The current dominant computing mode in the AEC (Architecture, Engineering and Construction) domain is standalone based, causing fragmentation and fundamental interoperability problems. This makes the collaboration required to deal with the interconnected and complex tasks associated with a sustainable and resilient built environment extremely difficult. This article aims to discuss how the latest computing technologies can be leveraged for the AEC domain and Building Information Modelling (BIM) in particular. These technologies include Cloud Computing, the Internet of Things and Big Data Analytics. The data rich BIM domain will be analysed to identify relevant characteristics, opportunities and the likely challenges. A clear case will be established detailing why BIM needs these technologies and how they can be brought together to bring about a paradigm shift in the industry. Having identified the potential application of new technologies, a future platform will be proposed. It will carry out large scale, realtime processing of data from all stakeholders. The platform will facilitate the collaborative interpretation, manipulation and analysis of data for the whole lifecycle of building projects. It will be flexible, intelligent and able to autonomously execute analysis and choose the relevant tools. This will form a base for a step-change for computing tools in the AEC domain.
The large slow oscillation (SO, 0.5-2Hz) that characterises slow-wave sleep is crucial to memory consolidation and other physiological functions. Manipulating slow oscillations can enhance sleep and memory, as well as benefitting the immune system. Closed-loop auditory stimulation (CLAS) has been demonstrated to increase the SO amplitude and to boost fast sleep spindle activity (11-16Hz). Nevertheless, not all such stimuli are effective in evoking SOs, even if they are precisely phase-locked. Here, we studied whether it is possible to use ongoing activity patterns to determine which oscillations to stimulate in order to effectively enhance SOs or SO-locked spindle activity. To this end, we trained classifiers using the morphological characteristics of the ongoing SO, as measured by electroencephalography (EEG), to predict whether stimulation would lead to a benefit in terms of the resulting SO and spindle amplitude. Separate classifiers were trained using trials from spontaneous control and stimulated datasets, and we evaluated their performance by applying them to held-out data both within and across conditions. We were able to predict both when large SOs will occur spontaneously, and whether a phase-locked auditory click will effectively enlarge them with an accuracy of ~70%. We were also able to predict when stimulation would elicit spindle activity with an accuracy of ~60%. Finally, we evaluate the importance of the various SO features used to make these predictions. Our results offer new insight into SO and spindle dynamics and provide a new method for online optimisation of stimulation.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.