Good health and well-being are primary goals within the list of Sustainable Development Goals (SDGs) proposed by the United Nations (UN) in 2015. New technologies, such as Internet of Things (IoT) and Cloud Computing, can aid to achieve that goal by enabling people to improve their lifestyles and have a more healthy and comfortable life. Pollution monitoring is especially important in order to avoid exposure to fine particles and to control the impact of human activity on the natural environment. Some of the sources of hazardous gas emissions can be found indoors. For instance, carbon monoxide (CO), which is considered a silent killer because it can cause death, is emitted by water heaters and heaters that rely on fossil fuels. Existing solutions for indoor pollution monitoring suffer from some drawbacks that make their implementation impossible for households with limited financial resources. This paper presents the development of IdeAir, a low-cost IoT-based air quality monitoring system that aims to reduce the disadvantages of existing systems. IdeAir was designed as a proof of concept to capture and determine the concentrations of harmful gases in indoor environments and, depending on their concentration levels, issue alarms and notifications, turn on the fan, and/or open the door. It has been developed following the Test-Driven Development Methodology for IoT-based Systems (TDDM4IoTS), which, together with the tool (based on this methodology) used for the automation of the development of IoT-based systems, has facilitated the work of the developers. Preliminary results on the functioning of IdeAir show a high level of acceptance by potential users. 

Throughout the evolution of software systems, empirical methodologies have been used in their development process, even in the Internet of Things (IoT) paradigm, to develop IoT-based systems (IoTS). In this paper, we review the fundamentals included in the manifesto for agile software development, especially in the Scrum methodology, to determine its use and role in IoTS development. Initially, 4303 documents were retrieved, a number that was reduced to 186 after applying automatic filters and by the relevance of their titles. After analysing their contents, only 60 documents were considered. Of these, 38 documents present the development of an IoTS using some methodology, 8 present methodologies focused on the construction of IoTS software, and 14 present methodologies close to the systems life cycle (SLC). Finally, only one methodology can be considered SLC-compliant. Out of 38 papers presenting the development of some IoTS following a methodology for traditional information systems (ISs), 42.1% have used Scrum as the only methodology, while 10.5% have used Scrum combined with other methodologies, such as eXtreme Programming (XP), Kanban and Rapid Prototyping. In the analysis presented herein, the existing methodologies for developing IoTSs have been grouped according to the different approaches on which they are based, such as agile, modelling, and service oriented. This study also analyses whether the different proposals consider the standard stages of the development process or not: planning and requirements gathering, solution analysis, solution design, solution coding and unit testing (construction), integration and testing (implementation), and operation and maintenance. In addition, we include a review of the automated frameworks, platforms, and tools used in the methodologies analysed to improve the development of IoTSs and the design of their underlying architectures. To conclude, the main contribution of this work is a review for IoTS researchers and developers regarding existing methodologies, frameworks, platforms, tools, and guidelines for the development of IoTSs, with a deep analysis framed within international standards dictated for this purpose. 

In our recently published paper, we met a bunch of amazing elders and provided them with some gadgets, wristbands mainly, and we followed them while they performed a shopping task. Our health experts had previously evaluated the dependence of the elderly. With both sets of data, coming from our health experts and from the sensors of the wristband, we created a machine learning model that predicts, with 97% accuracy, the degree of dependence of the elders. Hence, we probed that we can automatically measure the dependence of the elderly in an unintrusive manner, just with a wristband. These results can save GPs time and can save cost to the health systems by the early detection of dependence. We believe that sensors and machine learning can help doctors in the automation and early detection of health issues.

Sometimes we do not have enough labeled data to train our machine learning models, especially with deep learning.  In that case, instead of using discriminative techniques, we could use generative techniques. In this work, we analyzed several deep generative algorithms their advantages and disadvantages, and some challenges ahead. We plan to try some of these algorithms to improve our studies.

To develop software to stimulate cognitive functions of attention, memory, reasoning, planning, language, and perception in Mexican older adults, and to evaluate the usability of software based on system utility, information quality, and interface quality.

For the development of the cognitive stimulation software, an inductive-deductive methodology was used in three stages: Analysis (system requirements), design and coding (cognitive stimulation software), evaluation (usability results).

The usability of the software was assessed in 89 older adults between the ages of 60 and 84 years, through a usability questionnaire with evidence of reliability and validity.

Eight exercises about attention, seven on memory, three on reasoning, one about planning and language, and two on perception were developed. We evaluated the usability of the developed software using the Computer System Usability Questionnaire, obtaining medium-high usability in 76.2% of the participants regarding the system utility, in 77.7% concerning the information quality and, in 84.2% in the interface quality.

The software was developed considering aspects of usability and based on changes and losses associated with aging, as well as on the stimulation of cognitive functions related to instrumental activities of daily living, including exercises based on traditional pencil-paper exercises.

In this work, we could detect basic movement intentions with low-cost headbands (wearables) in only a couple of seconds. Our next step is to develop an app that could press screen buttons just with the imagination (and a little help of the headband and our deep learning algorithms). With this research, we tried to empower low-mobility people with low-cost and low-intrusive devices.

The population in developed countries is aging and this fact results in high elderly health costs, as well as a decrease in the number of active working members to support these costs. This could lead to a collapse of the current systems. One of the first insights of the decline in elderly people is frailty, which could be decelerated if it is detected at an early stage. Nowadays, health professionals measure frailty manually through questionnaires and tests of strength or gait focused on the physical dimension. Sensors are increasingly used to measure and monitor different e-health indicators while the user is performing Basic Activities of Daily Life (BADL). In this paper, we present a system based on microservices architecture, which collects sensory data while the older adults perform Instrumental ADLs (IADLs) in combination with BADLs. IADLs involve physical dimension, but also cognitive and social dimensions. With the sensory data we built a machine learning model to assess frailty status which outperforms the previous works that only used BADLs. Our model is accurate, ecological, non-intrusive, flexible and can help health professionals to automatically detect frailty.

In most developed countries, the population is gradually ageing. Due to this, there is an increasing demand for technologies whose design is specifically oriented towards meeting the needs of the elderly. In this paper, we describe a web-based cognitive training tool for elderly people, called VIRTRAEL, which comprises 18 exercises presented in 13 working sessions. In order to reach a high degree of user acceptance, we have applied a user-centred development methodology and a guide defining a set of design principles and usability guidelines specifically intended for older people. Moreover, a usability questionnaire to assess VIRTRAEL has been especially designed to be completed by this type of users. Both guide and questionnaire can be easily applied in other software developments, and especially in those related to the specific domain of cognitive training for this user group. As a means to objectively measure the usability of VIRTRAEL, an EFA (Exploratory Factor Analysis) has been conducted on a 32-item questionnaire with 149 subjects. The results confirm that our proposal is usable and highlight some differences between user groups (female versus male users, and those who live alone versus those living with other people) that should be taken into consideration in future developments. 

The objective of this study was to evaluate the effects of a cognitive stimulation software on attention, memory, reasoning, planning and frequency of activities of daily living, in Mexican older adults. To carry out this research, an experimental research design was used, comprising two groups (experimental, n=28 and control on a waiting list, n=33) with pre- and post-evaluation, where adults over 60 years of age gathered in meeting centers to complete a sociodemographic data sheet, a psychometric test that evaluates attention, memory, reasoning, planning, and an inventory of activities of daily living of the elderly. The participants interacted with the software via touchscreens for 12 cognitive stimulation exercises. The results indicate improvements in the participants’ attention and concentration, and in the types of work, logic, and spontaneous memory, as well as a significant increase in the frequency of instrumental activities in the home by participants of both sexes, and in the social activities of the men. It was concluded that cognitive stimulation software can be used in Mexican older adults to achieve improvements in cognitive functioning. This is justified due to the importance of maintaining cognitive abilities in old age, since their deterioration affects activities of daily living, which are essential for an independent life.

In collaboration with the EU H2020 projects: IoTCrawler and ACTIVAGE, we developed a light model to semantically annotate streams. IoT-Stream takes advantage of common knowledge sharing of the semantics, but keeps the inferences and queries simple.

The system architecture is based on commonly used architectures in the field of IoT, such as web services, microservices, and middleware. Our system approach includes the semantic annotations that take place in the pipeline of IoT services and sensory data analytics. It includes modules needed to annotate, consume, and query data annotated with IoT-Stream.

We developed tools that could be used in conjunction with the IoT-Stream model and facilitate the use of semantics in IoT, and provide examples of instantiation of the system for different use cases.

Our society is growing old and health resources are shrinking. The early detection of some problems in elder adults could leverage the health systems and provide longer and healthy living. Mobile health (m-Health) systems can inform elderly people who live alone continuously about their health status by ubiquitously collecting and analysing data from sensors (in the environment and wearables) and smartphones. The sensors in the m-Health systems can not only collect the physical dimension of health but also the cognitive and mental dimensions. This up-to-date health status information could help caregivers and doctors in the prevention of illnesses and accidents.

We have designed an m-Health system with wearables and smartphones. The software architecture is based on the Fog/Edge paradigm and microservices, which provides efficiency, scalability, flexibility, adaptation, and maintainability. The system uses several artificial intelligence techniques. On the one hand, a rule-based subsystem detects activities of daily living (ADLs) from events (shopping, visiting the health centre, making a phone call, specific values of sensors, etc.) On the other hand, a machine learning module infers the health status of the user.

Currently, we are working on the continuous collection (in the cloud) of heterogeneous data from sensors and their analysis. Our current case study consists of the detection of stress and its causes, while the elderly are carrying out ADLs. Our system allows registering activities, environmental data, and feelings.

This system is ubiquitous, centered on the elder, and can detect the first symptoms of deterioration and inform caregivers or doctors about the health status changes for early interventions.

This paper presents a development methodology for Internet of Things (IoT)-based Systems (IoTS) that gathers ideas from several of the most outstanding software development paradigms nowadays, such as Model-Driven Engineering (MDE) and Test-Driven Development (TDD), in addition to incorporating the principles that govern agile software development methodologies, such as SCRUM and XP. The methodology presented here, called Test-Driven Development Methodology for IoTS (TDDM4IoTS), has been proposed after an exhaustive review of different software development methodologies, leading us to conclude that none of them are specially oriented towards the development of IoTS. The methodology mainly consists of eleven phases, whose order of application can be established by the team that will develop the project in question. In this paper, we suggest an order to follow, as well as existing software tools that could be used as support for obtaining the corresponding deliverables at each phase.

The increasing adoption of mobile computing technology in the health and social domains offers new possibilities, for instance, promoting active aging. Health deterioration in elderly people could be successfully assessed by monitoring activities of daily living (ADLs) through mobile technology. In particular, frailty affects several dimensions (physical, psychological, and social) of human functioning, which are required to perform instrumental ADLs (IADLs). Starting from the definition of a model, this paper proposes the design of an intelligent mobile health system to assess frailty in an ecological way: to automatize the frailty assessment through wearable sensors, unobtrusively in free-living environments, and using machine learning in order to reduce the traditional efforts of clinicians assessing frailty. It supports automatic data collection from sensors and artificial intelligence analysis during the performance of real IADLs by elderly. The proposed system uses mobile/wearable devices, follows a microservices software architecture, and implements machine learning algorithms. A technical validation of the proposal is shown.

In our recently published paper, we met a bunch of amazing elders and provided them with some gadgets, wristbands mainly, and we followed them while they performed a shopping task. Our health experts had previously evaluated the dependence of the elderly. With both sets of data, coming from our health experts and from the sensors of the wristband, we created a machine learning model that predicts, with 97% accuracy, the degree of dependence of the elders. Hence, we probed that we can automatically measure the dependence of the elderly in an unintrusive manner, just with a wristband. These results can save GPs time and can save cost to the health systems by the early detection of dependence. We believe that sensors and machine learning can help doctors in the automation and early detection of health issues.