Acoustic Anomaly Detection for Machine Sounds based on Image Transfer Learning

Müller, Robert; Ritz, Fabian; Illium, Steffen; Linnhoff‐Popien, Claudia

doi:10.5220/0010185800490056

Cited by 33 publications

(6 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The model was pre-trained with the ImageNet dataset, instead (Deng et al, 2009). ImageNet pre-trained models have been successfully used to boost the performance of CNNs models in audio classification tasks in recent years (Gwardys and Grzywczak, 2014;Müller et al, 2020;Palanisamy et al, 2020;Zhong et al, 2020;Gong et al, 2021).…”

Section: Deep Learning Algorithmsmentioning

confidence: 99%

Automatic acoustic recognition of pollinating bee species can be highly improved by Deep Learning models accompanied by pre-training and strong data augmentation

et al. 2023

View full text Add to dashboard Cite

IntroductionBees capable of performing floral sonication (or buzz-pollination) are among the most effective pollinators of blueberries. However, the quality of pollination provided varies greatly among species visiting the flowers. Consequently, the correct identification of flower visitors becomes indispensable to distinguishing the most efficient pollinators of blueberry. However, taxonomic identification normally depends on microscopic characteristics and the active participation of experts in the decision-making process. Moreover, the many species of bees (20,507 worldwide) and other insects are a challenge for a decreasing number of insect taxonomists. To overcome the limitations of traditional taxonomy, automatic classification systems of insects based on Machine-Learning (ML) have been raised for detecting and distinguishing a wide variety of bioacoustic signals, including bee buzzing sounds. Despite that, classical ML algorithms fed by spectrogram-type data only reached marginal performance for bee ID recognition. On the other hand, emerging systems from Deep Learning (DL), especially Convolutional Neural Networks (CNNs), have provided a substantial boost to classification performance in other audio domains, but have yet to be tested for acoustic bee species recognition tasks. Therefore, we aimed to automatically identify blueberry pollinating bee species based on characteristics of their buzzing sounds using DL algorithms.MethodsWe designed CNN models combined with Log Mel-Spectrogram representations and strong data augmentation and compared their performance at recognizing blueberry pollinating bee species with the current state-of-the-art models for automatic recognition of bee species.Results and DiscussionWe found that CNN models performed better at assigning bee buzzing sounds to their respective taxa than expected by chance. However, CNN models were highly dependent on acoustic data pre-training and data augmentation to outperform classical ML classifiers in recognizing bee buzzing sounds. Under these conditions, the CNN models could lead to automating the taxonomic recognition of flower-visiting bees of blueberry crops. However, there is still room to improve the performance of CNN models by focusing on recording samples for poorly represented bee species. Automatic acoustic recognition associated with the degree of efficiency of a bee species to pollinate a particular crop would result in a comprehensive and powerful tool for recognizing those that best pollinate and increase fruit yields.

show abstract

Section: Deep Learning Algorithmsmentioning

confidence: 99%

Automatic acoustic recognition of pollinating bee species can be highly improved by Deep Learning models accompanied by pre-training and strong data augmentation

et al. 2023

View full text Add to dashboard Cite

show abstract

“…An embedded spatial similarity measure using a neural network and attention mechanisms that absorb time-frequency stretching are the two main components of SPIDERnet's detection system for anomalous sounds. Instead of utilizing deep AEs, Müller et al [5] suggest neural networks that are pre-trained on the image classification task to extract features. Anomaly detection models are subsequently trained using these characteristics.…”

Section: Related Workmentioning

confidence: 99%

An EfficientNet-Based Weighted Ensemble Model for Industrial Machine Malfunction Detection Using Acoustic Signals

et al. 2022

View full text Add to dashboard Cite

Detecting and preventing industrial machine failures are significant in the modern manufacturing industry because machine failures substantially increase both maintenance and manufacturing costs. Recently, state-of-the-art deep learning techniques that use acoustic signals have been widely applied to solve industrial machine malfunction detection problems in order to reduce maintenance and manufacturing costs. The authors of this research propose a deep learning-based industrial machine malfunction detection model that uses acoustic signals to classify normal and abnormal conditions of industrial machines. In particular, a weighted ensemble model based on EfficientNet-B0, B5, and B7 is considered to improve classification performance. Case studies involving an open dataset for Malfunctioning Industrial Machine Investigation and Inspection (MIMII) validate that the proposed EfficientNet-based weighted ensemble model provides better classification performance than individual classifiers and other ensemble models.

show abstract

“…Muller et al [ 3 ] proposed the use of ImageNet pre-trained CNNs (e.g., ResNet-18 [ 12 ] and AlexNet [ 13 ]) for automatic feature extraction from Mel-spectrograms. The extracted features are subsequently fed to traditional machine learning methods such as Gaussian Mixture Models and Support Vector Machines for inference.…”

Section: Related Workmentioning

confidence: 99%

“…A variety of deep learning-driven techniques have been introduced for acoustic anomaly detection (AAD) in recent years, including dense autoencoders [ 1 , 2 ], convolutional autoencoders [ 2 ], and pre-trained convolutional neural networks [ 3 ]. Although deep learning-driven methods have demonstrated excellent accuracy in detecting anomalous sounds, the widespread adoption of these methods remains limited.…”

Section: Introductionmentioning

confidence: 99%

OutlierNets: Highly Compact Deep Autoencoder Network Architectures for On-Device Acoustic Anomaly Detection

Abbasi

Famouri²,

Shafiee

et al. 2021

Sensors

View full text Add to dashboard Cite

Human operators often diagnose industrial machinery via anomalous sounds. Given the new advances in the field of machine learning, automated acoustic anomaly detection can lead to reliable maintenance of machinery. However, deep learning-driven anomaly detection methods often require an extensive amount of computational resources prohibiting their deployment in factories. Here we explore a machine-driven design exploration strategy to create OutlierNets, a family of highly compact deep convolutional autoencoder network architectures featuring as few as 686 parameters, model sizes as small as 2.7 KB, and as low as 2.8 million FLOPs, with a detection accuracy matching or exceeding published architectures with as many as 4 million parameters. The architectures are deployed on an Intel Core i5 as well as a ARM Cortex A72 to assess performance on hardware that is likely to be used in industry. Experimental results on the model’s latency show that the OutlierNet architectures can achieve as much as 30x lower latency than published networks.

show abstract

Acoustic Anomaly Detection for Machine Sounds based on Image Transfer Learning

Cited by 33 publications

References 36 publications

Automatic acoustic recognition of pollinating bee species can be highly improved by Deep Learning models accompanied by pre-training and strong data augmentation

Automatic acoustic recognition of pollinating bee species can be highly improved by Deep Learning models accompanied by pre-training and strong data augmentation

An EfficientNet-Based Weighted Ensemble Model for Industrial Machine Malfunction Detection Using Acoustic Signals

OutlierNets: Highly Compact Deep Autoencoder Network Architectures for On-Device Acoustic Anomaly Detection

Contact Info

Product

Resources

About