Natalia Díaz Rodríguez

A survey on ontologies for human behavior recognition

Describing user activity plays an essential role in ambient intelligence. In this work, we review different methods for human activity recognition, classified as data-driven and knowledge-based techniques. We focus on context ontologies whose ultimate goal is the tracking of human behavior. After studying upper and domain ontologies, both useful for human activity representation and inference, we establish an evaluation criterion to assess the suitability of the different candidate ontologies for this purpose. As a result, any missing features, which are relevant for modeling daily human behaviors, are identified as future challenges.

A fuzzy ontology for semantic modelling and recognition of human behaviour

We propose a fuzzy ontology for human activity representation, which allows us to model and reason about vague, incomplete, and uncertain knowledge. Some relevant subdomains found to be missing in previous proposed ontologies for this domain were modelled as well. The resulting fuzzy OWL 2 ontology is able to model uncertain knowledge and represent temporal relationships between activities using an underlying fuzzy state machine representation. We provide a proof of concept of the approach in work scenarios such as the office domain, and also make experiments to emphasize the benefits of our approach with respect to crisp ontologies. As a result, we demonstrate that the inclusion of fuzzy concepts and relations in the ontology provide benefits during the recognition process with respect to crisp approaches.

Understanding Movement and Interaction: An Ontology for Kinect-Based 3D Depth Sensors

Microsoft Kinect has attracted great attention from research communities, resulting in numerous interaction and entertainment applications. However, to the best of our knowledge, there does not exist an ontology for 3D depth sensors. Including automated semantic reasoning in these settings would open the doors for new research, making possible not only to track but also understand what the user is doing. We took a first step towards this new paradigm and developed a 3D depth sensor ontology, modelling different features regarding user movement and object interaction. We believe in the potential of integrating semantics into computer vision. As 3D depth sensors and ontology-based applications improve further, the ontology could be used, for instance, for activity recognition, together with semantic maps for supporting visually impaired people or in assistance technologies, such as remote rehabilitation.

A Framework for Context-Aware Applications for Smart Spaces

This paper presents an approach for developing context-aware intelligent applications for Smart Space-based infrastructure. The goal is to model and process context information using our development tool and Nokias Smart-M3 architecture. We propose an adaptable and scalable context ontology, an ambient computing framework based on Smart Spaces and a rule based reasoning to infer higher level context. Our approach deals with several key issues in context aware ubiquitous computing such as adaptive and proactive changes in the environment, incorporation of novel sources of context information and automatic code generation from Context Ontologies to provide seamless interoperability.

Registered Nurses’ Experiences with the Medication Administration Process

Background. Registered nurses (RNs) have a role in the medication administration process (MAP) multiple times per day in a hectic hospital environment. This requires a great deal from the RNs in order to accomplish the demanding task of avoiding adverse drug events. However, the process has not been widely studied from the nurses’ perspective. Aim. The aim of this study was to describe the different stages of MAP from the RNs’ perspective. Methods. A qualitative descriptive research design, with a purposive sample involving thematic interviews of 20 RNs and questions to them in a paper form, was conducted in two medical units. Data was analyzed by using deductive content analysis. Results. The results revealed that RNs confront numerous problems such as equivocal prescriptions, problems with information technology (IT), unavailability or incompatibility of the medicines, a substantial amount of generic substitutions, and changing medicine brands. Disruptions and distraction run through each stage of the MAP, excluding prescribing. The RNs desire support in all stages of the MAP. Conclusion. There are areas to improve in each stage of the MAP from the RNs perspective. Real-time and ubiquitous documentation, along with software including the data and knowledge required in medication management, is needed.

Can IT health-care applications improve the medication tray-filling process at hospital wards? An exploratory study using eye-tracking and stress response

Filling medication trays and dispensing them at hospital wards is a painstaking, time-consuming and tedious task involving searching for medication in large shelves, double checking in the daily filled tray that the appearance, amount and concentration of each medication corresponds to the prescription, as well as analysing the timing conditions, among other details. Finally, if needed, finding equivalent compounds containing no secondary effects is also crucial, as well as being aware of the dynamically changing treatments in patients located, e.g., in surgery wards. Once the tray is filled, similar concerns and checks need to be done before dispensing the medication to the patient. We conducted a pilot in two university hospital wards using eye-tracking glasses and stress response to assess the tasks that take time the most and are most meticulous or stressing for the nurses. The aim is to use the findings to implement a mobile application that helps saving time and proneness to errors daily in such complex nursing procedures.

An approach to improve semantics in Smart Spaces using reactive fuzzy rules

Human behaviour representation and modelling in Smart Spaces are crucial tasks in Ambient Intelligence environments. A problem found among existing technologies is that the environment sensor data is always provided as crisp events. However, to model behaviour in reactive Smart Spaces we need to identify user patterns, which are not always performed in the same way or happening at the same time/frequency. Hence, the handling of imprecision is essential to model human behaviour in a realistic way. In order to connect these two paradigms, we suggest a combined architecture to fill the gap between quantitative Smart Space architectures (which provide raw crisp events) and qualitative aspects such as fuzzy reasoning and learning algorithms, that extract intelligence from data. With this aim, we propose to use Semantic Web principles of independence and interoperability to build an integrated framework to take advantage of the benefits of both crisp and fuzzy models. Our contribution in this work is a proof of concept to demonstrate how a hybrid architecture, with a reactive rule-based subscription mechanism, can empower users to model everyday activities semantically or control what happens on their surroundings, among other advantages.

Extending Semantic Web Tools for Improving Smart Spaces Interoperability and Usability

This paper explores the main challenges to be tackled for more accessible, and easy to use, Smart Spaces. We propose to use Semantic Web principles of interoperability and flexibility to build an end-user graphical model for rapid prototyping of Smart Spaces applications. This approach is implemented as a visual rule-based system that can be mapped into SPARQL queries. In addition, we add support to represent imprecise and fuzzy knowledge. Our approach is exemplified in the experimental section using a context-aware test-bed scenario.

Twenty Years of Interdisciplinary Studies: the "MEZA" Program's Contributions to Society, Ecology, and the Education of Postgraduate Students

Management of arid ecosystems (MEZA by its Spanish acronym) is a Master of Science program that started in 1990 when very few interdisciplinary programs in environmental management existed in the world. Graduates and current students recognize the importance of a group of pioneers in multidisciplinary practice who have translated the scientific findings and insights of a diverse scholarly community into practical applications within the city in which the University of Baja California, El Sauzal campus, is located and its surrounding arid and coastal rural areas. Students and teachers have produced 20 ecosystem management plans, which have trained the students in practical teamwork. Most of these plans addressed an inquiry by a local community or government decision maker, which is considered to be the key origin of a project. In this paper, the MEZA program that the teachers designed is briefly described, and a series of projects are given as examples of their work. Two projects are more thoroughly explained because all of the coauthors (2009 and 2010 students) participated in these projects and believe that it is a valuable experience to share with others.

Rapid prototyping of semantic applications in smart spaces with a visual rule language

One of the major limitations of Ambient Intelligent systems today is the lack of semantic models in human behavior and the environment, so that the system can recognize the specific activity being performed by the users and act accordingly. In this context, we address the general problem of knowledge representation in Smart Spaces. In order to monitor and act over human behavior in intelligent environments, we design a sufficiently simple and flexible visual language to be managed by non-expert users, thus facilitating the programming of the environment. The prototype of the visual language serves to represent rules about human behavior to provide the Smart Space with more usability. These rules can be mapped into SPARQL queries and rule subscriptions. In addition, we add support to represent imprecise and fuzzy knowledge. The proposed general-domain language can help managing resource allocation, assisting people with special needs, in remote monitoring and other domains.