Deep learning for unsupervised feature extraction in audio signals: Monaural source separation

Nykaza, Edward T.; Boedihardjo, Arnold P.; Oates, Tim; Netchaev, Anton; Bunkley, Steven L.; Blevins, Matthew G.

doi:10.1121/1.4971016

Cited by 4 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If the content of each image is labeled based on the manual processing method, the cost will be relatively high. erefore, labeling the content of images based on the intelligent methods has become the main research direction in the field of computer technology at present [1][2][3].…”

Section: Introductionmentioning

confidence: 99%

Attention Feature Network Extraction Combined with the Generation Algorithm of Multimedia Image Description

Sun

2021

Advances in Multimedia

View full text Add to dashboard Cite

In view of the issue that the features of the images in the shallow layer cannot be fully utilized when the image description is generated and the target association of the image cannot be sufficiently obtained, a generation method for the description of the acquisition of attention images is put forward in this paper. The proportions of the features of images at various depths are autonomously assigned based on the content data of the language model, and the images thus generated are all pictures with image features with attention. In this way, the effect of description generation of images has been improved. After the testing of the database, the results indicate that the calculation method of the algorithm put forward in this paper is more accurate than the top-down multimedia image algorithm generated by a single attention.

show abstract

Section: Introductionmentioning

confidence: 99%

Attention Feature Network Extraction Combined with the Generation Algorithm of Multimedia Image Description

Sun

2021

Advances in Multimedia

View full text Add to dashboard Cite

show abstract

“…Given that various high-performance computation subpaths are different in the accuracy of recognition, the application of SVM combined with the KNN algorithm can be implemented based on the characteristic vector of 3D images according to high-performance calculation. From the nal experimental results, it can be seen that the proposed method can be applied to the secondary recognition algorithm for 3D image characteristics based on the criteria of baroclinic distance [3][4][5]. 3D images have been massively used in s high-resolution processing, characteristic extraction, image classi cation, and many other elds attributing to their superior all-day, real-time, long-range, and high-resolution features.…”

Section: Introductionmentioning

confidence: 99%

Visualization of the Residual Network for 3D Image Recognition considering the SVM Combined with the K-Nearest Neighbor Algorithm

Liu¹

2022

Mobile Information Systems

View full text Add to dashboard Cite

The support vector machine (SVM) combined with the K-nearest neighbor (KNN) algorithm is applied to the 3D image recognition algorithm to cope with the issues of 3D image recognition in the image processing process. In this paper, the KNN algorithm is used to extend the eigenvalues of the residual network from frequency to complex plane according to the eigenvalues of 3D images, and the relevant data are extracted from the images by using the corresponding separation rules of the SVM. Subsequently, a sparse observation model is established based on the SVM combined with the KNN, and the 3D image processing issue is converted to a residual network visualization issue of 3D image recognition by establishing a parameterized database. Meanwhile, detection of high-resolution distance of 3D images is conducted, and the variational inference method is used to visualize and analyze the 3D images accordingly. Finally, through the experimental study, it can be known that the method of SVM combined with the KNN algorithm can reach an accuracy of up to 94.18% in the dataset of the Princeton 3D polygonal models. After comparison with the existing SVM-KNN method and deep learning, it can be concluded that the method put forward in this paper has a higher recognition rate and stronger anti-interference capacity, and the algorithm has a superior convergence speed with less adjustment parameters.

show abstract

“…Meanwhile, the computer cannot understand all the information contained in the image. Based on this, using deep learning to extract image features has become a hot research direction [3][4][5]. The emerging neural network technology can simulate the interaction between the biological neural system and the real world, and has achieved some research results in the fields of artificial intelligence and pattern recognition.…”

Section: Introductionmentioning

confidence: 99%

Thermal energy diagnosis of boiler plant by computer image processing and neural network technology

Sang

Sun

2020

THERM SCI

View full text Add to dashboard Cite

The paper aims to study the identification and diagnosis of infrared thermal fault of airborne circuit board of equipment, expand the application of intelligent algorithm in infrared thermal fault diagnosis, and promote the development of computer image processing technology and neural network technology in the field of thermal diagnosis. Taking the airborne circuit board in the boiler plant as the research object, first, the sequential analysis method was selected to collect the temperature changes during the operation of the circuit board. Second, on the basis of convolutional neural network, the program was written in Python, and the Relu function was used as the activation function establish the thermal fault diagnosis method of the on-board circuit board of the boiler plant equipment based on the convolutional neural network model. Third, based on the support vector machine intelligent algorithm, genetic algorithm was used to optimize the parameters, and combined with the grey prediction model, the infrared thermal fault diagnosis scheme of the circuit board of the multistage support vector machine boiler plant equipment was constructed. The results showed that the accuracy of the model after 6000 iterations was stable between 0.92-0.96, and the loss function value was stable at about 0.17. After the optimization of genetic algorithm, the accuracy of thermal fault diagnosis based on support vector machine model was optimized. Compared with grey prediction model, the accuracy of support vector machine model for fault diagnosis was higher, mean square error value was 0.0258, and the correlation coefficient was 91.55%. To sum up, the support vector machin model shows higher accuracy than grey prediction model, which can be used for thermal fault diagnosis.

show abstract

Deep learning for unsupervised feature extraction in audio signals: Monaural source separation

Cited by 4 publications

References 0 publications

Attention Feature Network Extraction Combined with the Generation Algorithm of Multimedia Image Description

Attention Feature Network Extraction Combined with the Generation Algorithm of Multimedia Image Description

Visualization of the Residual Network for 3D Image Recognition considering the SVM Combined with the K-Nearest Neighbor Algorithm

Thermal energy diagnosis of boiler plant by computer image processing and neural network technology

Contact Info

Product

Resources

About