A comparative study on prediction of the indoor soundscape in museums via machine learning

This paper presents the preliminary findings of a soundscape research, which uses machine learning to make a prediction about human perception for indoor auditory environments. Museums of Çengelhan Rahmi Koc and Erim Tan are selected as the case study settings for data collection. The survey questionnaire basically consisted of three parts which are concerned with identifying the socio-cultural status, the personal tendencies, and evaluation of the physical and auditory environment. Before constructing of grounding the predictive model, data went through analyses to normalize and to eliminate the irrelevant items. Preliminary findings demonstrated how an indoor auditory environment would be perceived based on the individuals’ socio-cultural status, tendencies, preference and expectation from the space and physical elements of the space with together constructing a preliminary grounding model to use Machine / Deep learning algorithm.