Clustering and classification of residential noise sources in apartment buildings based on machine learning using spectral and temporal characteristics

Jeong-hun Kim; Song-mi Lee; Su-hong Kim; Eun-sung Song; Jong-kwan Ryu

doi:10.7776/ASK.2023.42.6.603

All Issue

2023 Vol.42, Issue 6 Preview Page Next Page

Research Article

Clustering and classification of residential noise sources in apartment buildings based on machine learning using spectral and temporal characteristics 주파수 및 시간 특성을 활용한 머신러닝 기반 공동주택 주거소음의 군집화 및 분류

30 November 2023. pp. 603-616

PDF XML

Abstract

In this study, machine learning-based clustering and classification of residential noise in apartment buildings was conducted using frequency and temporal characteristics. First, a residential noise source dataset was constructed . The residential noise source dataset was consisted of floor impact, airborne, plumbing and equipment noise, environmental, and construction noise. The clustering of residential noise was performed by K-Means clustering method. For frequency characteristics, L_eq and L_max values were derived for 1/1 and 1/3 octave band for each sound source. For temporal characteristics, Leq values were derived at every 6 ms through sound pressure level analysis for 5 s. The number of k in K-Means clustering method was determined through the silhouette coefficient and elbow method. The clustering of residential noise source by frequency characteristic resulted in three clusters for both L_eq and L_max analysis. Temporal characteristic clustered residential noise source into 9 clusters for L_eq and 11 clusters for L_max. Clustering by frequency characteristic clustered according to the proportion of low frequency band. Then, to utilize the clustering results, the residential noise source was classified using three kinds of machine learning. The results of the residential noise classification showed the highest accuracy and f1-score for data labeled with Leq values in 1/3 octave bands, and the highest accuracy and f1-score for classifying residential noise sources with an Artificial Neural Network (ANN) model using both frequency and temporal features, with 93 % accuracy and 92 % f1-score.

Keywords

Residential noise in apartment

Spectral and temporal characteristics

Clustering

Classification

Machine learning

Dataset

본 연구는 주파수 및 시간 특성을 활용하여 머신러닝 기반 공동주택 주거소음의 군집화 및 분류를 진행하였다. 먼저, 공동주택 주거소음의 군집화 및 분류를 진행하기 위하여 주거소음원 데이터셋을 구축하였다. 주거소음원 데이터셋은 바닥충격음, 공기전달음, 급배수 및 설비소음, 환경소음, 공사장 소음으로 구성되었다. 각 음원의 주파수 특성은 1/1과 1/3 옥타브 밴드별 L_eq와 L_max값을 도출하였으며, 시간적 특성은 5 s 동안의 6 ms 간격의 음압레벨 분석을 통해 L_eq값을 도출하였다. 공동주택 주거소음원의 군집화는 K-Means clustering을 통해 진행하였다. K-Means의 k의 개수는 실루엣 계수와 엘보우 방법을 통해 결정하였다. 주파수 특성을 통한 주거소음원 군집화는 모든 평가지수에서 3개로 군집되었다. 주파수 특성 기준으로 분류된 각 군집별 시간적 특성을 통한 주거소음원 군집화는 L_eq평가지수의 경우 9개, L_max 경우는 11개로 군집되었다. 주파수 특성을 통해 군집된 각 군집은 타 주파수 대역 대비 저주파 대역의 음에너지의 비율 또한 조사되었다. 이후, 군집화 결과를 활용하기 위한 방안으로 세 종류의 머신러닝 방법을 이용해 주거소음을 분류하였다. 주거소음 분류 결과, 1/3 옥타브 밴드의 L_eq값으로 라벨링된 데이터에서 가장 높은 정확도와 f1-score가 나타났다. 또한, 주파수 및 시간적 특성을 모두 사용하여 인공신경망(Artificial Neural Network, ANN) 모델로 주거소음원을 분류했을 때 93 %의 정확도와 92 %의 f1-score로 가장 높게 나타났다.

키워드

공동주택 주거소음

주파수와 시간적 특성

군집화

분류

머신러닝

데이터셋

References

Gwanghwamun Ilbunga, http://19gwanghwamoon1st.pa.go.kr/, (Last viewed November 24, 2023).

Korea Environment Corporation, "Casebook of complaints from neighboring," in Ministry of Environment, edited by Floor Noise, Management Centre, Case book, 2018.

Joint housing management dispute mediation central committee, "Infrastructure and transport, central committee for management dispute mediation of multi-unit dwelling: Guidebook of noise prevention and management," Ministry of Land, Guide book, 2020.

K. J. Piczak, "ESC: Dataset for environmental sound classification," Proc. ACM Int. Conf. Multimed. 1015-1018 (2015). 10.1145/2733373.2806390

D. Stowell, D. Giannoulis, E. Benetos, and M. D. Plumbley, "Detection and classification of acoustic scenes and events," Proc. DCASE, 1733-1746 (2023). 10.1109/TMM.2015.2428998

H. K. Shin, S. H. Park, and K. W. Kim, "Inter-floor noise classification using convolutional neural network," Plos One, 15, e0243758 (2020). 10.1371/journal.pone.024375833351829PMC7755197

H. Choi, H. Yang, S. Lee, and W. Seong, "Classification of inter-floor noise type/position via convolutional neural network-based supervised learning," Appl. Sci. 9, 3735 (2019). 10.3390/app9183735

H. Choi, W. Seong, and H. Yang, "Source type classification and localization of inter-floor noise with a single sensor and knowledge transfer between reinforced concrete buildings," Appl. Sci. 11, 5399 (2021). 10.3390/app11125399

H. G. Park, G. O. Baek, and D. H. Moon, "Modal Parameter of floor and walls in residual building" (in Korean), Proc. KSNVE Annual Spring Conf. 682-685 (2015).

J. K. Ryu, I. H. Kim, and J. C. Go, "Heavy-weight floor impact sound and vibration with structure types in apartment building" (in Korean), J. Acoust. Soc. Kr. Suppl. 1(s) 34, 212 (2015).

M. J. Kim, J. Y. Sohn, and H. S. Kim, "Contribution ratio of each surface of receiving room for floor impact sound transmission by using sound intensity method" (in Korean), Proc. Spring Annual Conf. AIK, 311-313 (1998).

K. W. Kim, J. S. Kang, S. E. Lee, and K. S. Yang, "Floor impact sound isolation performance by composition of ceiling and wall" (in Korean), Trans. Korean Soc. Noise Vib. Eng. 15, 465-473 (2005). 10.5050/KSNVN.2005.15.4.465

S. Lee, D. Hwang, J. Park, and J. Y. Jeon, "Cause and perception of amplitude modulation of heavy-weight impact sound in concrete wall structure," Build. Environ. 94, 785-792 (2015). 10.1016/j.buildenv.2015.04.020

Y. Kwak, S. Lee, J. Park, D. Hwang, J. Y. Jeon, and J. Park, "Effect of the static compressive load on vibration propagation in multistory buildings and resulting heavyweight floor impact sounds," J. Acoust. Soc. Am. 142, 308-316 (2017). 10.1121/1.499429028764414

J. Y. Jeon, "Subjective evaluation of floor impact noise based on the model of ACF/IACF," J. sound Vib. 241, 147-155 (2001). 10.1006/jsvi.2000.3286

J. Ryu, H. Sato, K. Kurakata, A. Hiramitsu, M. Tanaka, and T. Hirota, "Relation between annoyance and single-number quantities for rating heavy-weight floor impact sound insulation in wooden houses," J. Acoust. Soc. Am. 129, 3047-3055 (2011). 10.1121/1.356166021568408

S. Kim, J. Kim, S. Lee, H. Song, M. Song, and J. Ryu, "Effect of temporal pattern of impact sound on annoyance: Children's impact sounds on the floor," Build. Environ. 208, 108609 (2022). 10.1016/j.buildenv.2021.108609

Floor Noise, Management Centre, "Interfloor noise neighbor center 2019 civil complaint statistics status," Mon. Rep., Korea Environment Corporation, 2019.

ISO 10052, Acoustics - Field Measurements of Airborne and Impact Sound Insulation and of Service Equipment Sound - Survey Method (2021).

J. Jeong and J. Ryu, "Survey method for field measurement of rubber ball impact sound in reinforced concrete apartment houses," Acta Acust. 7, 1-12 (2023). 10.1051/aacus/2023023

J. Ryu and H. Song, "Effect of building facade on indoor transportation noise annoyance in terms of frequency spectrum and expectation for sound insulation," Appl. Acoust. 152, 21-30 (2019). 10.1016/j.apacoust.2019.03.020

S. H. Park, P. J. Lee, and B. K. Lee, "Levels and sources of neighbour noise in heavyweight residential buildings in Korea," Appl. Acoust. 120, 148-157 (2017). 10.1016/j.apacoust.2017.01.012

G. Hamerly and C. Elkan, "Learning the k in k-means," Proc. NIPS, 281-288 (2003).

P. J. Rousseeuw, "A graphical aid to the interpretation and validation of cluster analysis," J. Comput. Appl. Math. 20, 53-65 (1987). 10.1016/0377-0427(87)90125-7

C. Shi, B. Wei, S. Wei, W. Wang, H. Liu, and J. Liu, "A quantitative discriminant method of elbow point for the optimal number of clusters in clustering algorithm," EURASIP J. Wirel. Commun. Netw. 2021, 1-16 (2020). 10.1186/s13638-021-01910-w

L. Beranek, Concert Halls and Opera Houses: Music, Acoustics, and Architecture (Springer, New York, 2004), pp. 662. 10.1007/978-0-387-21636-2PMC522193

M. E. Nilsson, "A-weighted sound pressure level as an indicator of perceived loudness and annoyance of road-traffic sound," J. Sound Vib. 302, 197-207 (2007). 10.1016/j.jsv.2006.11.010

W. S. Noble, "What is a support vector machine?," Nat. biotechnolo. 24, 1565-1567 (2006). 10.1038/nbt1206-156517160063

L. E. Peterson, "K-nearest neighbor," Scholarpedia, 4, 1883 (2009). 10.4249/scholarpedia.1883

A. K. Jain, J. Mao, and K. M. Mohiuddin, "Artificial neural networks: A tutorial," Computer, 29, 31-44 (1996). 10.1109/2.485891

C. Goutte and E. Gaussier, "A probabilistic interpretation of precision, recall and F-score, with implication for evaluation," Proc. LNISA, 345-359 (2005). 10.1007/978-3-540-31865-1_25

Information

Publisher :The Acoustical Society of Korea
Publisher(Ko) :한국음향학회
Journal Title :The Journal of the Acoustical Society of Korea
Journal Title(Ko) :한국음향학회지
Volume : 42
No :6
Pages :603-616
Received Date : 2023-09-27
Revised Date : 2023-11-16
Accepted Date : 2023-11-20
DOI :https://doi.org/10.7776/ASK.2023.42.6.603

The Journal of the Acoustical Society of KoreaISSN:1225-4428(Print) 2287-3775(Online)한국음향학회

All Issue