DEVELOPMENT OF machine learning PLATFORM FOR ENVIRONMENTAL NOISE MONITORING
Budget: $30 – $250 USD
ABSTRACT
This project aims to make a case study of using Machine Learning (ML) classification of sounds originated from environment which are considered as noise pollution in cities and compared them with the recommended levels by international standards such as World Health Organization (WHO). The sound collection will be carried out using necessary sound capture tools before ML classification models are utilized for the sound recognition. In addition to ML, subjective perception questionnaire will be conducted to provide qualitative analysis of community perceptions based on noise pollution survey. The findings are expected to provide a guideline of the conducive environment for carrying out tasks in the presence of noise and recommends measures for noise mitigation under specific conditions. The noise data collected from both quantitative and qualitative measurements will be stored in a repository for a comprehensive data warehousing of which big data analytics will be used to help decision-making processes and policy making by stakeholders such as municipals, housing agencies and town planners in smart cities.
This project aims to make a case study of using Machine Learning (ML) classification of sounds originated from environment which are considered as noise pollution in cities and compared them with the recommended levels by international standards such as World Health Organization (WHO). The sound collection will be carried out using necessary sound capture tools before ML classification models are utilized for the sound recognition. In addition to ML, subjective perception questionnaire will be conducted to provide qualitative analysis of community perceptions based on noise pollution survey. The findings are expected to provide a guideline of the conducive environment for carrying out tasks in the presence of noise and recommends measures for noise mitigation under specific conditions. The noise data collected from both quantitative and qualitative measurements will be stored in a repository for a comprehensive data warehousing of which big data analytics will be used to help decision-making processes and policy making by stakeholders such as municipals, housing agencies and town planners in smart cities.