Abstract
Epilepsy is one of the most common neurological disorders, affecting up to 1% of the World population. Patients with epilepsy may suffer from severe consequences from seizures (e.g. injuries) when not monitored. Automatic seizure detection systems could mitigate this problem, improving seizure tracking and alerting a caregiver during a seizure. Existing unimodal solutions for seizure detection, based on electroencephalogram (EEG) and electrocardiogram (ECG) still have an unacceptable level of false positives, which can be reduced by combining these two biosignals. In this paper, EEG and ECG data from 7 epileptic patients with diverse recording length and seizure types were used for analyzing the importance of multimodal seizure detection, at a total of around 110 h 2 m. A leave one seizure out cross validation was selected, grouping data containing the period before a seizure and the seizure period. A proof of concept of multimodal seizure detection which uses a deep learning architecture directly on raw data is performed - a Fully Convolutional Neural Network and an architecture based on LSTM were tested. The network based on LSTM achieved better performance - using the best of one or a combination of both signals, all patients had above 91% detected seizures, a specificity per epoch above 0.96 +/- 0.06 and a detection delay below 8.5 +/- 12 s. These results show potential for developing a patient-specific approach for seizure detection that can be transferred to the ambulatory.

Abstract
In public transport, traveler dissatisfaction is widespread, due to long waits and travel time, or the low frequency of the service provided. Public transport providers are increasingly concerned about improving the service provided. To improve public transport, detailed knowledge of the network and its weaknesses is necessary. An easy and cheap way to achieve this information is to extract knowledge from the data daily collected in a public transport network. Thus, this chapter focuses on data analysis resulting from the smartcard-based ticketing system. The main objective is to detect patterns of average speed for all days of the week and times of the day, along with pairs of consecutive stops. To perform the analyses, the average speed was deduced from ticketing data, and clustering methods were applied. The results show that it is possible to find segments with similar patterns and identify days and times with similar patterns.

Abstract
This article presents an analysis of conventional single-phase cascaded H-bridge multilevel inverters composed of two and three cells. The dc-link can be a dc source or a floating capacitor. Two methods are given to regulate the floating capacitor voltage. In this way, according to the capacitor voltage balancing method used, operating regions and power distribution on the floating capacitor are presented for different dc-link voltage ratios and several ranges of modulation index and load power factor. A mathematical analysis is done in order to demonstrate the influence of the modulation index and load power factor over the power distribution. Finally, simulation and experimental results are provided to validate the theoretical considerations.

Abstract
This paper aims to contribute to the lack of design knowledge on digital platforms (DPs), by studying the new and specific context of DPs managed by industrial business associations (IBAs) to improve the inter- nationalisation of small and medium enterprises (SMEs). A specific objective is to elicit detailed digital plat- form ?s requirements and features for this particular organisational context. A design science research (DSR) approach is adopted to develop design propositions (the artifact), following the context -intervention -me- chanism -outcome logic (CIMO-logic). The design propositions are derived for DPs that can support different types of generative mechanisms of social interaction: information sharing, collaboration, and collective action. The design propositions are obtained by balancing empirical knowledge based on interviews performed with IBAs and SMEs in Portugal and in the UK, with theoretical knowledge from the literature of information systems, DPs and collaborative networks (CNs). The utility of the design propositions is further evaluated by experts and IBAs. The findings are proved to be relevant for practice, mainly for IBAs, SMEs, and digital platform designers to develop more effective collaborative DPs and sociotechnical systems, supporting CNs and the internationalisa- tion needs of SMEs. The knowledge generated in this study brings new design knowledge on DPs, contributing with design propositions translated into tangible and concrete requirements and capabilities, situated in a specific context and empirical setting.

Abstract
The paper introduces Gamified Education Interoperability Language (GEdIL), designed as a means to represent the set of gamification concepts and rules applied to courses and exercises separately from their actual educational content. This way, GEdIL allows not only for an easy yet effective specification of gamification schemes for educational purposes, but also sharing them among instructors and reusing in various courses. GEdIL is published as an open format, independent from any commercial vendor, and supported with dedicated open-source software.

Abstract
Agricultural robotics is nowadays a complex, challenging, and relevant research topic for the sustainability of our society. Some agricultural environments present harsh conditions to robotics operability. In the case of steep-slope vineyards, there are several robotic challenges: terrain irregularities, characteristics of illumination, and inaccuracy/unavailability of the Global Navigation Satellite System. Under these conditions, robotics navigation, mapping, and localization become a challenging task. Performing these tasks with safety and accuracy, a reliable and advanced Navigation stack for robots working in a steep slope vineyard is required. This paper presents the integration of several robotic components, path planning aware of robot centre of gravity and terrain slope, occupation grid map extraction from satellite images, a localization and mapping procedure based on high-level visual features reliable under GNSS signals blockage/missing, for steep-slope robots. © 2021, Springer Nature Switzerland AG.