Abstract

Abstract
Wiki articles are created and maintained by a crowd of editors, producing a continuous stream of reviews. Reviews can take the form of additions, reverts, or both. This crowdsourcing model is exposed to manipulation since neither reviews nor editors are automatically screened and purged. To protect articles against vandalism or damage, the stream of reviews can be mined to classify reviews and profile editors in real-time. The goal of this work is to anticipate and explain which reviews to revert. This way, editors are informed why their edits will be reverted. The proposed method employs stream-based processing, updating the profiling and classification models on each incoming event. The profiling uses side and content-based features employing Natural Language Processing, and editor profiles are incrementally updated based on their reviews. Since the proposed method relies on self-explainable classification algorithms, it is possible to understand why a review has been classified as a revert or a non-revert. In addition, this work contributes an algorithm for generating synthetic data for class balancing, making the final classification fairer. The proposed online method was tested with a real data set from Wikivoyage, which was balanced through the aforementioned synthetic data generation. The results attained near-90% values for all evaluation metrics (accuracy, precision, recall, and F-measure).

Abstract
Electronic fare payment systems have gained much popularity around the world. These systems adopt a convenient and almost instantaneous payment process for public transport while also gathering data regarding onboard transactions in public transport. Much information about public transport passengers can be extracted, such as travel patterns, activities performed, and travel behavior. Despite the continuous growth of studies regarding these systems, there is still a lack of research to understand occasional passengers’ movement, such as tourists. This work presents the state of the art in these areas and presents a proposal to explore AFC data to understand the mobility profiles of tourists. This manuscript represents an advance in the literature and opens doors to the definition of policies to promote less visited places and mobility services adapted to tourists’ needs, resulting in a positive impact on the city’s economy and the overall enjoyment of the city for tourists. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Abstract
Energy poverty vulnerability constitutes a significant concern in Portugal, with 17.5% of the population being unable to keep their home adequately warm. Furthermore, there is evidence that a substantial number of children live in unhealthy homes. This study aims to comprehensively characterise a sample of 101 Portuguese families with children and their homes in order to identify opportunities for actions for promoting long-lasting energy efficiency and environment health-promoting behavioural changes. To accomplish this aim, two tools-a building survey checklist and a questionnaire to participants-were developed and implemented to collect harmonised data on building-specific characteristics and on participants' socioeconomic status and behaviour. The home visits for recruitment and data collection were conducted from July 2021 to April 2022. The results suggest that, for the population under study, the main opportunities for improvement include: (i) replacing low energy-efficient technologies, with high emission rates, namely those used for heating purposes, with cleaner and more efficient alternatives; (ii) providing citizens with detailed information about their home's energy use and indoor air quality and (iii) educating the population on the best-practices for reducing indoor air stuffiness, mitigating the risk of hazardous exposures, improving thermal comfort and saving energy.

Abstract
The interrogation of optical fiber sensors (OFS) often relies on complex devices such as optical spectrum analyzers (OSAs) that are expensive with low portability and mainly suited to laboratory measurements or dedicated interrogation systems with limited spectral range. An interrogation unit was designed and fabricated using a photodetector combined with a micro-electromechanical system and a Fabry-Perot interferometer (MEMS-FPI) working as a tunable filter with a response in the range 1350-1650 nm. Deconvolution techniques were applied to mitigate the effect of the broadband response of the tunable filter on the measured signal. The performance of the unit was validated with the interrogation of long-period fiber gratings (LPFGs) as temperature, refractive index (RI), and relative humidity (RH) sensors. For the temperature, a sensitivity of 0.135 +/- 0.007 nm/degrees C was obtained, which showed a 4.9% relative error when compared to the same measurement with an OSA. For the RI, a sensitivity of 147 +/- 11 nm/RIU was obtained, which showed a relative error lower than 1% when compared to the OSA. For the humidity, sensitivities of 0.742 +/- 0.005 and 0.056 +/- 0.006 nm/%RH were obtained, with errors of 2.75% and 6.67%, respectively, when compared to a commercial dedicated interrogation system. The low relative error obtained when compared to commercial alternatives shows the potential of the system to be used in real-time applications that require portability, low cost, energy efficiency, and capacity for integration in dedicated systems.

Abstract