Proceedings, 2018, UCAmI 2018

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. Full article

Currently, with the widespread penetration of mobile devices with Internet access, including the smartphones, they can allow specific and/or complementary activities in the health field as well as in other commercial sectors. To verify the impact of the studies about medical scientific publications relatives to cardiac mobile applications (app). This review corresponds to information in scientific journals of high impact. The intention of this review is respond to the follow question: How these research works have evaluated the performance of health mobile applications, with a special interest in cardiac issues? This review of these searches corresponds to an analysis by 4 categories, which are: Assessment of the wearables—Body Care, Use of sensors in the applications, app in health, Health Care—Comparisons of review app and app specialized commercial/clinical use. Only 6% of the app are associated with a medical professional, 15% is published by a professional medical society and 63% according to the opinions of the user. It provides evidence of how some apps have been evaluated, and in some cases the effectiveness of the estimated accuracy is not in line with the real situation. In Panama, a platform has been presented that permit the integration of health applications for patient follow-up. AmI-HEALTH has been developed to provide a mechanism for self-management of hypertensive patient data, by re-cording elements such as blood pressure (systolic, diastolic and pulse). In this point is very important to remember to the near relation between the Cardiac Issues and the hypertension condition. This makes us reflect on the true implications that bring us closer to these technological innovations. Today, our world is so changing and globalized. Full article

Video games and electroencephalography (EEG) can be used together in more than one way: cognitive analysis, mood analysis or Brain-Computer Interfaces (BCI), for instance. Nowadays, these two fields are gaining popularity when working together. We have consider that it is important to know what approaches are the most used when using video games and EEG, so we have performed a systematic review through the literature about these two fields together to find the most relevant techniques. Once identified a list of techniques, we briefly explained for what they can be used. Also, we have made a ranking of these techniques by their popularity to get some perspective about them all. After the process, we have concluded that the used techniques are really diverse and that approaches used to BCI and cognitve analysis are very similar between them. Full article

Nutrition e-coaches have demonstrated to be a successful tool to foster healthy eating habits, most of these systems are based on graphical user interfaces where users select the meals they have ingested from predefined lists and receive feedback on their diet. On one side the use of conversational interfaces based on natural language processing allows users to interact with the coach more easily and with fewer restrictions. However, on the other side natural language introduces more ambiguity, as instead of selecting the input from a predefined finite list of meals, the user can describe the ingests in many different ways that must be translated by the system into a tractable semantic representation from which to derive the nutritional aspects of interest. In this paper, we present a method that improves state-of-the-art approaches by means of the inclusion of nutritional semantic aspects at different stages during the natural language understanding processing of the user written or spoken input. The outcome generated is a rich nutritional interpretation of each user ingest that is independent of the modality used to interact with the coach. Full article

Personal Health Records (PHR) are electronic tools managed by the patients themselves, allowing them to store and consult health data anywhere and at any time using an electronic device. Precisely because of the type of users they are aimed at, it is essential to guarantee that PHR are easy to use. However, having a PHR that is usable does not mean that it is the best in terms of energy efficiency. Taking into account the large number of users that this type of portal is aimed at, achieving savings in energy consumption when running the portal’s tasks can have a considerable impact. In this paper we present an initial approach that studies the interaction between usability and energy efficiency of PHRs, attempting to determine if a given PHR makes efficient use of the resources it needs for the execution of its tasks. To do this, we have used the EET device, which allows us to collect the consumption of different hardware components when running software (in our case the PHR), and the usability criteria defined by Dix. Full article

Heart disease is currently one of the leading causes of death in developed countries. The electrocardiogram is an important source of information for identifying these conditions, therefore, becomes necessary to seek an advanced system of diagnosis based on these signals. In this paper we used samples of electrocardiograms of MIT-related database with ten types of pathologies and a rate corresponding to normal (healthy patient), which are processed and used for extraction from its two branches of a wide range of features. Next, various techniques have been applied to feature selection based on genetic algorithms, principal component analysis and mutual information. To carry out the task of intelligent classification, 3 different scenarios have been considered. These techniques allow us to achieve greater efficiency in the classification methods used, namely support vector machines (SVM) and decision trees (DT) to perform a comparative analysis between them. Finally, during the development of this contribution, the use of very non-invasive devices (2 channel ECG) was analyzed, we could practically classify them as wearable, which would not need interaction by the user, and whose energy consumption is very small to extend the average life of the user been on it. Full article

Deep learning has for a long time been recognized as a powerful tool in the field of medicine for making predictions or detecting abnormalities in a patient’s data. However, up until recently, hosting of these neural networks has been relegated to the domain of servers and powerful workstations due to the vast amount of resources they require. This trend has been steadily shifting in the recent years, and we are now beginning to see more and more mobile applications with similar capabilities. Deep neural networks hosted completely on mobile platforms are extremely valuable for providing healthcare services to remote areas without network connectivity. Yet despite this, there is very little information regarding the migration process of an existing server-based neural network to a mobile environment. In this work, we describe the various techniques and considerations that should be taken into account when developing a deep-learning enabled mobile application with offline support. We illustrate the above by providing a concrete example through our experience in migrating to mobile an in-house developed medical application for detecting early signs of traumatic brain injuries. Full article

: Currently, advances in technology have permitted increases in the life expectancy of older adults. As a result, a large segment of the world population is 60’s years old, and over. Depression is an important disease in older adults is depression, which seriously affects the moods and behavior of elderly. Novel technologies for smart cities allow us to monitor people and prevent problematic situations related to this mental illness. In this paper, we propose a predictive model to automatically detect depression in older adults. The model is based on machine-learning techniques to analyze the data obtained by a sensor that monitores the daily activities of older adults. Also, the model was evaluated obtaining promising results. Full article

Autistic people have difficulties in recognizing and expressing emotions from/to other people. Technologies can help to facilitate the communication and understanding between autistic and other people. This work particularly investigates the requirements autistic adolescents have on technologies that can measure bodily responses to recognize their emotions. A smartwatch, smart-patch and infrared camera were evaluated as potential everyday use devices to measure emotion. User requirements on emotion recognition technologies were elicited through an online survey (73 completed responses) and ten semi-structured interviews with autistic adolescents. The smartwatch is the preferred product, followed by the smart-patch. Infrared cameras are deemed unsuitable devices. Full article

Software applications have been identified as potentially suitable tools to assist older adults in several aspects of their lives, like healthcare, emotional support and personal security. However, developing usable and useful applications for this population represents an important challenge, given that no systematic solutions have been proposed to support such a process. This article hypothesizes that a model-driven engineering (MDE) approach can help generate suitable user interfaces for elderly people, making the development process repeatable and allowing the systematic reuse of design knowledge about products for these end-users. To determine the validity of such hypothesis, the article presents the results of a case study where a healthcare supporting system for older adults, developed by using an MDE approach, was evaluated in four older adult care centers. The results obtained were highly positive, showing MDE as a possible path to address systematically the development of these applications. Full article

The fluctuation of affective states is a contributing factor to sport performance variability. The context surrounding athletes during their daily life and the evolution of their physiological variables beyond sport events are relevant factors, as they modulate the affective state of the subject over time. However, traditional procedures to assess the affective state are limited to self-reported questionnaires within controlled settings, thus removing the impact of the context. This work proposes a multimodal, context-aware platform that combines the data acquired through smartphones and wearable sensors to assess the affective state of the athlete. The platform is aimed at ubiquitously monitoring the fluctuations of affective states during longitudinal studies within naturalistic environments, overcoming the limitations of previous studies and allowing for the complete evaluation of the factors that could modulate the affective state. This system will also facilitate and expedite the analysis of the relationship between affective states and sport performance. Full article

The appropriate categorisation of written information by health professionals is very important to guarantee its accessibility. Unfortunately, the information technology tools that support professionals on that task imply a heavy workload, so that the responsibility for categorising the written content is often delegated to administrative staff. Well-known health ontologies such as SNOMED-CT or MeSH provide a representation of the clinical contents to be used by the information systems. This research proposes a computer based method to automatically extract and code the diagnostics, procedures and treatments according to health ontologies. A Knowledge Management System based on an extended version of Drupal is used to implement and evaluate this proposal. Results provide a positive evidence on the application of the method to support medical professionals. Full article

Performance Status (PS) variability is a powerful tool to evaluate overall condition, treatment needs and survival chances of cancer patients. Traditionally, its assessment has relied on the experience of oncologists when interpreting results of clinical tests and when interviewing the patients. Meanwhile, consumer-level activity trackers have obtained good results in behavior-change oriented intervention trials and Fitbit devices have demonstrated enough reliability to provide objective data related to physical activity, but the clinical possibilities of the data collected has been neglected. This work presents a system design for ubiquitous assessment of PS by means of objective and quantifiable data from different sources: medical history, self-reported quality-of-life questionnaires and a commercial activity tracker Fitbit Alta HR. The system proposed aims to contextualize and model the recovery process of breast cancer patients during chemotherapy treatment. Full article

An informal caregiver is exposed to an emotional overload, which can lead to high stress levels. To provide caregivers with awareness about their emotions, we propose an emotion-tracking platform based on Facebook status updates. For this purpose, we trained several classification models to assign emotions to Facebook status updates. Then, we developed a Facebook application that connected to each user’s profile, gathered their status updates, classified their emotions, and generated a summary. We tested the application with 54 participants, finding the relative precision to be 84%, while the platform was perceived to be valuable and novel. Participants thought the application allowed them to think about their emotions and the information they share. Full article

Behavioral sensing systems collect data from smartphones, wearables, and other devices with the aim of analyzing and making sense of them. In this work, we present InCense IoT, a collective sensing system which uses mobile and ubiquitous sensors for collecting behavior data of groups of participants in shared spaces. This paper describes the concept of collective sensing, an implementation onto InCense called InCense IoT, innovative features, advantages over individual-centric sensing systems. Finally, this paper presents results of a use case using it in monitoring behaviors in mother-child interactions. Full article

Chronic Obstructive Pulmonary Disease (COPD) is the third leading cause of death according to the World Health Organization (WHO). Like any chronic disease, the clinical process of COPD affects the patient’s life. Currently, clinical processes are inefficient, causing a loss of quality of life for patients and a high economic increase in the costs borne by family members, health systems and society. This paper presents a new approach to the redesign of the process for the management of COPD based on the use of the strategy of continuous improvement Business Process Management. This approach aims to improve the efficiency of the management of chronic diseases such as COPD, while achieving a higher quality of life and patient satisfaction. Full article

The most important risk factors for cardiovascular health are smoking and a sedentary lifestyle. This paper proposes Evitapp, a mobile application designed to promote physical activity and smoking cessation. The application does not use additional tracking devices, rather relying on phone sensors to track physical activity, and on users logging their behavior. Nineteen users tested the application over 10 days. Participants found the applications easy to use and used them approximately once per day. Even though the habits of the experiment participants did not change significantly, those who used the smoking cessation application reported decreasing their smoking habit. Full article

Affective Computing aims at developing systems to recognize, process and interpret emotions. This paper presents a sensorized toy with affective functionalities through cognitive services based on IBM Watson technology. The purpose of this research is to improve the quality of life through the assistance oftherapies with children and preadolescents to support emotion perception. This is focused from three points of view: (a) self-perception, (b) empathy and, (c) social-emotional skills. MAmIoTie was evaluated with 10 healthy preadolescent subjects to assess how effectively it analyzes users’ emotional perception. The results were generally positive in terms of analysis, though there were aspects that behaved in a way we did not expect. Full article

Supervised activity recognition algorithms require labeled data to train classification models. Labeling an activity can be performed trough observation, in controlled conditions, or thru self-labeling. The two first approaches are intrusive, which makes the task tedious for the person performing the activity, as well as for the one tagging the activity. This paper proposes a technique for activity labeling using subtle gestures that are simple to execute, and that can be sensed and recognized using smartwatches. The signals obtained by the inertial sensor in a smartwatch are used to train classification algorithms in order to identify the gesture. We obtained data from 15 participants who executed 6 proposed gestures in 3 different positions. 208 characteristics were computed from the accelerometer and gyroscope signals and were used to train two classification algorithms to detect the six proposed gestures. The results obtained achieve a precision of 81% for the 6 subtle gestures, and 91% when using only the first 3 gestures. Full article

Many services and commodities have been deployed in airport terminals to provide additional conveniences. About half of revenues of airports in Europe come from the on-site non-aeronautical services offered. For this reason, the optimization of the existing resources is critical to maximize the profitability of the rented spaces. The main objective of this work is to present the design and development of a simulator that models and emulates the behavior of categorized groups of travelers. The behavior is quantified in relation to the time that such travelers spend in the airport and the use that they made of the different spaces. With this tool, the managers can simulate the influence of the deployment of different resources in such travelers’ behavior. A real case study is used to show the validity and promising results of the software tool. Full article

The adaptation of cities to a future in which connectivity is at the service of the citizens will be a reality by creating interaction spaces and augmented urban areas. The research on this field falls within the scope of Smart Cities (SC) with the advantages that the common public spaces provide as new points for information exchange between the city, the urban furniture and their citizens. Kiosk systems have been recognized as an appropriate mean for providing event-aware and localized information to the right audience at the right time. Hence, in this article, we provide a vision of an eco-system of multifunctional urban furniture, where kiosks are part of them, designed not only for digital interaction but for sustainable use and symbolic integration into the urban environment as well. The proposed approach is conceived to drive services through digital urban nodes that facilitate tailored citizen-city communication and interaction. The central element of the designed platform consists on an intelligent digital kiosk which features a series of hardware and software components for sensing different environmental conditions, multimodal interaction with users and for conveying the captured data to the Cloud. The custom-based contents visualized to the users are controlled remotely through a management tool that allows to set-up and configure the digital kiosk. This system is not presented as an ad-hoc solution for one specific purpose but instead, it becomes a platform that can accommodate and solve the needs of every kind of user that populates urban shared-use spaces. Full article

In this paper, a sensor network architecture is presented. This work proposes an early warning system for river overflows. The sensor network consists of a river level sensor node that measures the distance between the sensor and the mass of water using a precision ultrasonic sensor. The recorded information is transmitted to a receiving node by radio frequency (915 MHz) using LoRa modulation. The receiving node is implemented in a Raspberry Pi, it processes the information in real time and publishes the alert using a social network (Twitter). Finally, a prototype of the river level node was tested, obtaining a measurement range from 20 cm to 2 m. The receiving node was located 500 m away from the sensor node, that received the data packets sent without loss of data. Full article

Patrolling and surveillance in cities around the world is a principal activity to guarantee the security of its citizens that is why nowadays the use of technology is of vital importance in order to identify offenses and criminal groups. The present article proposes the development of a model which generates dynamic routes applying artificial intelligence with the algorithm K-means, to identify critical points when patrolling a circuit within Ecuadorian territory. Also, the API tool from Google Maps is used to design the routes and the ways of transportation that are going to be utilized by the police agent. It showed good results in the testing phase and there has been developed a mobile application based on Android technology. Full article

Urban mobility optimization problem has a great focus in the context of Smart cities. To its solution a very important factor is the transport demand, which is mostly inferred using Big Data and Artificial Intelligence techniques from Automatic Fare Collection (AFC) and mobile devices data. In this paper a novel approach, based on Transport Demand Management techniques is proposed, using technology to produce a more active social involvement in the planning and optimization of mobility. This paper describes, a first step to this long-term objective, the general architecture and current implementation of an explicit multi-modal transport demand system for Smart Cities, which is being developed in the frame of MUSA—I project in the city of Madrid. Full article

The use of Crowd Simulation for re-enacting different real life scenarios has been studied in the literature. In this field of research, the interplay between ambient assisted living solutions and the behavior of pedestrians in large installations is highly relevant. However, when designing these simulations, the necessary simplifications may result in different ranges of accuracy. The more realistic the simulation task is, the more complex and computational expensive it becomes. We present an approach towards a reasonable trade-off: given a complex and computational expensive crowd simulation, how to produce fast crowd simulations whose results approximate the results of the detailed and more realistic model. These faster simulations can be used to forecast the outcome of several scenarios, enabling the use of simulations in decision-making methods. This work contributes with a simplified faster simulation model that uses a graph of queues for modeling an environment where a set of agents will navigate. This model is configured using Genetic Algorithms (GA) applied to data obtained from complex 3D crowd simulations. This is illustrated with a proof-of-concept scenario where a 3D simulation of one floor of a faculty building, with its corresponding students, is re-enacted in the network of queues version. The success criteria are achieving a similar total number of people in particular floor areas along the simulation in both the simplified simulation and the original one. The experiments confirm that this approach approximates the number of people in each area with a sufficient degree of fidelity with respect to the results that are obtained by a more complex 3D simulator. Full article

Travel Time plays a key role in the quality of service in road-based mass transit systems. In this type of mass transit systems, travel time of a public transport line is the sum of the dwell time at each bus stop and the nonstop running time between pair of consecutives bus stops of the line. The aim of the methodology presented in this paper is to obtain the behavior patterns of these times. Knowing these patterns, it would be possible to reduce travel time or its variability to make more reliable travel time predictions. To achieve this goal, the methodology uses data related to check-in and check-out movements of the passengers and vehicles GPS positions, processing this data by Data Mining techniques. To illustrate the validity of the proposal, the results obtained in a case of use in presented. Full article

The global population is ageing, as a consequence of this there will be a greater incidence of ageing related illnesses which cause cognitive impairment–such as Alzheimer’s disease. Within residential care homes, such cognitive impairment can lead to wandering of individuals beyond the boundaries of safety provided. This wandering, particularly in urban areas can be life threatening. This study introduces a novel solution to detect, and alert caregivers of, egress of at-risk inhabitants of a care home. This solution operates through a combination of wearable Bluetooth beacons and beam-formed listening devices. In an evaluation process involving 275 egress events, this solution proved to offer accurate operation with no incidence of false positives. Notably, this solution has been deployed within a real residential care home environment for over 12 months. Proposed future work discusses improvements to this solution. Full article

There is a growing social awareness about accessibility. The accessibility in cities and public spaces has become in an important issue in official agendas due to recent European directives. There are several studies on the way to improve accessibility in cities but they do not offer the possibility of view if solutions applied are valid over time. This paper proposes a method to measure the degree of accessibility of a city or urban area by using data from conflicting accessibility points collected by the own citizens. It will allow us to visualize in a concise way how accessible a city is and its progression in the time. Full article

The movement in favor of the use of bicycles as an alternative to mobility has been booming in the last two decades. This has been inserted within the policy of revaluation of the urban environment and improvement of the quality of life in the city. In this work we expose: an analytical model of cyclist transit, the design of a cycling simulator and a path analysis and visualization tool. The objective of this simulator is to determine the appropriate streets to install bikeways in the city of Puerto Madryn. The results of this work can be extrapolated to other intermediate cities, which present low density and high population growth, with a size of less than 150,000 inhabitants. Full article

Smart Cities aim to increase citizens’ quality of life. Smart Government is a part of Smart Cities domain aiming to enhance the communication and interactions of citizens and companies with government. The SIMPATICO framework combines machine and human intelligence to simplify e-services i.e., web accessible apps to accomplish administrative procedures online, and thus enable a more widespread adoption of electronic procedures. This paper reviews the impact of instrumenting e-services, in Galicia region in Spain, with SIMPATICO features, e.g., text and workflow simplication, autocompletion of personal data and public procedure documentation and support through crowdsourced questions and answers. Particularly, taking into account the lessons learnt at the first pilot evaluation with Elderly people, this paper describes the public procedure model proposed by SIMPATICO which backs the application of diverse strategies to better support users while facing the completion of complex administrative procedures. Full article

Location data is a powerful source of information to discover user’s trends and routines. A suitable identification of the user context can be exploited to provide automatically services adapted to the user preferences. In this paper, we define a Dynamic Bayesian Network model and propose a method that processes location annotated data in order to train the model. Finally, our model enables us to predict future location contexts from the user patterns. A case study evaluates the proposal using real-world data of a location-based social network. Full article

Blue Low Energy technology is playing an important role nowadays in ubiquitous systems, being the beacons a key element. The configuration of parameters related to the beacons, such as their transmission power or their advertising interval should be studied in order to build fingerprinting indoor positioning systems based on this technology as accurate as possible. In this work, we study the impact and the interplay of those parameters in static indoor positioning as well as the orientation effect in the calibration phase. To reduce the time of data collection, a semi-automatic system is introduced. Full article

The aim of this paper is to determine a thermally comfortable air temperature in an automated living room. This calculated temperature should serve as input for a user-specific and dynamic heating control in an automated living space. In addition to the usual physical factors (air temperature, humidity, air velocity and radiation temperature), individual clothing and activity should be taken into account. The calculation of such a temperature is based on different methods and indices which are usually used for the evaluation of the thermal comfort. The thermal insulation of the worn clothing is determined by 3 different methods. These is a radio frequency identification system, a thermal imaging camera system and a theoretical calculation of the clothing likely to be worn based on temperature data. The activity performed is only taken into account indirectly through the generated heart rate. All these methods are ultimately very well suited for use in temperature regulation in an automated home, but require further research and extensive evaluation. Full article

In this paper, we present a methodology for Real-Time Activity Recognition of Interleaved Activities based on Fuzzy Logic and Recurrent Neural Networks. Firstly, we propose a representation of binary-sensor activations based on multiple Fuzzy Temporal Windows. Secondly, an ensemble of activity-based classifiers for balanced training and selection of relevant sensors is proposed. Each classifier is configured as a Long Short-Term Memory with self-reliant detection of interleaved activities. The proposed approach was evaluated using well-known interleaved binary-sensor datasets comprised of activities of daily living. Full article

Music Education is a part of the Primary School curriculum in Spain. Students get only 45 min per week organized by group lessons. Thus, it is complicated for teachers to give individualized attention. Additionally, learning to play an instrument is difficult with the current method. In this paper, we propose a methodology and the development of a digital tool as a complement to learn flute at home, in a persuasive and guided manner, using the virtual teacher metaphor. Students can listen to the selected repertoire, recording their performances and receiving advices from their devices (smartphone or tablet). Finally, the teacher will receive feedback for the evolution of each student in order to offer individual advice in the classroom. Full article

Water management has become a global priority in recent decades. The demand for water resources is increasing in cities due to the increase in population and the intensive use of water in economic activities and ornamentation. The problem is exacerbated when cities are built on desert regions, this is the case of Lima which is the second largest city built on a desert after Cairo. In this type of cities, it is necessary to minimize water consumption in activities that do not cover the priority needs of the population. For this reason, one of the most important tasks in the management of water resources in Lima is the optimization of water use in irrigation of parks, malls and other public green areas, necessary to offer a good quality of life to citizens. This research develops a smart decision support system to optimize irrigation in city parks. The proposed methodology takes 4 variables: land area, temperature, park humidity and weather forecast. First, strategic segmentation of the total area of the park is carried out, followed by the use of low-cost sensors to construct real-time humidity and temperature maps of the land area. Afterwards, a fuzzy inference system (FIS) that incorporates the knowledge of agronomists to process vague information in terms of computer interpretable language, together with the data collected from the variables and humidity and temperature maps is built, to assess the need for irrigation of each segment of the park. A dashboard is made to facilitate the visualization of results, including humidity and temperature maps, the weather forecast for the area and the recommendation of the FIS, which supports decision-making on irrigation needs in each segment of the park. The methodology was applied in a case study that corresponds to a San Isidro park in the city of Lima. Significant expected savings were obtained in terms of water resources and monetary units, which demonstrates the viability of the application of this smart system oriented at supporting decision-making on smart irrigation in the city’s parks. Full article

Foodbar is a Cloud-based gastroevaluation solution, leveraging IBM Watson cognitive services. It brings together machine and human intelligence to enable cognitive gastroevaluation of “tapas” or “pintxos” , i.e., small miniature bites or dishes. Foodbar matchmakes users’ profiles, preferences and context against an elaborated knowledge graph based model of user and machine generated information about food items. This paper reasons about the suitability of this novel way of modelling heterogeneous, with diverse degree of veracity, information to offer more stakeholder satisfying knowledge exploitation solutions, i.e., those offering more relevant and elaborated, directly usable, information to those that want to take decisions regarding food in miniature. An evaluation of the information modelling power of such approach is performed highlighting why such model can offer better more relevant and enriched answers to natural language questions posed by users. Full article

Adaptation is very important in IOT systems, due to their continuously changing environments. Changes may come from different elements of the architecture underlying an IOT system. Existing literature pays special attention to changes in the Service layer using evolution agents or context aware approaches to manage adaptations to said changes. In this paper, we elaborate on eight challenges that developers face when building adaptive IOT systems. Such challenges take into account changes at the Services layer, but also in the Middleware and Physical layers. These challenges serve us as a research agenda to foster IOT technology. As a starting point, we design an architecture to deal with the posited challenges. Various of the architectural components are inspired on a reference architecture, and complemented by new components to manage dynamic adaptations in response to the identified challenges. Preliminary experiments provide an initial insight about the feasibility and/or impact of our adaptive architecture. Full article

Blockchain enables the creation of distributed ledgers as a type of database that is shared, replicated, and synchronized among the members of a network. In this paper we analyze how distributed ledgers can be used for empowering end-users to self-manage their own data, enabling third parties to access those data under a cryptographic management model. We propose a use case where both blockchain and smart contracts are employed by using cryptographic technology to enable user empowerment of data management in AmI. Finally, we analyze strengths and weaknesses of the proposed scenario. Full article

Recently blockchain technology has been advocated as a solution fitting many different problems in several applicative fields; among these fields there is the Internet of Things (IoT) too. In this paper we show the most significant properties of a blockchain, how they suite the use case of a cryptocurrency and how they map onto the needs of IoT systems. We claim that a blockchain does not provide a significant advantage with respect to other database technologies in a field such as Internet of Things where computational power comes at a premium, energy is often scarce and storage scalability is a major challenge. Full article

In the framework of the Internet of Things (IoT) and more specifically the Internet of Vehicles (IoV), vehicles are called upon to play a key role as mobile sensors. Their high mobility and the large amount of electronics they currently deploy allow them to act as mobile information collectors in the places where they circulate. Together with these capabilities, the deployment of communications systems that allow them to share this information will make possible the massive deployment of the so-called Cooperative Intelligent Transport Systems (C-ITS). In this context, this article presents RODEO as a methodology that allows vehicles to use the current mobile communications systems to make V2V (Vehicle to Vehicle) communications, minimizing the number of resources needed. This paper analyses the performance of RODEO (Rrm fOr unDerlay vEhicle cOmmunications) from the perspective of energy performance, understood as the number of bytes transmitted per watt consumed. Full article

IoT devices provide with real-time data to a rich ecosystems of services and applications that will be of uttermost importance for ubiquitous computing. The volume of data and the involved subscribe/notify signaling will likely become a challenge also for access and core netkworks. Designers may opt for microservice architectures and fog computing to address this challenge while offering the required flexibility for the main players of ubiquitous computing: nomadic users. Microservices require strong security support for Fog computing, to rely on nodes in the boundary of the network for secure data collection and processing. IoT low cost devices face outdated certificates and security support, due to the elapsed time from manufacture to deployment. In this paper we propose a solution based on microservice architectures and DNSSEC, DANE and chameleon signatures to overcome these difficulties. We will show how trap doors included in the certificates allow a secure and flexible delegation for off-loading data collection and processing to the fog. The main result is showing this requires minimal manufacture device configuration, thanks to DNSSEC support. Full article

Currently, there is an increasing interest in the use of Radio Frequency Identification (RFID) tags which incorporate passive or battery-less sensors. These systems are known as computational RFID (CRFID). Several CRFID tags together with a reader set up an RFID sensor network. The reader powers up the tags’ microcontroller and their attached sensor using radio frequency waves, and tags backscatter, not only their $EPC$ code but also the value of those sensors. The current standard for interrogating these CRFID tags is the EPC global Class 1 Generation 2 (EPC C1G2). When several tags are located inside the reader interrogation area, the EPC C1G2 results in very poor performance to obtain sensor data values. To solve this problem, a novel protocol for streaming sensor data is presented. The proposed protocol increases the Sensor Read Rate ( $SRR$ ), defined as the number of sensor data reads per second, compared to the standard. Additionally, this paper presents a prototype of an RFID sensor network to compare the proposed custom protocol with the standard, obtaining a 53% of improvement in $SRR$ with respect to the EPC C1G2. Full article

The wearable industry has experienced a notable growth over the last decade, especially in fitness or e-health trackers. These trackers bring new functionalities that require collecting a great amount of sensitive information about the user. This fact has made fitness trackers the target of deliberate attacks, e.g., eavesdropping, unauthorized account access, fake firmware update, and so on. For this reason, this paper describes a vulnerability study on one of the most popular fitness trackers in 2017, together with the mobile application associated to the tracker. The study results show what vulnerabilities of the communications among agents (i.e., wearable device, mobile application and server) could put at risk users sensitive information and privacy. Full article

In this work, we detail a methodology based on Convolutional Neural Networks (CNNs) to detect falls from non-invasive thermal vision sensors. First, we include an agile data collection to label images in order to create a dataset that describes several cases of single and multiple occupancy. These cases include standing inhabitants and target situations with a fallen inhabitant. Second, we provide data augmentation techniques to increase the learning capabilities of the classification and reduce the configuration time. Third, we have defined 3 types of CNN to evaluate the impact that the number of layers and kernel size have on the performance of the methodology. The results show an encouraging performance in single-occupancy contexts, with up to $92\%$ of accuracy, but a $10\%$ of reduction in accuracy in multiple-occupancy. The learning capabilities of CNNs have been highlighted due to the complex images obtained from the low-cost device. These images have strong noise as well as uncertain and blurred areas. The results highlight that the CNN based on 3-layers maintains a stable performance, as well as quick learning. Full article

Fall detection can improve the security and safety of older people and alert when fall occurs. Fall detection systems are mainly based on wearable sensors, ambient sensors, and vision. Each method has commonly known advantages and limitations. Multimodal and data fusion approaches present a combination of data sources in order to better describe falls. Publicly available multimodal datasets are needed to allow comparison between systems, algorithms and modal combinations. To address this issue, we present a publicly available dataset for fall detection considering Inertial Measurement Units (IMUs), ambient infrared presence/absence sensors, and an electroencephalogram Helmet. It will allow human activity recognition researchers to do experiments considering different combination of sensors. Full article

Action recognition is important for various applications, such as, ambient intelligence, smart devices, and healthcare. Automatic recognition of human actions in daily living environments, mainly using wearable sensors, is still an open research problem of the field of pervasive computing. This research focuses on extracting a set of features related to human motion, in particular the motion of the upper and lower limbs, in order to recognize actions in daily living environments, using time-series of joint orientation. Ten actions were performed by five test subjects in their homes: cooking, doing housework, eating, grooming, mouth care, ascending stairs, descending stairs, sitting, standing, and walking. The joint angles of the right upper limb and the left lower limb were estimated using information from five wearable inertial sensors placed on the back, right upper arm, right forearm, left thigh and left leg. The set features were used to build classifiers using three inference algorithms: Naive Bayes, K-Nearest Neighbours, and AdaBoost. The F- $measure$ average of classifying the ten actions of the three classifiers built by using the proposed set of features was 0.806 ( $\sigma$ = 0.163). Full article

Optimal power usage and consumption require continuous monitoring, forecasting electric energy consumption and renewable generation. To facilitate integration of renewable energies and optimize their resources, new communication and data processing technologies are used in new projects. This article shows the works and results obtained in the eoTICC project. The objective is to design and develop an intelligent energy manager using the Archimedes wind turbine and a solar generation system, both integrated in industrial and residential power facilities. Solutions based on Artificial Intelligence paradigms and Internet of Things protocols allow automatic decision making to optimize energy management. In a facility, the energy demand and weather forecasts can be known by an intelligent energy manager. With these conditions, the energy manager can develop rules based on decision trees to automate control actions aimed at optimizing the use of energy. This article shows the architecture of IoT infrastructure and the first rules designed in the project. The result obtained provides improvements in the use of renewable energy in current facilities that do not use this type of intelligent management. The improvements allow to use the energy at the time of generation, avoiding unnecessary storage. Full article

The challenge of recognizing different personal activities while living in an apartment is of great interest for the AAL community. Many different approaches have been presented trying to achieve good accuracies in activity recognition, combined with different heuristics, windowing and segmentation methods. In this paper we want to revisit the basic methodology proposed by a naive Bayes implementation with emphasis on multi-type event-driven location-aware activity recognition. Our method combines multiple events generated by binary sensors fixed to everyday objects, a capacitive smart floor, the received signal strength (RSS) from BLE beacons to a smart-watch and the sensed acceleration of the actor’s wrist. Our new method does not use any segmentation phase, it interprets the received events as soon as they are measured and activity estimations are generated in real-time without any post-processing or time-reversal re-estimation. An activity prediction model is used in order to guess the more-likely next activity to occur. The evaluation results show an improved performance when adding new sensor type events to the activity engine estimator. Classification results achieve accuracies of about 68%, which is a good figure taking into account the high number of different activities to classify (24). Full article

The Human Health and Activity Laboratory (H²Al) is a new research facility at Luleå University of Technology implemented during 2018 as a smart home environment in an educational training apartment for nurses and therapists at the Luleå campus. This paper presents the design and implementation of the lab together with a discussion on potential impact. The aim is to identify and overcome economical, technical and social barriers to achieve an envisioned good and equal health and welfare within and from home environments. The lab is equipped with multiple sensor and actuator systems in the environment, worn by persons and based on digital information. The systems will allow for advanced capture, filtering, analysis and visualization of research data such as A/V, EEG, ECG, EMG, GSR, respiration and location while being able to detect falls, sleep apnea and other critical health and wellbeing issues. The resulting studies will be aimed towards supporting and equipping future home environments and care facilities, spanning from temporary care to primary care at hospitals, with technologies for activity and critical health and wellness issue detection. The work will be conducted at an International level and within a European context, based on a collaboration with other smart labs, such that experiments can be replicated at multiple sites. This paper presents some initial lessons learnt including design, setup and configuration for comparison of sensor placements and configurations as well as analytical methods. Full article

Data driven approaches for human activity recognition learn from pre-existent large-scale datasets to generate a classification algorithm that can recognize target activities. Typically, several activities are represented within such datasets, characterized by multiple features that are computed from sensor devices. Often, some features are found to be more relevant to particular activities, which can lead to the classification algorithm providing less accuracy in detecting the activity where such features are not so relevant. This work presents an experimentation for human activity recognition with features derived from the acceleration data of a wearable device. Specifically, this work analyzes which features are most relevant for each activity and furthermore investigates which classifier provides the best accuracy with those features. The results obtained indicate that the best classifier is the k-nearest neighbor and furthermore, confirms that there do exist redundant features that generally introduce noise into the classification, leading to decreased accuracy. Full article

Human behaviour analysis through smartphone devices has been an active field for more than a decade and there are still a lot of key aspects to be addressed. This paper surveys the state-of-the-art in human behaviour analysis based on smartphones. We categorise prior works into four main sensing modalities related to physical, cognitive, emotional and social behaviour. Finally, we conclude with the outcomes of this survey and we illustrate our ideas for future research in the area of human behaviour understanding. Full article

The Open Data Initiative (ODI) has been previously proposed to facilitate the sharing of annotated datasets within the pervasive health care research community. This paper outlines the requirements for the ODI portal based on the ontological data model of the ODI and its typical usage scenarios. In the context of an action research framework, the paper outlines the ODI platform, the design of a prototype user interface for the purposes of initial evaluation and its technical review by third-party researchers (n = 3). The main findings from the technical review were found to be the need for a more flexible user interface to reflect the different experimental configurations in the research community, provision for describing dataset usage, and dissemination conditions. The technical review also identified the value of permitting datasets with variable quality, as noisy datasets are useful in the testing of activity recognition algorithms. Revisions to the ODI ontology and platform are proposed based on the findings from this study. Full article

Windowing is an established technique employed within dense sensing environments to extract relevant features from sensor data streams. Among the established approaches of Explicit, Time-based and Sensor-Event based windowing, Dynamic windowing approaches are beginning to emerge. These dynamic approaches claim to address the inherent shortcomings of the aforementioned established approaches by determining the appropriate window length for live sensor data streams in real-time, thereby offering the potential to optimize and increase the recognition of these sensor represented activities. Beyond these potential benefits, dynamic approaches can also support anomaly detection by actively uncovering new, unknown window patterns within a trained model. This paper presents findings from a study which utilizes data from a single source dataset, towards benchmarking and comparing more traditional windowing approaches against a dynamic windowing approach. The experiments conducted on a real-world smart home dataset suggest Time-based windowing is the best approach. Through evaluation of results, Dynamic windowing approaches may benefit from carefully annotated datasets. Full article

Recent publications focus on the importance of designing an Ambient Intelligence that can be sensitive to human values and responsible for its societal impact. Obtaining and properly modeling these requirements can be a challenging task. Co-creation and social sciences methods are frequently applied in order to discover what end-users need using methods such as field/case studies where interviews or focus group sessions are conducted. However, those methods can be limited. This paper introduces two complementary approaches, one using traditional semi-structured and in-depth interviews, and another one based on 3D simulation modeling. The context is a research project where interviews were conducted to caregivers of people with Alzheimer disease. When designing the solution, it is important to account what kind of technology the end-users are expecting and what scenarios need to be accounted. So, the paper first summarizes what technology this collective is seeking or willing to accept. Then it proceeds with a brief summary of one of the interviews. Following, it shows the process of transferring this information to actual 3D simulations and discusses the benefits of doing so in the context of Ambient Assisted Living. Full article

This paper presents a cross-sectional study to analyze the impact on cognitive decline of a set of characteristics used for frailty assessment in elderly people. Considered characteristics come from several dimensions, including anthropometric, biological, nutritional, functional and mobility. Cognitive functioning is estimated by the Mini-Mental State Examination test. Additionally, mobility dimension is assessed from two perspectives: one based on direct observation of ambulation through subjective gait analyses; and the other performing explicit gait trials by using the instrumentation provided. In order to accomplish the purpose of this research, a multiple logistic regression analysis is carried out. Variables are grouped according to popular and/or standardized categories adopted in other clinical studies. Mini-Mental State Examination represents the dependent variable, while the characteristics for frailty assessment make up the set of explanatory variables. The multiple logistic regression is performed using a sample of 81 frail elders from two nursing homes in Spain. The results obtained indicate that frail elders aged 90 years of older, with moderate dependence in daily functioning, moderate risk of falls and with a stride interval gait variability greater than 6% were most likely to suffer cognitive decline, representing what is called cognitive frails. Full article

Studies on ambient computing technologies have shown their potential for assisting older adults to manage medications. However, their results cannot be generalizable, since they were conducted in different settings. We assessed the feasibility of a Medication Ambient Display (MAD) to improve the medication adherence of low-income Mexican older adults with mild-cognitive impairment (MCI). Through semi-structured interviews to 11 dyads of older adults and family caregivers who used MAD, we identified the effects of the setting conditions in the adoption and use of our technology. Our results showed that older adults forgot less to medicate. However, we observed that seniors have risky medication-related behaviors as a consequence of the challenges impose by our setting, such as the lack of adequate pharmaceutical policies regarding the rational use of medicines and the follow-up on patients’ medication regimens. We outline design implications for developing ambient computing technology to reduce drug adverse events associated with these challenges. Full article

The diversification and evolution of social media tools conveys users to adopt new systems and use new features of existing ones. Although this dynamism is suitably addressed by digital natives, it usually limits the technology adoption capability of digital immigrants, e.g., older adults, who react more slowly and with less confidence to the introduction of new computing systems. In order to support digital immigrants to deal with such a challenge, this paper proposes a ubiquitous system that mediates the communication supported by client applications and regular social interaction media such as, Gmail, WhatsApp, and Telegram. The system, named Social Message Translator, translates social media messages in both directions and self-adapts the process according to the behavior of end-users. Thus, it deals with the digital diversification of the former and also with the changes in the social media preferences of end-users. Consequently, digital immigrants are able to perceive as useful the supporting technology for longer time spans. The correctness of the message translation system was evaluated using a laboratory case study. The obtained results were highly positive, opening several opportunities to use this translator in several social interaction scenarios. Full article

Modelling ubiquitous collaborative systems that support people-driven processes represents a major challenge for software designers, since there is no a workflow that helps identify the scenarios in which the interaction among the participants could take place. Typically, this reduces the effectiveness of the resulting systems and increases the uncertainty during their developments. This paper proposes a visual modeling notation that allows designers to identify these potential interactions scenarios, and characterize them properly. The usability and expressiveness of this proposal was evaluated and compared to the most representative modeling notation reported in the literature to address this design challenge. The obtained results were highly positive, opening thus several opportunities to improve the design of ubiquitous collaborative systems. Full article

E-Learning is a response to the new educational needs of society and an important development in Information and Communication Technologies. However, this trend presents many challenges, such as the lack of an architecture that allows a unified management of heterogeneous string dictionaries required by all the users of e-learning environments, which we face in this paper. We mean the string dictionaries needed in information retrieval, content development, “key performance indicators” generation and course management applications. As an example, our approach can deal with different indexation dictionaries required by the course contents and the different online forums that generate a huge number of messages with an unordered structure and a great variety of topics. Our architecture will generate an only dictionary that is shared by all the stakeholders involved in the e-learning process. Full article

Small-animal phobias has been treated using in vivo exposure therapies (IVET) and virtual reality exposure therapies (VRET). Recently, augmented reality for exposure therapies (ARET) has also been presented and validated as a suitable tool. In this work we identified an ensemble of feedback factors that affect the user experience of patients using ARET systems for the treatment of small-animal phobias, and propose a taxonomy to characterize this kind of applications according to the feedback factors used in the application. Further, we present a customized version of the taxonomy by considering factors/attributes specific to the visual stimuli. To the best of our knowledge, no other work has identified nor provided an explicit classification or taxonomy of factors that affect the user experience of patients using this kind of systems for the treatment of small-animal phobias. Our final aim is to two-fold: (i) provide a tool for the design, classification and evaluation of this kind of systems, and (ii) inspire others to conduct further work on this topic. Full article

Early warning consists of monitoring precursors of a potential hazard to understand if it is evolving to a real risk and then be able to orchestrate an early response before the event happens in order to reduce its impact and damages. It mainly consists on collecting updated and reliable data that can help emergency operators to understand how a situation is evolving and project its consequences, that is, to support situation awareness on a potential risk. This process could be improved by integrating volunteers and citizens into the data collection process given that they are intelligent sensors equipped with mobile devices that can be used almost everywhere to collect and share information. In this paper we introduce a system relying upon ubiquitous computing to integrate citizens in checking the evolution of potential hazards. An asynchronous focus group technique to assess the system with EM professionals is also described in the paper. Full article

Effective preparedness for reacting in case of a severe emergency requires that many experts with various backgrounds evaluate the possible scenarios and come up with a single, unified plan which considers all opinions. This is a typical collaborative decision-making scenario, characterized by a process cycle involving modelling the process, defining the objectives of the decision outcome, gathering data, generating options and evaluating them according to the defined objectives. This is a decision-making scenario which requires the participation of various experts, who must evaluate and compare many scenarios. Each expert will have a partial knowledge about where people may be at the time of the emergency and how they will react. In emergency scenarios the geographical information often plays a significant importance, since plans need to consider the geography of the terrain from which the population should be evacuated, the safe areas where the population should be taken to, the ways connecting evacuations, and how the rescue teams can reach the places where the emergency occurred. This work presents a tool that can help a group of experts with various types of expertise, generate, visualize and compare the outcomes of various hypotheses. The paper also presents a real case simulation in the event of a tsunami following an earthquake at a site in northern Chile and the possibilities of evacuating people to safer zones. Full article

An application of Bluetooth beacons is here proposed to perform real-time tracking of the locations and movements of airport staff through different monitored airport infrastructure elements, such as rooms, terminals or boarding gates. With respect to this, the aim is to provide an efficient location service of airport workers and users through an indoor tracking controller based on fuzzy logic. For this purpose, a mobile application and a Web service have been implemented. This location knowledge may be decisive while performing common airport procedures or managing airport resources, staff or emergency situations aiming at ensuring a short response time. Likewise, the proposed system integrates an operational module of coordination to facilitate the communications of users at the airport. Besides, particular attention has been paid to the security of communication between mobile devices and the Web service, both regarding secure authentication of users and protection of confidentiality of information exchanged between airport staff. Full article

Migrants, ethnic minorities and people from culturally and linguistically diverse (CALD) communities are often more vulnerable to natural disasters due to cultural barriers and limited proficiency in the dominant language, which sometimes undermine their ability to access, interpret and respond to warnings. Technology can assist in engendering culturally and linguistically appropriate communication with CALD communities if key challenges are identified. This study contributes by reviewing relevant literature with the aim of ascertaining the most pressing challenges requiring technological interventions. Three broad issues (i.e., trust, message tailoring, and message translation) are identified and discussed, and potential solutions for addressing these issues are recommended. Full article

Internet of Things (IoT) have become a hot topic since the official introduction of IPv6. Research on Wireless Sensors Networks (WSN) move towards IoT as the communication platform and support provided by the TCP/UDP/IP stack provides a wide variety of services. The communication protocols need to be designed in such a way that even simple microcontrollers with small amount of memory and processing speed can be interconnected in a network. For this different protocols have been proposed. The most extended ones, MQTT and CoAP, represent two different paradigms. In this paper, we present a CoAP extension to support soft real-time communications among sensors, actuators and users. The extension facilitates the instrumentation of applications oriented to improve the quality of life of vulnerable communities contributing to the social good. Full article

Community wireless mesh networks have emerged as cooperative initiatives to provide Internet Access in areas where traditional ISP costs are not affordable for the population. It is common in wireless mesh networks sharing several capacity limited Internet gateways to provide Internet access. As routing does not handle capacity planning, end-users have to select gateways in such a way that the overall capacity of all gateways could be used effectively. An efficient gateway selection should minimize the processing logic and measurements over the mesh network. Selecting a high performance gateway can also ensure that the overall network load is balanced. This paper presents RIMO, a standalone best-effort algorithm for client nodes to select their preferred gateway without interacting with other client nodes. RIMO-based selection matches the gateway performance of the reference brute-force and omniscient algorithms for 60% of the test duration while reducing the gateway performance measurement cost from a factor of n to 2. With a reduced overhead and high efficiency, the RIMO algorithm automates the aggregation of multiple Internet gateways in wireless mesh networks, which results in robust last mile Internet connectivity to people in vulnerable situation. Full article

High rates of indigence characterize several countries in Latin America, such as Mexico. In the north of our country, the phenomenon of migration contributes to indigence. To get a preliminary understanding of the needs of indigents in our community, we conducted interviews with homeless and migrants. This helped us identify preliminary system requirements that led to the design of a digital bracelet to enable local agencies to monitor and provide support to the indigents who roam the city. We refined our conceptual design through an iterative process of contextual inquiry, persona development, prototyping, and user assessment. An evaluation of our design was conducted with the coordinator of the main social assistance agency of the municipality, which allowed us to confirm the system potential to be used and adopted. Full article

In recent decades, the environment has suffered the negative consequences of industrial development and overexploitation, and the effect of growing population. There are many areas and sectors where actions can be taken to minimize negative environmental impacts. Despite the current technological advances in society, there is a pending debt to nature, environment and care of air quality. This paper presents a system based on Wireless Sensor Networks, whose objective is to monitor environmental conditions in airport environments. Since the proposed system allows managing notifications and alerts when dangerous conditions are detected, it can also be considered a procedure to protect critical infrastructures in general. Due to the importance of security requirements in these facilities, the system includes several cryptographic measures to provide robust authentication and encryption of information. Full article

Detecting activities of daily living (ADL) allows for rich inference about user behavior, which can be of use in the care of for example, elderly people, chronic diseases, and psychological conditions. This paper proposes a domain knowledge-based solution for detecting 24 different ADLs in the UJA dataset. The solution is inspired by a Finite State Machine and performs activity recognition unobtrusively using only binary sensors. Each day in the dataset is segmented into: morning, day, evening in order to facilitate the inference from the sensors. The model performs the ADL recognition in two steps. The first step is to detect the sequence of activities in a given event stream of binary sensors, and the second step is to assign a starting and ending times for each of detected activities. Our proposed model achieved an accuracy of 81.3% using only a very small amount of operations, making it an interesting approach for resource-constrained devices that are common in smart environments. It should be noted, however, that the model can end up in faulty states which could cause a series of mis-classifications before the model is returned to the true state. Full article

Activity recognition (AR) is a subtask in pervasive computing and context-aware systems, which presents the physical state of human in real-time. These systems offer a new dimension to the widely spread applications by fusing recognized activities obtained from the raw sensory data generated by the obtrusive as well as unobtrusive revolutionary digital technologies. In recent years, an exponential growth has been observed for AR technologies and much literature exists focusing on applying machine learning algorithms on obtrusive single modality sensor devices. However, University of Jaén Ambient Intelligence (UJAmI), a Smart Lab in Spain has initiated a 1st UCAmI Cup challenge by sharing aforementioned varieties of the sensory data in order to recognize the human activities in the smart environment. This paper presents the fusion, both at the feature level and decision level for multimodal sensors by preprocessing and predicting the activities within the context of training and test datasets. Though it achieves 94% accuracy for training data and 47% accuracy for test data. However, this study further evaluates post-confusion matrix also and draws a conclusion for various discrepancies such as imbalanced class distribution within the training and test dataset. Additionally, this study also highlights challenges associated with the datasets for which, could improve further analysis. Full article

This work addresses the problem of human activity identification in an ubiquitous environment, where data is collected from a wide variety of sources. In our approach, after filtering noisy sensor entries, we learn user’s behavioral patterns and activities’ sensor patterns through the construction of weighted finite automata and regular expressions respectively, and infer the inhabitant’s position for each activity through frequency distribution of floor sensor data. Finally, we analyze the prediction results of this strategy, which obtains 90.65% accuracy for the test data. Full article

This short paper presents the activity recognition results obtained from the CAR-CSIC team for the UCAmI’18 Cup. We propose a multi-event naive Bayes classifier for estimating 24 different activities in real-time. We use all the sensorial information provided for the competition, i.e., binary sensors fixed to everyday objects, proximity BLE-based tags, location-aware smart floor sensing and the wrist’s acceleration. The results using training data-sets of 7 days show accuracies (true positives) about 68%; however for the three extra data-sets of the competition we were able to reach a 60.5% accuracy. Full article

Although there have been many studies aimed at the field of Human Activity Recognition, the relationship between what we do and where we do it has been little explored in this field. The objective of this paper is to propose an approach based on machine learning to address the challenge of the 1st UCAmI cup, which is the recognition of 24 activities of daily living using a dataset that allows to explore the aforementioned relationship, since it contains data collected from four data sources: binary sensors, an intelligent floor, proximity and acceleration sensors. The methodology for data mining projects CRISP-DM was followed in this work. To perform synchronization and classification tasks a java desktop application was developed. As a result, the accuracy achieved in the classification of the 24 activities using 10-fold-cross-validation on the training dataset was 92.1%, but an accuracy of 60.1% was obtained on the test dataset. The low accuracy of the classification might be caused by the class imbalance of the training dataset; therefore, more labeled data are necessary for training the algorithm. Although we could not obtain an optimal result, it is possible to iterate in the methodology to look for a way to improve the obtained results. Full article

We detail the solution to the UCAmI Cup Challenge to recognizing on going activities at home from sensor measurements. We use binary sensors and proximity sensor measurements for the recognition. We use an hybrid strategy, combining a probabilistic model and a definition-based model. The former consists of a Hidden Markov Model using the result of a neural network as emission probabilities. It is trained with the labelled data provided by the Cup. The latter approach takes advantage of the descriptions provided for each of the activities which are expressed in logical statements based on the sensors states. We then combine the results with a weighted average. We compare the performance of each individual strategy and of the combined strategy. Full article

Many real-world applications, which are focused on addressing the needs of a human, require information pertaining to the activities being performed. The UCAmI Cup is an event held within the context of the International Conference on Ubiquitous Computing and Ambient Intelligence, where delegates are given the opportunity to use their tools and techniques to analyse a previously unseen human activity recognition dataset and to compare their results with others working in the same domain. In this paper, the human activity recognition dataset used relates to activities of daily living generated in the UJAmI Smart Lab, University of Jaén. The dataset chosen for the first edition of the UCAmI Cup represents 246 activities performed over a period of ten days carried out by a single inhabitant. The dataset includes four data sources: (i) event streams from 30 binary sensors, (ii) intelligent floor location data, (iii) proximity data between a smart watch worn by the inhabitant and 15 Bluetooth Low Energy beacons and (iv) acceleration of the smart watch. In this first edition of the UCAmI Cup, 26 participants from 10 different countries contacted the organizers to obtain the dataset.‬‬‬‬‬ Full article