Sequential decision fusion of multibiometrics applied to text-dependent speaker verification for controlled errors

Reliability of the performance of biometric identity verification systems remains a significant challenge. Individual biometric samples of the same person (identity class) are not identical at each presentation and performance degradation arises from intra-class variability and inter-class similarity. These limitations lead to false accepts and false rejects that are dependent. It is therefore difficult to reduce the rate of one type of error without increasing the other. The focus of this dissertation is to investigate a method based on classifier fusion techniques to better control the trade-off between the verification errors using text-dependent speaker verification as the test platform. A sequential classifier fusion architecture that integrates multi-instance and multisample fusion schemes is proposed. This fusion method enables a controlled trade-off between false alarms and false rejects. For statistically independent classifier decisions, analytical expressions for each type of verification error are derived using base classifier performances. As this assumption may not be always valid, these expressions are modified to incorporate the correlation between statistically dependent decisions from clients and impostors. The architecture is empirically evaluated by applying the proposed architecture for text dependent speaker verification using the Hidden Markov Model based digit dependent speaker models in each stage with multiple attempts for each digit utterance. The trade-off between the verification errors is controlled using the parameters, number of decision stages (instances) and the number of attempts at each decision stage (samples), fine-tuned on evaluation/tune set. The statistical validation of the derived expressions for error estimates is evaluated on test data. The performance of the sequential method is further demonstrated to depend on the order of the combination of digits (instances) and the nature of repetitive attempts (samples). The false rejection and false acceptance rates for proposed fusion are estimated using the base classifier performances, the variance in correlation between classifier decisions and the sequence of classifiers with favourable dependence selected using the 'Sequential Error Ratio' criteria. The error rates are better estimated by incorporating user-dependent (such as speaker-dependent thresholds and speaker-specific digit combinations) and class-dependent (such as clientimpostor dependent favourable combinations and class-error based threshold estimation) information. The proposed architecture is desirable in most of the speaker verification applications such as remote authentication, telephone and internet shopping applications. The tuning of parameters - the number of instances and samples - serve both the security and user convenience requirements of speaker-specific verification. The architecture investigated here is applicable to verification using other biometric modalities such as handwriting, fingerprints and key strokes.

On adaptive HMM state estimation

In this paper new online adaptive hidden Markov model (HMM) state estimation schemes are developed, based on extended least squares (ELS) concepts and recursive prediction error (RPE) methods. The best of the new schemes exploit the idempotent nature of Markov chains and work with a least squares prediction error index, using a posterior estimates, more suited to Markov models then traditionally used in identification of linear systems.

An external field prior for the hidden Potts model with application to cone-beam computed tomography

In images with low contrast-to-noise ratio (CNR), the information gain from the observed pixel values can be insufficient to distinguish foreground objects. A Bayesian approach to this problem is to incorporate prior information about the objects into a statistical model. A method for representing spatial prior information as an external field in a hidden Potts model is introduced. This prior distribution over the latent pixel labels is a mixture of Gaussian fields, centred on the positions of the objects at a previous point in time. It is particularly applicable in longitudinal imaging studies, where the manual segmentation of one image can be used as a prior for automatic segmentation of subsequent images. The method is demonstrated by application to cone-beam computed tomography (CT), an imaging modality that exhibits distortions in pixel values due to X-ray scatter. The external field prior results in a substantial improvement in segmentation accuracy, reducing the mean pixel misclassification rate for an electron density phantom from 87% to 6%. The method is also applied to radiotherapy patient data, demonstrating how to derive the external field prior in a clinical context.

Improved maritime target tracker using colour fusion

Searching for humans lost in vast stretches of ocean has always been a difficult task. This paper investigates a machine vision system that addresses this problem by exploiting the useful properties of alternate colour spaces. In particular, the paper investigates the fusion of colour information from the HSV, RGB, YCbCr and YIQ colour spaces within the emission matrix of a Hidden Markov Model tracker to enhance video based maritime target detection. The system has shown promising results. The paper also identifies challenges still needing to be met.

An effective approach to verbose queries using a limited dependencies language model

Intuitively, any `bag of words' approach in IR should benefit from taking term dependencies into account. Unfortunately, for years the results of exploiting such dependencies have been mixed or inconclusive. To improve the situation, this paper shows how the natural language properties of the target documents can be used to transform and enrich the term dependencies to more useful statistics. This is done in three steps. The term co-occurrence statistics of queries and documents are each represented by a Markov chain. The paper proves that such a chain is ergodic, and therefore its asymptotic behavior is unique, stationary, and independent of the initial state. Next, the stationary distribution is taken to model queries and documents, rather than their initial distri- butions. Finally, ranking is achieved following the customary language modeling paradigm. The main contribution of this paper is to argue why the asymptotic behavior of the document model is a better representation then just the document's initial distribution. A secondary contribution is to investigate the practical application of this representation in case the queries become increasingly verbose. In the experiments (based on Lemur's search engine substrate) the default query model was replaced by the stable distribution of the query. Just modeling the query this way already resulted in significant improvements over a standard language model baseline. The results were on a par or better than more sophisticated algorithms that use fine-tuned parameters or extensive training. Moreover, the more verbose the query, the more effective the approach seems to become.

Towards the implementation of vision-based UAS sense-and-avoid

Machine vision represents a particularly attractive solution for sensing and detecting potential collision-course targets due to the relatively low cost, size, weight, and power requirements of the sensors involved. This paper describes the development of detection algorithms and the evaluation of a real-time flight ready hardware implementation of a vision-based collision detection system suitable for fixed-wing small/medium size UAS. In particular, this paper demonstrates the use of Hidden Markov filter to track and estimate the elevation (β) and bearing (α) of the target, compares several candidate graphic processing hardware choices, and proposes an image based visual servoing approach to achieve collision avoidance

The use of economic evaluation in CAM : an introductory framework

Background For CAM to feature prominently in health care decision-making there is a need to expand the evidence-base and to further incorporate economic evaluation into research priorities. In a world of scarce health care resources and an emphasis on efficiency and clinical efficacy, CAM, as indeed do all other treatments, requires rigorous evaluation to be considered in budget decision-making. Methods Economic evaluation provides the tools to measure the costs and health consequences of CAM interventions and thereby inform decision making. This article offers CAM researchers an introductory framework for understanding, undertaking and disseminating economic evaluation. The types of economic evaluation available for the study of CAM are discussed, and decision modelling is introduced as a method for economic evaluation with much potential for use in CAM. Two types of decision models are introduced, decision trees and Markov models, along with a worked example of how each method is used to examine costs and health consequences. This is followed by a discussion of how this information is used by decision makers. Conclusions Undoubtedly, economic evaluation methods form an important part of health care decision making. Without formal training it can seem a daunting task to consider economic evaluation, however, multidisciplinary teams provide an opportunity for health economists, CAM practitioners and other interested researchers, to work together to further develop the economic evaluation of CAM.

Detection versus false alarm characterisation of a vision-based airborne dim-target collision detection system

This paper presents a preliminary flight test based detection range versus false alarm performance characterisation of a morphological-hidden Markov model filtering approach to vision-based airborne dim-target collision detection. On the basis of compelling in-flight collision scenario data, we calculate system operating characteristic (SOC) curves that concisely illustrate the detection range versus false alarm rate performance design trade-offs. These preliminary SOC curves provide a more complete dim-target detection performance description than previous studies (due to the experimental difficulties involved, previous studies have been limited to very short flight data sample sets and hence have not been able to quantify false alarm behaviour). The preliminary investigation here is based on data collected from 4 controlled collision encounters and supporting non-target flight data. This study suggests head-on detection ranges of approximately 2.22 km under blue sky background conditions (1.26 km in cluttered background conditions), whilst experiencing false alarms at a rate less than 1.7 false alarms/hour (ie. less than once every 36 minutes). Further data collection is currently in progress.

Fat and thin adaptive HMM filters for vision based detection of moving targets

Computer vision is an attractive solution for uninhabited aerial vehicle (UAV) collision avoidance, due to the low weight, size and power requirements of hardware. A two-stage paradigm has emerged in the literature for detection and tracking of dim targets in images, comprising of spatial preprocessing, followed by temporal filtering. In this paper, we investigate a hidden Markov model (HMM) based temporal filtering approach. Specifically, we propose an adaptive HMM filter, in which the variance of model parameters is refined as the quality of the target estimate improves. Filters with high variance (fat filters) are used for target acquisition, and filters with low variance (thin filters) are used for target tracking. The adaptive filter is tested in simulation and with real data (video of a collision-course aircraft). Our test results demonstrate that our adaptive filtering approach has improved tracking performance, and provides an estimate of target heading not present in previous HMM filtering approaches.

HMM triangle relative entropy concepts in sequential change detection applied to vision-based dim target manoeuvre detection

The quick detection of abrupt (unknown) parameter changes in an observed hidden Markov model (HMM) is important in several applications. Motivated by the recent application of relative entropy concepts in the robust sequential change detection problem (and the related model selection problem), this paper proposes a sequential unknown change detection algorithm based on a relative entropy based HMM parameter estimator. Our proposed approach is able to overcome the lack of knowledge of post-change parameters, and is illustrated to have similar performance to the popular cumulative sum (CUSUM) algorithm (which requires knowledge of the post-change parameter values) when examined, on both simulated and real data, in a vision-based aircraft manoeuvre detection problem.

Multiple cameras for audio-visual speech recognition in an automotive environment

Audio-visualspeechrecognition, or the combination of visual lip-reading with traditional acoustic speechrecognition, has been previously shown to provide a considerable improvement over acoustic-only approaches in noisy environments, such as that present in an automotive cabin. The research presented in this paper will extend upon the established audio-visualspeechrecognition literature to show that further improvements in speechrecognition accuracy can be obtained when multiple frontal or near-frontal views of a speaker's face are available. A series of visualspeechrecognition experiments using a four-stream visual synchronous hidden Markov model (SHMM) are conducted on the four-camera AVICAR automotiveaudio-visualspeech database. We study the relative contribution between the side and central orientated cameras in improving visualspeechrecognition accuracy. Finally combination of the four visual streams with a single audio stream in a five-stream SHMM demonstrates a relative improvement of over 56% in word recognition accuracy when compared to the acoustic-only approach in the noisiest conditions of the AVICAR database.

Characterization of sky-region morphological-temporal airborne collision detection

Automated airborne collision-detection systems are a key enabling technology for facilitat- ing the integration of unmanned aerial vehicles (UAVs) into the national airspace. These safety-critical systems must be sensitive enough to provide timely warnings of genuine air- borne collision threats, but not so sensitive as to cause excessive false-alarms. Hence, an accurate characterisation of detection and false alarm sensitivity is essential for understand- ing performance trade-offs, and system designers can exploit this characterisation to help achieve a desired balance in system performance. In this paper we experimentally evaluate a sky-region, image based, aircraft collision detection system that is based on morphologi- cal and temporal processing techniques. (Note that the examined detection approaches are not suitable for the detection of potential collision threats against a ground clutter back- ground). A novel collection methodology for collecting realistic airborne collision-course target footage in both head-on and tail-chase engagement geometries is described. Under (hazy) blue sky conditions, our proposed system achieved detection ranges greater than 1540m in 3 flight test cases with no false alarm events in 14.14 hours of non-target data (under cloudy conditions, the system achieved detection ranges greater than 1170m in 4 flight test cases with no false alarm events in 6.63 hours of non-target data). Importantly, this paper is the first documented presentation of detection range versus false alarm curves generated from airborne target and non-target image data.

High-resolution loss of heterozygosity screening implicates PTPRJ as a potential tumor suppressor gene that affects susceptibility to non-Hodgkin's Lymphoma

We employed a Hidden-Markov-Model (HMM) algorithm in loss of heterozygosity (LOH) analysis of high-density single nucleotide polymorphism (SNP) array data from Non-Hodgkin’s lymphoma (NHL) entities, follicular lymphoma (FL), and diffuse large B-cell lymphoma (DLBCL). This revealed a high frequency of LOH over the chromosomal region 11p11.2, containing the gene encoding the protein tyrosine phosphatase receptor type J (PTPRJ). Although PTPRJ regulates components of key survival pathways in B-cells (i.e., BCR, MAPK, and PI3K signaling), its role in B-cell development is poorly understood. LOH of PTPRJ has been described in several types of cancer but not in any hematological malignancy. Interestingly, FL cases with LOH exhibited down-regulation of PTPRJ, in contrast no significant variation of expression was shown in DLBCLs. In addition, sequence screening in Exons 5 and 13 of PTPRJ identified the G973A (rs2270993), T1054C (rs2270992), A1182C (rs1566734), and G2971C (rs4752904) coding SNPs (cSNPs). The A1182 allele was significantly more frequent in FLs and in NHLs with LOH. Significant over-representation of the C1054 (rs2270992) and the C2971 (rs4752904) alleles were also observed in LOH cases. A haplotype analysis also revealed a significant lower frequency of haplotype GTCG in NHL cases, but it was only detected in cases with retention. Conversely, haplotype GCAC was over-representated in cases with LOH. Altogether, these results indicate that the inactivation of PTPRJ may be a common lymphomagenic mechanism in these NHL subtypes and that haplotypes in PTPRJ gene may play a role in susceptibility to NHL, by affecting activation of PTPRJ in these B-cell lymphomas.

A new method to detect loss of heterozygosity using cohort heterozygosity comparisons

Background Loss of heterozygosity (LOH) is an important marker for one of the 'two-hits' required for tumor suppressor gene inactivation. Traditional methods for mapping LOH regions require the comparison of both tumor and patient-matched normal DNA samples. However, for many archival samples, patient-matched normal DNA is not available leading to the under-utilization of this important resource in LOH studies. Here we describe a new method for LOH analysis that relies on the genome-wide comparison of heterozygosity of single nucleotide polymorphisms (SNPs) between cohorts of cases and un-matched healthy control samples. Regions of LOH are defined by consistent decreases in heterozygosity across a genetic region in the case cohort compared to the control cohort. Methods DNA was collected from 20 Follicular Lymphoma (FL) tumor samples, 20 Diffuse Large B-cell Lymphoma (DLBCL) tumor samples, neoplastic B-cells of 10 B-cell Chronic Lymphocytic Leukemia (B-CLL) patients and Buccal cell samples matched to 4 of these B-CLL patients. The cohort heterozygosity comparison method was developed and validated using LOH derived in a small cohort of B-CLL by traditional comparisons of tumor and normal DNA samples, and compared to the only alternative method for LOH analysis without patient matched controls. LOH candidate regions were then generated for enlarged cohorts of B-CLL, FL and DLBCL samples using our cohort heterozygosity comparison method in order to evaluate potential LOH candidate regions in these non-Hodgkin's lymphoma tumor subtypes. Results Using a small cohort of B-CLL samples with patient-matched normal DNA we have validated the utility of this method and shown that it displays more accuracy and sensitivity in detecting LOH candidate regions compared to the only alternative method, the Hidden Markov Model (HMM) method. Subsequently, using B-CLL, FL and DLBCL tumor samples we have utilised cohort heterozygosity comparisons to localise LOH candidate regions in these subtypes of non-Hodgkin's lymphoma. Detected LOH regions included both previously described regions of LOH as well as novel genomic candidate regions. Conclusions We have proven the efficacy of the use of cohort heterozygosity comparisons for genome-wide mapping of LOH and shown it to be in many ways superior to the HMM method. Additionally, the use of this method to analyse SNP microarray data from 3 common forms of non-Hodgkin's lymphoma yielded interesting tumor suppressor gene candidates, including the ETV3 gene that was highlighted in both B-CLL and FL.