Search

Breastfeeding is an unquestionable right of mothers and their children; however, it is not a one-womanjob. For breastfeeding to succeed, women must have access to appropriate support and guidance. The COVID-19 pandemic and subsequent restriction measures and lockdown to reduce community spread of the disease have negatively impacted breastfeeding support from health services and thus, in mothers’ breastfeeding experiences., Peer Reviewed, Postprint (published version)

Durant els darrers anys, el camp de la intel·ligència artificial i l’aprenentatge automàtic ha experimentat un creixement revolucionari gràcies als avenços en àrees com l’aprenentatge profund, i que han obert les portes a noves solucions, eines i tecnologies que fins ara eren impossibles d’implementar. Algunes d’aquestes aplicacions les trobem ja instaurades en el nostre dia a dia en àmbits com el reconeixement facial, la detecció d’anomalies en temàtiques molt diverses, la predicció borsària o meteorològica, i l’optimització de processos, entre molts d’altres. Actualment, però, la gran majoria estan encara en desenvolupament o es troben a l’espera de resoldre problemes relacionats amb la seguretat, la legalitat i fins i tot amb l’ètica dels agents intel·ligents implicats. S’estan plantejant situacions i conseqüències derivades de l’ús d’aquest tipus de sistemes que mai abans s’havien hagut de considerar. La quantitat de recursos econòmics i professionals que s’estan destinant a aquest camp és enorme, atès el seu potencial, tant per empreses privades com per altres institucions investigadores. És per això que existeix també força preocupació per l’ús d’aquesta tecnologia i els seus propietaris, ja que pot suposar un avantatge determinant sobre la resta d’empreses o països, i esdevenir un perill molt seriós voluntàriament o involuntàriament, per una desviació entre el comportament que esperem del sistema i el que n’obtenim. Per exemple, hi ha nombrosos exemples documentats d’agents intel·ligents que tenen un comportament esbiaixat per falta de contextsociocultural. (1) També cal tenir en compte que, com a eina digital que és, la seva integració en els processos actuals pot arribar a ser massa ràpida per a un món físic de persones que cal que acompanyi. L’automatització d’algunes tasques que fins ara desenvolupaven únicament els humans suposarà un canvi molt important en el tipus de feina del futur, raó per la qual cal anar-se preparant i mirar amb deteniment les repe, Durante los últimos años, el campo de la inteligencia artificial i el aprendizaje automático ha experimentado un crecimiento revolucionario gracias a avances en áreas como el aprendizaje profundo, y que han abierto las puertas a nuevas soluciones, herramientas y tecnologías que hasta ahora eran imposibles de implementar Algunas de estas aplicaciones las encontramos ya instauradas en nuestro día a día en ámbitos como el reconocimiento facial, la detección de anomalías de origen diverso, la predicción bursátil o meteorológica y la optimización de procesos, entre muchos otros. Sin embargo, actualmente la gran mayoría están aún en desarrollo o se encuentra a la espera de resolver problemas relacionados con la seguridad, la legalidad o incluso con la ética de los agentes inteligentes implicados. Se están planteando situaciones y consecuencias derivadas del uso de este tipo de sistemas que nunca antes habían sido necesarias de considerar. La cantidad de recursos económicos y profesionales que se están destinando a este campo es enorme, dado su potencial, tanto por empresas privadas como por otras instituciones investigadoras. Por ello, existe también bastante preocupación por el uso de esta tecnología y sus propietarios, ya que puede suponer una ventaja determinante sobre las demás empresas o países y convertirse en un peligro muy serio voluntaria o involuntariamente por una desviación entre el comportamiento esperado o deseado del sistema y el que obtenemos. Por ejemplo, existen numerosos ejemplos documentados de agentes inteligentes que tienen un comportamiento racista o sexista por haber usado datos sesgados durante el entrenamiento o por falta de contexto sociocultural. (1) Hay que tener en cuenta que, como herramienta digital que es, su integración en los procesos actuales puede llegar a ser demasiado rápida para un mundo físico de personas que es necesario que acompañe. La automatización de algunas tareas que hasta ahora desarrollaban únicamente los humanos supondrá, During the last years, the field of artificial intelligence and machine learning has experienced a revolutionary growth due to advances in areas such as deep learning, which have opened the doors to new solutions, tools and technologies that were impossible to implement until now. Some of these applications are already installed in our everyday life in areas like facial recognition, anomaly detection, weather and stock market forecasting and process optimization, among many others. Nonetheless, nowadays most of them are still under development or waiting for problems related to security, laws or even ethics of the intelligent agents to be solved. New situations and consequences arising from the use of this kind of systems are being considered for the first time. The amount of economic and professional resources that are being allocated to this field is huge, because of its potential, both by private companies and by other research institutions. For this reason, there is also a big concern about the use of this technology and its owners, since it can be a determining advantage over other companies or countries and become a very serious danger voluntarily or involuntarily due to a deviation between the behaviour that we expect or we want from the system and the one we actually get. For example, there are lots of documented cases of intelligent agents with racist or sexist behaviour because of the use of biased data during training or lack of sociocultural context. (1) We must consider that, as a digital tool it is, the integration of artificial intelligence into current processes may happen too fast for a physical world of people that will have to follow. The automation of some tasks that have been always carried out by humans will cause a very important change in the type of work of the future, which is why we must start preparing and thinking deeply about the impact of setting up a system with these characteristics. However, in today's world many processes are ineff

Resolved

Resolved

Resolved

Resolved

Resolved

Resolved

Resolved

Resolved

Resolved

© . This manuscript version is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0, This paper characterizes part of an interdisciplinary research effort on Artificial Intelligence (AI) techniques and tools applied to Environmental Decision-Support Systems (EDSS). WaWO+ the ontology we present here, provides a set of concepts that are queried, advertised and used to support reasoning about and the management of urban water resources in complex scenarios as a River Basin. The goal of this research is to increase efficiency in Data and Knowledge interoperability and data integration among heterogeneous environmental data sources (e.g., software agents) using an explicit, machine understandable ontology to facilitate urban water resources management within a River Basin., Peer Reviewed, Postprint (author's final draft)

Wastewater management is a complex task involving a wide range of technical environmental and social factors. Furthermore, it typically requires the coordination of a heterogeneous society of actors with different goals. Regulations and protocols can be effectively used to tackle this complexity. In this chapter we present a norm-aware multi-agent system for social simulations in a river basin. The norms we present are inspired in European policies for wastewater management and they can evolve through time., Peer Reviewed, Postprint (author's final draft)

With the growth of the Internet, computational systems have become more and more complex, often including complicate interconnected networks of autonomous components. The need to bring some organisational structure into autonomous systems becomes urgent, as this allows regulating the behaviour of the different autonomous components to ensure their objectives are aligned with the holistic objectives of the system. Normative Systems are one of the mechanisms that can be applied to define and enforce acceptable behaviour within distributed electronic systems which should comply with some (human) regulations. One of the requirements to effectively implement Normative Systems is to be able to assess, at runtime, the state of the normative environment. Existing lines of research have already tried to tackle this issue on some simple scenarios. However, more complex scenarios may appear, for instance, scenarios where the normative context is not static, but it expands and contracts as new norms are added to the institution and removed from it respectively. As in human legal systems, it is easy to foresee that some of these electronic normative environments will not be static. They should be able to evolve through time as regulations change, effectively adapting to new situations and behaviours. Under these conditions, a monitoring system must be able to continue computing the state of the normative environment at runtime, as often we can not afford to perform the changes on the normative context off-line. Furthermore, it must be guaranteed the monitoring system can keep producing states of the normative environment that are consistent with the changes performed on the normative context. For instance, if a norm has been removed from the normative context, it does not make sense anymore to compute normative states where the norm has been violated. In this thesis we present NoMoDEI, a normative monitoring framework for dynamic Electronic Institutions. We formalize and develop, Amb l'expansió d'Internet els sistemes computacionals han esdevingut més complexos, sovint incorporant complicades xarxes interconnectades de components autònoms. Es per això que la necessitat d'incorporar estructures organitzacionals en el sistemes autònoms s 'accentua, donat que aquestes estructures permeten regular el comportament dels diferents components autònoms, tot assegurant que els seus objectius es troben alineats amb els objectius generals del sistema. Els Sistemes Normatius (i.e. Normative Systems) són un dels mecanismes que podem aplicar per definir i imposar patrons acceptables de comportament dintre de sistemes electrònics distribuïts. Això esdevé especialment important quan el sistema es troba regimentat per regulacions (normalment humanes). Un dels requeriments per implementar Sistemes Normatius és ser capaços de determinar, en temps d'execució, l'estat de l'entorn normatiu. Existeixen línies de recerca que ja han tractat aquest problema en alguns escenaris simples. El món real però ens ofereix escenaris més complexes, com per exemple, escenaris on el context normatiu no és estàtic, si no que s'expandeix i contrau a mesura que noves normes són afegides o eliminades de la institució. Tal com passa als sistemes legals humans, és fàcil preveure que alguns contextos normatius electrònics no seran estàtics. Aquests contextos haurien de ser capaços d'evolucionar a través del temps a mesura que les regulacions canvien, adaptant-se a noves situacions i comportaments. Sota aquestes condicions, un sistema de monitorització ha de ser capaç de continuar calculant l'estat de l'entorn normatiu en temps d'execució, ja que sovint no ens podem permetre realitzar els canvis a l'entorn normatiu aturant el procés de monitorització. És més s'ha de garantir que el sistema de monitorització sigui capaç de continuar produint es tats de l’entorn normatiu de forma consistent amb els canvis realitzats. Per exemple, el fet d'eliminar una norma fa que no tingui gaire sentit co, Postprint (published version)

Location Based Social Networks (LBSN) like Twitter or Instagram are a good source for user spatio-temporal behavior. These networks collect data from users in such a way that they can be seen as a set of collective and distributed sensors of a geographical area. A low rate sampling of user’s location information can be obtained during large intervals of time that can be used to discover complex patterns, including mobility profiles, points of interest or unusual events. These patterns can be used as the elements of a knowledge base for different applications in different domains like mobility route planning, touristic recommendation systems or city planning. The aim of this paper is twofold, first to analyze the frequent spatio-temporal patterns that users share when living and visiting a city. This behavior is studied by means of frequent itemsets algorithms in order to establish some associations among visits that can be interpreted as interesting routes or spatio-temporal connections. Second, to analyze how the spatio-temporal behavior of a large number of users can be segmented in different profiles. These behavioral profiles are obtained by means of clustering algorithms that show the different patterns of behavior of visitors and citizens. The data analyzed was obtained from the public data feeds of Twitter and Instagram within an area surrounding the cities of Barcelona and Milan for a period of several months. The analysis of these data shows that these kind of algorithms can be successfully applied to data from any city (or general area) to discover useful patterns that can be interpreted on terms of singular places and areas and their temporal relationships., Peer Reviewed, Postprint (author's final draft)

The wide adoption of smart mobile devices makes the concept of human as a sensor possible, opening the door to new ways of solving recurrent problems that occur in everyday life by taking advantage of the information these devices can produce. In the case of this paper, we present part of the work done in the EU project SUPERHUB and introduce how geolocated positioning coming from such devices can be used to infer the current context of the city, e.g., disruptive events, and how this information can be used to provide services to the end-users., Peer Reviewed, Postprint (author’s final draft)

The term Smart City is tipically applied to urban and metropolitan areas where Information and Communication Technologies provide ways to enable social, cultural and urban development, improving social and political capacities and/or efficiency. In this paper we will show the potential of Artificial Intelligence techniques for augmenting ICT solutions to both increase the cities competiveness but also the active participation of citizens in those processes, making Smart Cities smarter. As example we will describe the usage of Artificial Intellgence techniques to provide Smart Mobility in the context of the SUPERHUB Project., Postprint (published version)

Cities concentrate enough Social Network (SN) activity to empower rich models. We present an approach to event discovery based on the information provided by three SN, minimizing the data properties used to maximize the total amount of usable data. We build a model of the normal city behavior which we use to detect abnormal situations (events). After collecting half a year of data we show examples of the events detected and introduce some applications., Peer Reviewed, Postprint (published version)

Location Based Social Networks (LBSN) have become an interesting source for mining user behavior. These networks (e.g. Twitter, Instagram or Foursquare) collect spatio-temporal data from users in a way that they can be seen as a set of collective and distributed sensors on a geographical area. Processing this information in different ways could result in patterns useful for several application domains. These patterns include simple or complex user visits to places in a city or groups of users that can be described by a common behavior. The domains of application range from the recommendation of points of interest to visit and route planning for touristic recommender systems to city analysis and planning. This paper presents the analysis of data collected for several months from such LBSN inside the geographical area of two large cities. The goal is to obtain by means of unsupervised data mining methods sets of patterns that describe groups of users in terms of routes, mobility patterns and behavior profiles that can be useful for city analysis and mobility decisions., Peer Reviewed, Postprint (published version)

This paper presents the results obtained of using LISP for real-time event detection and how these results are interpreted and used within the context of SUPERHUB, a European-Funded projected aimed to achieve a more sustainable mobility behaviour in cities. Real-time detection allows faster reaction for decision making processes as well as a valuable asset for policy makers to know what should be done when an unexpected event occurs. The use of LISP has facilitated most of this process and, specially, supported to parallelize the capture, aggregation and interpretation of data., Postprint (published version)

Assistive Technologies (AT) are an application area where several Artificial Intelligence techniques and tools have been successfully applied to support elder or impeded people on their daily activities. However, approaches to AT tend to center in the user-tool interaction, neglecting the user's connection with its social environment (such as care-takers, relatives and health professionals) and the possibility to monitor undesired behaviour providing both adaptation to a dynamic environment and early response to potentially dangerous situations. In previous work we have presented Coaalas, an intelligent social and norm-aware device for elder people that is able to autonomously organize, reorganize and interact with the different actors involved in elder-care, either human actors or other devices. In this paper we put our work into context, by first examining what are the desirable properties of such a system, analysing the state of the art on the relevant topics, and verifying the validity of our proposal., Postprint (author’s final draft)

Artificial Intelligence techniques and tools have been applied to Assistive Technologies (AT) in order to support elder or impeded people on their daily activities. A common application are intelligent pill dispensers and reminders that help the patient comply with his medication. This has become even more important, as patients suffering from multiple pathologies are prescribed cocktails of drugs that require strict compliance in order to achieve a successful treatment. Existing intelligent pill dispensers tend to focus in the user-tool interaction, neglecting user’s connection with its social environment and the possibility to monitor patient’s behaviour, effectively adapting to a dynamic environment and providing early response to potentially dangerous situations by detecting unexpected or undesired patterns of behaviour. In previous work we have presented COAALAS, an intelligent social and norm-aware device for elder people that is able to autonomously organize, reorganize and interact with the different actors involved in elder-care, either human actors or other devices. In this paper, we present SPiDer an intelligent pill dispenser integrated with the COAALAS architecture., Peer Reviewed, Postprint (author's final draft)

In agent research, emergent narrative aims for practical solutions to the narrative paradox problem in both drama and interactive scenarios. At the same time, organisational frameworks can be used in games to provide flexibility, adaptiveness, or social-awareness. In this paper, we propose an extension of our cOncienS framework to support emergent narrative in games with two objectives: 1) provide social-awareness in emergent narrative by means of an organisational model, and 2) create convincing dynamic and flexible storytelling in games., Peer Reviewed, Postprint (published version)

Non-compliance with prescribed medication is a major problem for elder people living alone in developed countries. Forgetfulness and confusion can lead to it, specially when multiple pathologies require a cocktail of diff erent medications each delivered at different time intervals during di fferent periods of time. Assistive technologies, a recent application area for a wide range of Arti cial Intelligence techniques and tools, have been e ectively used for supporting people in their daily activities. This paper introduces the design and implementation of a system for assisting elder people on following the treatment prescribed by a professional, with the novelty of being based in social and organisational aware assistive technology., Postprint (published version)

Assistive technologies are applied to support people in their daily life. Most approaches focus solely on the direct interaction between users – in our case, disabled patients - and the assistive tool, but Artificial Intelligence (AI) has the potential to provide innovative mechanisms and methods capable of taking into account more complex interactions. For instance, such an approach can take into account the important role that third parties may have in user activities, and explicitly reflect the social constraints that apply in the relationship between device and patient. In COAALAS (COmpanion for Ambient Assisted Living on Alive-ShareIt platforms), organizational and normative structures are used to model the sensor network around disabled users as societies, along with the expected behavioural patterns, effectively supporting smart assistive tools that integrate in perfect harmony with the humans around them. The result is an assistive society of ambient-aware assistive tools., Postprint (published version)