(A) noise monitoring system for localization and classification of inter-floor noise in apartment house공동주택 층간 소음의 발생 위치 및 종류 파악을 위한 소음 감지 시스템

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 252
  • Download : 0
Due to the high population density, Korea has a very high rate of apartment house compared to other countries. In such environment, many people are unavoidably suffering from inter-floor noise, and disputes caused by inter-floor noise has become serious social problems. This paper proposes a noise monitoring system for precise data recording of inter-floor noise occurrence in apartment house. The proposed system measures the sound pressure level of noise, and estimates the direction of noise source along with the type of noise. An embedded sensor board with attached microphones is used in this system. The measurement of the noise level is implemented by digital signal processing techniques. Noise source localization is performed using estimated TDOA (Time difference of arrival) from microphone array. Noise type classification is done through the nearest neighbor classifier by extracting meaningful features from the noise signal. Recorded data from the proposed system is expected to be used as an important reference data for any case of disputes due to inter-floor noise.
Advisors
Kyung, Chong-Minresearcher경종민researcher
Description
한국과학기술원 :전기및전자공학부,
Publisher
한국과학기술원
Issue Date
2018
Identifier
325007
Language
eng
Description

학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2018.2,[iii, 38 p. :]

Keywords

Inter-floor noise▼aSound pressure level▼aMicrophone array▼aTDOA▼aSound localization▼aFeature extraction▼aNearest-neighbor classifier▼aSound classification; 층간 소음▼a소음 세기▼a마이크로폰 어레이▼a도착 시간 차이▼a소음원 위치 파악▼a특징 추출▼a최근접 분류기▼a소음 종류 분류

URI
http://hdl.handle.net/10203/266703
Link
http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=734021&flag=dissertation
Appears in Collection
EE-Theses_Master(석사논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0