Resultados de búsqueda para context-awareness

It is well-known that context impacts running instances of a process. Thus, defining and using contextual information may help to improve the predictive monitoring of business processes, which is one of the main challenges in process mining. However, identifying this contextual information is not an easy task because it might change depending on the target of the prediction. In this paper, we propose a novel methodology named CAP3 (Context-aware Process Performance indicator Prediction) which involves two phases. The first phaseguides process analysts on identifying the context for the predictive monitoring of process performance indicators (PPIs), which are quantifiable metrics focused on measuring the progress of strategic objectives aimed to improve the process. The second phase involves a context-aware predictive monitoring technique that incorporates the relevant context information as input for the prediction. Our methodology leverages context-oriented domain knowledge and experts’ feedback to discover the contextual information useful to improve the quality of PPI prediction with a decrease of error rates in most cases, by adding this information as features to the datasets used as input of the predictive monitoring process. We experimentally evaluated our approach using two-real-life organizations. Process experts from both organizations applied CAP3 methodology and identified the contextual information to be used for prediction. The model learned using this information achieved lower error rates in most cases than the model learned without contextual information confirming the benefits of CAP3.This paper was published in IEEE Access, 2020, Vol. 8, pp. 222050 – 222063, doi: 10.1109/ACCESS.2020.3044670

Dealing with variability in open-ended environments requires robots to adapt themselves according to the perceived situation in order to achieve the required quality of service (defined in terms of safety, performance or energy consumption, among other criteria). In this sense, context awareness and runtime self-adaptation allows moving autonomous robot navigation one step forward. The ambition of the MIRoN Project was to provide a complete framework enabling designers to endow robots with the ability of self-adapting their course of action at runtime, according to the external and internal context information available. Our proposal relies on the systematic use of models for dynamically reconfiguring the robot behavior, defined in terms of Behavior Trees, according to the runtime prediction and estimation of quality of service metrics based on system-level non-functional properties.

Internet of Things (IoT) has radically transformed the world; currently, every device can be connected to the Internet and provide valuable information for decision-making. In spite of the fast evolution of technologies accompanying the grow of IoT, one of the remaining challenges in this scope is the design of a Service Oriented Architecture (SOA) for IoT, which facilitates the inclusion of data coming from several IoT devices as well the delivery of such data among system agents, real-time data processing and service provision to users. Furthermore, context-aware data processing and architec-tures still pose a challenge, regardless of being key requirements in order to get stronger IoT architectures. Besides, with the objective of sharing information across platforms, collaborative architectures for data sharing in the scope of the IoT are an essential re-quirement for giving additional value to any decision-making process. To sum up, IoT architectures should provide essential elements such as sensor devices, offered services, communication networks and event context processing; always promoting key features such as interoperability, reliability and scalability.
To face this challenge, we propose a COLLaborative ConText Aware Service Ori-ented Architecture (COLLECT), which facilitates: (1) Implementing reliable collabo-ration among several nodes through a collaborative Event Driven SOA. (2) Ensuring system scalability and interoperability through the opportunity of federating Enterprise Service Buses (ESB) in the cloud and through distributed Complex Event Processing (CEP). (3) Facilitating the task of processing information and publishing and subscrib-ing to distributed complex events of interest in the context of the application.

Air quality is one of the key topics in the focus of Internet of Things (IoT) appli-cations and smart cities, since it plays an essential role for citizens nowadays and is currently a worldwide concern. Indeed, air pollution can seriously affect citi-zens’ health; particularly, air pollution may worsen and favour certain illnesses or even cause death to specific risk groups. The fact is that due to this worldwide concern, several IoT systems for air quality monitoring have been created over the last years. Nevertheless, the problem is that monitoring alone is not enough; it is necessary to ensure compliance with the following requirements: (1) air quali-ty information and alerts have to be updated in real time; (2) the information has to be actively provided to citizens in a user-friendly way; (3) the information provided to users, in particular to risks groups, needs to be adapted to their spe-cific features and (4) the system should also take into account the type of activity the user is going to be involved in and adapt notifications accordingly.
Currently, most systems providing air quality information lack several of such key characteristics; as a result, information does not reach citizens in a sim-ple way and notifications neither consider citizens’ specific characteristics nor take their physical activity into account. In order to tackle these challenges effec-tively, and to pay special attention to context-awareness issues, we present Air4People: an air quality monitoring and context-aware notification system, which permits obtaining the user’s air quality relevant context, processing both the data coming from IoT air information sources and from the user context, and notifying users in real time when a health risk for their particular context is de-tected.

Traditional recommendation systems offer relevant items (e.g., books, movies, music, etc.) to users, but they are not designed for mobile environments. In those environments, the context (e.g., the location, the time, the weather, the presence of other people, etc.) and the movements of the users may be important factors to obtain relevant and helpful recommendations. The emergence of context-aware recommendation systems has prompted the growth of recommendation algorithms that incorporate context information. However, most existing research in this field considers only static context information, despite the fact that exploiting dynamic context information would be very helpful in mobile computing scenarios. Moreover, the design and implementation of generic frameworks to support an easy development of context-aware recommendation systems has been relatively unexplored. In this paper, we present our ongoing work to develop a context-aware recommendation framework for distributed and mobile environments, which will allow suggesting relevant items to mobile users.