Abstract

Abstract
This work considers the problem of segmenting heart sounds into their fundamental components. We unify statistical and data-driven solutions by introducing Markov-based Neural Networks (MNNs), a hybrid end-toend framework that exploits Markov models as statistical inductive biases for an Artificial Neural Network (ANN) discriminator. We show that an MNN leveraging a simple onedimensional Convolutional ANN significantly outperforms two recent purely data-driven solutions for this task in two publicly available datasets: PhysioNet 2016 (Sensitivity: 0.947 +/- 0.02; Positive Predictive Value : 0.937 +/- 0.025) and the CirCor DigiScope 2022 (Sensitivity: 0.950 +/- 0.008; Positive Predictive Value: 0.943 +/- 0.012). We also propose a novel gradient-based unsupervised learning algorithm that effectively makes the MNN adaptive to unseen datum sampled from unknown distributions. We perform a cross dataset analysis and show that an MNN pre-trained in the CirCor DigiScope 2022 can benefit from an average improvement of 3.90% Positive Predictive Value on unseen observations from the PhysioNet 2016 dataset using this method.

Abstract
This study presents a novel approach to cope with the human behaviour uncertainty during Human-Robot Collaboration (HRC) in dynamic and unstructured environments, such as agriculture, forestry, and construction. These challenging tasks, which often require excessive time, labour and are hazardous for humans, provide ample room for improvement through collaboration with robots. However, the integration of humans in-the-loop raises open challenges due to the uncertainty that comes with the ambiguous nature of human behaviour. Such uncertainty makes it difficult to represent high-level human behaviour based on low-level sensory input data. The proposed Fuzzy State-Long Short-Term Memory (FS-LSTM) approach addresses this challenge by fuzzifying ambiguous sensory data and developing a combined activity recognition and sequence modelling system using state machines and the LSTM deep learning method. The evaluation process compares the traditional LSTM approach with raw sensory data inputs, a Fuzzy-LSTM approach with fuzzified inputs, and the proposed FS-LSTM approach. The results show that the use of fuzzified inputs significantly improves accuracy compared to traditional LSTM, and, while the fuzzy state machine approach provides similar results than the fuzzy one, it offers the added benefits of ensuring feasible transitions between activities with improved computational efficiency.

Abstract
A área de conhecimento associada à gestão de ativos potencia a extração de valor de ativos físicos, incorporando uma abordagem integrada que envolve riscos, custos e desempenho. Este trabalho propõe uma nova abordagem para selecionar projetos de investimento em infraestruturas no âmbito da gestão de ativos. A métrica padrão utilizada para a seleção de projetos em ativos múltiplos é o Índice de Valor de Infraestruturas (IVI), que tem sido utilizado para caracterizar ativos do setor de águas em diversos países. Este trabalho desenvolveu dois modelos de programação linear inteira mista. O primeiro modelo de otimização trata de um problema de alocação de orçamento de capital selecionando projetos de investimento com vista à maximização da condição dos ativos. O segundo modelo de otimização trata de um problema de planeamento de orçamento, visando minimizar o capital necessário para manter os ativos nas condições desejadas. A aplicação dos modelos é ilustrada por um estudo de caso de uma empresa que opera no setor da água em Portugal. Os resultados obtidos nos diferentes cenários analisados são discutidos com vista a apoiar o desenho de políticas de gestão de ativos mais eficientes.

Abstract
The study of the evacuation of buildings in emergency fire situations has deserved the attention of researchers for decades, particularly regarding the real-time guiding of occupants in their way to exit the building. However, finding solutions to guide the occupants evacuating a building requires a thorough knowledge of that domain. Using ontological models to model the knowledge of a domain allows the understanding of that domain to be shared. This paper presents an ontological model that pretends to reinforce and deepen knowledge of the domain under study and help develop solutions and systems capable of guiding the occupants during a building evacuation. The ontology was developed following the METHONTOLOGY methodology, and for implementation, the Protege tool was used. The ontological model was successfully submitted to a thorough evaluation process and is publicly available on the Web.

Abstract
Purpose The purpose of this study is to explore the potential and growth of big data across several industries between 2016 and 2020. This study aims to analyze the behavior of interest in big data within the community and to identify areas with the greatest potential for future big data adoption. Design/methodology/approach This research uses Google Trends to characterize the community's interest in big data. Community interest is measured on a scale of 0-100 from weekly observations over the past five years. A total of 16 industries were considered to explore the relative interest in big data for each industry. Findings The findings revealed that big data has been of high interest to the community over the past five years, particularly in the manufacturing, computers and electronics industries. However, over the 2020s the interest in the theme decreased by more than 15%, especially in the areas where big data typically had the greatest potential interest. In contrast, areas with less potential interest in big data such as real estate, sport and travel have registered an average growth of less than 10%. Originality/value To the best of the author's knowledge, this study is original in complementing the traditional survey approaches launched among the business communities to discover the potential of big data in specific industries. The knowledge of big data growth potential is relevant for players in the field to identify saturation and emerging opportunities for big data adoption.