Information set supported deep learning architectures for improving noisy image classification

Bhardwaj, Saurabh; Wang, Yizhi; Yu, Gui; Wang, Yue

doi:10.1038/s41598-023-31462-6

Cited by 2 publications

(1 citation statement)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although classical deep learning models [20][21][22][23][24][25][26][27] have demonstrated good results in bird sound recognition, the model design relies heavily on human experience and is subjective. Furthermore, the current mainstream method involves extracting bird sound signals, converting them into Mel spectra, and feeding them into a deep learning model.…”

Section: Introductionmentioning

confidence: 99%

Bird Sound Feature Extraction and Recognition Model Design Based on Neural Network Architecture Search

jiang,

zhang,

yang

2024

Preprint

View full text Add to dashboard Cite

Birds are of great significance to biodiversity. Bird sounds have obvious characteristics per species, and they are an important way forbids to communicate and transmit information. Accurate identification of bird species plays a critical role in biodiversity surveys. The development of deep learning has made it possible to identify bird species through acoustic characteristics. However, most of the deep learning-based research on bird sound recognition relies too much on traditional experience and subjective human-designed feature extraction and model design, regardless of whether they are optimal for the bird sound data. Therefore, this study proposes a deep learning model based on neural architecture search, which uses a simple and equivalent node to design the model structure for feature extraction and recognition and takes the inferring time as part of the loss function to balance classification accuracy and running time, reducing model complexity. During the feature extraction phase, the final model selects 36 as the optimal number of Mel filter banks. On a dataset of 264 bird sounds, the neural network architecture search-based model achieves an average classification accuracy of 92.44% and a maximum classification accuracy of 98.14%. This study provides a meaningful exploration for achieving bird sound recognition without relying on traditional experience and subjective human design.

show abstract

Section: Introductionmentioning

confidence: 99%

Bird Sound Feature Extraction and Recognition Model Design Based on Neural Network Architecture Search

jiang,

zhang,

yang

2024

Preprint

View full text Add to dashboard Cite

show abstract

Wear fault diagnosis in hydro-turbine via the incorporation of the IWSO algorithm optimized CNN-LSTM neural network

Dao,

Zeng,

Zou

et al. 2024

Preprint

View full text Add to dashboard Cite

Diagnosing hydro-turbine wear fault is crucial for the safe and stable operation of hydropower units. A hydro-turbine wear fault diagnosis method based on improved WT (wavelet threshold algorithm) preprocessing combined with IWSO (improved white shark optimizer) optimized CNN-LSTM (convolutional neural network-long-short term memory) is proposed. The improved WT algorithm is utilized for denoising the preprocessing of the original signals. The CNN-LSTM hydro-turbine wear fault diagnosis model is constructed. Aiming at the problem that the WSO algorithm quickly falls into local optimum and premature convergence, tent chaotic mapping is used to initialize the population and birds flock search behavior. The cosine elite variation strategy is introduced to improve convergence speed and accuracy. Hyperparameter tuning of CNN-LSTM model based on IWSO algorithm. The experimental results show that the accuracy of the proposed method reaches 96.2%, which is 8.9% higher than that of the IWSO-CNN-LSTM model without denoising. The study also found that the diagnostic accuracy of hydro-turbine wear faults increased with increasing sediment concentration in the water. This study can supplement the existing hydro-turbine condition monitoring and fault diagnosis system. Meanwhile, diagnosing wear faults in hydro-turbines can improve power generation efficiency and quality and minimize resource consumption.

show abstract

Information set supported deep learning architectures for improving noisy image classification

Cited by 2 publications

References 17 publications

Bird Sound Feature Extraction and Recognition Model Design Based on Neural Network Architecture Search

Bird Sound Feature Extraction and Recognition Model Design Based on Neural Network Architecture Search

Wear fault diagnosis in hydro-turbine via the incorporation of the IWSO algorithm optimized CNN-LSTM neural network

Contact Info

Product

Resources

About