Aimilia Papagiannaki

The main goal of this project is to develop expert intelligence tools to be incorporated in commercial energy management platforms for proactive energy management in buildings to further optimize energy savings. To this end, three (3) fuzzy logic powered tools will be deployed to be incorporated in well-known SaaS platforms used for energy management to further improve decision making related to smart fault detection and diagnostics as well as intelligent predictive maintenance of basic building equipment. The first tool, the so-called expert FDD analyser, will be a core fault detection and diagnostics tool related to common building equipment, such as HVACs, PV plants, pumps, etc., enhancing ongoing monitoring-based performance management of building systems to save energy and extend equipment life. The second tool, the so-called HVAC system optimizer, will be based on a fuzzy inference engine for optimizing HVAC system operation in order to increase comfort, reduce energy costs an...

for dissemination) In this deliverable, our primary efforts were focused on identifying approaches for discovering a set of relevant and informative indicators for frailty. During this process, the state of the art was first analyzed and the clinical experts’ input was taken into account. Then, the multidimensional data analysis problem was formulated as a tensor decomposition problem and several techniques were outlined. Moreover, preliminary work was performed on data mining techniques towards discovering associations between frailty, and physiological or behavioral patterns. Finally, fueled by previous work on data fusion, three schemes were explored. This first version of the deliverable whose final version is due on M24 sets the ground for the data analysis techniques that will be used to discover new frailty metrics.

Buildings consume a significant percentage of the world’s energy resources. The rapid depletion of energy resources, has imparted researchers to focus on energy conservation and wastage. The next generation of intelligent buildings is becoming a trend to cope with the needs of energy and environmental ease in buildings. This advances the intelligent control of building to fulfill the occupants’ need. Intelligent system control for sustainable buildings is dynamic and highly complex.

The physiological monitoring of older people using wearable sensors has shown great potential in improving their quality of life and preventing undesired events related to their health status. Nevertheless, creating robust predictive models from data collected unobtrusively in home environments can be challenging, especially for vulnerable ageing population. Under that premise, we propose an activity recognition scheme for older people exploiting feature extraction and machine learning, along with heuristic computational solutions to address the challenges due to inconsistent measurements in non-standardized environments. In addition, we compare the customized pipeline with deep learning architectures, such as convolutional neural networks, applied to raw sensor data without any pre- or post-processing adjustments. The results demonstrate that the generalizable deep architectures can compensate for inconsistencies during data acquisition providing a valuable alternative.