Automatic classification of traffic noise

Acoustic signal classification consists of extracting the features from a sound, and of using these features to identify classes the sound is liable to fit •• Different types of noise coming from different vehicles mix in the environment and identifying a particular vehicle is a challenging one. Feature Extraction is done to identify the characteristic of the vehicle. The characteristic of each vehicle will be used to detect its presence and classify its type. Six different features of the vehicle acoustic signals are calculated and then further utilized as input to the classification system. These features include Signal Energy, Energy Entropy, Zero-Crossing Rate, Spectral Roll-Off, Spectral Centroid and Spectral Flux. All these features are extracted from each and every acoustic signal of the vehicles.

show abstract

“…Those statistic values are the final feature values that characterize the input audio signal. The features considered here are [8,9,10],…”

Section: Experimentation and Resultsmentioning

confidence: 99%

Acoustic signal based feature extraction for vehicular classification

Padmavathi

Shanmugapriya

Kalaivani

2010

2010 3rd International Conference on Advanced Computer Theory and Engineering(ICACTE)

View full text Add to dashboard Cite

show abstract

“…The major challenge in this field is the automatic classification of audio [27]. Recent studies on the classification of traffic noise have been conducted, for example, to identify the type of vehicle through roadside noise [28,29] and evaluate passengers' subjective experience by categorizing the cabin's interior noise [30]. However, compared with traffic noise, the factors influencing vehicle interior noise of subway trains are considerably more complicated.…”

Section: Introductionmentioning

confidence: 99%

Using Vehicle Interior Noise Classification for Monitoring Urban Rail Transit Infrastructure

Wang

et al. 2020

Sensors

View full text Add to dashboard Cite

This study developed a multi-classification model for vehicle interior noise from the subway system, collected on smartphones. The proposed model has the potential to be used to analyze the causes of abnormal noise using statistical methods and evaluate the effect of rail maintenance work. To this end, first, we developed a multi-source data (audio, acceleration, and angle rate) collection framework via smartphone built-in sensors. Then, considering the Shannon entropy, a 1-second window was selected to segment the time-series signals. This study extracted 45 features from the time- and frequency-domains to establish the classifier. Next, we investigated the effects of balancing the training dataset with the Synthetic Minority Oversampling Technique (SMOTE). By comparing and analyzing the classification results of importance-based and mutual information-based feature selection methods, the study employed a feature set consisting of the top 10 features by importance score. Comparisons with other classifiers indicated that the proposed XGBoost-based classifier runs fast while maintaining good accuracy. Finally, case studies were provided to extend the applications of this classifier to the analysis of abnormal vehicle interior noise events and evaluate the effects of rail grinding.

show abstract

“…In combination with a Multilayer Neural Network, both MPEG-7 and MFCC attained the highest averaged recognition accuracies in a corpus containing road vehicles, aircrafts, trains and industrial noises. Besides comparing different signal features, Fisher Linear Discriminant and K-Nearest Neighbor (KNN) were evaluated in (Sobreira et al, 2008) for the recognition of specifically road traffic noise sources (cars, trucks and scooters). Experimental results showed that KNN was the machine learning technique yielding the best performance, specifically when considering feature combination (MFCC, Sub-band Energy Ratio (SBER) and Spectral Roll-Off (SRO)).…”

Section: Related Workmentioning

confidence: 99%

Hierarchical Classification of Environmental Noise Sources Considering the Acoustic Signature of Vehicle Pass-Bys

Valero¹,

Álías²

2012

Archives of Acoustics

View full text Add to dashboard Cite

This work is focused on the automatic recognition of environmental noise sources that affect humans' health and quality of life, namely industrial, aircraft, railway and road traffic. However, the recognition of the latter, which have the largest influence on citizens' daily lives, is still an open issue. Therefore, although considering all the aforementioned noise sources, this paper especially focuses on improving the recognition of road noise events by taking advantage of the perceived noise differences along the road vehicle pass-by (which may be divided into different phases: approaching, passing and receding).To that effect, a hierarchical classification scheme that considers these phases independently has been implemented. The proposed classification scheme yields an averaged classification accuracy of 92.5%, which is, in absolute terms, 3% higher than the baseline (a traditional flat classification scheme without hierarchical structure). In particular, it outperforms the baseline in the classification of light and heavy vehicles, yielding a classification accuracy 7% and 4% higher, respectively. Finally, listening tests are performed to compare the system performance with human recognition ability. The results reveal that, although an expert human listener can achieve higher recognition accuracy than the proposed system, the latter outperforms the non-trained listener in 10% in average.

show abstract

Automatic classification of traffic noise

Cited by 15 publications

References 5 publications

Acoustic signal based feature extraction for vehicular classification

Acoustic signal based feature extraction for vehicular classification

Using Vehicle Interior Noise Classification for Monitoring Urban Rail Transit Infrastructure

Hierarchical Classification of Environmental Noise Sources Considering the Acoustic Signature of Vehicle Pass-Bys

Contact Info

Product

Resources

About