This project is intended to resolve the hurdle of lack of predictive maintenance in industries. The elimination of the risk of downtime and the reduction of maintenance costs are precious for the industry, because it is currently a barrier for increasing the production and accelerating creation of better products that can provide higher profits. Therefore, the industry has strong need to adapt an easy-to-implement and easy-to-use solution. This led NEURONSW LTD. to the concept of prediction of mechanical malfunction of machinery by mechanical sound analysis. Neuron soundware (NeuronSW) is an innovative breakthrough solution combining advanced algorithms, machine learning and big data analysis to emulate the human auditory cortex enabling the early detection and prediction of mechanical malfunction of machinery. Through NeuronSW, manufacturers achieve intelligent audio diagnostics to monitor the key machinery equipment using the sound they generate. The integrated hardware and software platform automatically gathers sound of machines in real time and continuously assess the equipment health and operates similarly how experienced technicians use their ears to diagnose broken machines. It works offline and online and can be integrated into existing software or third party IoT platforms. This effectively transforms data into knowledge and actions. Sound and vibration sensors (microphones) can be quickly and cheaply installed on all types of machinery, enabling assets without digital interface or operated by legacy systems to be digitalized without expensive upgrades.

Research in neurophysiology includes both analysis of data from neuronal systems (networks of brain cells; both live and cultured), and development of models to explain both the processes that form the character of data, and the high level function that these express; i.e. behaviour and thought. Capturing and analysing data from neuronal systems is time-consuming, difficult and expensive: many techniques exist, some using multichannel electrical recording, and some using ion-sensitive fluorescent dyes. Different techniques have different advantages: some have high time resolution, whereas others have high space resolution. The models that derive from this data also exist at many levels, from the detailed modelling of membrane-embedded ion channels and neurotransmitters to compartmental neural models, through models of small neural networks, to larger models of many thousands of neurons. All models and algorithms are hungry for data to determine their many parameters and characteristics. Currently this activity is largely a one-lab science: datasets are shared within a lab, and with some computational modellers. The research is also not organised to ensure that data and models produced by small communities of specialist researchs can easily be integrated to contribute to the bigger picture. Datasets are discarded after the experimentor has completed their experimental report, or are archived in a format that is not widely accessible. This project aims to use the GRID to change that: it will enable experimenters to archive their datasets in a structure, making them widely accessible for modellers and algorithm developers to exploit. Experimental datasets are useless without accurate descriptions of the experimental conditions, and hence an appropriate set of metadata will developed to augment the data, allowing the project researchers to collaborate more widely and persistently by sharing data in a sensible, referenced form. Further, the project will provide integrated and co-ordinated services for the neuroscience data, enabling neuronal signal detection, sorting and analysis, as well as visualisation and modelling. Data security is critically important to experimentors: they do not wish to be simply anonymous contributors of data, but to be directly involved in further analysis of their datasets, and this will be supported. Further we will enable direct near real-time analysis of streamed experimental data, providing information to distributed teams of specialists that will allow difficult experiments to be optimised. These interventions will catalyse a step change in research practice in this area of neuroscience, which will allow best value to be derived from the significant research investment that is made in order to understand the brain.

As the world is becoming more urbanized and cities of the future need to be people-centred, robust evidence-based knowledge on the underlying biological and psychological processes, by which Urban Planning & Design influence brain circuits and human behaviour, will be critical for policy making on urban health. Emotions are key drivers of our decisions; similarly, our choices are the conduit for our well-being and health. Thus, research focusing on the signals triggered in our neurobiological architecture, responsible for emotions and decisions, while humans interact with the urban environment will shed light on how to improve population health, physical and/or mental. The eMOTIONAL Cities project was designed to fully characterise the intensity and complexity of urban health challenges and inequalities. By exploring the mechanisms and their dynamic, it complements conventional descriptive perspectives focused on exposure-outcome associations. It adopts a systems approach, based on natural experiments and actual problems of case-study cities (Copenhagen, Lisbon, London; and Lansing/Detroit in the USA). Building on theoretical foundations, novel eMOTIONAL city mapping will be generated by combining spatial analysis on social/health data with neuroscience experiments. Our research relies on mixed (qualitative/quantitative) methods and uses multidisciplinary instruments from Urban Planning & Design (GIS for land use, transport, climate and health), Neuroscience (fMRI, EEG) and Data Science & Technology (AI, Big Data and VR/AR reality). The analysis also addresses gender aspects and contemplates a clinical study to show that urban design can impact a vulnerable elderly population at risk of developing dementia. Finally, a novel machine-learning scenario discovery framework will allow testing and impact assessment (for cost-effectiveness, barriers and facilitators) of urban policy strategies to turn EU cities into smart, sustainable and inclusive environments. The eMOTIONAL Cities is a part of the European Cluster on Urban Health.