NoiseCo:Smartphone-Based Noise Collection And Correction

Nowadays,noise pollution is worsening.It has become an outstanding problem in urban life as it affects people's heath both physically and psychologically.Noise pollution can cause hypertension,high stress levels,tinnitus,hearing loss,sleep disturbance,and its effects on human health are the hot topics in the recent environment studies recently.However,it is generally difficult for ordinary people to access real-time noise level information because the means for that are very limited;they can know their environment noise only through major facilities such as noise level display board or noise measuring stations.One more option to know the surrounding noise is by using sound level meter.Therefore,measuring noise level by network distribution and fixed point are so traditional ways for public and can no longer satisfy people's needs.With the population of smartphones and possibility of noise monitoring based on crowd sensing,being equipped with a high-quality microphone,a smartphone can potentially serve as a handy noise level meter.We implemented a prototype called NoiseCo,and we solve in this paper two problems in measuring noise by smartphone.First,how can we calibrate the difference between smartphones and the stranded noise measuring tool.Second,how can we calibrate the difference between different smartphones? Through experiments,we can observe such a linear relationship between the collected data by smartphone and the one collected by stranded noise measuring tool,and after combining A-weighting and smoothing,we are able to calibrate the smartphone after fitting it so that the result is so closed to the stranded tools' result.Moreover,we solve the difference between smartphones of different models by calibrating each model manually to get the parameters based on the same sound source condition.