Detection and measurement of Plasmodiophora brassicae

Clubroot, caused by Plasmodiophora brassicae, is one of the most important diseases of brassicas. Management of clubroot is difficult, and the best means of avoiding the disease include planting in areas where P. brassicae is not present and using plants and growing media free from pathogen inoculum. As P. brassicae is not culturable, its detection has traditionally relied on plant bioassays, which are time-consuming and require large amounts of glasshouse space. More recently, fluorescence microscopy, serology, and DNA-based methods have all been used to test soil, water, or plant samples for clubroot. The use of fluorescence microscopy to detect and count pathogen spores in the soil requires significant operator skill and is unlikely to serve as the basis for a routine diagnostic test. By contrast, serologic assays are inexpensive and amenable to high-throughput screening but need to be based on monoclonal antibodies because polyclonal antisera cannot be reproduced and are therefore of limited quantity. Several polymerase chain reaction (PCR)-based assays have also been developed; these are highly specific for P. brassicae and have been well-correlated with disease severity. As such, PCR-based diagnostic tests have been adopted to varying extents in Canada and Australia, but wide implementation has been restricted by sample processing costs. Efforts are underway to develop inexpensive serologic on-farm diagnostic kits and to improve quantification of pathogen inoculum levels through real-time PCR. Proper detection and quantification of P. brassicae will likely play an increasingly important role in the development of effective clubroot management strategies.

Optimal sensor placement and measurement of wind for water quality studies in urban reservoirs

We collaborate with environmental scientists to study the hydrodynamics and water quality in an urban district, where the surface wind distribution is an essential input but undergoes high spatial and temporal variations due to the complex urban landform created by surrounding buildings. In this work, we study an optimal sensor placement scheme to measure the wind distribution over a large urban reservoir with a limited number of wind sensors. Unlike existing sensor placement solutions that assume Gaussian process of target phenomena, this study measures the wind which inherently exhibits strong non-Gaussian yearly distribution. By leveraging the local monsoon characteristics of wind, we segment a year into different monsoon seasons which follow a unique distribution respectively. We also use computational fluid dynamics to learn the spatial correlation of wind in the presence of surrounding buildings. The output of sensor placement is a set of the most informative locations to deploy the wind sensors, based on the readings of which we can accurately predict the wind over the entire reservoir surface in real time. 10 wind sensors are finally deployed around or on the water surface of an urban reservoir. The in-field measurement results of more than 3 months suggest that the proposed sensor placement and spatial prediction approach provides accurate wind measurement which outperforms the state-of-the-art Gaussian model based or interpolation based approaches.

Applying a multi-agent classifier system with a novel trust measurement method to classifying medical data

In this paper, we present the application of a Multi-Agent Classifier System (MACS) to medical data classification tasks. The MACS model comprises a number of Fuzzy Min-Max (FMM) neural network classifiers as its agents. A trust measurement method is used to integrate the predictions from multiple agents, in order to improve the overall performance of the MACS model. An auction procedure based on the sealed bid is adopted for the MACS model in determining the winning agent. The effectiveness of the MACS model is evaluated using the Wisconsin Breast Cancer (WBC) benchmark problem and a real-world heart disease diagnosis problem. The results demonstrate that stable results are produced by the MACS model in undertaking medical data classification tasks. © 2014 Springer Science+Business Media Singapore.

Sensor placement and measurement of wind for water quality studies in urban reservoirs

We study the water quality in an urban district, where the surface wind distribution is an essential input but undergoes high spatial and temporal variations due to the impact of surrounding buildings. In this work, we develop an optimal sensor placement scheme to measure the wind distribution over a large urban reservoir using a limited number of wind sensors. Unlike existing solutions that assume Gaussian process of target phenomena, this study measures the wind that inherently exhibits strong non-Gaussian yearly distribution. By leveraging the local monsoon characteristics of wind, we segment a year into different monsoon seasons that follow a unique distribution respectively. We also use computational fluid dynamics to learn the spatial correlation of wind. The output of sensor placement is a set of the most informative locations to deploy the wind sensors, based on the readings of which we can accurately predict the wind over the entire reservoir in real time. Ten wind sensors are deployed. The in-field measurement results of more than 3 months suggest that the proposed sensor placement and spatial prediction scheme provides accurate wind measurement that outperforms the state-of-the-art Gaussian model based on interpolation-based approaches.

Real-time ultrasound measures of lumbar erector spinae and multifidus: reliability and comparison to magnetic resonance imaging

In this work we examine the reliability and validity (in comparison to magnetic resonance imaging; MRI) of real-time ultrasound measures of lumbar erector spinae thickness. We also consider the between-day reliability of the lumbar multifidus muscle area as measured via ultrasound. 23 male subjects aged 21-45 years were measured three times over the course of nine days by one operator. The first (L1) through to the fifth (L5) lumbar vertebral levels were measured on the left and right sides. MRI was performed on the same day as first ultrasound scanning. For between-day intra-rater reliability, intra-class correlation co-efficients (ICCs), standard error of the measurement, minimal detectable difference and co-efficients of variation (CVs) were calculated along with their 95% confidence intervals and Bland-Altman analysis was performed. On Bland-Altman analysis, erector spinae thickness and multifidus area ultrasound measures 'agreed' with equivalent MR measures, though the correlation between MR and ultrasound measures was typically poor to moderate. For both ultrasound measures, the ICCs ranged from 'moderate' to 'excellent' at individual vertebral levels, although multifidus area (CV ranged from 8 to 15%) was less reliable than erector spinae thickness (CV ranged from 6 to 10%). 'Agreement' on Bland-Altmann analysis was present between days for all ultrasound measures. Averaging between sides and between vertebral levels improved reliability. Average erector spinae thickness showed a CV of 5.5% (ICC 0.77) and average multifidus area 6.2% (ICC 0.80).