In apartment houses, noise between floors can disturb pleasant living environments and cause disputes between neighbors. As a means of resolving disputes caused by inter-floor noise, noises are recorded for 24 hours in a household to verify whether the inter-floor noise exceeded the legal standards. If the noise exceeds the legal standards, the recorded sound is listened to, and it is checked whether the noise comes from neighboring households. When done manually, this process requires time and is costly, and there is a problem of whether the listener’s judgments of the sound source are consistent. This study aims to classify inter-floor noise according to noise sources by using a convolutional neural network model. A total of 1,515 sound sources of data recorded for 24 h from three households were annotated, and 40 4s audio clips of six noise sources, including “Footsteps,” “Dragging furniture,” “Hammering,” “Instant impact (dropping a heavy item),” “Vacuum cleaner,” and “Public announcement system” were identified. Moreover, datasets of 16 classes using ESC50’s urban sound category audio were used to distinguish the inter-floor noise heard indoors from the external noise. Although DenseNet, ResNet, Inception, and EfficientNet are models that use images as their domains, they showed an accuracy of 91.43–95.27% when classifying the inter-floor noise dataset. Among the reviewed models, ResNet showed an accuracy of 95.27±2.30% as well as a highest performance level in the F1 score, precision, and recall metrics. Additionally, ResNet showed the shortest inference time. This paper concludes by suggesting that the present findings can be extended in future research for monitoring acoustic elements of indoor soundscape.

No abstract

No abstract

No abstract

In 2006, the Korean Ministry of Environment established <The 1st Water Environment Management Master Plan>. The plan aimed at “Clean Water, Eco River 2015” and guided water quality protection and strengthened water management. This study evaluated the achievement of the target water quality among the 33 mid-level basins in the Nakdong River basin and assessments of the causes of non-achievement of the target water quality by mid-level basins. According to the 2015 water quality data, only 16 of the 33 mid-level basins achieved the target water quality. The low achievement of the target water quality was attributed to the failure to predict the pollutant load at the time of planning, problems with the management of tributaries, implementation of the <Four major river restoration project>, and problems with the representativeness of the water quality representative points. In addition, feasibility studies on the water quality monitoring representative point used in each mid-level basin were also performed; some mid-level basins required improvement or change of the representative points. This study also suggested further research to improve water quality, such as detailed studies of the management of pollutant load, mainstream tributaries, and water quality indicators, for the revision of the current ongoing <The 2nd Water Environment Management Master Plan>.