Alleviating ‘overfitting’ via genetically-regularised neural network

A hybrid genetic algorithm/scaled conjugate gradient regularisation method is designed to alleviate ANN `over-fitting'. In application to day-ahead load forecasting, the proposed algorithm performs better than early-stopping and Bayesian regularisation, showing promising initial results.

Health risk from the use of roof-harvested rainwater in Southeast Queensland, Australia, as potable or nonpotable water, determined using quantitative microbial risk assessment

A total of 214 rainwater samples from 82 tanks were collected in urban Southeast Queensland (SEQ) in Australia and analysed for the zoonotic bacterial and protozoan pathogen using real-time binary PCR and quantitative PCR (qPCR). Quantitative Microbial Risk Assessment (QMRA) analysis was used to quantify the risk of infection associated with the exposure to potential pathogens from potable and non-potable uses of roof-harvested rainwater. Of the 214 samples tested, 10.7%, 9.8%, and 5.6%, and 0.4% samples were positive for Salmonella invA, Giardia lamblia β-giardin , Legionella pneumophila mip, and Campylobacter jejuni mapA genes. Cryptosporidium parvum could not be detected. The estimated numbers of viable Salmonella spp., G. lamblia β-giradin, and L. pneumophila genes ranged from 1.6 × 101 to 9.5 × 101 cells, 1.4 × 10-1 to 9.0 × 10-1 cysts, and 1.5 × 101 to 4.3 × 101 per 1000 ml of water, respectively. Six risk scenarios were considered from exposure to Salmonella spp., G. lamblia and L. pneumophila. For Salmonella spp., and G. lamblia, these scenarios were: (1) liquid ingestion due to drinking of rainwater on a daily basis (2) accidental liquid ingestion due to garden hosing twice a week (3) aerosol ingestion due to showering on a daily basis, and (4) aerosol ingestion due to hosing twice a week. For L. pneumophila, these scenarios were: (5) aerosol inhalation due to showering on a daily basis, and (6) aerosol inhalation due to hosing twice a week. The risk of infection from Salmonella spp., G. lamblia, and L. pneumophila associated with the use of rainwater for showering and garden hosing was calculated to be well below the threshold value of one extra infection per 10,000 persons per year in urban SEQ. However, the risk of infection from ingesting Salmonella spp. and G. lamblia via drinking exceeds this threshold value, and indicates that if undisinfected rainwater were ingested by drinking, then the gastrointestinal diseases of Salmonellosis and Giardiasis is expected to range from 5.0 × 100 to 2.8 × 101 (Salmonellosis) and 1.0 × 101 to 6.4 × 101 (Giardiasis) cases per 10,000 persons per year, respectively. Since this health risk seems higher than that expected from the reported incidences of gastroenteritis, the assumptions used to estimate these infection risks are critically examined. Nonetheless, it would seem prudent to disinfect rainwater for potable use.

Lean project management in large scale industrial project via standardization

Lean project management is the comprehensive adaption of other lean concept like lean construction, lean manufacturing and lean thinking into project management context. Execution of many similar industrial projects creates the idea of lean project management in companies and rapidly growing in industries. This paper offers the standardization method in order to achieve Lean project management in large scale industrial project. Standardization refers to all activity which makes two projects most identical and unify to each other like standardization of design, reducing output variability, value analysis and strategic management. Although standard project may have minor effi ciency decrease, compare to custom built project; but great advantage of standard project like cost saving, time reduction and quality improvement justify standardization methodology. This paper based on empirical experience in industrial project and theoretical analysis of benefi ts of project standardization.

Empirical Bayes method in the study of traffic safety via heterogeneous negative multinomial model

In the study of traffic safety, expected crash frequencies across sites are generally estimated via the negative binomial model, assuming time invariant safety. Since the time invariant safety assumption may be invalid, Hauer (1997) proposed a modified empirical Bayes (EB) method. Despite the modification, no attempts have been made to examine the generalisable form of the marginal distribution resulting from the modified EB framework. Because the hyper-parameters needed to apply the modified EB method are not readily available, an assessment is lacking on how accurately the modified EB method estimates safety in the presence of the time variant safety and regression-to-the-mean (RTM) effects. This study derives the closed form marginal distribution, and reveals that the marginal distribution in the modified EB method is equivalent to the negative multinomial (NM) distribution, which is essentially the same as the likelihood function used in the random effects Poisson model. As a result, this study shows that the gamma posterior distribution from the multivariate Poisson-gamma mixture can be estimated using the NM model or the random effects Poisson model. This study also shows that the estimation errors from the modified EB method are systematically smaller than those from the comparison group method by simultaneously accounting for the RTM and time variant safety effects. Hence, the modified EB method via the NM model is a generalisable method for estimating safety in the presence of the time variant safety and the RTM effects.

Managing process model complexity via concrete syntax modifications

While Business Process Management (BPM) is an established discipline, the increased adoption of BPM technology in recent years has introduced new challenges. One challenge concerns dealing with the ever-growing complexity of business process models. Mechanisms for dealing with this complexity can be classified into two categories: 1) those that are solely concerned with the visual representation of the model and 2) those that change its inner structure. While significant attention is paid to the latter category in the BPM literature, this paper focuses on the former category. It presents a collection of patterns that generalize and conceptualize various existing mechanisms to change the visual representation of a process model. Next, it provides a detailed analysis of the degree of support for these patterns in a number of state-of-the-art languages and tools. This paper concludes with the results of a usability evaluation of the patterns conducted with BPM practitioners.

A hybrid Chinese information retrieval model

A distinctive feature of Chinese test is that a Chinese document is a sequence of Chinese with no space or boundary between Chinese words. This feature makes Chinese information retrieval more difficult since a retrieved document which contains the query term as a sequence of Chinese characters may not be really relevant to the query since the query term (as a sequence Chinese characters) may not be a valid Chinese word in that documents. On the other hand, a document that is actually relevant may not be retrieved because it does not contain the query sequence but contains other relevant words. In this research, we propose a hybrid Chinese information retrieval model by incorporating word-based techniques with the traditional character-based techniques. The aim of this approach is to investigate the influence of Chinese segmentation on the performance of Chinese information retrieval. Two ranking methods are proposed to rank retrieved documents based on the relevancy to the query calculated by combining character-based ranking and word-based ranking. Our experimental results show that Chinese segmentation can improve the performance of Chinese information retrieval, but the improvement is not significant if it incorporates only Chinese segmentation with the traditional character-based approach.

Multiscale analysis of protein functions and stochastic modelling of gene transcriptional regulatory networks

Genomic and proteomic analyses have attracted a great deal of interests in biological research in recent years. Many methods have been applied to discover useful information contained in the enormous databases of genomic sequences and amino acid sequences. The results of these investigations inspire further research in biological fields in return. These biological sequences, which may be considered as multiscale sequences, have some specific features which need further efforts to characterise using more refined methods. This project aims to study some of these biological challenges with multiscale analysis methods and stochastic modelling approach. The first part of the thesis aims to cluster some unknown proteins, and classify their families as well as their structural classes. A development in proteomic analysis is concerned with the determination of protein functions. The first step in this development is to classify proteins and predict their families. This motives us to study some unknown proteins from specific families, and to cluster them into families and structural classes. We select a large number of proteins from the same families or superfamilies, and link them to simulate some unknown large proteins from these families. We use multifractal analysis and the wavelet method to capture the characteristics of these linked proteins. The simulation results show that the method is valid for the classification of large proteins. The second part of the thesis aims to explore the relationship of proteins based on a layered comparison with their components. Many methods are based on homology of proteins because the resemblance at the protein sequence level normally indicates the similarity of functions and structures. However, some proteins may have similar functions with low sequential identity. We consider protein sequences at detail level to investigate the problem of comparison of proteins. The comparison is based on the empirical mode decomposition (EMD), and protein sequences are detected with the intrinsic mode functions. A measure of similarity is introduced with a new cross-correlation formula. The similarity results show that the EMD is useful for detection of functional relationships of proteins. The third part of the thesis aims to investigate the transcriptional regulatory network of yeast cell cycle via stochastic differential equations. As the investigation of genome-wide gene expressions has become a focus in genomic analysis, researchers have tried to understand the mechanisms of the yeast genome for many years. How cells control gene expressions still needs further investigation. We use a stochastic differential equation to model the expression profile of a target gene. We modify the model with a Gaussian membership function. For each target gene, a transcriptional rate is obtained, and the estimated transcriptional rate is also calculated with the information from five possible transcriptional regulators. Some regulators of these target genes are verified with the related references. With these results, we construct a transcriptional regulatory network for the genes from the yeast Saccharomyces cerevisiae. The construction of transcriptional regulatory network is useful for detecting more mechanisms of the yeast cell cycle.

Relationships between preventive activities, psychosocial factors and recurrence of venous leg ulcers : a prospective study

Aim To identify relationships between preventive activities, psychosocial factors and leg ulcer recurrence in patients with chronic venous leg ulcers. Background Chronic venous leg ulcers are slow to heal and frequently recur, resulting in years of suffering and intensive use of health care resources. Methods A prospective longitudinal study was undertaken with a sample of 80 patients with a venous leg ulcer recruited when their ulcer healed. Data were collected from 2006–2009 from medical records on demographics, medical history and ulcer history; and from self-report questionnaires on physical activity, nutrition, preventive activities and psychosocial measures. Follow-up data were collected via questionnaires every three months for 12 months after healing. Median time to recurrence was calculated using the Kaplan-Meier method. A Cox proportional-hazards regression model was used to adjust for potential confounders and determine effects of preventive strategies and psychosocial factors on recurrence. Results: There were 35 recurrences in a sample of 80 participants. Median time to recurrence was 27 weeks. After adjustment for potential confounders, a Cox proportional hazards regression model found that at least an hour/day of leg elevation, six or more days/week in Class 2 (20–25mmHg) or 3 (30–40mmHg) compression hosiery, higher social support scale scores and higher General Self-Efficacy scores remained significantly associated (p<0.05) with a lower risk of recurrence, while male gender and a history of DVT remained significant risk factors for recurrence. Conclusion Results indicate that leg elevation, compression hosiery, high levels of self-efficacy and strong social support will help prevent recurrence.

Association between indoor air pollution measurements and respiratory health in women and children in Lao PDR

This article presents the results of a study on the association between measured air pollutants and the respiratory health of resident women and children in Lao PDR, one of the least developed countries in Southeast Asia. The study, commissioned by the World Health Organisation, included PM10, CO and NO2 measurements made inside 181 dwellings in nine districts within two provinces in Lao PDR over a 5- month period (12/05–04/06), and respiratory health information (via questionnaires and peak expiratory flow rate (PEFR) measurements) for all residents in the same dwellings. Adjusted odds ratios were calculated separately for each health outcome using binary logistic regression. There was a strong and consistent positive association between NO2 and CO for almost all questionnaire-based health outcomes for both women and children. Women in dwellings with higher measured NO2 had more than triple of the odds of almost all of the health outcomes, and higher concentrations of NO2 and CO were significantly associated with lower PEFR. This study supports a growing literature confirming the role of indoor air pollution in the burden of respiratory disease in developing countries. The results will directly support changes in health and housing policy in Lao PDR.

How can soil monitoring networks be used to improve predictions of organic carbon pool dynamics and CO2 fluxes in agricultural soils?

Abstract As regional and continental carbon balances of terrestrial ecosystems become available, it becomes clear that the soils are the largest source of uncertainty. Repeated inventories of soil organic carbon (SOC) organized in soil monitoring networks (SMN) are being implemented in a number of countries. This paper reviews the concepts and design of SMNs in ten countries, and discusses the contribution of such networks to reducing the uncertainty of soil carbon balances. Some SMNs are designed to estimate country-specific land use or management effects on SOC stocks, while others collect soil carbon and ancillary data to provide a nationally consistent assessment of soil carbon condition across the major land-use/soil type combinations. The former use a single sampling campaign of paired sites, while for the latter both systematic (usually grid based) and stratified repeated sampling campaigns (5–10 years interval) are used with densities of one site per 10–1,040 km². For paired sites, multiple samples at each site are taken in order to allow statistical analysis, while for the single sites, composite samples are taken. In both cases, fixed depth increments together with samples for bulk density and stone content are recommended. Samples should be archived to allow for re-measurement purposes using updated techniques. Information on land management, and where possible, land use history should be systematically recorded for each site. A case study of the agricultural frontier in Brazil is presented in which land use effect factors are calculated in order to quantify the CO2 fluxes from national land use/management conversion matrices. Process-based SOC models can be run for the individual points of the SMN, provided detailed land management records are available. These studies are still rare, as most SMNs have been implemented recently or are in progress. Examples from the USA and Belgium show that uncertainties in SOC change range from 1.6–6.5 Mg C ha−1 for the prediction of SOC stock changes on individual sites to 11.72 Mg C ha−1 or 34% of the median SOC change for soil/land use/climate units. For national SOC monitoring, stratified sampling sites appears to be the most straightforward attribution of SOC values to units with similar soil/land use/climate conditions (i.e. a spatially implicit upscaling approach). Keywords Soil monitoring networks - Soil organic carbon - Modeling - Sampling design