Abstract
An intrusion detection system (IDS) is an important tool to prevent potential threats to systems and data. Anomaly-based IDSs may deploy machine learning algorithms to classify events either as normal or anomalous and trigger the adequate response. When using supervised learning, these algorithms require classified, rich, and recent datasets. Thus, to foster the performance of these machine learning models, datasets can be generated from different sources in a collaborative approach, and trained with multiple algorithms. This paper proposes a vote-based architecture to generate classified datasets and improve the performance of supervised learning-based IDSs. On a regular basis, multiple IDSs in different locations send their logs to a central system that combines and classifies them using different machine learning models and a majority vote system. Then, it generates a new and classified dataset, which is trained to obtain the best updated model to be integrated into the IDS of the companies involved. The proposed architecture trains multiple times with several algorithms. To shorten the overall runtimes, the proposed architecture was deployed in Fed4FIRE+ with Ray to distribute the tasks by the available resources. A set of machine learning algorithms and the proposed architecture were assessed. When compared with a baseline scenario, the proposed architecture enabled to increase the accuracy by 11.5% and the precision by 11.2%.

Abstract
In this work new rosamine-silica composites were prepared and their sensing ability towards different amines was assessed. Rice husk wastes were used as a biogenic silica source. Silica was extracted by thermal treatment, before rice husk ash and after acid leaching with citric acid-treated rice husk ash. Mesoporous material (SBA-15) was also prepared using the extracted silica. The prepared materials were characterized by several techniques such as FTIR, XRD, SEM and N-2 adsorption. The materials were then used as adsorbents of the chromophore N-methylpyridinium rosamine (Ros4PyMe). The obtained loaded composites were tested in solution for amines sensing (n-butylamine, aniline, putrescine and cadaverine). The detection studies were analyzed by fluorescence and revealed 40% and 48% quenching in fluorescence intensity for the composite Ros4PyMe@SBA in the presence of the biogenic amines cadaverine and putrescine, respectively. The composite was also sensitive in the powder form, changing the color from violet to pale pink in the presence of putrescine vapors with a fast response (around 2 min), the process being reversible by exposure to air.

Abstract
The tremendous increase in photographs that are captured each day by common users has been favoured by the availability of high quality devices at accessible costs, such as smartphones and digital cameras. However, the quantity of captured photos raises new challenges regarding the access and management of image repositories. This paper describes a lightweight distributed framework intended to help overcome these problems. It uses image metadata in EXIF format, already widely added to images by digital acquisition devices, and automatic facial recognition to provide management and search functionalities. Moreover, a visualization functionality using a graph-based strategy was integrated, enabling an enhanced and more interactive navigation through search results and the corresponding relations.

Abstract
Long period fiber gratings coated with TiO2 and poly(ethylene-co-vinyl acetate) (PEVA), a polymeric structure permeable biogenic amines found in foodstuff, were used to detect these compounds through the wavelength shift of its attenuation band. © 2022 The Author(s).

Abstract
In recent years there have been several commercial products designated as "augmented books". These use gamification and augmented reality technologies to provide the reader with more layers of information, thereby fostering the use of the book in new ways. So, in this article we describe part of the research and outcomes of the Portuguese project CHIC – C3, aimed at designing and developing a platform for managing the production of digital content connected with printed books. Furthermore, we developed a model for the gamification of digital content based on the printed book, mainly aimed at educational purposes. A proof of concept for the model was built in the form of a companion platform, supported by the Moodle LMS, fully integrated with the main CHIC website. Readers were able to access the platform, engage in several content related games, and interact with other readers.

Abstract
The automotive software industry is gradually introducing new functionalities and technologies that increase the efficiency, safety, and comfort of vehicles. These functionalities are quickly accepted by consumers; however, the consequences of this evolution are twofold. First, developing correct systems that integrate more applications and hardware is becoming more complex. To cope with this, new standards (such as Adaptive AUTOSAR) and frameworks (such as AMALTHEA) are being proposed, to assist the development of flexible systems based on high-performance electronic control units (ECU). Second, the increase of functionality is supported by a dramatic increase of electronic parts on automotive systems. Consequently, the impact of software on the electrical power and energy non-functional requirements of automotive systems has come under focus. In this paper we propose an automatic and self-contained approach that supplements a model of an automotive system described on the AMALTHEA platform with energy-related annotations. From the analysis of simulation (or execution) traces of the modelled software, we estimate the power consumption for each software component, on a target hardware platform. This method enables energy analysis during the entire development life-cycle; furthermore, it contributes for the development of energy management strategies for dynamic and self-adaptive systems.