Search

The growing demand for effective healthcare has driven advances in digital health. This digitization supposes a challenge from the point of view of privacy and the treatment of sensitive personal data while providing non-intrusive and easy-to-use digital mechanisms. This paper presents Contigo: a health monitoring system that integrates a mobile application and a web platform for detecting anomalies using Federated Learning techniques. The mobile application collects health and personal data to train a personal predictive model. It is then anonymized and aggregated into a global model to improve efficiency, reducing adoption time for new users. At the same time, the web platform allows healthcare professionals to access the data for its analysis and validation. Contigo addresses the need for user-friendly digital mechanisms in healthcare, addressing privacy concerns while improving data-driven decision-making for professionals and personalized patient care. This approach ensures privacy and facilitates continuous model improvement, providing personalized, proactive, and non-intrusive patient health analytics.

Dropout prediction is a problem that is being addressed with machine learning algorithms; thus, appropriate approaches to address the dropout rate are needed. The selection of an algorithm to predict the dropout rate is only one problem to be addressed. Other aspects should also be considered, such as which features should be selected and how to measure accuracy while considering whether the features are appropriate according to the business context in which they are employed. To solve these questions, the goal of this paper is to develop a systematic literature review to evaluate the development of existing studies and to predict the dropout rate in contractual settings using machine learning to identify current trends and research opportunities. The results of this study identify trends in the use of machine learning algorithms in different business areas and in the adoption of machine learning algorithms, including which metrics are being adopted and what features are being applied. Finally, some research opportunities and gaps that could be explored in future research are presented.

Depending on the Internet as the main source of information regarding all aspects of our life is becoming a trend. People seek relevant information, suggestions, and recommendations in an overloaded online world and through social ties regarding their daily activities, including places to visit and restaurants to try new food. The wide variety of choices that are available online causes information overloading, which thereby complicates the selection process. Traditional recommender systems are mostly dependent on a conventional model that is based on user-item-rating interaction without considering contextual information. We claim that new generations of recommendation systems able to exploit context in an innovative and efficient way is important and may statistically yield more significant rating predictions. However, only few research works have focused on how to effectively and efficiently exploit context metadata in Deep Learning (DL)-based recommendations. The main reason lies, perhaps most significantly, in the fact that most current DL algorithms are not intrinsically designed to incorporate contextual tags. In this paper, we provide a significant contribution for filling this gap by designing a hybrid algorithm that retrofits and repurposes a pre-filtering contextual incorporation method and feeds the new dimension to a DL-based neural collaborative filtering method, thus preserving and recovering the benefits of both without their limitations. The paper also reports quantitative results that show that our method outperforms the baselines by statistically significant margins.

The explosive growth of the mobile application market in recent years has led to a large concomitant mobile software industry whose components are, in many cases, startups and small-size software providers. The success of these applications and the firms behind them depends on a subtle balance between different dimensions mainly affected by their architectural design, such as user satisfaction, resource consumption, operating costs, and timing. The present communication describes a framework with a specific set of practices for identifying the boundaries of different architectural designs -in this article we apply it to estimate both the smartphone's resource consumption and the operating costs in the cloud- and thus help in the architectural decision-making process. This will enable mobile software developers to predict at early stages which architectural design best suits their business model in accordance with the number of users and the expected use of the application and even provide an advance alert of when architectural choices will need to be reviewed, obviating the need for costly architectural re-design in further phases.

Sensor/Actuator devices are currently being massively adopted, often as nodes of larger sensor networks. These sensor networks are typically dedicated to context acquisition (e.g., get temperature) as well as providing acting services (e.g., open the blinds). However, regarding their own data storage, data is usually sent to Fog/Cloud servers. Fog/Cloud storage solutions provide several advantages over sensor network storage solutions, but also some drawbacks. For instance, in Cloud environments, privacy and legal issues may appear, while in Fog, additional costly hardware must be purchased and maintained, at least a server with redundant storage or many servers when distributed data storage is required. Nowadays, sensor nodes count in thousands around us, and they have significantly increased their storage and computational capabilities over the past few years. Therefore, traditional Fog/Cloud storage solutions could be combined or even replaced by Mist/Edge storage solutions for many use cases. A principal contribution of this paper is a novel data distribution and replication storage solution for wireless sensor networks, the first to consider sensor node heterogeneity to find the optimal storage replication according to node capabilities. The solution has been carefully planned and implemented to run even in very low-end microcontrollers, that lives in many of our surrounding smart devices. Other contributions include data comparing Mist/Edge and Amazon S3 regular storage, showing that there remains plenty of room for research into Mist/Edge storage, as well as into the industry itself.

Over the last years, the Internet of Things has fostered a growing interest in context-aware mobile applications; this fact is mainly due to highly favoring information provision from multiple Internet-connected devices. To identify user context, these applications collect information from the user and his/her environment and typically filter app information, so that the user receives only the interesting and relevant information. However, such a task usually implies further resource consumption on user mobile devices, not only regarding battery usage but also in terms of network traffic. Accordingly, although context-aware applications can improve user experiences in their daily lives, they must ensure the maintenance of low-level resource consumption; otherwise, the applications are promptly replaced by less consuming ones, and therefore, removed from the mobile market. In this paper, we evaluate and discuss several architectural styles for context-aware mobile applications, as well as, providing a set of guidelines to decide on the right architecture for a particular app depending on its characteristics. The use of such guidelines when choosing the right architectural style can strongly influence the resource consumption of context-aware mobile applications. Following these guidelines, user satisfaction of a context-aware mobile application may be improved, thus guaranteeing the app success.

The dietary habits of people directly impact their health conditions. Especially in elder populations (in 2017, 6.7% of the world’s population was over 65 years of age), these habits could lead to important-nutrient losses that could seriously affect their cognitive and functional state. Recently, a great research effort has been devoted to using different technologies and proposing different techniques for monitoring food-intake. Nevertheless, these techniques are usually generic but make use of the most innovative technologies and methodologies to obtain the best possible monitoring results. However, a large percentage of elderly people live in depopulated rural areas (in Spain, 28.1% of the elderly population lives in this type of area) with a fragile cultural and socioeconomic context. The use of these techniques in these environments is crucial to improving this group’s quality of life (and even reducing their healthcare expenses). At the same time, it is especially challenging since they have very specific and strict requirements regarding the use and application of technology. In this Systematic Literature Review (SLR), we analyze the most important proposed technologies and techniques in order to identify whether they can be applied in this context and if they can be used to improve the quality of life of this fragile collective. In this SLR, we have analyzed 326 papers. From those, 29 proposals have been completely analyzed, taking into account the characteristics and requirements of this population.

The massive amount of traffic required by the emerging Internet of Things (IoT) paradigm can be supported by the imminent arrival of 5G next-generation networks. However, the limited capacity of resources in IoT nodes, e.g., battery lifetime or buffer space, opens a challenge to be taken into account when proposing new routing solutions on IoT scenarios with intermittent connectivity. In this paper, we propose the concept of Opportunistic Context-Virtual Networks (OCVNs). The novelty of this approach is to create virtual groups of nodes that share interests in common for routing purposes. Therefore, only the nodes that are interested in the content of the messages that are flowing throughout the network are used as relaying nodes, providing their own resources for the sake of the communication. By leveraging the use of store-carry-and-forward mechanisms, a novel routing algorithm is proposed and evaluated over two realistic scenarios. Experimental results reveal that our solution outperforms other well-known opportunistic routing algorithms in terms of delivery probability and overhead ratio, while resource usage of relaying nodes is significantly reduced.

The aging of the population has increased the research efforts focused on eldercare. In this area, nutrition is a topic of particular interest. A significant number of problems related with aging have their origin in a deficient nutrition. Many elders suffer changes in their nutritional patterns and these changes can cause serious deterioration of their physical condition. Therefore, to be able to address nutritional problems in the elderly, their nutritional patterns must be recorded and analyzed in an easy and efficient way. From a technological point of view, numerous works focus on monitoring the food intake, not only of elders but also of the general population. However, these works usually do not take into account the problems associated with an aging population. In this paper we present a survey of existing technological solutions for monitoring food intake. The analyzed solution are categorized based on their technological implementation and their adaptation to the needs of an aging population.