Sensor technology is increasingly applied for the purpose of monitoring elderly’s Activities of Daily Living (ADL), a set of activities used by physicians to benchmark physical and cognitive decline. Visualizing deviations in ADL can help medical specialists and nurses to recognize disease symptoms at an early stage. This paper presents possible visualizations for identifying such deviations. These visualizations have been iteratively explored and developed with three different medical specialists to better understand which deviations are relevant according to the different medical specialisms and explore how these deviations should be best presented. The study results suggest that the participants found a monthly bar graph in which activities are represented by colours as the most suitable from the ones presented. Although the visualizations of every ADL was found to be more or less relevant by the different medical specialists, the preference for focusing on specific ADL’s varied from specialist to specialist.
The maturing field of Wireless Sensor Networks (WSN) results in long-lived deployments that produce large amounts of sensor data. Lightweight online on-mote processing may improve the usage of their limited resources, such as energy, by transmitting only unexpected sensor data (anomalies). We detect anomalies by analyzing sensor reading predictions from a linear model. We use Recursive Least Squares (RLS) to estimate the model parameters, because for large datasets the standard Linear Least Squares Estimation (LLSE) is not resource friendly. We evaluate the use of fixed-point RLS with adaptive thresholding, and its application to anomaly detection in embedded systems. We present an extensive experimental campaign on generated and real-world datasets, with floating-point RLS, LLSE, and a rule-based method as benchmarks. The methods are evaluated on prediction accuracy of the models, and on detection of anomalies, which are injected in the generated dataset. The experimental results show that the proposed algorithm is comparable, in terms of prediction accuracy and detection performance, to the other LS methods. However, fixed-point RLS is efficiently implementable in embedded devices. The presented method enables online on-mote anomaly detection with results comparable to offline LS methods. © 2013 IEEE.
In the GoGreen project an intelligent home that is able to identify inhabitants and events that take place is created. The location of sounds that are being produced is an important feature for the context awareness of this system. A a wireless solution that uses low-cost sensor nodes and microphones is described. Experiments show that solutions that only use the three sensor nodes that are closest to the origin of the sounds provide the best solutions, with an average accuracy of 40 cm or less.Paper published for the ICT Open 2013 proceedings (27-28 November 2013, Eindhoven).
MULTIFILE
This project aims to develop a measurement tool to assess the inclusivity of experiences for people with varying challenges and capabilities on the auditory spectrum. In doing so, we performed an in-depth exploration of scientific literature and findings from previous projects by Joint Projects. Based on this, we developed an initial conceptual model that focuses on sensory perception, emotion, cognition, and e[ort in relation to hearing and fatigue. Within, this model a visitor attraction is seen as an “experienscape” with four key elements: content, medium, context, and individual. In co-creative interviews with experts by experience with varying challenges on the auditory spectrum, they provided valuable insights that led to a significant expansion of this initial model. This was a relevant step, as in the scientific and professional literature, little is known about the leisure experiences of people with troubled hearing. For example, personal factors such as a person’s attitude toward their own hearing loss and the social dynamics within their group turned out to greatly influence the experience. The revised model was then applied in a case study at Apenheul, focusing on studying differences in experience of their gorilla presentation amongst people with varying challenges on the auditory spectrum.Societal issueThe Netherlands is one of the countries in Europe with the highest density of visitor attractions. Despite this abundance, many visitor attractions are not fully accessible to everyone, particularly to visitors with disabilities who sometimes are not eligible to ride due to safety concerns, yet when eligible generally still encounter numerous barriers. Accessibility of visitor attractions can be approached in various ways. However, because the focus often lies on operational and technical aspects (e.g., reducing stimuli at certain times of the day by turning o[ music, o[ering alternative wheelchair entrances), strategic and community-focused approaches are often overlooked. More importantly, there is also a lack of attention to the experience of visitors with disabilities. This becomes apparent from several studies from Joint Projects, where visitor attractions are being visited together with experts by experience with various disabilities. Nevertheless, experience is often being regarded as the 'core product' of the leisure sector. The right to meet, discover, develop, relax and thus enjoy this core product is hindered for many people with disabilities due to a lack of knowledge, inaccessibility (physical, digital, social, communicative as well as financial) and discrimination in society. Additionally, recreation entrepreneurs still face a significant gap in reaching the potential market of guests with disabilities and their networks. Thus, despite the numerous initiatives in the leisure sector aimed at improving accessibility on technical and operational fronts, often people with disabilities are still not being able to experience the same kind of enjoyment as those without. These observations form the pressing impetus for initiating the current research project, tapping into the numerous opportunities for learning, development and growth on making leisure offer more inclusive.Benefit to societyIn total, the current project approach comes with a number of enrichments in terms of both knowledge and methodology: a mixed-methods approach that allows for comparing data from different sources to obtain a more complete picture of the experience; a methodological co-design process that honours the 'nothing about us without us' principle; and benchmarking for a group (i.e., people with challenges on the auditory spectrum) that despite the size of its population has thus far mostly been overlooked.
The bi-directional communication link with the physical system is one of the main distinguishing features of the Digital Twin paradigm. This continuous flow of data and information, along its entire life cycle, is what makes a Digital Twin a dynamic and evolving entity and not merely a high-fidelity copy. There is an increasing realisation of the importance of a well functioning digital twin in critical infrastructures, such as water networks. Configuration of water network assets, such as valves, pumps, boosters and reservoirs, must be carefully managed and the water flows rerouted, often manually, which is a slow and costly process. The state of the art water management systems assume a relatively static physical model that requires manual corrections. Any change in the network conditions or topology due to degraded control mechanisms, ongoing maintenance, or changes in the external context situation, such as a heat wave, makes the existing model diverge from the reality. Our project proposes a unique approach to real-time monitoring of the water network that can handle automated changes of the model, based on the measured discrepancy of the model with the obtained IoT sensor data. We aim at an evolutionary approach that can apply detected changes to the model and update it in real-time without the need for any additional model validation and calibration. The state of the art deep learning algorithms will be applied to create a machine-learning data-driven simulation of the water network system. Moreover, unlike most research that is focused on detection of network problems and sensor faults, we will investigate the possibility of making a step further and continue using the degraded network and malfunctioning sensors until the maintenance and repairs can take place, which can take a long time. We will create a formal model and analyse the effect on data readings of different malfunctions, to construct a mitigating mechanism that is tailor-made for each malfunction type and allows to continue using the data, albeit in a limited capacity.
The bi-directional communication link with the physical system is one of the main distinguishing features of the Digital Twin paradigm. This continuous flow of data and information, along its entire life cycle, is what makes a Digital Twin a dynamic and evolving entity and not merely a high-fidelity copy. There is an increasing realisation of the importance of a well functioning digital twin in critical infrastructures, such as water networks. Configuration of water network assets, such as valves, pumps, boosters and reservoirs, must be carefully managed and the water flows rerouted, often manually, which is a slow and costly process. The state of the art water management systems assume a relatively static physical model that requires manual corrections. Any change in the network conditions or topology due to degraded control mechanisms, ongoing maintenance, or changes in the external context situation, such as a heat wave, makes the existing model diverge from the reality. Our project proposes a unique approach to real-time monitoring of the water network that can handle automated changes of the model, based on the measured discrepancy of the model with the obtained IoT sensor data. We aim at an evolutionary approach that can apply detected changes to the model and update it in real-time without the need for any additional model validation and calibration. The state of the art deep learning algorithms will be applied to create a machine-learning data-driven simulation of the water network system. Moreover, unlike most research that is focused on detection of network problems and sensor faults, we will investigate the possibility of making a step further and continue using the degraded network and malfunctioning sensors until the maintenance and repairs can take place, which can take a long time. We will create a formal model and analyse the effect on data readings of different malfunctions, to construct a mitigating mechanism that is tailor-made for each malfunction type and allows to continue using the data, albeit in a limited capacity.