Auflistung nach Autor:in "Preuveneers, Davy"
1 - 3 von 3
Treffer pro Seite
Sortieroptionen
- KonferenzbeitragGait Authentication based on Spiking Neural Networks(BIOSIG 2021 - Proceedings of the 20th International Conference of the Biometrics Special Interest Group, 2021) Rúa, Enrique Argones; van Hamme, Tim; Preuveneers, Davy; Joosen, WouterIn this paper we address gait authentication using a novel approach based on spiking neural networks (SNNs). This technology has proven advantages regarding energy consumption and it is a perfect match with some proposed neuromorphic hardware chips, which can lead to a broader adoption of user device applications of artificial intelligence technologies. One of the challenges when using this technology is the training of the network itself, since it is not straightforward to apply well-known error backpropagation, massively used in traditional artificial neural networks (ANNs). In this paper we propose a new derivation of error backpropagation for the spiking neural networks that integrates lateral inhibition and provides competitive results when compared to state of the art ANNs in the context of IMU-based gait authentication.
- KonferenzbeitragGait template protection using HMM-UBM(BIOSIG 2018 - Proceedings of the 17th International Conference of the Biometrics Special Interest Group, 2018) Van hamme, Tim; Argones Rúa, Enrique; Preuveneers, Davy; Joosen, WouterThis paper presents a hidden Markov model-Universal background model gait authentication system, which is also incorporated into a template protection based on a fuzzy commitment scheme.We show that with limited enrollment data the HMM-UBM system achieves a very competitive equal error rate of 1% using one sensor. The proposed template protection scheme benefits from eigenfeatures coming from multiple Universal background model systems fused with a novel technique that minimizes the bit error rate for genuine attempts. This allows the protected system to achieve a false rejection rate below 5% with an effective key length of 64 bits.
- KonferenzbeitragProbabilistic event processing for situational awareness(12th International Conference on Innovative Internet Community Services (I2CS 2012), 2012) Preuveneers, Davy; Landmark, Andreas D.; Wienhofen, Leendert W. M.Over the last century the continuous innovation of technology, coupled with a steady increase in the size of the healthcare organizations, has created a need for information systems supporting healthcare professionals with their daily tasks and decisions. Modern hospitals are full of technology producing electronic records of events and activities, with the opportunity of these events culminating in a wealth of information that these semi-autonomous experts can tap into to improve situational awareness, facilitate coordination and take better informed decisions. However, processing these footprints, contextualizing and inferring over them presents several interesting challenges to the current state of Complex Event Processing methods. This article looks at challenges presented by an information system for perioperative process support and how contextualization and adequate tool support can provide the essential backdrop for meaningful inference.