Search

Nowadays, there are millions of smart devices connected to the Internet. The purpose of these devices is to make people’s lives easier. Thanks to the collaboration among them, the possibilities that the Internet of Things brings can grow exponentially. However, many manufacturers develop closed protocols and devices to protect their market share, limiting in many ways this collaboration. This paper presents a conceptual architecture that improves the proactive collaboration between IoT devices regardless of the protocols developed by their manufacturers. This architecture aims to identify entities in smart environments, describe their features and interfaces, and identify strategies fostering their collaborations. As a result, devices from different manufacturers can communicate to create a collaborative environment in a simple, efficient, and affordable way. This architecture has been evaluated in a real and a simulated environment, to validate its feasibility and efficiency.

Software-defined networking (SDN) is a paradigm that provides flexibility and programmability to computer networks. By introducing SDN nodes in a legacy IP network topology, network operators can benefit on higher control over the infrastructure. However, this migration is not a fast or straightforward process. Furthermore, to provide an adequate quality of service in hybrid IP/SDN networks, the coordination of both IP and SDN paradigm is fundamental. In this paper, this coordination is used to solve two optimization problems that are typically solved separately: (i) traffic load balancing and (ii) power consumption minimization. Each of these problems has opposing objectives, and thus, their joint consideration implies striking a balance between them. Therefore, this paper proposes the Hybrid Spreading Load Algorithm (HSLA) heuristic that jointly faces the problems of balancing traffic by minimizing link utilization and network’s power consumption in a hybrid IP/SDN network. HSLA is evaluated over differently sized topologies using different methods to select which nodes are migrated from IP to SDN. These evaluations reveal that alternative approaches that only address one of the objectives are outperformed by HSLA.

Dropout prediction is a problem that must be addressed in various organizations, as retaining customers is generally more profitable than attracting them. Existing approaches address the problem considering a dependent variable representing dropout or non-dropout, without considering the dynamic perspetive that the dropout risk changes over time. To solve this problem, we explore the use of random survival forests combined with clusters, in order to evaluate whether the prediction performance improves. The model performance was determined using the concordance probability, Brier Score and the error in the prediction considering 5200 customers of a Health Club. Our results show that the prediction performance in the survival models increased substantially in the models using clusters rather than that without clusters, with a statistically significant difference between the models. The model using a hybrid approach improved the accuracy of the survival model, providing support to develop countermeasures considering the period in which dropout is likely to occur. info:eu-repo/semantics/publishedVersion

During the last years, huge efforts have been conducted to reduce the Information and Communication Technology (ICT) sector energy consumption due to its impact on the carbon footprint, in particular, the one coming from networking equipment. Although the irruption of programmable and softwarized networks has opened new perspectives to improve the energy-efficient solutions already defined for traditional IP networks, the centralized control of the Software-Defined Networking (SDN) paradigm entails an increase in the time required to compute a change in the network configuration and the corresponding actions to be carried out (e.g., installing/removing rules, putting links to sleep, etc.). In this paper, a Machine Learning solution based on Logistic Regression is proposed to predict energy-efficient network configurations in SDN. This solution does not require executing optimal or heuristic solutions at the SDN controller, which otherwise would result in higher computation times. Experimental results over a realistic network topology show that our solution is able to predict network configurations with a high feasibility (>95%), hence improving the energy savings achieved by a benchmark heuristic based on Genetic Algorithms. Moreover, the time required for computation is reduced by a factor of more than 500,000 times.

Today, the number of interconnected devices and the amount of personal information gathered by them increases tremendously resulting in the need for development tools to harness its potential. New devices are continually being introduced in the daily life of people, and they are already producing an unprecedented amount of data related to people's well-being. However, taking advantage of such information to create innovative Internet of Bodies solutions heavily relies on manually gathering the needed information from several sources on services and the devices involved. In this paper, we present a novel Human Data Model - a new tool to combine personal information from several sources, perform computations over that information, and proactively schedule computer-human interactions. Developers that use the proposed model would obtain an opportunity to create the Internet of Bodies solutions using high-level abstractions of the users' personal information and taking advantage of the distributed approach of the model. acceptedVersion

The Internet of Things (IoT) paradigm is leading to the deployment of an extensive number of smart devices capable of assisting companies and people in their daily activities. For this paradigm to be effective, these devices must exchange a huge amount of information and be coordinated in unpredictable, dynamic, and very complex scenarios. So far, cloud computing has centralized data storage and offered coordination of devices. However, as the number of deployed smart devices increases and the requirements of IoT solutions are more stringent, cloud computing hardly meets them. Fog computing has emerged as a middle layer between end‐devices and cloud environments to support the requirements of IoT applications that cannot be met by the current edge‐cloud model. A great effort has been devoted during the past few years to the development of this fog vision. Most of these solutions focused on improving specific characteristics, but not on supporting all the key requirements of an IoT solution. Thus, a deep investigation of these solutions to understand how they can be connected and coordinated to meet these necessities is essential. In this paper, we distinguish the most vital necessities that IoT solutions present to accomplish a right operation. Also, by analyzing the available solutions, we propose a novel global architectural model for fog computing meeting the recognized demands. We also provide a novel scientific taxonomy for breaking down the overviewed solutions. We conclude by analyzing the most essential recommendations in Fog computing for IoT, thereby distinguishing open issues and research frontiers that must be prioritized in order to have a totally developed fog computing environment, ready to meet the IoT solutions' prerequisites.

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 Ministerio de Ciencia, Innovación y Universidades RTI2018-094591-B-I00 Ministerio de Ciencia, Innovación y Universidades PGC2018-094905-B-I00 Junta de Andalucía APOLO (US-1264651) Ministerio de Ciencia e Innovación HORATIO (RTI2018-101204–B–C21) Ministerio de Ciencia, Innovación y Universidades RED2018-102654-T Interreg V-A España-Portugal (POCTEP) 0499-4IE-PLUS-4-E Junta de Andalucía UMA18-FEDERJA-180 Junta de Extremadura GR18112 Junta de Extremadura IB18030

In the mobile device market there is a large number of applications to help people monitor intake or provide suggestions to lose weight and manage a healthy diet. However, the vast majority of these apps consume a lot of time by having to introduce food one by one. This paper presents the work to develop and pilot test a new Android application, FoodScan, aimed at people over 70, specially those from rural environments or with limited technical knowledge, to manage their food from the items that appear on their grocery receipts, avoiding the obligation to introduce one by one those foods, and generating recommendations. To achieve this final objective, specific objectives have been completed as indicated in the methods section. We conducted a review of current calorie control applications to learn about their weaknesses and strengths. Different algorithms were tested to expedite the introduction of food into the application and the most suitable for the FoodScan application was selected. Likewise, several options were taken into account to create the knowledge base of food, taking into account dietary recommendations for people over 70 years. Once developed, a pilot evaluation was carried out with a convenience sample of 109 volunteers in rural areas of Caceres and Valladolid (Spain) and Alentejo (Portugal). They tested FoodScan for a month after which they completed a user satisfaction survey. 93 % (101/109) believed that the app was easy to download and install, 66 % (72/109) thought that it was easy to use, 47 % (51/109) noted that the charts with the recommendations helped them with diet control and 49 % (53/109) indicated that FoodScan helped them improve healthy eating habits. One-month pilot evaluation data suggested that most users found the app somewhat helpful for monitoring food intake, easy to download and easy to use.

The growing informatization of the environment allows modeling people’s behavior as a social workflow, where both individual actions and interactions with other people are captured. This modelling includes actions that are part of an individual’s routine, as well as less frequent events. Although infrequent actions may provide relevant information, it is routine behaviors that characterize users. However, the extraction of this knowledge is not simple. There are problems when analyzing together large amounts of traces from many users, resulting into a social workflow that does not clearly depict their behavior, either individually or as a group. Tools that allow grouping/filtering of users with a common behavior pattern are needed, to analyze each of these groups separately. This study presents the federated process mining and an associated tool, SOWCompact. Its potential is validated through the case study called activities of daily living (ADL). Using federated process mining, along with current process mining techniques, more compact processes using only the social workflow’s most relevant information are obtained, while allowing the analysis of these social workflows. Universidad de Málaga. Campus de Excelencia Internacional Andalucía Tech

The Internet of Things (IoT) is more present in our daily lives than ever before, turning everyday physical objects into smart devices. However, these devices often need excessive human interaction before reaching their best performance, making them time-consuming and reducing their usability. Nowadays, Artificial Intelligence (AI) techniques are being used to process data and to find ways to automate different behaviours. However, achieving learning models capable of handling any situation is a challenging task, worsened by time training restrictions. This paper proposes a Federated Learning solution to manage different IoT environments and provide accurate predictions, based on the user’s preferences. To improve the coexistence between devices and users, this approach makes use of other users’ previous behaviours in similar environments, and proposes predictions for newcomers to the federation. Also, for existing participants, it provides a closer personalization, immediate availability and prevents most manual interactions. The approach has been tested with synthetic and real data and identifies the actions to be performed with 94% accuracy on regular users.

The flexibility and programmability provided by the Software-Defined Networking (SDN) paradigm allow network operators to upgrade their legacy IP network infrastructures with the aim of improving their control over the network. However, the full migration from IP to SDN is not straightforward, at least, in the short term. Thus, transitory network infrastructures combining IP and SDN nodes (named hybrid IP/SDN networks) are required to coexist, while the correct coordination between paradigms is crucial to maintain the required Quality of Service. In this paper, two optimization problems that are normally solved separately due to their opposite nature: i) traffic load balancing and ii) the reduction of network power consumption, are jointly considered. In particular, an heuristic named Hybrid Spreading Load Algorithm (HSLA), is proposed to jointly minimize the Maximum Link Utilization (MLU) and the network power consumption during the transition from IP to SDN networks. Simulations over topologies of different size considering diverse selection methods for the replacement of the nodes reveal that HSLA outperforms other state-of-the-art approaches that specifically tackle only one objective, either the traffic load balancing or the reduction of the network power consumption.

Nowadays, people’s medical records are crucial when it comes to providing treatments, discovering pathologies, or keeping track of health status. Advances in technology have allowed these records to be increasingly digitized, to the point that they can be consulted by specialists from anywhere. This also allows people to report their health status, allergies, or treatments. However, knowing a person’s medical history is a delicate and complex process, and accessing these digitized data is not always possible due to problems with network connectivity or physical communication with the person. In this work, we propose a solution for medical staff to obtain a patient’s medical history through facial recognition, and without the need for an internet connection. This proposal is based on the development of an architecture that allows connecting nearby mobile devices of doctors and patients without an internet connection to obtain the desired information using facial recognition as an authentication method. The architecture has been validated with the development of a mobile application that, by focusing on the patient’s face with the camera of the doctor’s mobile device, makes it possible to obtain the patient’s medical information. With this proposal, it is possible to obtain the medical history of a person in dangerous situations or where the connectivity is limited or non-existent, in a simple and fast way.

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 Internetconnected devices. To identify user context, these applications collect information from the user and his/her environment and typically lter 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 traf c. Accordingly, although context-aware applications can improve user experiences in their daily lives, they must ensure the maintenance of lowlevel 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 in uence 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.

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.

Opportunistic data sharing allows users to receive real-time, dynamic data directly from peers. These systems not only allow large-scale cooperative sensing but they also empower users to fully control what information is sensed, stored, and shared, enhancing an individual's control over their own potentially private data. While there exist context-aware frameworks that allow individual users to define when and what shared information peers can consume, these approaches have limited expressiveness and do not allow data owners to modulate the granularity of the information released depending on a particular peer or situation. In addition, these frameworks do not consider the consuming peers' privacy, i.e., how much information they have to provide to get access to some desired data. In this paper, we present PADEC, a context-sensitive, privacy-aware framework that allows users to define rich access control rules over their resources and to attach levels of granularity to each rule in order to precisely define who has access to what data when and at what level of detail. Our evaluation shows that PADEC is more expressive than other access control mechanisms and protects the provider’s privacy up to 90% more.

The growing number of devices in the Web of Things (WoT) allows larger and more complex smart environments. These environments aim to provide the desired state for the people, adapting the devices to their preferences. The characteristics of the environment, the people and the devices generate a multitude of interconnections and behaviours in specific situations. However, managing these situations is not straightforward because of their changing nature. Tools are needed to identify and automate these interactions according to the desired conditions. In this demo we present SMOTE (Situation Management fOr SmarT Environments), a tool for proactively managing situations in WoT environments, improving the management of different entities and reducing the effort for adapting devices to people’s preferences.

The increasing capabilities of end devices has led to a wider distribution of the computation and the massive deployment of distributed mobile applications. The success of these applications is highly dependent on the Quality of Service they provide. This quality is especially difficult to assess due to the large number of entities involved and their heterogeneity. Current tools are usually focused on evaluating the QoS provided by a single entity. Nevertheless, the QoS of distributed applications not only depend on the QoS of each entity, the interactions among entities has also to be evaluated. Therefore, new techniques are required to perform a comprehensive evaluation of the expected QoS of these applications before their production deployment. This paper presents a framework, called Perses, for launching virtual environments to simulate and test the execution of distributed mobile applications. This simulation provides results of the QoS achieved. Moreover, the framework has been integrated into a DevOps methodology in order to automate its execution. Video showcase- https://youtu.be/wpIApe_sPFE. Ministerio de Ciencia, Innovación y Universidades RTI2018-101204-B-C21 (HORATIO) Ministerio de Economía y Competitividad BELI (TIN2015-70560-R) Interreg V-A España-Portugal (POCTEP) 0499-4IE-PLUS-4-E Ministerio de Ciencia, Innovación y Universidades TIN2016-81978-REDT Junta de Extremadura GR18112 Junta de Extremadura IB18030 Junta de Andalucía APOLO (US-1264651)

The symptoms of depression cause patients to face psychological barriers that dictate the search for treatment. Also, people’s daily behavior allows us to identify different symptoms of depression in combination with intelligent devices that accompany us in almost any situation and contain a large number of sensors. In this sense, mobile devices can be used to monitor people’s behavior and, thus, identify if people could have diseases such as depression. However, current technologies or applications require constant user intervention to provide an approximate diagnosis of possible symptoms, which is a major barrier for patients. This work presents a set of applications designed for mobile devices that passively detect the symptoms of depression, reducing possible obstacles in the identification of this disease. This detection is based on information obtained from mobile devices, such as device use, locations and text message content. In addition, this information can be monitored by experts in the field of health, with the aim of providing a more complete diagnosis. Therefore, thanks to the analysis of this information and the use of the developed applications, the detection of these symptoms is transparent to the person and can also be monitored by specialized health professionals.

Global population is facing a widespread ageing. In next decades, the increasing percentage of people over sixty-five will be significant, which will impact society in several ways. The health system will be one of the sectors specially involved, exploiting the technology as a perfect allied. However, a big percentage of adults live in rural areas where almost 40% of inhabitants are seniors and technological infrastructure is often insufficient. Thus, factors like isolation, loneliness and lack of eHealth solutions conform a difficult context for this population sector. In this paper, a solution to provide isolation monitoring to elders living alone in places with lack of Internet connectivity is proposed. The proposed architecture allows the detection of emergencies in elderly’s homes through presence patterns monitoring. Thus, potential home accidents or health emergencies can be detected. Furthermore, this model has been validated through simulations with the analysis of the required energy consumption, delivery probability and latency, obtaining a significant good performance.

Leveraging the Internet of Things (IoT) in intensive domains, such as in the Industrial Internet of Things (IIoT) or Internet of Medical Things (IoMT), provides automation and sensing solutions for complex environments through the interconnection of different sensors and actuators. However, these scenarios usually demand to meet stringent Quality of Service (QoS) requirements to work properly. Fog computing, a paradigm that brings computation and storage closer to the edge, and Software-Defined Networking (SDN), a networking paradigm that enables for network scalability and flexibility, can be combined. To do so, fog nodes that integrate both, computation resources and SDN capabilities, are leveraged to meet these stringent needs. Clearly, the placement of such fog nodes plays a key role in the achieved QoS. In this paper, an optimal fog node placement formulation is evaluated in an emulated fog and SDN environment. Results show that an optimal fog node placement can achieve a reduction of up to 59% in the network latency with a minimal jitter compared with other well-known placement methods.