Classifier selection using sequential error ratio criterion for multi-instance and multi-sample fusion

Classifier selection is a problem encountered by multi-biometric systems that aim to improve performance through fusion of decisions. A particular decision fusion architecture that combines multiple instances (n classifiers) and multiple samples (m attempts at each classifier) has been proposed in previous work to achieve controlled trade-off between false alarms and false rejects. Although analysis on text-dependent speaker verification has demonstrated better performance for fusion of decisions with favourable dependence compared to statistically independent decisions, the performance is not always optimal. Given a pool of instances, best performance with this architecture is obtained for certain combination of instances. Heuristic rules and diversity measures have been commonly used for classifier selection but it is shown that optimal performance is achieved for the `best combination performance' rule. As the search complexity for this rule increases exponentially with the addition of classifiers, a measure - the sequential error ratio (SER) - is proposed in this work that is specifically adapted to the characteristics of sequential fusion architecture. The proposed measure can be used to select a classifier that is most likely to produce a correct decision at each stage. Error rates for fusion of text-dependent HMM based speaker models using SER are compared with other classifier selection methodologies. SER is shown to achieve near optimal performance for sequential fusion of multiple instances with or without the use of multiple samples. The methodology applies to multiple speech utterances for telephone or internet based access control and to other systems such as multiple finger print and multiple handwriting sample based identity verification systems.

Error and uncertainty of adult age estimation of the pubic symphysis in an Australian sub-population using computed tomography

After attending this presentation, attendees will gain awareness of: (1) the error and uncertainty associated with the application of the Suchey-Brooks (S-B) method of age estimation of the pubic symphysis to a contemporary Australian population; (2) the implications of sexual dimorphism and bilateral asymmetry of the pubic symphysis through preliminary geometric morphometric assessment; and (3) the value of three-dimensional (3D) autopsy data acquisition for creating forensic anthropological standards. This presentation will impact the forensic science community by demonstrating that, in the absence of demographically sound skeletal collections, post-mortem autopsy data provides an exciting platform for the construction of large contemporary ‘virtual osteological libraries’ for which forensic anthropological research can be conducted on Australian individuals. More specifically, this study assesses the applicability and accuracy of the S-B method to a contemporary adult population in Queensland, Australia, and using a geometric morphometric approach, provides an insight to the age-related degeneration of the pubic symphysis. Despite the prominent use of the Suchey-Brooks (1990) method of age estimation in forensic anthropological practice, it is subject to intrinsic limitations, with reports of differential inter-population error rates between geographical locations1-4. Australian forensic anthropology is constrained by a paucity of population specific standards due to a lack of repositories of documented skeletons. Consequently, in Australian casework proceedings, standards constructed from predominately American reference samples are applied to establish a biological profile. In the global era of terrorism and natural disasters, more specific population standards are required to improve the efficiency of medico-legal death investigation in Queensland. The sample comprises multi-slice computed tomography (MSCT) scans of the pubic symphysis (slice thickness: 0.5mm, overlap: 0.1mm) on 195 individuals of caucasian ethnicity aged 15-70 years. Volume rendering reconstruction of the symphyseal surface was conducted in Amira® (v.4.1) and quantitative analyses in Rapidform® XOS. The sample was divided into ten-year age sub-sets (eg. 15-24) with a final sub-set of 65-70 years. Error with respect to the method’s assigned means were analysed on the basis of bias (directionality of error), inaccuracy (magnitude of error) and percentage correct classification of left and right symphyseal surfaces. Morphometric variables including surface area, circumference, maximum height and width of the symphyseal surface and micro-architectural assessment of cortical and trabecular bone composition were quantified using novel automated engineering software capabilities. The results of this study demonstrated correct age classification utilizing the mean and standard deviations of each phase of the S-B method of 80.02% and 86.18% in Australian males and females, respectively. Application of the S-B method resulted in positive biases and mean inaccuracies of 7.24 (±6.56) years for individuals less than 55 years of age, compared to negative biases and mean inaccuracies of 5.89 (±3.90) years for individuals greater than 55 years of age. Statistically significant differences between chronological and S-B mean age were demonstrated in 83.33% and 50% of the six age subsets in males and females, respectively. Asymmetry of the pubic symphysis was a frequent phenomenon with 53.33% of the Queensland population exhibiting statistically significant (χ2 - p<0.01) differential phase classification of left and right surfaces of the same individual. Directionality was found in bilateral asymmetry, with the right symphyseal faces being slightly older on average and providing more accurate estimates using the S-B method5. Morphometric analysis verified these findings, with the left surface exhibiting significantly greater circumference and surface area than the right (p<0.05). Morphometric analysis demonstrated an increase in maximum height and width of the surface with age, with most significant changes (p<0.05) occurring between the 25-34 and 55-64 year age subsets. These differences may be attributed to hormonal components linked to menopause in females and a reduction in testosterone in males. Micro-architectural analysis demonstrated degradation of cortical composition with age, with differential bone resorption between the medial, ventral and dorsal surfaces of the pubic symphysis. This study recommends that the S-B method be applied with caution in medico-legal death investigations of unknown skeletal remains in Queensland. Age estimation will always be accompanied by error; therefore this study demonstrates the potential for quantitative morphometric modelling of age related changes of the pubic symphysis as a tool for methodological refinement, providing a rigor and robust assessment to remove the subjectivity associated with current pelvic aging methods.

Bayesian designs with frequentist and Bayesian error rate considerations

So far, most Phase II trials have been designed and analysed under a frequentist framework. Under this framework, a trial is designed so that the overall Type I and Type II errors of the trial are controlled at some desired levels. Recently, a number of articles have advocated the use of Bavesian designs in practice. Under a Bayesian framework, a trial is designed so that the trial stops when the posterior probability of treatment is within certain prespecified thresholds. In this article, we argue that trials under a Bayesian framework can also be designed to control frequentist error rates. We introduce a Bayesian version of Simon's well-known two-stage design to achieve this goal. We also consider two other errors, which are called Bayesian errors in this article because of their similarities to posterior probabilities. We show that our method can also control these Bayesian-type errors. We compare our method with other recent Bayesian designs in a numerical study and discuss implications of different designs on error rates. An example of a clinical trial for patients with nasopharyngeal carcinoma is used to illustrate differences of the different designs.

Sunglasses, traffic signals, and color vision deficiencies

Purpose: To determine (a) the effect of different sunglass tint colorations on traffic signal detection and recognition for color normal and color deficient observers, and (b) the adequacy of coloration requirements in current sunglass standards. Methods: Twenty color-normals and 49 color-deficient males performed a tracking task while wearing sunglasses of different colorations (clear, gray, green, yellow-green, yellow-brown, red-brown). At random intervals, simulated traffic light signals were presented against a white background at 5° to the right or left and observers were instructed to identify signal color (red/yellow/green) by pressing a response button as quickly as possible; response times and response errors were recorded. Results: Signal color and sunglass tint had significant effects on response times and error rates (p < 0.05), with significant between-color group differences and interaction effects. Response times for color deficient people were considerably slower than color normals for both red and yellow signals for all sunglass tints, but for green signals they were only noticeably slower with the green and yellow-green lenses. For most of the color deficient groups, there were recognition errors for yellow signals combined with the yellow-green and green tints. In addition, deuteranopes had problems for red signals combined with red-brown and yellow-brown tints, and protanopes had problems for green signals combined with the green tint and for red signals combined with the red-brown tint. Conclusions: Many sunglass tints currently permitted for drivers and riders cause a measurable decrement in the ability of color deficient observers to detect and recognize traffic signals. In general, combinations of signals and sunglasses of similar colors are of particular concern. This is prima facie evidence of a risk in the use of these tints for driving and cautions against the relaxation of coloration limits in sunglasses beyond those represented in the study.

Sequential decision fusion for controlled detection errors

Information fusion in biometrics has received considerable attention. The architecture proposed here is based on the sequential integration of multi-instance and multi-sample fusion schemes. This method is analytically shown to improve the performance and allow a controlled trade-off between false alarms and false rejects when the classifier decisions are statistically independent. Equations developed for detection error rates are experimentally evaluated by considering the proposed architecture for text dependent speaker verification using HMM based digit dependent speaker models. The tuning of parameters, n classifiers and m attempts/samples, is investigated and the resultant detection error trade-off performance is evaluated on individual digits. Results show that performance improvement can be achieved even for weaker classifiers (FRR-19.6%, FAR-16.7%). The architectures investigated apply to speaker verification from spoken digit strings such as credit card numbers in telephone or VOIP or internet based applications.

Automatic speaker recognition under adverse conditions

Speaker verification is the process of verifying the identity of a person by analysing their speech. There are several important applications for automatic speaker verification (ASV) technology including suspect identification, tracking terrorists and detecting a person’s presence at a remote location in the surveillance domain, as well as person authentication for phone banking and credit card transactions in the private sector. Telephones and telephony networks provide a natural medium for these applications. The aim of this work is to improve the usefulness of ASV technology for practical applications in the presence of adverse conditions. In a telephony environment, background noise, handset mismatch, channel distortions, room acoustics and restrictions on the available testing and training data are common sources of errors for ASV systems. Two research themes were pursued to overcome these adverse conditions: Modelling mismatch and modelling uncertainty. To directly address the performance degradation incurred through mismatched conditions it was proposed to directly model this mismatch. Feature mapping was evaluated for combating handset mismatch and was extended through the use of a blind clustering algorithm to remove the need for accurate handset labels for the training data. Mismatch modelling was then generalised by explicitly modelling the session conditions as a constrained offset of the speaker model means. This session variability modelling approach enabled the modelling of arbitrary sources of mismatch, including handset type, and halved the error rates in many cases. Methods to model the uncertainty in speaker model estimates and verification scores were developed to address the difficulties of limited training and testing data. The Bayes factor was introduced to account for the uncertainty of the speaker model estimates in testing by applying Bayesian theory to the verification criterion, with improved performance in matched conditions. Modelling the uncertainty in the verification score itself met with significant success. Estimating a confidence interval for the "true" verification score enabled an order of magnitude reduction in the average quantity of speech required to make a confident verification decision based on a threshold. The confidence measures developed in this work may also have significant applications for forensic speaker verification tasks.

Effect of pedestrian movement on MIMO-OFDM channel capacity in an indoor environment

The rapid growth of mobile telephone use, satellite services, and now the wireless Internet and WLANs are generating tremendous changes in telecommunication and networking. As indoor wireless communications become more prevalent, modeling indoor radio wave propagation in populated environments is a topic of significant interest. Wireless MIMO communication exploits phenomena such as multipath propagation to increase data throughput and range, or reduce bit error rates, rather than attempting to eliminate effects of multipath propagation as traditional SISO communication systems seek to do. The MIMO approach can yield significant gains for both link and network capacities, with no additional transmitting power or bandwidth consumption when compared to conventional single-array diversity methods. When MIMO and OFDM systems are combined and deployed in a suitable rich scattering environment such as indoors, a significant capacity gain can be observed due to the assurance of multipath propagation. Channel variations can occur as a result of movement of personnel, industrial machinery, vehicles and other equipment moving within the indoor environment. The time-varying effects on the propagation channel in populated indoor environments depend on the different pedestrian traffic conditions and the particular type of environment considered. A systematic measurement campaign to study pedestrian movement effects in indoor MIMO-OFDM channels has not yet been fully undertaken. Measuring channel variations caused by the relative positioning of pedestrians is essential in the study of indoor MIMO-OFDM broadband wireless networks. Theoretically, due to high multipath scattering, an increase in MIMO-OFDM channel capacity is expected when pedestrians are present. However, measurements indicate that some reductions in channel capacity could be observed as the number of pedestrians approaches 10 due to a reduction in multipath conditions as more human bodies absorb the wireless signals. This dissertation presents a systematic characterization of the effects of pedestrians in indoor MIMO-OFDM channels. Measurement results, using the MIMO-OFDM channel sounder developed at the CSIRO ICT Centre, have been validated by a customized Geometric Optics-based ray tracing simulation. Based on measured and simulated MIMO-OFDM channel capacity and MIMO-OFDM capacity dynamic range, an improved deterministic model for MIMO-OFDM channels in indoor populated environments is presented. The model can be used for the design and analysis of future WLAN to be deployed in indoor environments. The results obtained show that, in both Fixed SNR and Fixed Tx for deterministic condition, the channel capacity dynamic range rose with the number of pedestrians as well as with the number of antenna combinations. In random scenarios with 10 pedestrians, an increment in channel capacity of up to 0.89 bits/sec/Hz in Fixed SNR and up to 1.52 bits/sec/Hz in Fixed Tx has been recorded compared to the one pedestrian scenario. In addition, from the results a maximum increase in average channel capacity of 49% has been measured while 4 antenna elements are used, compared with 2 antenna elements. The highest measured average capacity, 11.75 bits/sec/Hz, corresponds to the 4x4 array with 10 pedestrians moving randomly. Moreover, Additionally, the spread between the highest and lowest value of the the dynamic range is larger for Fixed Tx, predicted 5.5 bits/sec/Hz and measured 1.5 bits/sec/Hz, in comparison with Fixed SNR criteria, predicted 1.5 bits/sec/Hz and measured 0.7 bits/sec/Hz. This has been confirmed by both measurements and simulations ranging from 1 to 5, 7 and 10 pedestrians.

Robust speaker verification via fusion of speech and lip modalities

This paper investigates the use of lip information, in conjunction with speech information, for robust speaker verification in the presence of background noise. It has been previously shown in our own work, and in the work of others, that features extracted from a speaker's moving lips hold speaker dependencies which are complementary with speech features. We demonstrate that the fusion of lip and speech information allows for a highly robust speaker verification system which outperforms the performance of either sub-system. We present a new technique for determining the weighting to be applied to each modality so as to optimize the performance of the fused system. Given a correct weighting, lip information is shown to be highly effective for reducing the false acceptance and false rejection error rates in the presence of background noise

The use of speech and lip modalities for robust speaker verification under adverse conditions

Investigates the use of lip information, in conjunction with speech information, for robust speaker verification in the presence of background noise. We have previously shown (Int. Conf. on Acoustics, Speech and Signal Proc., vol. 6, pp. 3693-3696, May 1998) that features extracted from a speaker's moving lips hold speaker dependencies which are complementary with speech features. We demonstrate that the fusion of lip and speech information allows for a highly robust speaker verification system which outperforms either subsystem individually. We present a new technique for determining the weighting to be applied to each modality so as to optimize the performance of the fused system. Given a correct weighting, lip information is shown to be highly effective for reducing the false acceptance and false rejection error rates in the presence of background noise

Sequential Fusion Using Correlated Decisions for Controlled Verification Errors

Fusion techniques have received considerable attention for achieving lower error rates with biometrics. A fused classifier architecture based on sequential integration of multi-instance and multi-sample fusion schemes allows controlled trade-off between false alarms and false rejects. Expressions for each type of error for the fused system have previously been derived for the case of statistically independent classifier decisions. It is shown in this paper that the performance of this architecture can be improved by modelling the correlation between classifier decisions. Correlation modelling also enables better tuning of fusion model parameters, ‘N’, the number of classifiers and ‘M’, the number of attempts/samples, and facilitates the determination of error bounds for false rejects and false accepts for each specific user. Error trade-off performance of the architecture is evaluated using HMM based speaker verification on utterances of individual digits. Results show that performance is improved for the case of favourable correlated decisions. The architecture investigated here is directly applicable to speaker verification from spoken digit strings such as credit card numbers in telephone or voice over internet protocol based applications. It is also applicable to other biometric modalities such as finger prints and handwriting samples.

Sequential fusion of decisions from adaptive and random samples for controlled verification of errors

Fusion techniques have received considerable attention for achieving performance improvement with biometrics. While a multi-sample fusion architecture reduces false rejects, it also increases false accepts. This impact on performance also depends on the nature of subsequent attempts, i.e., random or adaptive. Expressions for error rates are presented and experimentally evaluated in this work by considering the multi-sample fusion architecture for text-dependent speaker verification using HMM based digit dependent speaker models. Analysis incorporating correlation modeling demonstrates that the use of adaptive samples improves overall fusion performance compared to randomly repeated samples. For a text dependent speaker verification system using digit strings, sequential decision fusion of seven instances with three random samples is shown to reduce the overall error of the verification system by 26% which can be further reduced by 6% for adaptive samples. This analysis novel in its treatment of random and adaptive multiple presentations within a sequential fused decision architecture, is also applicable to other biometric modalities such as finger prints and handwriting samples.

Physiological, perceptual and technical responses to on-court tennis training on hard and clay courts

The aim of this study was to investigate the effect of court surface (clay v hard-court) on technical, physiological and perceptual responses to on-court training. Four high-performance junior male players performed two identical training sessions on hard and clay courts, respectively. Sessions included both physical conditioning and technical elements as led by the coach. Each session was filmed for later notational analysis of stroke count and error rates. Further, players wore a global positioning satellite device to measure distance covered during each session; whilst heart rate, countermovement jump distance and capillary blood measures of metabolites were measured before, during and following each session. Additionally a respective coach and athlete rating of perceived exertion (RPE) were measured following each session. Total duration and distance covered during of each session were comparable (P>0.05; d<0.20). While forehand and backhands stroke volume did not differ between sessions (P>0.05; d<0.30); large effects for increased unforced and forced errors were present on the hard court (P>0.05; d>0.90). Furthermore, large effects for increased heart rate, blood lactate and RPE values were evident on clay compared to hard courts (P>0.05; d>0.90). Additionally, while player and coach RPE on hard courts were similar, there were large effects for coaches to underrate the RPE of players on clay courts (P>0.05; d>0.90). In conclusion, training on clay courts results in trends for increased heart rate, lactate and RPE values, suggesting sessions on clay tend towards higher physiological and perceptual loads than hard courts. Further, coaches appear effective at rating player RPE on hard courts, but may underrate the perceived exertion of sessions on clay courts.

Evaluation of the Suchey-Brooks Method of age estimation in an Australian subpopulation using computed tomography of the pubic symphyseal surface

Despite the prominent use of the Suchey-Brooks (S-B) method of age estimation in forensic anthropological practice, it is subject to intrinsic limitations, with reports of differential inter-population error rates between geographical locations. This study assessed the accuracy of the S-B method to a contemporary adult population in Queensland, Australia and provides robust age parameters calibrated for our population. Three-dimensional surface reconstructions were generated from computed tomography scans of the pubic symphysis of male and female Caucasian individuals aged 15–70 years (n = 195) in Amira® and Rapidform®. Error was analyzed on the basis of bias, inaccuracy and percentage correct classification for left and right symphyseal surfaces. Application of transition analysis and Chi-square statistics demonstrated 63.9% and 69.7% correct age classification associated with the left symphyseal surface of Australian males and females, respectively, using the S-B method. Using Bayesian statistics, probability density distributions for each S-B phase were calculated, providing refined age parameters for our population. Mean inaccuracies of 6.77 (±2.76) and 8.28 (±4.41) years were reported for the left surfaces of males and females, respectively; with positive biases for younger individuals (<55 years) and negative biases in older individuals. Significant sexual dimorphism in the application of the S-B method was observed; and asymmetry in phase classification of the pubic symphysis was a frequent phenomenon. These results recommend that the S-B method should be applied with caution in medico-legal death investigations of Queensland skeletal remains and warrant further investigation of reliable age estimation techniques.

Fundamentals of business process management

Encompasses the whole BPM lifecycle, including process identification, modelling, analysis, redesign, automation and monitoring Class-tested textbook complemented with additional teaching material on the accompanying website Covers both relevant conceptual background, industrial standards and actionable skills Business Process Management (BPM) is the art and science of how work should be performed in an organization in order to ensure consistent outputs and to take advantage of improvement opportunities, e.g. reducing costs, execution times or error rates. Importantly, BPM is not about improving the way individual activities are performed, but rather about managing entire chains of events, activities and decisions that ultimately produce added value for an organization and its customers. This textbook encompasses the entire BPM lifecycle, from process identification to process monitoring, covering along the way process modelling, analysis, redesign and automation. Concepts, methods and tools from business management, computer science and industrial engineering are blended into one comprehensive and inter-disciplinary approach. The presentation is illustrated using the BPMN industry standard defined by the Object Management Group and widely endorsed by practitioners and vendors worldwide. In addition to explaining the relevant conceptual background, the book provides dozens of examples, more than 100 hands-on exercises – many with solutions – as well as numerous suggestions for further reading. The textbook is the result of many years of combined teaching experience of the authors, both at the undergraduate and graduate levels as well as in the context of professional training. Students and professionals from both business management and computer science will benefit from the step-by-step style of the textbook and its focus on fundamental concepts and proven methods. Lecturers will appreciate the class-tested format and the additional teaching material available on the accompanying website fundamentals-of-bpm.org.