We disentangle the efficacy of individual non-pharmaceutical interventions (NPIs), including digital contact tracing (DCT), with a novel behaviour-driven agent-based model (ABM) to inform ongoing pandemic preparedness efforts. Our model's Zeitgeber architecture delineates contextual characteristics, daytime, daily routines, locations, and activities. method determines each agent's current location behaviour in realistic environment under restrictions NPIs. viral load transfer between agents...

In computational optical imaging and wireless communications, signals are acquired through linear coded noisy projections, which recovered algorithms. Deep model-based approaches, i.e., neural networks incorporating the sensing operators, state-of-the-art for signal recovery. However, these methods require exact knowledge of operator, is often unavailable in practice, leading to performance degradation. Consequently, we propose a new recovery paradigm based on distillation. A teacher model,...

The new Coronavirus pandemic has promoted the development of mobile and wearable computing in unprecedented ways. We discuss how on-body devices can help to fight may stay as a toolset effectively deal with infectious diseases future.

Various installations and appliances used by building occupants are manually operated, including office devices, kitchen appliances, washing basins, etc. By monitoring usage thus energy consumption, could received feedback on their needs, which is considered vital to spur conservation. In this work, we investigate a novel generation of 2D-matrix thermopile sensors for recognising objects object-occupant interactions from heat patterns total 21 activities using single sensor installation. The...

This paper presents a dynamically adaptive proximity controller (APC) to balance energy consumption and user comfort of computer screens in office environments. Our APC system detects desk activities, such as working with the screen (screen on) being away off) controls accordingly. Ultra-sound range (USR) sensors were used measure proximity. To compensate for USR measurement errors, timing parameters adapted previous switch-off operations corrected using implicit feedback. The feedback was...

The advances of pervasive technology offer new standards for user comfort by adding intelligence to ubiquitous home and office appliances. With being the core some newly constructed buildings, it is important design a scalable, robust, context-aware architecture, which not only has enough longevity evolving capabilities sustain itself over building's lifetime, but also provides potential additional features be added Building Management Systems (BMS). Such may include energy preservation...

We present a framework to mine relations and group variables that represent measurement status information from sensors actuators in office buildings. Our work is motivated by the need manage growing numbers of devices related automation functions buildings are currently often manually commissioned maintained. approach relies on idea building at same location will change value temporal relation can be discovered. Based event sequences derived various modalities, our initially mines...

Background: Disease-modifying antirheumatic drugs (bDMARDs) have shown efficacy in treating Rheumatoid Arthritis (RA). Predicting treatment outcomes for RA is crucial as approximately 30% of patients do not respond to bDMARDs and only half achieve a sustained response. This study aims leverage machine learning predict both initial response at 6 months 12 using baseline clinical data. Methods: Baseline data were collected from 154 treated the University Hospital Erlangen, Germany. Five models...

We present an approach to infer relative position and orientation of ubiquitous building-installed low-resolution spatial sensors using real-life measurements. Commercial buildings accumulate a "zoo" heterogeneous devices, as new generations emerging modalities become available. The increasing number building pose challenging commissioning maintenance tasks that require sensor arrangement information. In this work we focus on which can track objects in their field view, i.e., sensors....

We present intervention study on energy saving investigating the benefit of controlling ceiling lighting based occupant presence information obtained at each desk. show that fine-grained sensing and control is particularly beneficial for in open plan office spaces. Our was conducted a 63.8m <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> modern space over time 1.5 months. Ultrasound sensors were installed to obtain Self-dimming lights...

We present a novel stochastic recognition model based on Kernel Density Estimation (KDE) that uses minimal set of features derived from ultrasound ranging sensors (USR) to detect presence at the desk area. In our approach, USR are mounted screens provide proximity estimations objects and users in front them. Based continuous two screen-attached USRs, were extracted describe distance motion user objects. Our approach provides instantaneous estimation results, which is essential for energy...

Depletion of fossil fuel and the ever-increasing need for energy in residential commercial buildings have triggered in-depth research on many saving monitoring mechanisms. Currently, users are only aware their overall consumption its cost a shared space. Due to lack information individual consumption, not being able fine-tune usage. Further, even-splitting spaces does help creating awareness. With advent Internet Things (IoT) wearable devices, apportioning total household occupants can be...

In this paper, we introduce the increasing belief criterion in association rule mining. The uses a recursive application of Bayes' theorem to compute rule's belief. Extracted rules are required have their increase with last observation. We extend taxonomy mining algorithms new branch for Bayesian mining~(BRM), which as selection criterion. contrast, well-established frequent mining~(FRM) relies on minimum-support concept extract rules. derive properties criterion, such boundary,...

Wearable devices have paved the way for several contextaware applications in field of health-care, sports and entertainment to improve well-being users. During rehabilitation patients need accurate feedback on their physiotherapy preferably near real-time. This users can empower speed recovery. We present here a system that analyzes activities provide real-time feedback. Specifically, we analyze exercises performed during knee where undergoing therapy often visit doctors Moreover, they...

We propose a novel knowledge extraction method based on Bayesian-inspired association rule mining to classify anxiety in heterogeneous, routinely collected data from 9,924 palliative patients. The extracts rules mined using lift and local support as selection criteria. extracted are used assess the maximum evidence supporting rejecting for each patient test set. evaluated predictive accuracy by calculating area under receiver operating characteristic curve (AUC). evaluation produced an AUC...

Ideally, building devices should be installed in a set-and-forget manner with minimum device configuration. In practice however, the correct interaction between all must assured order for to function properly, e.g., each motion detector has associated ceiling lamps. Currently, initial commissioning of is manual task, labour intensive and prone errors. this work, we show how use state art management systems (BMS) modern design minimize time. We summarize data mining techniques which extract...