“Building performance evaluation: The case of McClay Library”

The government of the UK has set an ambitious target that all newly built homes be carbon neutral by 2016 and to achieving an overall 80% carbon emission by 2050. Carbon Trust in 2009 published a research revealing that non-domestic buildings accounted for 18% of the emissions in the UK. They argued that to achieve the targets of low carbon emission there is need for better building stock that are better used. The evaluation of the performance of buildings is therefore critical if the understanding of how they are used is to be known. This paper is a brief building performance evaluation of the newly build library at Queens University Belfast carried out during the summer of 2010. It employed the Post-Occupancy Evaluation (POE) methodology to assess its performance. The results reveal that despite the intelligent technologies in the building there was a mismatch between the measured data and the perception of users of its performance. The study suggests the need for further study for reasons of dichotomy of the data. Keywords: building performance evaluation, carbon reduction strategies, passive environmental design techniques, active renewable energy technologies, Northern Ireland

Building autonomous sensitive artificial listeners (Extended abstract)

This paper describes a substantial effort to build a real-time interactive multimodal dialogue system with a focus on emotional and non-verbal interaction capabilities. The work is motivated by the aim to provide technology with competences in perceiving and producing the emotional and non-verbal behaviours required to sustain a conversational dialogue. We present the Sensitive Artificial Listener (SAL) scenario as a setting which seems particularly suited for the study of emotional and non-verbal behaviour, since it requires only very limited verbal understanding on the part of the machine. This scenario allows us to concentrate on non-verbal capabilities without having to address at the same time the challenges of spoken language understanding, task modeling etc. We first summarise three prototype versions of the SAL scenario, in which the behaviour of the Sensitive Artificial Listener characters was determined by a human operator. These prototypes served the purpose of verifying the effectiveness of the SAL scenario and allowed us to collect data required for building system components for analysing and synthesising the respective behaviours. We then describe the fully autonomous integrated real-time system we created, which combines incremental analysis of user behaviour, dialogue management, and synthesis of speaker and listener behaviour of a SAL character displayed as a virtual agent. We discuss principles that should underlie the evaluation of SAL-type systems. Since the system is designed for modularity and reuse, and since it is publicly available, the SAL system has potential as a joint research tool in the affective computing research community.