• 대한의용생체공학회:의공학회지
• /
• 제34권1호
• /
• pp.8-13
• /
• 2013

Persons with sensorineural hearing impairment have troubles in hearing at noisy environments because of their deteriorated hearing levels and low-spectral resolution of the auditory system and therefore, they use hearing aids to compensate weakened hearing abilities. Various algorithms for hearing loss compensation and environmental noise reduction have been implemented in the hearing aid; however, the performance of these algorithms vary in accordance with external sound situations and therefore, it is important to tune the operation of the hearing aid appropriately in accordance with a wide variety of sound situations. In this study, a sound classification algorithm that can be applied to the hearing aid was suggested. The proposed algorithm can classify the different types of speech situations into four categories: 1) speech-only, 2) noise-only, 3) speech-in-noise, and 4) music-only. The proposed classification algorithm consists of two sub-parts: a feature extractor and a speech situation classifier. The former extracts seven characteristic features - short time energy and zero crossing rate in the time domain; spectral centroid, spectral flux and spectral roll-off in the frequency domain; mel frequency cepstral coefficients and power values of mel bands - from the recent input signals of two microphones, and the latter classifies the current speech situation. The experimental results showed that the proposed algorithm could classify the kinds of speech situations with an accuracy of over 94.4%. Based on these results, we believe that the proposed algorithm can be applied to the hearing aid to improve speech intelligibility in noisy environments.

• 한국소음진동공학회논문집
• /
• 제25권4호
• /
• pp.299-305
• /
• 2015

A statistical annoyance model to railway noise at platform was proposed by jury evaluation test performed in hearing laboratory. ITX-Saemaeul and Mugunghwa were chosen as the noise sources of the test, and announcement sound was included to simulate real situation. Logistic regression analysis produced %HA_LAB curve. Hosmer-Lemeshow test and classification accuracy test were used to verify the model's statistical significance. It was shown that the model which was generated from relatively small number of samples is statistically significant.

• 한국도로학회논문집
• /
• 제17권6호
• /
• pp.11-18
• /
• 2015

PURPOSES : The purpose of this thesis is to evaluate the effectiveness of an active noise cancellation (ANC) system in reducing the traffic noise level against frequencies from the predictive model developed by previous research. The predictive model is based on ISO 9613-2 standards using the Noble close proximity (NCPX) method and the pass-by method. This means that the use of these standards is a powerful tool for analyzing the traffic noise level because of the strengths of these methods. Traffic noise analysis was performed based on digital signal processing (DSP) for detecting traffic noise with the pass-by method at the test site. METHODS : There are several analysis methods, which are generally divided into three different types, available to evaluate traffic noise predictive models. The first method uses the classification standard of 12 vehicle types. The second method is based on a standard of four vehicle types. The third method is founded on 5 types of vehicles, which are different from the types used by the second method. This means that the second method not only consolidates 12 vehicle types into only four types, but also that the results of the noise analysis of the total traffic volume are reflected in a comparison analysis of the three types of methods. The constant percent bandwidth (CPB) analysis was used to identify the properties of different frequencies in the frequency analysis. A-weighting was applied to the DSP and to the transformation process from analog to digital signal. The root mean squared error (RMSE) was applied to compare and evaluate the predictive model results of the three analysis methods. RESULTS : The result derived from the third method, based on the classification standard of 5 vehicle types, shows the smallest values of RMSE and max and min error. However, it does not have the reduction properties of a predictive model. To evaluate the predictive model of an ANC system, a reduction analysis of the total sound pressure level (TSPL), dB(A), was conducted. As a result, the analysis based on the third method has the smallest value of RMSE and max error. The effect of traffic noise reduction was the greatest value of the types of analysis in this research. CONCLUSIONS : From the results of the error analysis, the application method for categorizing vehicle types related to the 12-vehicle classification based on previous research is appropriate to the ANC system. However, the performance of a predictive model on an ANC system is up to a value of traffic noise reduction. By the same token, the most appropriate method that influences the maximum reduction effect is found in the third method of traffic analysis. This method has a value of traffic noise reduction of 31.28 dB(A). In conclusion, research for detecting the friction noise between a tire and the road surface for the 12 vehicle types needs to be conducted to authentically demonstrate an ANC system in the Republic of Korea.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2006년도 추계학술대회논문집
• /
• pp.757-762
• /
• 2006

The method of promoing sound surroundings with the new concept named 'Soundscape' attracts the public attention. This new method is the way of active promoting acoustic surroundings to offer the vitality, comfort and identity of urban space and relative quietness by masking the noise with natural and signal sounds. Therefore, this research has the purpose of finding out the method of soundscape concept of urban public space for the comfort acoustic surroundings.

• 한국음향학회지
• /
• 제38권1호
• /
• pp.39-46
• /
• 2019

본 논문에서는 합성곱 신경망(Convolutional Neural Network, CNN) 구조를 이용하여 잡음 환경에서 음향신호를 분류할 때, 인식률을 높이는 결합 특징을 제안한다. 반면, Wiener filter를 이용한 강인한 log Mel-filter bank와 PNCCs(Power Normalized Cepstral Coefficients)는 CNN 구조의 입력으로 사용되는 2차원 특징을 형성하기 위해 추출됐다. 자연환경에서 43종의 조류 울음소리를 포함한 ebird 데이터베이스는 분류 실험을 위해 사용됐다. 잡음 환경에서 결합 특징의 성능을 평가하기 위해 ebird 데이터베이스를 3종류의 잡음을 이용하여 4개의 다른 SNR (Signal to Noise Ratio)(20 dB, 10 dB, 5 dB, 0 dB)로 합성했다. 결합 특징은 Wiener filter를 적용한 log-Mel filter bank, 적용하지 않은 log-Mel filter bank, 그리고 PNCC와 성능을 비교했다. 결합 특징은 잡음이 없는 환경에서 1.34 % 인식률 향상으로 다른 특징에 비해 높은 성능을 보였다. 추가적으로, 4단계 SNR의 잡음 환경에서 인식률은 shop 잡음 환경과 schoolyard 잡음 환경에서 각각 1.06 %, 0.65 % 향상했다.

• Child Health Nursing Research
• /
• 제26권2호
• /
• pp.296-308
• /
• 2020

Purpose: The purpose of this study was to identify the noise level and frequency experienced by premature infants receiving incubator care in the neonatal intensive care unit (NICU). Methods: The participants were 20 premature infants receiving incubator care in the NICU of a university hospital in Daejeon Metropolitan city. The noise level was measured using a professional sound-level meter (ET-958, FLUS, Shenzhen, China) based on a noise classification table developed by the author. The data were analyzed with descriptive statistics, the t-test, analysis of variance, and Pearson correlation coefficients using SPSS for Windows version 22.0. Results: The average noise level experienced by premature infants receiving incubator care in the NICU was 51.25 dB (range: 45.0~81.7 dB). The frequency of noises was highest for factors related to nursing activities (40.3%), followed by human factors (29.1%), machine alarm sounds (20.1%), incubator operation (6.6%), and internal environmental factors (3.9%). Conclusion: According to the above results, the noise level experienced by premature infants receiving incubator care in the NICU exceeded the recommendations of the American Academy of Pediatrics. Therefore, it is necessary to develop an interventional program to reduce noise in the NICU, and to conduct follow-up studies to verify its effectiveness.

• 한국해양공학회지
• /
• 제34권4호
• /
• pp.277-284
• /
• 2020

Underwater acoustics, which is the study of phenomena related to sound waves in water, has been applied mainly in research on the use of sound navigation and range (SONAR) systems for communication, target detection, investigation of marine resources and environments, and noise measurement and analysis. The main objective of underwater acoustic remote sensing is to obtain information on a target object indirectly by using acoustic data. Presently, various types of machine learning techniques are being widely used to extract information from acoustic data. The machine learning techniques typically used in underwater acoustics and their applications in passive SONAR systems were reviewed in the first two parts of this work (Yang et al., 2020a; Yang et al., 2020b). As a follow-up, this paper reviews machine learning applications in SONAR signal processing with a focus on active target detection and classification.

• 한국음향학회지
• /
• 제42권6호
• /
• pp.603-616
• /
• 2023

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.

• 한국군사과학기술학회지
• /
• 제20권4호
• /
• pp.505-513
• /
• 2017

Cavitation is a phenomenon caused by vapour cavities that is produced in rapid pressure changes. When the cavitation happened, the sound pressure level of a underwater radiated noise is increased rapidly. As a result, it can increase the probability of the identification or classification of a our warship's acoustic signature by an enemy ship. However, there is a problem that it is hard to precisely detect the occurrence of a cavitation noise. Therefore, this paper presents recent improvements in terms of the cavitation noise measurement by using continuous wavelet transform and DEMON(Detection of Envelope Modulation on Noise) signal processing. Then, we present that the suggested scheme is more suitable for detecting the cavitation than existing algorithms.

• 한국음향학회지
• /
• 제39권5호
• /
• pp.406-413
• /
• 2020

본 논문에서는 조류와 양서류 울음소리의 구별 정확도를 높이기 위해 게이트 선형유닛과 자가주의 집중 모듈을 활용해서 데이터의 중요한 부분을 중심으로 특징 추출 및 데이터 프레임의 중요도를 판별해 구별 정확도를 높인다. 이를 위해 먼저 1차원의 음향 데이터를 로그 멜 스펙트럼으로 변환한다. 로그 멜 스펙트럼에서 배경잡음같이 중요하지 않은 정보는 게이트 선형유닛을 거쳐 제거한다. 그러고 난 뒤 시간 축에 자가주의집중기법을 적용해 구별 정확도를 높인다. 사용한 데이터는 자연환경에서 멸종위기종을 포함한 조류 6종의 울음소리와 양서류 8종의 울음소리로 구성했다. 그 결과, 게이트 선형유닛 알고리즘과 시간 축에서 자가주의집중을 적용한 구조의 평균 정확도는 조류를 구분했을 때 91 %, 양서류를 구분했을 때 93 %의 분류율을 보였다. 또한, 기존 알고리즘보다 약 6 % ~ 7 % 향상된 정확도를 보이는 것을 확인했다.