Formal Modeling Techniques for Ambient Assisted Living

Abstract

In the development of systems of ambient assisted living (AAL), formalized models and analysis techniques can provide a ground that makes development amenable to a systematic approach. We consider the following formal modeling tools and techniques: fault trees, evidential reasoning, evidential ontology networks, temporal logic, hidden Markov models and partially observable Markov models. We review them in the perspective of their potential in the realm of AAL, recalling the general traits and potential of each of them, and highlighting how this can be concretely deployed within the AAL realm. To this end, we present a number of scenarios providing insight on how each technique can match the needs of different types of problem in the application domain.The present and forecasted evolution of population demographics demands new approaches to the delivery of health and social care (World Health Organization 2010). Technology may largely contribute both to the efficiency and effectiveness of services through solutions that range from assistive technologies such as medication management and cognitive prosthetics to wearable healthmonitoring systems (Paradiso et al. 2005). As a common trait, all these approaches pose a crucial problem pertaining to the automated extraction of high-level semantic information from low-level data acquired through technological devices. This process may take a major role in the profiling of the patient (Atallah and Yang 2009), which in turn provides a basis for supporting decisions needed for effective Ageing Int (2011) 36:192-216

Evaluating the Reliability of Ambient-Assisted Living Business Processes

“…For instance, other heat sources can affect temperature sensors. Parente et al (2011) present a use case where they monitor the health of patients considering heart and body activities. The system uses a heart rate monitor, a pulse oxymeter, and a sphygmomanometer to monitor the heart activity.…”

“…Indeed, while reliability has been a major concern for networking, critical and real-time applications, as well as middleware (Parente et al, 2011;Siewiorek and Swarz, 2014); the increasing use of workflow, specifically, in more critical systems, justifies the works on workflow reliability.…”

“…We made vary the reliability of the following elements: each sensor, the transmission from sensors to the BAN gateway, and the transmission from the BAN gateway to the HMS through the home gateway. Parente et al (2011) propose reliability values for the type of sensors used in our use case, namely the Heart Rate Monitor (HRM), the Pulse Oxymeter (POxy), the Shygmomanometer (Shygm), and the Accelerometer (Acc), which are used to initialise the atribute calculatedReliability of the tasks "read value".…”

“…Therefore, the impact of a less reliable system can range from a false alarm transmitted to a certain caregiver and/or emergency unit service, to serious patient injury due to wrong, delayed or even non-delivered care. Current research works and industry products related with AAL and overall to Internet of Things (IoT) applied to healthcare already provide redundancy checks and alerts to prevent greater impacts to patients using them (see, for instance, Parente et al, 2011;Siewiorek and Swarz, 2014). Nevertheless, these efforts to increase reliability are usually self-contained to some components of an AAL system, i.e., reliability is commonly evaluated for each component, regardless of its position in a certain sequence of activities to trigger some action (alert, register or even actuate).…”

“…The Body Area Network (BAN) sensor devices are used for monitoring vital signs, i.e., heart and body activity in this example (based on Parente et al, 2011). The heart activity is assessed through the heart rate, the blood oxygen, and the blood pressure, by using a heart rate monitor, a pulse oxymeter and a sphygmomanometer, respectively.…”