Abstract
Internet voting has been trialed or introduced for several countries, including Norway, Portugal, United States, United Kingdom and Switzerland as an additional voting channel to increase voter turnout and, also to modernize the electoral process. However, only Estonia has successful introduced internet voting, deploying e-enabled elections in general governmental levels. This paper aims to provide an exploratory study on the Estonian internet voting model to identify pre-conditions for internet voting introduction in Portugal, addressing legal, technical and technological considerations. For doing so, it includes a cross-country comparative analysis in two perspectives. Firstly, an analysis in the Estonian electoral framework, highlighting the most important legal adaptations that make possible internet voting introduction to identify potential transformation for the Portuguese context. Secondly, to provide a technological overview towards the Portuguese e-government ecosystem to seek similar conditions that can make internet voting possible in Estonia.

Abstract

Abstract

Abstract

Abstract

Abstract
Human Activity Recognition is focused on the use of sensing technology to classify human activities and to infer human behavior. While traditional machine learning approaches use hand-crafted features to train their models, recent advancements in neural networks allow for automatic feature extraction. Auto-encoders are a type of neural network that can learn complex representations of the data and are commonly used for anomaly detection. In this work we propose a novel multi-class algorithm which consists of an ensemble of auto-encoders where each auto-encoder is associated with a unique class. We compared the proposed approach with other state-of-the-art approaches in the context of human activity recognition. Experimental results show that ensembles of auto-encoders can be efficient, robust and competitive. Moreover, this modular classifier structure allows for more flexible models. For example, the extension of the number of classes, by the inclusion of new auto-encoders, without the necessity to retrain the whole model. (c) 2021 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY license (http:// creativecommons.org/licenses/by/4.0/).