Fingerprint recognition systems are vulnerable to artificial spoof fingerprint attacks, like molds made of silicone, gelatin or Play-Doh. "Liveness detection", which is to detect vitality information from the biometric signature itself, has been proposed to defeat these kinds of spoof attacks. The goal for the LivDet 2009 competition is to compare different methodologies for softwarebased fingerprint liveness detection with a common experimental protocol and large dataset of spoof and live images. This competition is open to all academic and industrial institutions which have a solution for software-based fingerprint vitality detection problem. Four submissions resulted in successful completion: Dermalog, ATVS, and two anonymous participants (one industrial and one academic). Each participant submitted an algorithm as a Win32 console application. The performance was evaluated for three datasets, from three different optical scanners, each with over 1500 images of "fake" and over 1500 images of "live" fingerprints. The best results were from the algorithm submitted by Dermalog with a performance of 2.7% FRR and 2.8% FAR for the Identix (L-1) dataset. The competition goal is to become a reference event for academic and industrial research in software-based fingerprint liveness detection and to raise the visibility of this important research area in order to decrease risk of fingerprint systems to spoof attacks.

Reliability of classification performance is important for many biomedical applications. A classification model which considers reliability in the development of the model such that unreliable segments are rejected would be useful, particularly, in large biomedical data sets. This approach is demonstrated in the development of a technique to reliably determine sleep and wake using only the electrocardiogram (ECG) of infants. Typically, sleep state scoring is a time consuming task in which sleep states are manually derived from many physiological signals. The method was tested with simultaneous 8-h ECG and polysomnogram (PSG) determined sleep scores from 190 infants enrolled in the collaborative home infant monitoring evaluation (CHIME) study. Learning vector quantization (LVQ) neural network, multilayer perceptron (MLP) neural network, and support vector machines (SVMs) are tested as the classifiers. After systematic rejection of difficult to classify segments, the models can achieve 85%-87% correct classification while rejecting only 30% of the data. This corresponds to a Kappa statistic of 0.65-0.68. With rejection, accuracy improves by about 8% over a model without rejection. Additionally, the impact of the PSG scored indeterminate state epochs is analyzed. The advantages of a reliable sleep/wake classifier based only on ECG include high accuracy, simplicity of use, and low intrusiveness. Reliability of the classification can be built directly in the model, such that unreliable segments are rejected.

No abstract

Heart rate variability and actigraphy offer alternative techniques for sleep-wake identification compared to manual sleep scoring from a polysomnograph. The advantages include high accuracy, simplicity of use, and low intrusiveness. These advantages are valuable for determining sleep-wake states in such highly sensitive groups as infants. A learning vector quantization neural network was tested as a predictor. The accuracy of the neural network was compared to "gold standard" hand-scored polysomnographs. The prediction results are in agreement with other studies, thus validating the suggested methodology.

Acute myocardial infarction (AMI) is one of the leading causes of death in the US. While heart rate variability (HRV) has been widely studied for ischemia detection, the changes in cardiac contractility variability have not yet been explored. This paper presents novel variability analysis using 23 linear and non-linear measures during myocardial ischemia. Multiple physiologic measures of cardiac contractility and heart rate variability are analyzed and compared before and after acute coronary artery occlusion in a swine model. Change in the spread of the Poincare plot of RR intervals was highly negatively correlated with the change in contractility reflective of ischemia (r=-0.92, p<0.05). The change in approximate entropy of the S1 heart sound intensity was also highly correlated (r=0.96, p<0.05) with the change in contractility due to ischemia. These preliminary results show the potential utility of nonlinear measures of variability to detect changes in the autonomic tone due to ischemia. These parameters, if measured continuously, may be used for early detection of AMI events in patients with implantable devices. Further research in a larger clinical study is warranted to confirm these findings.

No abstract

No abstract

Abstract:Introduction: Research trials that involve testing of physiological response to exercise and that include tests from more than one institution, or tests across long time periods, may be required to include tests from different ergometer types, mainly treadmill or leg cycle ergometer. The purpose of this study was to establish equivalence of metabolic demand when comparing treadmill to cycle ergometer protocols.Methods: Published equations were used to derive external power output performed on a cycle ergometer and treadmill to match external power output performance across the range of typical body weights for subjects.Results: When comparing a submaximal walking versus 10-watt incremental cycling protocol, the percent difference in metabolic demand ranged from -35% to 39% across the range of body weights from 50 kg to 150 kg. For the modified Bruce treadmill protocol, watts on the cycle had to be increased to match metabolic demand as body weight of the subject increases. Conclusion:To match estimated external power output performed on a treadmill, external power output on a leg cycle ergometer must be increased as body weight increases.