Variance-covariance based weighing for neural network ensembles

Neural network (NN) is a popular artificial intelligence technique for solving complicated problems due to their inherent capabilities. However generalization in NN can be harmed by a number of factors including parameter's initialization, inappropriate network topology and setting parameters of the training process itself. Forecast combinations of NN models have the potential for improved generalization and lower training time. A weighted averaging based on Variance-Covariance method that assigns greater weight to the forecasts producing lower error, instead of equal weights is practiced in this paper. While implementing the method, combination of forecasts is done with all candidate models in one experiment and with the best selected models in another experiment. It is observed during the empirical analysis that forecasting accuracy is improved by combining the best individual NN models. Another finding of this study is that reducing the number of NN models increases the diversity and, hence, accuracy.

Personal ICT Ensembles and Ubiquitous Information Systems Environments: Key Issues and Research Implications

Personal information and communication technologies (ICTs) have become commonplace. Today many people own, or have access to, a range of different computing and communication devices, information technologies, and services, which they incorporate into their everyday routines. Increasingly, these technologies impact the way that individuals work, socialize, and play. Workers are bringing their personal ICTs to the office, and organizations are tailoring their computing environments toward ubiquitous integration with personal ICTs. These developments are opening up new ways of working, but they also create new challenges for organizations in accommodating this “nonaffiliated” use as part of their information systems environments. In this article we propose a framework for analyzing the composition and impact of personal ICT ensembles. The framework is positioned as pre-theory that invites further development and empirical testing. We illustrate how the proposed framework could be applied to consider personal ICT use across the work/home context. Several implications stemming from the notion of a personal ICT ensemble are highlighted, including practical considerations for nonaffiliated use in organizations. We conclude with suggestions for further development of the proposed framework.

Community-onset Escherichia coli infection resistant to expanded- spectrum cephalosporins in low-prevalence countries

Background
By global standards the prevalence of community onset expanded-spectrum cephalosporin resistant Escherichia coli (ESC-R-EC) remains low in Australia and New Zealand. Of concern, our countries are in a unique position with high extramural resistance pressure from close population and trade links to Asia-Pacific neighbours with high ESC-R-EC rates. We aim to characterize the risks and dynamics of community onset ESC-R-EC in our low-prevalence region.

Methods
A case-control methodology was used. Patients with ESC-R-EC or susceptible E. coli isolated from blood or urine were recruited at six geographically dispersed tertiary hospitals in Australia and New Zealand. Epidemiological data was prospectively collected and bacteria were retained for analysis.

Results
In total, 182 patients (91 cases and 91 controls) were recruited. Multivariate logistic regression identified risk factors for ESC-R amongst E. coli including birth on the Indian subcontinent (OR=11.13, 2.17-56.98, p=0.003), urinary tract infection in the past year (per infection OR=1.430, 1.13-1.82, p=0.003), travel to South East Asia, China, Indian subcontinent, Africa and the Middle East (OR=3.089, 1.29-7.38, p=0.011), prior exposure to trimethoprim+/-sulfamethoxazole &/or an expanded-spectrum cephalosporin (OR=3.665, 1.30-10.35, p=0.014) and healthcare exposure in the previous six months (OR=3.16, 1.54-6.46, p=0.02).

Amongst our ESC-R-EC the blaCTX-M ESBLs was dominant (83% of ESC-R-EC), and the worldwide pandemic clone ST-131 was frequent (45% of ESC-R-EC).

Conclusion
In our low prevalence setting, ESC-R amongst community onset E. coli may be associated with both ‘export’ from healthcare facilities into the community and direct ‘import’ into the community from high-prevalence regions.

Empirical investigation of decision tree ensembles for monitoring cardiac complications of diabetes

Cardiac complications of diabetes require continuous monitoring since they may lead to increased morbidity or sudden death of patients. In order to monitor clinical complications of diabetes using wearable sensors, a small set of features have to be identified and effective algorithms for their processing need to be investigated. This article focuses on detecting and monitoring cardiac autonomic neuropathy (CAN) in diabetes patients. The authors investigate and compare the effectiveness of classifiers based on the following decision trees: ADTree, J48, NBTree, RandomTree, REPTree, and SimpleCart. The authors perform a thorough study comparing these decision trees as well as several decision tree ensembles created by applying the following ensemble methods: AdaBoost, Bagging, Dagging, Decorate, Grading, MultiBoost, Stacking, and two multi-level combinations of AdaBoost and MultiBoost with Bagging for the processing of data from diabetes patients for pervasive health monitoring of CAN. This paper concentrates on the particular task of applying decision tree ensembles for the detection and monitoring of cardiac autonomic neuropathy using these features. Experimental outcomes presented here show that the authors' application of the decision tree ensembles for the detection and monitoring of CAN in diabetes patients achieved better performance parameters compared with the results obtained previously in the literature.

Material damage: expanded cinema

Over a 35 year career de Bruyn’s bracing and immersive work has investigated legacies of trauma anddisplacement, dealing with the residue of the white Australia policy and his own experience ofchildhood migration to Australia from Holland.In recent years de Bruyn has presented his hand drawn 16mm animation films as performances, withde Bruyn manipulating the images live, and accompanying them with a live vocal soundtrack. returnsto Auckland to deliver an expanded cinema performance for 16mm projectors and voice.

Enhancing predictive accuracy of cardiac autonomic neuropathy using blood biochemistry features and iterative multitier ensembles

Blood biochemistry attributes form an important class of tests, routinely collected several times per year for many patients with diabetes. The objective of this study is to investigate the role of blood biochemistry for improving the predictive accuracy of the diagnosis of cardiac autonomic neuropathy (CAN) progression. Blood biochemistry contributes to CAN, and so it is a causative factor that can provide additional power for the diagnosis of CAN especially in the absence of a complete set of Ewing tests. We introduce automated iterative multitier ensembles (AIME) and investigate their performance in comparison to base classifiers and standard ensemble classifiers for blood biochemistry attributes. AIME incorporate diverse ensembles into several tiers simultaneously and combine them into one automatically generated integrated system so that one ensemble acts as an integral part of another ensemble. We carried out extensive experimental analysis using large datasets from the diabetes screening research initiative (DiScRi) project. The results of our experiments show that several blood biochemistry attributes can be used to supplement the Ewing battery for the detection of CAN in situations where one or more of the Ewing tests cannot be completed because of the individual difficulties faced by each patient in performing the tests. The results show that AIME provide higher accuracy as a multitier CAN classification paradigm. The best predictive accuracy of 99.57% has been obtained by the AIME combining decorate on top tier with bagging on middle tier based on random forest. Practitioners can use these findings to increase the accuracy of CAN diagnosis.

Expanded description of Lamproglena monodi (Copepoda: Lernaeidae), parasitizing native and introduced fishes in Brazil

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Influence of Osteopenia in Autogenous Bone Graft Healing With or Without Expanded Polytetrafluoroethylene Membranes: Histologic and Histomorphometric Study in Rats

Purpose: The aim of this study was to quantitatively evaluate and qualitatively describe autogenous bone graft healing with or without an expanded polytetrafluoroethylene (e-PTFE) membrane in ovariectornized rats. Materials and Methods: Eighty Wistar rats, weighing approximately 300 g each, were used. A graft was obtained from the parietal bone and fixed to the sidewall of each animal's left mandibular ramus. The animals were randomly divided into four experimental groups (n = 20 in each group): group 1, sham operated and autogenous bone graft only- group 2, sham operated and autogenous bone graft covered by e-PTFE membrane; group 3, ovariectornized (OVX) and autogenous bone graft only- group 4, OVX and autogenous bone graft covered by e-PTFE membrane. The animals were sacrificed at five different time points: immediately after grafting or at 7, 21, 45, or 60 days after grafting. Histologic examination and morphometric measurement of the sections were performed, and values were submitted to statistical analyses. Results: Both groups (sham and OVX) experienced loss of the original graft volume when it was not covered by the membrane, whereas use of the membrane resulted in additional bone formation beyond the edges of the graft and under the membrane. Histologic analysis showed integration of the grafts in all animals, although a larger number of marrow spaces was found in OVX groups. Conclusions: Association of bone graft with an e-PTFE membrane resulted in maintenance of its original volume as well as formation of new bone that filled the space under the membrane. Osteopenia did not influence bone graft repair, regardless of whether or not it was associated with e-PTFE membrane, but descriptive histologic analysis showed larger numbers of marrow spaces in the bone graft and receptor bed and formation of new bone in the OVX animals. INT J ORAL MAXILLOFAC IMPLANTS 2009;24:1074-1082

A new species and expanded distributions of freshwater Audouinella (Acrochaetiaceae, Rhodophyta) from Central Mexico and south-eastern Brazil

Eighteen collections of red-coloured Audouinella from Central Mexico and southeastern Brazil detected three species. The most common species, A. eugenea, is characterized by macroscopic thalli, the erect system consisting of filaments with cylindrical cells, undifferentiated into proximal and distal parts, and relatively large monosporangia (greater than or equal to 12.0 mum long). Spermatangia. and possible propagules were observed in some Mexican populations. This is the third Audouinella species observed to have gametangia and the first member of the Acrochaetiales with putative propagules. The second species, from Central Mexico, was characterized by the following features: macroscopic thalli, the erect system differentiated into proximal parts with cylindrical cells, unbranched or rarely branched, and distal parts with barrel-shaped cells, abundantly branched to form dense fascicles, with alternate or dichotomous branching, some at right-angles to the axis, and relatively large monosporangia (greater than or equal to 12.0 mum long). The morphologically distinct proximal and distal portions of the erect system, the latter forming dense fascicles, was a consistent character so far unknown in Audouinella; thus, we propose a new species, A. huastecana sp. nov. The third species is a microscopic epiphyte, A. meiospora, with a well-developed prostrate system composed of creeping and loosely aggregated filaments, and a short homogeneous erect system (less than or equal to 15 cells) of filaments with cylindrical or barrel-shaped cells and small monosporangia (less than or equal to 13.0 mum long). A. eugenea and A. meiospora are characterized for the first time from the Southern and Northern Hemispheres, respectively, both occurring mostly in areas of tropical or subtropical rainforests. A. meiospora is reported from new macroalgal hosts. A. eugenea and A. huastecana tended to occur in warm, alkaline waters with a high ion content that were moderate to fast flowing, whereas A. meiospora was not associated with particular habitats.

Gold nanoelectrode ensembles for direct trace electroanalysis of iodide

A procedure for the standardization of ensembles of gold nanodisk electrodes (NEE) of 30 nm diameter is presented, which is based on the analytical comparison between experimental cyclic voltammograms (CV) obtained at the NEEs in diluted solutions of redox probes and CV patterns obtained by digital simulation. Possible origins of defects sometimes found in NEEs are discussed. Selected NEEs are then employed for the study of the electrochemical oxidation of iodide in acidic solutions. CV patterns display typical quasi-reversible behavior which involves associated chemical reactions between adsorbed and solution species. The main CV characteristics at the NEE compare with those observed at millimeter sized gold disk electrodes (Au-macro), apart a slight shift in E1/2 values and slightly higher peak to peak separation at the NEE. The detection limit (DC) at NEEs is 0.3 mu M, which is more than one order of magnitude lower than DL at the Au-macro (4 RM). The mechanism of the electrochemical oxidation of iodide at NEEs is discussed. Finally, NEEs are applied to the direct determination of iodide at micromolar concentration levels in real samples, namely in some ophthalmic drugs and iodized table salt. (c) 2006 Elsevier B.V. All rights reserved.