• The Journal of the Acoustical Society of Korea
• /
• v.37 no.4
• /
• pp.256-261
• /
• 2018

There are three types of noise generated inside the vehicle: BSR (Buzz, Squeak, Rattle). In this paper, we propose a classifier that automatically classifies automotive BSR noise by using features extracted from deep convolutional neural networks. In the preprocessing process, the features of above three noises are represented as noise-map using STFT (Short-time Fourier Transform) algorithm. In order to cope with the problem that the position of the actual noise is unknown in the part of the generated noise map, the noise map is divided using the sliding window method. In this paper, internal parameter of the deep convolutional neural networks is visualized using the t-SNE (t-Stochastic Neighbor Embedding) algorithm, and the misclassified data is analyzed in a qualitative way. In order to analyze the classified data, the similarity of the noise type was quantified by SSIM (Structural Similarity Index) value, and it was found that the retractor tremble sound is most similar to the normal travel sound. The classifier of the proposed method compared with other classifiers of machine learning method recorded the highest classification accuracy (99.15 %).

• The Journal of the Acoustical Society of Korea
• /
• v.37 no.6
• /
• pp.469-474
• /
• 2018

As urban population increases, research on urban environmental noise is getting more attention. In this study, we classify the abnormal noise occurring in traffic situation by using a deep learning algorithm which shows high performance in recent environmental noise classification studies. Specifically, we classify the four classes of tire skidding sounds, car crash sounds, car horn sounds, and normal sounds using convolutional neural networks. In addition, we add three environmental noises, including rain, wind and crowd noises, to our training data so that the classification model is more robust in real traffic situation with environmental noises. Experimental results show that the proposed traffic sound classification model achieves better performance than the existing algorithms, particularly under harsh conditions with environmental noises.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 1996.04a
• /
• pp.246-252
• /
• 1996

본 연구는 아음속 충돌분류의 소음특성에 관한 연구로서 분류가 매끄러운 판(smooth plate)에 충돌 할 때 발생하는 충돌소음의 음압레벨, 지향성 그리고 음향파워 등을 구하기 위한 것이다. 연구방법은 Fig.1에서와 같이 노즐지름 d와 노즐과 평판과의 거리를 h라 할 때 노즐상류측에 있는 서지 탱크(surge tank)의 압력이 1.0atg에 도달한 상태에서 단계적으로 강하시키면서 h/d에 따른 충돌소음의 레벨을 측정하였다. 또한 탱크압력을 일정하게 유지시킨 상태에서 충돌소음의 지향성을 측정하고 음향파워를 계산하였다. 자유분류인 경우에도 같은 방법으로 측정하여 충돌음의 경우와 비교 고찰하였다.

• Journal of Broadcast Engineering
• /
• v.25 no.6
• /
• pp.845-853
• /
• 2020

In this paper, we propose a method for classifying environmental sound for selective noise cancellation in industrial sites. Noise in industrial sites causes hearing loss in workers, and researches on noise cancellation have been widely conducted. However, the conventional methods have a problem of blocking all sounds and cannot provide the optimal operation per noise type because of common cancellation method for all types of noise. In order to perform selective noise cancellation, therefore, we propose a method for environmental sound classification based on deep learning. The proposed method uses new sets of acoustic features consisting of temporal and statistical properties of Mel-spectrogram, which can overcome the limitation of Mel-spectrogram features, and uses convolutional neural network as a classifier. We apply the proposed method to five-class sound classification with three noise classes and two non-noise classes. We confirm that the proposed method provides improved classification accuracy by 6.6% point, compared with that using conventional Mel-spectrogram features.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 1996.10a
• /
• pp.65-70
• /
• 1996

엔진소음을 소음특성에 따라 분류하면 공력소음(Aerodynamic Noise), 연소소음(Combustion Noise), 기계적인 소음(Mechanical Noise)으로 나눌 수 있으며 소음원의 종류에 따라 분류하면 배기계소음(Exhaust System Noise)으로 나눌 수 있으며 소음원의 종류에 따라 분류하면 배기계소음(Exhaust System Noise), 흡기계소음(Intake System Noise), 냉각계소음(Cooling System Noise), 엔진표면소음(Engine System Noise)등으로 분류할 수 있다. 이러한 여러소음중 엔진 내부의 유동에 의한 흡배기계통으로의 소음방출은 자동차 실 내외 소음의 중요한 문제로 대두되는데, 이를 줄이기 위해 그 동안 소음기 등의 서브시스템의 형태와 그 위치조정에 관한 연구가 수행되어 왔다. 그러나 이것이 비용 또는 성능에 영향을 미치므로 본질적인 소음원을 규명해 내는 것이 필요하게 되었다. 흡배기계의 소음은 엔진의 흡입, 배기행 정시 피스톤의 운동에 의해 팽창 및 압축파 형태의 압력파(pressure wave)로 발생하게 되고, 밸브근방에서는 유동의 박리(separation)에 의해 발생하게 된다. 소음기 등의 서브시스템에서도 유동의 박리에 의해 발생하게 되며 특히 배기행정시 발생하는 압력파는 비선형영역에 있게된다. 흡기소음은 배기에 비해 그 크기가 작아서 그동안 등한시 되어왔으나 이것이 소비자의 불평요인으로 작용하므로써 이에 대한 연구도 활발히 수행되어야 한다. Bender, Bramer[1]는 흡배기계 소음의 외부 방사에 관하여 전반적으로 기술하였고 Sierens등[2]은 흡기계에서 1차원 MOC(Method of Characteristics)방법으로 비정상 유동해석을 하고 실험결과와 비교하였다. J.S.Lamancusa 등[3]은 흡기 소음원을 실험을 통해 예측하였고, 흡기소음도 비선형 거동을 보인다고 밝혔다. Yositaka Nishio 등[4]은 새로운 흡기실험장치를 고안하여 공명기(resonator)의 위치 변화에 의한 저소음 흡기계를 설계 초기단계에서부터 적용하려 하였다. 일반적으로 흡배기계의 복잡한 형상 때문에 대부분 실험을 통해 문제를 해결하려 하였고, 수치해석은 피스톤의 운동을 배제한 단순화한 흡배기계의 정상상태 유동해석이 주를 이루어왔다. Taghaui and Dupont 등[5]은 KIVA코드를 사용하여 흡기포트와 연소실 그리고 밸브의 움직임을 동시에 고려한 수치해석을 도입하였다. 하지만 이들이 밸브의 운동을 고려하기 위해 사용한 이동격자는 격자점은 시간에 따라 변화하지만 그 격자의 수가 일정하게 유지되어 있어서 밸브의 완전개폐를 해석할 수가 없다. 강희정[6]은 단일 실린더와 단일 배기밸브를 갖는 문제로 단순화하여 피스톤과 밸브의 움직임을 고려하므로써 배기행정 후 소음이 어떻게 전파해 나가는가를 연구하였다. 본 연구에서도 최소밸브간격과 최대밸브간격 사이에서만 계산이 가능하나 흡기의 경우는 밸브가 닫힐 때 생기는 압력파가 중요하므로 실린더와 밸브사이에 벽면조건을 주어 밸브의 개폐를 모사하였다.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.6
• /
• pp.201-208
• /
• 2014

In this paper, we propose the classifier structure design algorithm using DTW. Proposed algorithm uses DTW result to design the binary tree architecture based on the SVM which classify the multi-class data. Design the binary tree architecture for Support Vector Machine(SVM-BTA) using the threshold criterion calculated by the sum columns in square matrix which components are the reference data from each class. For comparison the performance of the proposed algorithm, compare the results of classifiers which binary tree structure are designed based on database and k-means algorithm. The data used for classification is 333 signals from 18 classes of underwater transient noise. The proposed classifier has been improved classification performance compared with classifier designed by database system, and probability of detection for non-biological transient signal has improved compare with classifiers using k-means algorithm. The proposed SVM-BTA classified 68.77% of biological sound(BO), 92.86% chain(CHAN) the mechanical sound, and 100% of the 6 kinds of the other classes.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.6
• /
• pp.603-616
• /
• 2023

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 L_eq 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.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 1994.04a
• /
• pp.191-194
• /
• 1994

본 연구는 디퓨저소음기의 여러가지 설계인자가 소음성능에 미치는 영향을 알아보기 위한 것으로 오리피스 상부의 분류 압력, 흡음재의 두께와 밀도 및 디퓨저의 단수를 변화시켜 그에 따른 영향을 실험적으로 구하였다.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2007.05a
• /
• pp.872-876
• /
• 2007

Road traffic noise map is effective method to save cost and time for environmental noise assessment. Generally, noise is calculated by using theoretical equation of noise prediction, and the calculated result can be influenced by various input factors. Especially, domestic vehicle classification method for traffic flow and heavy vehicle percentage is different from that of foreign countries. Thus, this can cause effect on the noise prediction results. In this study, noise prediction results by using domestic vehicle classification method are compared with those by foreign methods.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.22 no.2
• /
• pp.193-197
• /
• 2012

Road traffic noise map is effective method to save cost and time for environmental noise assessment. Generally, noise is calculated by using theoretical equation of noise prediction, and the calculated result can be influenced by various input factors. Especially, domestic vehicle classification method for traffic flow and heavy vehicle percentage is different from that of foreign countries. Thus, this can cause effect on the noise prediction results. In this study, noise prediction results by using domestic vehicle classification method are compared with those by foreign methods.