Search

Noninvasive ventilation (NIV) is an effective form of treatment in obesity hypoventilation syndrome (OHS) with severe OSA. However, there is paucity of evidence in patients with OHS without severe OSA phenotype.

Obesity hypoventilation syndrome is commonly treated with continuous positive airway pressure or non-invasive ventilation during sleep. Non-invasive ventilation is more complex and costly than continuous positive airway pressure but might be advantageous because it provides ventilatory support. To date there have been no long-term trials comparing these treatment modalities. We therefore aimed to determine the long-term comparative effectiveness of both treatment modalities.

Fuzzy systems have become widely accepted and applied in a host of domains such as control, electronics or mechanics. The software for construction of these systems has traditionally been exploited from tools, platforms and languages run on-premise computing infrastructure. On the other hand, rise and ubiquity of the cloud computing model has brought a revolutionary way for computing services deployment. The boost of cloud services is leading towards increasingly specific service offering just as data mining and machine learning service. Unfortunately, so far, no definition for fuzzy system as service is available. This paper identifies this opportunity and focus on developing a proposal for fuzzy system-as-a-service definition. To achieve this, the proposal pursues three objectives: the complete description of cloud services for fuzzy systems using semantic technology, the composition of services and the exploitation of the model in cloud platforms for integration with other services. As an illustrative case, a real-world problem is addressed with the proposed specification.

The purpose of this study was to determine whether the distance between the setter, the middle hitter and the second tempo attacker can predict the attack zone in Complex I in elite male volleyball. A total amount of 3,936 rallies corresponding to 23 matches of the Men’s World Championship 2010 were analysed following a category system, recurring to an observational methodology. Measured variables were Availability of the middle hitter, Attack type, Latitude of the middle hitter, setter, and second tempo attacker, Second tempo attack lane and Distance between players. Results suggest that a relationship with high level of significance (p<0.01) exists between the middle hitter’s position and setter’s position, regardless of the occurrence of a first tempo attack. Using a classification tree, it was observed that the middle hitter’s position was modified according to setter’s position, normally with a distance of one or two metres on his left. Furthermore, the variable Distance from setter to middle hitter emerged as a key factor to dismiss a second tempo attack in the central lane. This study provides a dynamical perspective about the spatial relationships between players, and how these constitute a key factor to dismiss or not a specific final attack zone.

Obesity hypoventilation syndrome (OHS) is associated with a high burden of cardiovascular morbidity (CVM) and mortality. The majority of patients with OHS have concomitant OSA, but there is a paucity of data on the association between CVM and OSA severity in patients with OHS. The objective of our study was to assess the association between CVM and OSA severity in a large cohort of patients with OHS.

Life Cycle Assessment (LCA) and intelligent data analysis can help in reducing carbon and water footprints of rail infrastructure construction projects. The goal is to improve the railway construction processes with regard to their environmental impact, mainly in those aspects related to climate change such as carbon and water footprints.

Time series data are becoming increasingly important due to the interconnectedness of the world. Classical problems, which are getting bigger and bigger, require more and more resources for their processing, and Big Data technologies offer many solutions. Although the principal algorithms for traditional vector-based problems are available in Big Data environments, the lack of tools for time series processing in these environments needs to be addressed. In this work, we propose a scalable and distributed time series transformation for Big Data environments based on well-known time series features (SCMFTS), which allows practitioners to apply traditional vector-based algorithms to time series problems. The proposed transformation, along with the algorithms available in Spark, improved the best results in the state-of-the-art on the Wearable Stress and Affect Detection dataset, which is the biggest publicly available multivariate time series dataset in the University of California Irvine (UCI) Machine Learning Repository. In addition, SCMFTS showed a linear relationship between its runtime and the number of processed time series, demonstrating a linear scalable behavior, which is mandatory in Big Data environments. SCMFTS has been implemented in the Scala programming language for the Apache Spark framework, and the code is publicly available.