Carlos Fernandez-Llatas

Process Mining for Individualized Behavior Modeling Using Wireless Tracking in Nursing Homes

The analysis of human behavior patterns is increasingly used for several research fields. The individualized modeling of behavior using classical techniques requires too much time and resources to be effective. A possible solution would be the use of pattern recognition techniques to automatically infer models to allow experts to understand individual behavior. However, traditional pattern recognition algorithms infer models that are not readily understood by human experts. This limits the capacity to benefit from the inferred models. Process mining technologies can infer models as workflows, specifically designed to be understood by experts, enabling them to detect specific behavior patterns in users. In this paper, the eMotiva process mining algorithms are presented. These algorithms filter, infer and visualize workflows. The workflows are inferred from the samples produced by an indoor location system that stores the location of a resident in a nursing home. The visualization tool is able to compare and highlight behavior patterns in order to facilitate expert understanding of human behavior. This tool was tested with nine real users that were monitored for a 25-week period. The results achieved suggest that the behavior of users is continuously evolving and changing and that this change can be measured, allowing for behavioral change detection.

Process Mining Methodology for Health Process Tracking Using Real-Time Indoor Location Systems

The definition of efficient and accurate health processes in hospitals is crucial for ensuring an adequate quality of service. Knowing and improving the behavior of the surgical processes in a hospital can improve the number of patients that can be operated on using the same resources. However, the measure of this process is usually made in an obtrusive way, forcing nurses to get information and time data, affecting the proper process and generating inaccurate data due to human errors during the stressful journey of health staff in the operating theater. The use of indoor location systems can take time information about the process in an unobtrusive way, freeing nurses, allowing them to engage in purely welfare work. However, it is necessary to present these data in a understandable way for health professionals, who cannot deal with large amounts of historical localization log data. The use of process mining techniques can deal with this problem, offering an easily understandable view of the process. In this paper, we present a tool and a process mining-based methodology that, using indoor location systems, enables health staff not only to represent the process, but to know precise information about the deployment of the process in an unobtrusive and transparent way. We have successfully tested this tool in a real surgical area with 3613 patients during February, March and April of 2015.

When the Social Meets the Semantic: Social Semantic Web or Web 2.5

The social trend is progressively becoming the key feature of current Web understanding (Web 2.0). This trend appears irrepressible as millions of users, directly or indirectly connected through social networks, are able to share and exchange any kind of content, information, feeling or experience. Social interactions radically changed the user approach. Furthermore, the socialization of content around social objects provides new unexplored commercial marketplaces and business opportunities. On the other hand, the progressive evolution of the web towards the Semantic Web (or Web 3.0) provides a formal representation of knowledge based on the meaning of data. When the social meets semantics, the social intelligence can be formed in the context of a semantic environment in which user and community profiles as well as any kind of interaction is semantically represented (Semantic Social Web). This paper first provides a conceptual analysis of the second and third version of the Web model. That discussion is aimed at the definition of a middle concept (Web 2.5) resulting in the convergence and integration of key features from the current and next generation Web. The Semantic Social Web (Web 2.5) has a clear theoretical meaning, understood as the bridge between the overused Web 2.0 and the not yet mature Semantic Web (Web 3.0).

Activity-based Process Mining for Clinical Pathways Computer aided design

Current trends in health management improvement demand the standardization of care protocols to achieve better quality and efficiency. The use of Clinical Pathways is an emerging solution for that problem. However, current Clinical Pathways are big manuals written in natural language and highly affected by human subjectivity. These problems make the deployment and dissemination of them extremely difficult in real practice environments. In this work, a complete computer based architecture to help the representation and execution of Clinical Pathways is suggested. Furthermore, the difficulties inherent to the design of formal Clinical Pathways in this way requires new specific design tools to help making the system useful. Process Mining techniques can help to automatically infer processes definition from execution samples. Yet, the classical Process Mining paradigm is not totally compatible with the Clinical Pathways paradigm. In this paper, a pattern recognition algorithm based in an evolution of the Process Mining classical paradigm is presented and evaluated as a solution to this situation. The proposed algorithm is able to infer Clinical Pathways from execution logs to support the design of Clinical Pathways.

Behaviour patterns detection for persuasive design in Nursing Homes to help dementia patients

Nursing homes usually host large accounts of persons with different levels of dementia. Detecting dementia process in early stages may allow the application of mechanisms to reduce or stop the cognitive impairment. Our ultimate objective is to demonstrate that the use of persuasive techniques may serve to motivate these subjects and induct re-learning mechanisms to stop mental impairment. Nevertheless, this requires the study of the behaviour of each patient individually in order to detect conduct disorders in their living ambient. This study presents a behavior pattern detection architecture based on the Ambient Assisted Living paradigm and Workflow Mining technology to enable re-learning mechanisms in dementia processes via providing tools to automate the conduct disorder detection. This architecture fosters the use of Workflows as representation languages to allow health professionals to represent persuasive motivation protocols in the AAL environment to react individually to dementia symptoms detected.

Ontology for Modeling Interaction in Ambient Assisted Living Environments

This paper describes a set of ontologies created in the framework of the European project VAALID that allows designers of Ambient Assisted Living (AAL) services to model and characterize an AAL environment, the involved actors and different kinds of spaces and devices. These ontologies also include aspects related to interactions among the different elements that have been defined in the modelled AAL solution. Interactions are described in terms of capabilities of each element by means of the Common Accessibility Profile.

Performance assessment of a closed‑loop system for diabetes management

Telemedicine systems can play an important role in the management of diabetes, a chronic condition that is increasing worldwide. Evaluations on the consistency of information across these systems and on their performance in a real situation are still missing. This paper presents a remote monitoring system for diabetes management based on physiological sensors, mobile technologies and patient/doctor applications over a service-oriented architecture that has been evaluated in an international trial (83,905 operation records). The proposed system integrates three types of running environments and data engines in a single service-oriented architecture. This feature is used to assess key performance indicators comparing them with other type of architectures. Data sustainability across the applications has been evaluated showing better outcomes for full integrated sensors. At the same time, runtime performance of clients has been assessed spotting no differences regarding the operative environment.

Timed Parallel Automaton: A Mathematical Tool for Defining Highly Expressive Formal Workflows

The definition and simulation of processes using Work flow technology is becoming more and more popular. In that way, to standardize and simulate complex processes it is needed high expressive languages able to be automatically executed by computers. Currently, high expressive languages that can be used for simulation and definition of processes are based in Petri Nets technology. Nevertheless, Petri Nets are difficult to understand by processes experts with no computer science training or expertise and are more complex to be executed than other simpler approaches like finite automatons. In this paper an automata based mathematical tool with a high expressivity capacity is presented. This framework is easier to understand also by non computer science expert sand its automation is simple in order to allow to experts to define formal work flows that can be easily automated.

Ambient assisted living spaces validation by services and devices simulation

The design of Ambient Assisted Living (AAL) products is a very demanding challenge. AAL products creation is a complex iterative process which must accomplish exhaustive prerequisites about accessibility and usability. In this process the early detection of errors is crucial to create cost-effective systems. Computer-assisted tools can suppose a vital help to usability designers in order to avoid design errors. Specifically computer simulation of products in AAL environments can be used in all the design phases to support the validation. In this paper, a computer simulation tool for supporting usability designers in the creation of innovative AAL products is presented. This application will benefit their work saving time and improving the final system functionality.

Applying evidence-based medicine in telehealth: an interactive pattern recognition approximation.

Born in the early nineteen nineties, evidence-based medicine (EBM) is a paradigm intended to promote the integration of biomedical evidence into the physicians daily practice. This paradigm requires the continuous study of diseases to provide the best scientific knowledge for supporting physicians in their diagnosis and treatments in a close way. Within this paradigm, usually, health experts create and publish clinical guidelines, which provide holistic guidance for the care for a certain disease. The creation of these clinical guidelines requires hard iterative processes in which each iteration supposes scientific progress in the knowledge of the disease. To perform this guidance through telehealth, the use of formal clinical guidelines will allow the building of care processes that can be interpreted and executed directly by computers. In addition, the formalization of clinical guidelines allows for the possibility to build automatic methods, using pattern recognition techniques, to estimate the proper models, as well as the mathematical models for optimizing the iterative cycle for the continuous improvement of the guidelines. However, to ensure the efficiency of the system, it is necessary to build a probabilistic model of the problem. In this paper, an interactive pattern recognition approach to support professionals in evidence-based medicine is formalized.