Modern access controls employ biometrics as a means of authentication to a great extent. For example, biometrics is used as an authentication mechanism implemented on commercial devices such as smartphones and laptops. This paper presents a fingerprint biometric cryptosystem based on the fuzzy commitment scheme and convolutional neural networks. One of its main contributions is a novel approach to automatic discretization of fingerprint texture descriptors, entirely based on a convolutional neural network, and designed to generate fixed-length templates. By converting templates into the binary domain, we developed the biometric cryptosystem that can be used in key-release systems or as a template protection mechanism in fingerprint matching biometric systems. The problem of biometric data variability is marginalized by applying the secure block-level Bose–Chaudhuri–Hocquenghem error correction codes, resistant to statistical-based attacks. The evaluation shows significant performance gains when compared to other texture-based fingerprint matching and biometric cryptosystems.

The increasing demand for energy-efficient and interconnected smart buildings, particularly in the tourism sector, has driven the adoption of advanced wireless technologies. IoT technologies are crucial in this evolution, improving modern buildings’ functionality and operational efficiency. This study investigates the utilization of various wireless technologies within Wireless Personal Area Networks (WPANs), including Bluetooth BLE 4.2, Bluetooth BLE 5.0, ZigBee, and Z-Wave, in smart buildings. A multiple-criteria decision-making (MCDM) approach, specifically the PIPRECIA-S model, was applied to evaluate these technologies based on criteria such as device connectivity, mobility, low energy consumption, scalability, flexibility, and interoperability. Simulations using the PIPRECIA-S model were conducted to assess technology performance across various real-world scenarios. The results indicate that ZigBee (0.2942) and Bluetooth BLE 5.0 (0.2602) provide superior performance in terms of energy efficiency and scalability, followed by Z-Wave (0.2550) and Bluetooth BLE 4.2 (0.1906). These findings provide decision-makers with data-driven recommendations for selecting the most suitable wireless technologies for smart buildings.

U cilju ostvarivanja visokog nivoa zaštite biometrijskih podataka otisaka prstiju homomorfnim šifarskim sistemima, od presudne važnosti je transformacija obeležja otisaka prstiju u vektorski opis fiksne dužine

The use of convolutional neural networks (CNNs) in the domain of biometric identification is examined in this paper