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.

Multi-level information fusion for environment aware robotic navigation

This thesis develops the hardware and software framework for an integrated navigation system. Dynamic data fusion algorithms are used to develop a system with a high level of resistance to the typical problems that affect standard navigation systems.

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.

Cetuximab plus chemotherapy in patients with advanced non-small-cell lung cancer (FLEX) : an open-label randomised phase III trial

Background: Use of cetuximab, a monoclonal antibody targeting the epidermal growth factor receptor (EGFR), has the potential to increase survival in patients with advanced non-small-cell lung cancer. We therefore compared chemotherapy plus cetuximab with chemotherapy alone in patients with advanced EGFR-positive non-small-cell lung cancer. Methods: In a multinational, multicentre, open-label, phase III trial, chemotherapy-naive patients (≥18 years) with advanced EGFR-expressing histologically or cytologically proven stage wet IIIB or stage IV non-small-cell lung cancer were randomly assigned in a 1:1 ratio to chemotherapy plus cetuximab or just chemotherapy. Chemotherapy was cisplatin 80 mg/m 2 intravenous infusion on day 1, and vinorelbine 25 mg/m 2 intravenous infusion on days 1 and 8 of every 3-week cycle) for up to six cycles. Cetuximab-at a starting dose of 400 mg/m 2 intravenous infusion over 2 h on day 1, and from day 8 onwards at 250 mg/m 2 over 1 h per week-was continued after the end of chemotherapy until disease progression or unacceptable toxicity had occurred. The primary endpoint was overall survival. Analysis was by intention to treat. This study is registered with ClinicalTrials.gov, number NCT00148798. Findings: Between October, 2004, and January, 2006, 1125 patients were randomly assigned to chemotherapy plus cetuximab (n=557) or chemotherapy alone (n=568). Patients given chemotherapy plus cetuximab survived longer than those in the chemotherapy-alone group (median 11·3 months vs 10·1 months; hazard ratio for death 0·871 [95% CI 0·762-0·996]; p=0·044). The main cetuximab-related adverse event was acne-like rash (57 [10%] of 548, grade 3). Interpretation: Addition of cetuximab to platinum-based chemotherapy represents a new treatment option for patients with advanced non-small-cell lung cancer. Funding: Merck KGaA. © 2009 Elsevier Ltd. All rights reserved.

Brain-inspired sensor fusion for navigating robots

Current state of the art robot mapping and navigation systems produce impressive performance under a narrow range of robot platform, sensor and environmental conditions, in contrast to animals such as rats that produce “good enough” maps that enable them to function under an incredible range of situations. In this paper we present a rat-inspired featureless sensor-fusion system that assesses the usefulness of multiple sensor modalities based on their utility and coherence for place recognition, without knowledge as to the type of sensor. We demonstrate the system on a Pioneer robot in indoor and outdoor environments with abrupt lighting changes. Through dynamic weighting of the sensors, the system is able to perform correct place recognition and mapping where the static sensor weighting approach fails.

Decision fusion from parts and samples for robust iris recognition

Fusion techniques can be used in biometrics to achieve higher accuracy. When biometric systems are in operation and the threat level changes, controlling the trade-off between detection error rates can reduce the impact of an attack. In a fused system, varying a single threshold does not allow this to be achieved, but systematic adjustment of a set of parameters does. In this paper, fused decisions from a multi-part, multi-sample sequential architecture are investigated for that purpose in an iris recognition system. A specific implementation of the multi-part architecture is proposed and the effect of the number of parts and samples in the resultant detection error rate is analysed. The effectiveness of the proposed architecture is then evaluated under two specific cases of obfuscation attack: miosis and mydriasis. Results show that robustness to such obfuscation attacks is achieved, since lower error rates than in the case of the non-fused base system are obtained.

Laser-radar data fusion with Gaussian Process Implicit Surfaces

This work considers the problem of building high-fidelity 3D representations of the environment from sensor data acquired by mobile robots. Multi-sensor data fusion allows for more complete and accurate representations, and for more reliable perception, especially when different sensing modalities are used. In this paper, we propose a thorough experimental analysis of the performance of 3D surface reconstruction from laser and mm-wave radar data using Gaussian Process Implicit Surfaces (GPIS), in a realistic field robotics scenario. We first analyse the performance of GPIS using raw laser data alone and raw radar data alone, respectively, with different choices of covariance matrices and different resolutions of the input data. We then evaluate and compare the performance of two different GPIS fusion approaches. The first, state-of-the-art approach directly fuses raw data from laser and radar. The alternative approach proposed in this paper first computes an initial estimate of the surface from each single source of data, and then fuses these two estimates. We show that this method outperforms the state of the art, especially in situations where the sensors react differently to the targets they perceive.

Autonomous multisensor calibration and closed-loop fusion for SLAM

The vast majority of current robot mapping and navigation systems require specific well-characterized sensors that may require human-supervised calibration and are applicable only in one type of environment. Furthermore, if a sensor degrades in performance, either through damage to itself or changes in environmental conditions, the effect on the mapping system is usually catastrophic. In contrast, the natural world presents robust, reasonably well-characterized solutions to these problems. Using simple movement behaviors and neural learning mechanisms, rats calibrate their sensors for mapping and navigation in an incredibly diverse range of environments and then go on to adapt to sensor damage and changes in the environment over the course of their lifetimes. In this paper, we introduce similar movement-based autonomous calibration techniques that calibrate place recognition and self-motion processes as well as methods for online multisensor weighting and fusion. We present calibration and mapping results from multiple robot platforms and multisensory configurations in an office building, university campus, and forest. With moderate assumptions and almost no prior knowledge of the robot, sensor suite, or environment, the methods enable the bio-inspired RatSLAM system to generate topologically correct maps in the majority of experiments.

Label-free SERS for natural product provenance

Introduction Natural product provenance is important in the food, beverage and pharmaceutical industries, for consumer confidence and with health implications. Raman spectroscopy has powerful molecular fingerprint abilities. Surface Enhanced Raman Spectroscopy’s (SERS) sharp peaks allow distinction between minimally different molecules, so it should be suitable for this purpose. Methods Naturally caffeinated beverages with Guarana extract, coffee and Red Bull energy drink as a synthetic caffeinated beverage for comparison (20 µL ea.) were reacted 1:1 with Gold nanoparticles functionalised with anti-caffeine antibody (ab15221) (10 minutes), air dried and analysed in a micro-Raman instrument. The spectral data was processed using Principle Component Analysis (PCA). Results The PCA showed Guarana sourced caffeine varied significantly from synthetic caffeine (Red Bull) on component 1 (containing 76.4% of the variance in the data). See figure 1. The coffee containing beverages, and in particular Robert Timms (instant coffee) were very similar on component 1, but the barista espresso showed minor variance on component 1. Both coffee sourced caffeine samples varied with red Bull on component 2, (20% of variance). ************************************************************ Figure 1 PCA comparing a naturally caffeinated beverage containing Guarana with coffee. ************************************************************ Discussion PCA is an unsupervised multivariate statistical method that determines patterns within data. Figure 1 shows Caffeine in Guarana is notably different to synthetic caffeine. Other researchers have revealed that caffeine in Guarana plants is complexed with tannins. Naturally sourced/ lightly processed caffeine (Monster Energy, Espresso) are more inherently different than synthetic (Red Bull) /highly processed (Robert Timms) caffeine, in figure 1, which is consistent with this finding and demonstrates this technique’s applicability. Guarana provenance is important because it is still largely hand produced and its demand is escalating with recognition of its benefits. This could be a powerful technique for Guarana provenance, and may extend to other industries where provenance / authentication are required, e.g. the wine or natural pharmaceuticals industries.

Biological performance of a polycaprolactone-based scaffold plus recombinant human morphogenetic protein-2 (rhBMP-2) in an ovine thoracic interbody fusion model

PURPOSE. We develop a sheep thoracic spine interbody fusion model to study the suitability of polycaprolactone-based scaffold and recombinant human bone morphogenetic protein-2 (rhBMP-2) as a bone graft substitute within the thoracic spine. The surgical approach is a mini- open thoracotomy with relevance to minimally invasive deformity correction surgery for adolescent idiopathic scoliosis. To date there are no studies examining the use of this biodegradable implant in combination with biologics in a sheep thoracic spine model. METHODS. In the present study, six sheep underwent a 3-level (T6/7, T8/9 and T10/11) discectomy with randomly allocated implantation of a different graft substitute at each of the three levels; (i) calcium phosphate (CaP) coated polycaprolactone-based scaffold plus 0.54μg rhBMP-2, (ii) CaP coated PCL- based scaffold alone or (iii) autograft (mulched rib head). Fusion was assessed at six months post-surgery. RESULTS. Computed Tomographic scanning demonstrated higher fusion grades in the rhBMP-2 plus PCL- based scaffold group in comparison to either PCL-based scaffold alone or autograft. These results were supported by histological evaluations of the respective groups. Biomechanical testing revealed significantly higher stiffness for the rhBMP-2 plus PCL- based scaffold group in all loading directions in comparison to the other two groups. CONCLUSION. The results of this study demonstrate that rhBMP-2 plus PCL- based scaffold is a viable bone graft substitute, providing an optimal environment for thoracic interbody spinal fusion in a large animal model.

6 versus 12 month performance of polycaprolactone-based scaffold plus recombinant human morphogenetic protein-2 (rhBMP-2) in an ovine thoracic interbody fusion model

Introduction Well-designed biodegradable scaffolds in combination with bone growth factors offer a valuable alternative to the current gold standard autograft in spinal fusion surgery Yong et al. (2013). Here we report on 6- vs 12- month data set evaluating the longitudinal performance of a CaP coated polycaprolactone (PCL) scaffold loaded with recombinant human bone morphogenetic protein-2 (rhBMP-2) as a bone graft substitute within a large preclinical animal model. Methods Twelve sheep underwent a 3-level (T6/7, T8/9 and T10/11) discectomy with randomly allocated implantation of a different graft substitute at each of the three levels; (i) calcium phosphate (CaP) coated polycaprolactone based scaffold plus 0.54µg rhBMP-2, (ii) CaP coated PCL- based scaffold alone or (iii) autograft (mulched rib head). Fusion assessments were performed via high resolution clinical computed tomography and histological evaluation were undertaken at six (n=6) and twelve (n=6) months post-surgery using the Sucato grading system (Sucato et al. 2004). Results The computed tomography fusion grades of the 6- and 12- months in the rhBMP-2 plus PCL- based scaffold group were 1.9 and 2.1 respectively, in the autograft group 1.9 and 1.3 respectively, and in the scaffold alone group 0.9 and 1.17 respectively. There were no statistically significant differences in the fusion scores between 6- and 12- month for the rhBMP plus PCL- based scaffold or PCL – based scaffold alone group however there was a significant reduction in scores in the autograft group. These scores were seen to correlate with histological evaluations of the respective groups. Conclusions The results of this study demonstrate the efficacy of scaffold-based delivery of rhBMP-2 in promoting higher fusion grades at 6- and 12- months in comparison to the scaffold alone or autograft group within the same time frame. Fusion grades achieved at six months using PCL+rhBMP-2 are not significantly increased at twelve months post-surgery.

Ultra sensitive label free surface enhanced Raman spectroscopy method for the detection of biomolecules

We present a proof of concept for a novel nanosensor for the detection of ultra-trace amounts of bio-active molecules in complex matrices. The nanosensor is comprised of gold nanoparticles with an ultra-thin silica shell and antibody surface attachment, which allows for the immobilization and direct detection of bio-active molecules by surface enhanced Raman spectroscopy (SERS) without requiring a Raman label. The ultra-thin passive layer (~1.3 nm thickness) prevents competing molecules from binding non-selectively to the gold surface without compromising the signal enhancement. The antibodies attached on the surface of the nanoparticles selectively bind to the target molecule with high affinity. The interaction between the nanosensor and the target analyte result in conformational rearrangements of the antibody binding sites, leading to significant changes in the surface enhanced Raman spectra of the nanoparticles when compared to the spectra of the un-reacted nanoparticles. Nanosensors of this design targeting the bio-active compounds erythropoietin and caffeine were able to detect ultra-trace amounts the analyte to the lower quantification limits of 3.5×10−13 M and 1×10−9 M, respectively.

Robust multiple-sensing-modality data fusion using Gaussian Process Implicit Surfaces

The ability to build high-fidelity 3D representations of the environment from sensor data is critical for autonomous robots. Multi-sensor data fusion allows for more complete and accurate representations. Furthermore, using distinct sensing modalities (i.e. sensors using a different physical process and/or operating at different electromagnetic frequencies) usually leads to more reliable perception, especially in challenging environments, as modalities may complement each other. However, they may react differently to certain materials or environmental conditions, leading to catastrophic fusion. In this paper, we propose a new method to reliably fuse data from multiple sensing modalities, including in situations where they detect different targets. We first compute distinct continuous surface representations for each sensing modality, with uncertainty, using Gaussian Process Implicit Surfaces (GPIS). Second, we perform a local consistency test between these representations, to separate consistent data (i.e. data corresponding to the detection of the same target by the sensors) from inconsistent data. The consistent data can then be fused together, using another GPIS process, and the rest of the data can be combined as appropriate. The approach is first validated using synthetic data. We then demonstrate its benefit using a mobile robot, equipped with a laser scanner and a radar, which operates in an outdoor environment in the presence of large clouds of airborne dust and smoke.

Data fusion and tracking with multiple UAVs

This chapter describes decentralized data fusion algorithms for a team of multiple autonomous platforms. Decentralized data fusion (DDF) provides a useful basis with which to build upon for cooperative information gathering tasks for robotic teams operating in outdoor environments. Through the DDF algorithms, each platform can maintain a consistent global solution from which decisions may then be made. Comparisons will be made between the implementation of DDF using two probabilistic representations. The first, Gaussian estimates and the second Gaussian mixtures are compared using a common data set. The overall system design is detailed, providing insight into the overall complexity of implementing a robust DDF system for use in information gathering tasks in outdoor UAV applications.

Score-level multibiometric fusion based on Dempster-Shafer theory incorporating uncertainty factors

While existing multi-biometic Dempster-Shafer the- ory fusion approaches have demonstrated promising perfor- mance, they do not model the uncertainty appropriately, sug- gesting that further improvement can be achieved. This research seeks to develop a unified framework for multimodal biometric fusion to take advantage of the uncertainty concept of Dempster- Shafer theory, improving the performance of multi-biometric authentication systems. Modeling uncertainty as a function of uncertainty factors affecting the recognition performance of the biometric systems helps to address the uncertainty of the data and the confidence of the fusion outcome. A weighted combination of quality measures and classifiers performance (Equal Error Rate) are proposed to encode the uncertainty concept to improve the fusion. We also found that quality measures contribute unequally to the recognition performance, thus selecting only significant factors and fusing them with a Dempster-Shafer approach to generate an overall quality score play an important role in the success of uncertainty modeling. The proposed approach achieved a competitive performance (approximate 1% EER) in comparison with other Dempster-Shafer based approaches and other conventional fusion approaches.