Abstract
We introduce the Harmonix set: a collection of annotations of beats, downbeats, and functional segmentation for over 900 full tracks that covers a wide range of western popular music. Given the variety of annotated music information types in this set, and how strongly these three types of data are typically intertwined, we seek to foster research that focuses on multiple retrieval tasks at once. The dataset includes additional metadata such as MusicBrainz identifiers to support the linking of the dataset to third-party information or audio data when available. We describe the methodology employed in acquiring this set, including the annotation process and song selection. In addition, an initial data exploration of the annotations and actual dataset content is conducted. Finally, we provide a series of baselines of the Harmonix set with reference beat-trackers, downbeat estimation, and structural segmentation algorithms.

Abstract
LoRa (along with its upper layers definition-LoRaWAN) is one of the most promising Low Power Wide Area Network (LPWAN) technologies for implementing Internet of Things (IoT)-based applications. Although being a popular technology, several works in the literature have revealed vulnerabilities and risks regarding the security of LoRaWAN v1.0 (the official 1st specification draft). The LoRa-Alliance has built upon these findings and introduced several improvements in the security and architecture of LoRa. The result of these efforts resulted in LoRaWAN v1.1, released on 11 October 2017. This work aims at reviewing and clarifying the security aspects of LoRaWAN v1.1. By following ETSI guidelines, we provide a comprehensive Security Risk Analysis of the protocol and discuss several remedies to the security risks described. A threat catalog is presented, along with discussions and analysis in view of the scale, impact, and likelihood of each threat. To the best of the authors' knowledge, this work is one of the first of its kind, by providing a detailed security risk analysis related to the latest version of LoRaWAN. Our analysis highlights important practical threats, such as end-device physical capture, rogue gateway and self-replay, which require particular attention by developers and organizations implementing LoRa networks.

Abstract
Entropy models the added information associated to data uncertainty, proving that stochasticity is not purely random. This paper explores the potential improvement of machine learning methodologies through the incorporation of entropy analysis in the learning process. A multi-layer perceptron is applied to identify patterns in previous forecasting errors achieved by a machine learning methodology. The proposed learning approach is adaptive to the training data through a re-training process that includes only the most recent and relevant data, thus excluding misleading information from the training process. The learnt error patterns are then combined with the original forecasting results in order to improve forecasting accuracy, using the Rényi entropy to determine the amount in which the original forecasted value should be adapted considering the learnt error patterns. The proposed approach is combined with eleven different machine learning methodologies, and applied to the forecasting of electricity market prices using real data from the Iberian electricity market operator – OMIE. Results show that through the identification of patterns in the forecasting error, the proposed methodology is able to improve the learning algorithms’ forecasting accuracy and reduce the variability of their forecasting errors.

Abstract

Abstract
Wikipedia is the largest on-line collaborative encyclopedia, containing information from a plethora of fields, including medicine. It has been shown that Wikipedia is one of the top visited sites by readers looking for information on this topic. The large reliance on Wikipedia for this type of information drives research towards the analysis of the quality of its articles. In this work, we evaluate and compare the quality of medicine-related articles in the English and Portuguese Wikipedia. For that we use metrics such as authority, completeness, complexity, informativeness, consistency, currency and volatility, and domain-specific measurements, in order to evaluate and compare the quality of medicine related articles in the English and Portuguese Wikipedia. We were able to conclude that the English articles score better across most metrics than the Portuguese articles.

Abstract
The growth of the Internet of Things (IoT) is raising significant impact in several contexts, e.g., in cities, at home, and even attached to the human body. This digital transformation is happening at a high pace and causing a great impact in our daily lives, namely in our attempt to make cities smarter in an attempt to increase their efficiency while reducing costs and increasing safety. However, this effort is being supported by the massive deployment of sensors throughout cities worldwide, leading to increase concerns regarding security and privacy. While some of these issues have already been tackled, device authentication remains without a viable solution, specially when considering a resilient decentralized approach that is the most suitable for this scenario, as it avoids some issues related to centralization, e.g., censorship and data leakage or profit from corporations. The provisioning is usually an arduous task that encompasses device configuration, including identity and key provisioning. Given the potential large number of devices, this process must be scalable and semi-autonomous, at least. This work presents a novel approach for provisioning IoT devices that adopts an architecture where other device acts as a manager that represents a CA, allowing it to be switched on/off during the provisioning phase to reduce single point of failure (SPOF) problems. Our solution combines One Time Password (OTP) on a secure token and cryptographic algorithms on a hybrid authentication system.