impact of future initiatives on knowledge, and ultimately behaviour, to be investigated.

Extraction and radioimmunoassay quantitation of neuropeptide Y (NPY) and vasoactive intestinal polypeptide (VIP) from human dental pulp tissue

The measurement of neuropeptides in complex biological tissue samples requires efficient and appropriate extraction methods so that immunoreactivity is retained for subsequent radioimmunoassay detection. Since neuropeptides differ in their molecular mass, charge and hydrophobicity, no single method will suffice for the optimal extraction of various neuropeptides. In this study, dental pulp tissue was obtained from 30 human non-carious teeth. Of the three different neuropeptide extraction methods employed, boiling in acetic acid in the presence of protease inhibitors yielded the highest levels of neuropeptide Y (NPY) and vasoactive intestinal polypeptide (VIP). High pressure liquid chromatography (HPLC) analysis of dental pulp tissue verified the authenticity of the neuropeptides extracted. © 2003 Elsevier Science Ltd. All rights reserved.

Neuropeptide YY1 receptor in human dental pulp cells of noncarious and carious teeth

Aim To determine the distribution of the NPY Y1 receptor in carious and noncarious human dental pulp tissue using immunohistochemistry. A subsidiary aim was to confirm the presence of the NPY Y1 protein product in membrane fractions of dental pulp tissue from carious and noncarious teeth using western blotting. Methodology Twenty two dental pulp samples were collected from carious and noncarious extracted teeth. Ten samples were processed for immunohistochemistry using a specific antibody to the NPY Y1 receptor. Twelve samples were used to obtain membrane extracts which were electrophoresed, blotted onto nitrocellulose and probed with NPY Y1 receptor antibody. Kruskal-Wallis one-way analysis of variance was employed to test for overall statistical differences between NPY Y1 levels in noncarious, moderately carious and grossly carious teeth. Results Neuropeptide Y Y1 receptor immunoreactivity was detected on the walls of blood vessels in pulp tissue from noncarious teeth. In carious teeth NPY Y1 immunoreactvity was observed on nerve fibres, blood vessels and inflammatory cells. Western blotting indicated the presence and confirmed the variability of NPY Y1 receptor protein expression in solubilised membrane preparations of human dental pulp tissue from carious and noncarious teeth. Conclusions Neuropeptide Y Y1 is expressed in human dental pulp tissue with evidence of increased expression in carious compared with noncarious teeth, suggesting a role for NPY Y1 in modulation of caries induced pulpal inflammation. © 2008 International Endodontic Journal.

Mutual Solubilities of Ammonium-Based Ionic Liquids with Water and with Water/Methanol Mixture

Over the last two decades, ionic liquids have gained importance as alternative solvents to conventional VOCs in the field of homogeneous catalysis. This success is not only due to their ability to dissolve a large amount of metal catalysts, but it is also due to their potential to enhance yields of enantiopure products. The art of preparation of a specific enantiomer is a highly desired one and searched for in pharmaceutical industry. This work presents a study on solubility in water and in water/methanol mixture of a set of ILs composed of the bis (trifluoromethylsulfonyl) imide anion and of the N-alkyl-triethyl-ammonium cation (abbrev. [NR,222][NTf2]) with the alkyl chain R ranging from 6 to 12 carbons. Mutual solubilities between ILs and water, as well as between ILs and methanol/water mixture were investigated in detail. These solubilities were measured using two well-known and accurate experimental techniques based on a volumetric and a cloud-point methods. Both methods enabled us to measure the Tx diagrams reflecting the mutual solubilities between water (or water/methanol) and selected ILs in the temperature range from 293.15 to 338.15 K. The data were fitted by using the modified Flory-Huggins equation proposed by de Sousa and Rebelo and compared also with the prediction carried out by the Cosmo-RS methodology

Fruit and vegetable intake and risk of cardiovascular disease

A high intake of fruit and vegetables (FV) has been shown to be associated with reduced risk of a number of chronic diseases, including CVD. This review aims to provide an overview of the evidence that increased FV intake reduces risk of CVD, focusing on studies examining total FV intake. This evidence so far available is largely based on prospective cohort studies, with meta-analyses demonstrating an association between increased FV intake and reduced risk of both CHD and stroke. Controlled intervention trials examining either clinical or cardiovascular risk factor endpoints are scarce. However, such trials have shown that an increase in FV consumption can lower blood pressure and also improve microvascular function, both of which are commensurate with a reduced risk of CVD. The effects of increased FV consumption on plasma lipid levels, risk of diabetes and body weight have yet to be firmly established. In conclusion, evidence that FV consumption reduces the risk of CVD is so far largely confined to observational epidemiology, with further intervention studies required.

Increasing fruit and vegetable intake has no effect on retinal vessel caliber in adults at high risk of developing cardiovascular disease

BACKGROUND AND AIM: Retinal vessel abnormalities are associated with cardiovascular disease (CVD) risk. To date, there are no trials investigating the effect of dietary factors on the retinal microvasculature. This study examined the dose response effect of fruit and vegetable (FV) intake on retinal vessel caliber in overweight adults at high CVD risk.

METHODS AND RESULTS: Following a 4 week washout period, participants were randomized to consume either 2 or 4 or 7 portions of FV daily for 12 weeks. Retinal vessel caliber was measured at baseline and post-intervention. A total of 62 participants completed the study. Self-reported FV intake indicated good compliance with the intervention, with serum concentrations of zeaxanthin and lutein increasing significantly across the groups in a dose-dependent manner (P for trend < 0.05). There were no significant changes in body composition, 24-h ambulatory blood pressure or fasting blood lipid profiles in response to the FV intervention. Increasing age was a significant determinant of wider retinal venules (P = 0.004) whereas baseline systolic blood pressure was a significant determinant of narrower retinal arterioles (P = 0.03). Overall, there was no evidence of any short-term dose-response effect of FV intake on retinal vessel caliber (CRAE (P = 0.92) or CRVE (P = 0.42)).

CONCLUSIONS: This study demonstrated no effect of increasing FV intake on retinal vessel caliber in overweight adults at high risk of developing primary CVD.

Fruit and vegetable intake and risk of incident of type 2 diabetes: results from the consortium on health and ageing network of cohorts in Europe and the United States (CHANCES)

BACKGROUND/OBJECTIVES: There is limited information to support definitive recommendations concerning the role of diet in the development of type 2 Diabetes mellitus (T2DM). The results of the latest meta-analyses suggest that an increased consumption of green leafy vegetables may reduce the incidence of diabetes, with either no association or weak associations demonstrated for total fruit and vegetable intake. Few studies have, however, focused on older subjects.

SUBJECTS/METHODS: The relationship between T2DM and fruit and vegetable intake was investigated using data from the NIH-AARP study and the EPIC Elderly study. All participants below the age of 50 and/or with a history of cancer, diabetes or coronary heart disease were excluded from the analysis. Multivariate logistic regression analysis was used to calculate the odds ratio of T2DM comparing the highest with the lowest estimated portions of fruit, vegetable, green leafy vegetables and cabbage intake.

RESULTS: Comparing people with the highest and lowest estimated portions of fruit, vegetable or green leafy vegetable intake indicated no association with the risk of T2DM. However, although the pooled OR across all studies showed no effect overall, there was significant heterogeneity across cohorts and independent results from the NIH-AARP study showed that fruit and green leafy vegetable intake was associated with a reduced risk of T2DM OR 0.95 (95% CI 0.91,0.99) and OR 0.87 (95% CI 0.87,0.90) respectively.

CONCLUSIONS: Fruit and vegetable intake was not shown to be related to incident T2DM in older subjects. Summary analysis also found no associations between green leafy vegetable and cabbage intake and the onset of T2DM. Future dietary pattern studies may shed light on the origin of the heterogeneity across populations.European Journal of Clinical Nutrition advance online publication, 17 August 2016;