Speaker verification using I-vector features

This PhD research has provided novel solutions to three major challenges which have prevented the wide spread deployment of speaker recognition technology: (1) combating enrolment/ verification mismatch, (2) reducing the large amount of development and training data that is required and (3) reducing the duration of speech required to verify a speaker. A range of applications of speaker recognition technology from forensics in criminal investigations to secure access in banking will benefit from the research outcomes.

Higher order spectra based support vector machine for arrhythmia classification

Heart rate variability (HRV) refers to the regulation of the sinoatrial node, the natural pacemaker of the heart by the sympathetic and parasympathetic branches of the autonomic nervous system. HRV analysis is an important tool to observe the heart’s ability to respond to normal regulatory impulses that affect its rhythm. Like many bio-signals, HRV signals are non-linear in nature. Higher order spectral analysis (HOS) is known to be a good tool for the analysis of non-linear systems and provides good noise immunity. A computer-based arrhythmia detection system of cardiac states is very useful in diagnostics and disease management. In this work, we studied the identification of the HRV signals using features derived from HOS. These features were fed to the support vector machine (SVM) for classification. Our proposed system can classify the normal and other four classes of arrhythmia with an average accuracy of more than 85%.

Classification of echolocation calls from 14 species of bat by Support Vector Machines and Ensembles of Neural Networks

Calls from 14 species of bat were classified to genus and species using discriminant function analysis (DFA), support vector machines (SVM) and ensembles of neural networks (ENN). Both SVMs and ENNs outperformed DFA for every species while ENNs (mean identification rate – 97%) consistently outperformed SVMs (mean identification rate – 87%). Correct classification rates produced by the ENNs varied from 91% to 100%; calls from six species were correctly identified with 100% accuracy. Calls from the five species of Myotis, a genus whose species are considered difficult to distinguish acoustically, had correct identification rates that varied from 91 – 100%. Five parameters were most important for classifying calls correctly while seven others contributed little to classification performance.

Reliable Fault Diagnosis for Low-Speed Bearings Using Individually Trained Support Vector Machines With Kernel Discriminative Feature Analysis

This paper proposes a highly reliable fault diagnosis approach for low-speed bearings. The proposed approach first extracts wavelet-based fault features that represent diverse symptoms of multiple low-speed bearing defects. The most useful fault features for diagnosis are then selected by utilizing a genetic algorithm (GA)-based kernel discriminative feature analysis cooperating with one-against-all multicategory support vector machines (OAA MCSVMs). Finally, each support vector machine is individually trained with its own feature vector that includes the most discriminative fault features, offering the highest classification performance. In this study, the effectiveness of the proposed GA-based kernel discriminative feature analysis and the classification ability of individually trained OAA MCSVMs are addressed in terms of average classification accuracy. In addition, the proposedGA- based kernel discriminative feature analysis is compared with four other state-of-the-art feature analysis approaches. Experimental results indicate that the proposed approach is superior to other feature analysis methodologies, yielding an average classification accuracy of 98.06% and 94.49% under rotational speeds of 50 revolutions-per-minute (RPM) and 80 RPM, respectively. Furthermore, the individually trained MCSVMs with their own optimal fault features based on the proposed GA-based kernel discriminative feature analysis outperform the standard OAA MCSVMs, showing an average accuracy of 98.66% and 95.01% for bearings under rotational speeds of 50 RPM and 80 RPM, respectively.

DS-VBF : dual sink vector-based routing protocol for underwater wireless sensor network

Underwater wireless sensor networks (UWSNs) have become the seat of researchers' attention recently due to their proficiency to explore underwater areas and design different applications for marine discovery and oceanic surveillance. One of the main objectives of each deployed underwater network is discovering the optimized path over sensor nodes to transmit the monitored data to onshore station. The process of transmitting data consumes energy of each node, while energy is limited in UWSNs. So energy efficiency is a challenge in underwater wireless sensor network. Dual sinks vector based forwarding (DS-VBF) takes both residual energy and location information into consideration as priority factors to discover an optimized routing path to save energy in underwater networks. The modified routing protocol employs dual sinks on the water surface which improves network lifetime. According to deployment of dual sinks, packet delivery ratio and the average end to end delay are enhanced. Based on our simulation results in comparison with VBF, average end to end delay reduced more than 80%, remaining energy increased 10%, and the increment of packet reception ratio was about 70%.

GPU accelerated algorithms for computing matrix function vector products with applications to exponential integrators and fractional diffusion

The efficient computation of matrix function vector products has become an important area of research in recent times, driven in particular by two important applications: the numerical solution of fractional partial differential equations and the integration of large systems of ordinary differential equations. In this work we consider a problem that combines these two applications, in the form of a numerical solution algorithm for fractional reaction diffusion equations that after spatial discretisation, is advanced in time using the exponential Euler method. We focus on the efficient implementation of the algorithm on Graphics Processing Units (GPU), as we wish to make use of the increased computational power available with this hardware. We compute the matrix function vector products using the contour integration method in [N. Hale, N. Higham, and L. Trefethen. Computing Aα, log(A), and related matrix functions by contour integrals. SIAM J. Numer. Anal., 46(5):2505–2523, 2008]. Multiple levels of preconditioning are applied to reduce the GPU memory footprint and to further accelerate convergence. We also derive an error bound for the convergence of the contour integral method that allows us to pre-determine the appropriate number of quadrature points. Results are presented that demonstrate the effectiveness of the method for large two-dimensional problems, showing a speedup of more than an order of magnitude compared to a CPU-only implementation.

Role of enhanced vector transmission of a new West Nile virus strain in an outbreak of equine disease in Australia in 2011

Background In 2011, a variant of West Nile virus Kunjin strain (WNVKUN) caused an unprecedented epidemic of neurological disease in horses in southeast Australia, resulting in almost 1,000 cases and a 9% fatality rate. We investigated whether increased fitness of the virus in the primary vector, Culex annulirostris, and another potential vector, Culex australicus, contributed to the widespread nature of the outbreak. Methods Mosquitoes were exposed to infectious blood meals containing either the virus strain responsible for the outbreak, designated WNVKUN2011, or WNVKUN2009, a strain of low virulence that is typical of historical strains of this virus. WNVKUN infection in mosquito samples was detected using a fixed cell culture enzyme immunoassay and a WNVKUN- specific monoclonal antibody. Probit analysis was used to determine mosquito susceptibility to infection. Infection, dissemination and transmission rates for selected days post-exposure were compared using Fisher’s exact test. Virus titers in bodies and saliva expectorates were compared using t-tests. Results There were few significant differences between the two virus strains in the susceptibility of Cx. annulirostris to infection, the kinetics of virus replication and the ability of this mosquito species to transmit either strain. Both strains were transmitted by Cx. annulirostris for the first time on day 5 post-exposure. The highest transmission rates (proportion of mosquitoes with virus detected in saliva) observed were 68% for WNVKUN2011 on day 12 and 72% for WNVKUN2009 on day 14. On days 12 and 14 post-exposure, significantly more WNVKUN2011 than WNVKUN2009 was expectorated by infected mosquitoes. Infection, dissemination and transmission rates of the two strains were not significantly different in Culex australicus. However, transmission rates and the amount of virus expectorated were significantly lower in Cx. australicus than Cx. annulirostris. Conclusions The higher amount of WNVKUN2011 expectorated by infected mosquitoes may be an indication that this virus strain is transmitted more efficiently by Cx. annulirostris compared to other WNVKUN strains. Combined with other factors, such as a convergence of abundant mosquito and wading bird populations, and mammalian and avian feeding behaviour by Cx. annulirostris, this may have contributed to the scale of the 2011 equine epidemic.

VIP Barcoding: Composition vector-based software for rapid species identification based on DNA barcoding

Species identification based on short sequences of DNA markers, that is, DNA barcoding, has emerged as an integral part of modern taxonomy. However, software for the analysis of large and multilocus barcoding data sets is scarce. The Basic Local Alignment Search Tool (BLAST) is currently the fastest tool capable of handling large databases (e.g. >5000 sequences), but its accuracy is a concern and has been criticized for its local optimization. However, current more accurate software requires sequence alignment or complex calculations, which are time-consuming when dealing with large data sets during data preprocessing or during the search stage. Therefore, it is imperative to develop a practical program for both accurate and scalable species identification for DNA barcoding. In this context, we present VIP Barcoding: a user-friendly software in graphical user interface for rapid DNA barcoding. It adopts a hybrid, two-stage algorithm. First, an alignment-free composition vector (CV) method is utilized to reduce searching space by screening a reference database. The alignment-based K2P distance nearest-neighbour method is then employed to analyse the smaller data set generated in the first stage. In comparison with other software, we demonstrate that VIP Barcoding has (i) higher accuracy than Blastn and several alignment-free methods and (ii) higher scalability than alignment-based distance methods and character-based methods. These results suggest that this platform is able to deal with both large-scale and multilocus barcoding data with accuracy and can contribute to DNA barcoding for modern taxonomy. VIP Barcoding is free and available at http://msl.sls.cuhk.edu.hk/vipbarcoding/.

The significance of controlled conditions in lentiviral vector titration and in the use of multiplicity of infection (MOI) for predicting gene transfer events

Background: Although lentiviral vectors have been widely used for in vitro and in vivo gene therapy researches, there have been few studies systematically examining various conditions that may affect the determination of the number of viable vector particles in a vector preparation and the use of Multiplicity of Infection (MOI) as a parameter for the prediction of gene transfer events. Methods: Lentiviral vectors encoding a marker gene were packaged and supernatants concentrated. The number of viable vector particles was determined by in vitro transduction and fluorescent microscopy and FACs analyses. Various factors that may affect the transduction process, such as vector inoculum volume, target cell number and type, vector decay, variable vector - target cell contact and adsorption periods were studied. MOI between 0-32 was assessed on commonly used cell lines as well as a new cell line. Results: We demonstrated that the resulting values of lentiviral vector titre varied with changes of conditions in the transduction process, including inoculum volume of the vector, the type and number of target cells, vector stability and the length of period of the vector adsorption to target cells. Vector inoculum and the number of target cells determine the frequencies of gene transfer event, although not proportionally. Vector exposure time to target cells also influenced transduction results. Varying these parameters resulted in a greater than 50-fold differences in the vector titre from the same vector stock. Commonly used cell lines in vector titration were less sensitive to lentiviral vector-mediated gene transfer than a new cell line, FRL 19. Within 0-32 of MOI used transducing four different cell lines, the higher the MOI applied, the higher the efficiency of gene transfer obtained. Conclusion: Several variables in the transduction process affected in in vitro vector titration and resulted in vastly different values from the same vector stock, thus complicating the use of MOI for predicting gene transfer events. Commonly used target cell lines underestimated vector titre. However, within a certain range of MOI, it is possible that, if strictly controlled conditions are observed in the vector titration process, including the use of a sensitive cell line, such as FRL 19 for vector titration, lentivector-mediated gene transfer events could be predicted. © 2004 Zhang et al; licensee BioMed Central Ltd.

In vivo velocity vector imaging and time-resolved strain rate measurements in the wall of blood vessels using MRI

In this paper, we present a new approach for velocity vector imaging and time-resolved measurements of strain rates in the wall of human arteries using MRI and we prove its feasibility on two examples: in vitro on a phantom and in vivo on the carotid artery of a human subject. Results point out the promising potential of this approach for investigating the mechanics of arterial tissues in vivo.

Comparison of decision tree, support vector machines, and Bayesian network approaches for classification of falls in Parkinson’s disease

Being able to accurately predict the risk of falling is crucial in patients with Parkinson’s dis- ease (PD). This is due to the unfavorable effect of falls, which can lower the quality of life as well as directly impact on survival. Three methods considered for predicting falls are decision trees (DT), Bayesian networks (BN), and support vector machines (SVM). Data on a 1-year prospective study conducted at IHBI, Australia, for 51 people with PD are used. Data processing are conducted using rpart and e1071 packages in R for DT and SVM, con- secutively; and Bayes Server 5.5 for the BN. The results show that BN and SVM produce consistently higher accuracy over the 12 months evaluation time points (average sensitivity and specificity > 92%) than DT (average sensitivity 88%, average specificity 72%). DT is prone to imbalanced data so needs to adjust for the misclassification cost. However, DT provides a straightforward, interpretable result and thus is appealing for helping to identify important items related to falls and to generate fallers’ profiles.

Mixed pixel analysis for flood mapping using extended support vector machine

This paper addresses the challenges of flood mapping using multispectral images. Quantitative flood mapping is critical for flood damage assessment and management. Remote sensing images obtained from various satellite or airborne sensors provide valuable data for this application, from which the information on the extent of flood can be extracted. However the great challenge involved in the data interpretation is to achieve more reliable flood extent mapping including both the fully inundated areas and the 'wet' areas where trees and houses are partly covered by water. This is a typical combined pure pixel and mixed pixel problem. In this paper, an extended Support Vector Machines method for spectral unmixing developed recently has been applied to generate an integrated map showing both pure pixels (fully inundated areas) and mixed pixels (trees and houses partly covered by water). The outputs were compared with the conventional mean based linear spectral mixture model, and better performance was demonstrated with a subset of Landsat ETM+ data recorded at the Daly River Basin, NT, Australia, on 3rd March, 2008, after a flood event.

Spectral unmixing with estimated adaptive endmember index using Extended Support Vector Machine

The most difficult operation in the flood inundation mapping using optical flood images is to separate fully inundated areas from the ‘wet’ areas where trees and houses are partly covered by water. This can be referred as a typical problem the presence of mixed pixels in the images. A number of automatic information extraction image classification algorithms have been developed over the years for flood mapping using optical remote sensing images. Most classification algorithms generally, help in selecting a pixel in a particular class label with the greatest likelihood. However, these hard classification methods often fail to generate a reliable flood inundation mapping because the presence of mixed pixels in the images. To solve the mixed pixel problem advanced image processing techniques are adopted and Linear Spectral unmixing method is one of the most popular soft classification technique used for mixed pixel analysis. The good performance of linear spectral unmixing depends on two important issues, those are, the method of selecting endmembers and the method to model the endmembers for unmixing. This paper presents an improvement in the adaptive selection of endmember subset for each pixel in spectral unmixing method for reliable flood mapping. Using a fixed set of endmembers for spectral unmixing all pixels in an entire image might cause over estimation of the endmember spectra residing in a mixed pixel and hence cause reducing the performance level of spectral unmixing. Compared to this, application of estimated adaptive subset of endmembers for each pixel can decrease the residual error in unmixing results and provide a reliable output. In this current paper, it has also been proved that this proposed method can improve the accuracy of conventional linear unmixing methods and also easy to apply. Three different linear spectral unmixing methods were applied to test the improvement in unmixing results. Experiments were conducted in three different sets of Landsat-5 TM images of three different flood events in Australia to examine the method on different flooding conditions and achieved satisfactory outcomes in flood mapping.