A Robust Feature Extraction Algorithm for the Classification of Acoustic Targets in Wild Environments

Huang, Jingchang; Xiao, Shiliang; Zhou, Qianwei; Guo, Feng; You, X. Z.; Li, Haiyan; Li, Baoqing

doi:10.1007/s00034-014-9953-8

Cited by 8 publications

(5 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The sound pressure level (SPL) of light-wheeled vehicle and the tracked vehicle are 75dB and 90dB respectively (The SPL is measured by the sound pressure meter HT-8352). Table 6 and Table 7 have shown the classification results of target vehicles using the method proposed in reference [27] and our proposed classification algorithm, respectively. During the test, each frame signal corresponds to one classification result.…”

Section: Rmse(θ)mentioning

confidence: 99%

“…In previous studies, our research team has designed a small-aperture microphone array system [23] for recognizing moving vehicle targets and has carried out related algorithm research in acoustic signal enhancement [24], target detection [25], [26], target classification [27], [28] and DOA estimation [29]- [31]. Based on our previous research, we aimed to design a microphone array node with ultra-low power by equipping the proposed robust practical algorithms.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Single-Mode Wild Area Surveillance Sensor With Ultra-Low Power Design Based on Microphone Array

et al. 2019

Self Cite

View full text Add to dashboard Cite

Acoustic sensors are used as an important sensor component in wireless sensor networks (WSNs) for wild environmental monitoring, because of its small size, light weight, and low power consumption. To further utilize the superiorities of acoustic sensor, this paper aims to design a single-mode wild area surveillance sensor based on acoustic sensors, which have the advantages of practicality, low hardware power consumption, and low software complexity. The proposed algorithm can effectively suppress wind noise and improve the performance of target detection, classification and direction of arrival (DOA) estimation. The power consumption test results show that the designed micro-sensor node has low power consumption of about 13.8 mW in on-duty mode and long-term continuous monitoring capability of about 33 days. The field experiment results reveal that the node has favorable performance in detection (detection rate as high as 96% with false alarm rate under 5%), tracking (error is less than 7.6 degree), and target classification (accuracy is greater than 92.6%).

show abstract

Section: Rmse(θ)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Single-Mode Wild Area Surveillance Sensor With Ultra-Low Power Design Based on Microphone Array

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…The Mel scale describes the nonlinearity of the human ear frequency. The relationship between the Mel frequency and the frequency is expressed by the following equation 3 (Huang, Xiao, & Zhou, 2015):…”

Section: Static Characteristic Parameter Extractionmentioning

confidence: 99%

Wood material recognition for industrial applications

Liu

Deng

et al. 2018

Systems Science & Control Engineering

View full text Add to dashboard Cite

Material recognition is an essential problem in the industrial automation community. In this study, we develop a machine learning method to identify the wood material. We extract various feature descriptors for the sound signal and perform a comprehensive comparison with the common classifier. The experimental validations achieve the best feature combination. Besides, we developed a practical stylus to collect sound signal from the wooden samples and present promising preliminary results.

show abstract

“…This result indicated that carefully capturing the acoustic component of bird sounds can be successfully applied for recognizing bird species. In addition, previous studies have demonstrated that characterizing the target acoustic component using well designed features can significantly improve the classification performance [8]- [11].…”

Section: Introductionmentioning

confidence: 99%

Investigation of Different CNN-Based Models for Improved Bird Sound Classification

Xie

Zhu

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Automatic bird sound classification plays an important role in monitoring and further protecting biodiversity. Recent advances in acoustic sensor networks and deep learning techniques provide a novel way for continuously monitoring birds. Previous studies have proposed various deep learning based classification frameworks for recognizing and classifying birds. In this study, we compare different classification models and selectively fuse them to further improve bird sound classification performance. Specifically, we not only use the same deep learning architecture with different inputs but also employ two different deep learning architectures for constructing the fused model. Three types of time-frequency representations (TFRs) of bird sounds are investigated aiming to characterize different acoustic components of birds: Mel-spectrogram, harmonic-component based spectrogram, and percussive-component based spectrogram. In addition to different TFRs, a different deep learning architecture, SubSpectralNet, is employed to classify bird sounds. Experimental results on classifying 43 bird species show that fusing selected deep learning models can effectively increase the classification performance. Our best fused model can achieve a balanced accuracy of 86.31% and a weighted F1-score of 93.31%. INDEX TERMS Bird sound classification, deep learning, class-based late fusion, time-frequency representation.

show abstract

A Robust Feature Extraction Algorithm for the Classification of Acoustic Targets in Wild Environments

Cited by 8 publications

References 16 publications

Single-Mode Wild Area Surveillance Sensor With Ultra-Low Power Design Based on Microphone Array

Single-Mode Wild Area Surveillance Sensor With Ultra-Low Power Design Based on Microphone Array

Wood material recognition for industrial applications

Investigation of Different CNN-Based Models for Improved Bird Sound Classification

Contact Info

Product

Resources

About