Deep kernel learning in extreme learning machines

Afzal, A. L.; Nair, Nikhitha K.; Asharaf, S.

doi:10.1007/s10044-020-00891-8

Cited by 21 publications

(13 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The kernel function can overcome the curse of dimensionality, and the samples that are linearly inseparable in the original space can be non-linearly mapped to a higher-dimensional space to make them linearly separable, thus improving the classification accuracy. Based on the superior performance of the kernel function, Huang [ 36 ] introduced the kernel function into ELM and proposed the KELM algorithm to further enhance the generalization ability and stability. In this paper, the kernel function and DELM are combined to construct a Deep Kernel Extreme Learning Machine (DKELM).…”

Section: Proposed Cs-dkelm Methodsmentioning

confidence: 99%

Fast Fault Diagnosis in Industrial Embedded Systems Based on Compressed Sensing and Deep Kernel Extreme Learning Machines

Shan

Bao

et al. 2022

Sensors

View full text Add to dashboard Cite

With the complexity and refinement of industrial systems, fast fault diagnosis is crucial to ensuring the stable operation of industrial equipment. The main limitation of the current fault diagnosis methods is the lack of real-time performance in resource-constrained industrial embedded systems. Rapid online detection can help deal with equipment failures in time to prevent equipment damage. Inspired by the ideas of compressed sensing (CS) and deep extreme learning machines (DELM), a data-driven general method is proposed for fast fault diagnosis. The method contains two modules: data sampling and fast fault diagnosis. The data sampling module non-linearly projects the intensive raw monitoring data into low-dimensional sampling space, which effectively reduces the pressure of transmission, storage and calculation. The fast fault diagnosis module introduces the kernel function into DELM to accommodate sparse signals and then digs into the inner connection between the compressed sampled signal and the fault types to achieve fast fault diagnosis. This work takes full advantage of the sparsity of the signal to enable fast fault diagnosis online. It is a general method in industrial embedded systems under data-driven conditions. The results on the CWRU dataset and real platforms show that our method not only has a significant speed advantage but also maintains a high accuracy, which verifies the practical application value in industrial embedded systems.

show abstract

Section: Proposed Cs-dkelm Methodsmentioning

confidence: 99%

Fast Fault Diagnosis in Industrial Embedded Systems Based on Compressed Sensing and Deep Kernel Extreme Learning Machines

Shan

Bao

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…k is the convolutional layer, s is the input data size and d is the convolution result size. Rectified Linear Unit (ReLu) [21] is used as an activation function to introduce non-linearity to the model, as demonstrated in Eq. ( 5):…”

Section: Feature Extraction Using Zfnetmentioning

confidence: 99%

“…Therefore, the details of recent advances made in supervised learning methods will be reviewed. LR and SVM are often used for ETD [21]. When the dataset is small, these strategies work better.…”

Section: Introductionmentioning

confidence: 99%

Energy Theft Identification Using Adaboost Ensembler in the Smart Grids

Irfan¹,

Ayub²,

Althobiani³

et al. 2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

“…Wang et al [67] present a unifying framework for deep learning and multiple kernel learning, a work of theoretical interest for those interested in using both schemes. Afzal et al [1] also explore the possibility of using arc-cosine kernel layers and fast methods to produce parameter matrices. Liu et al [40] presented a linearized kernel sparse representative classifier applied to subcortical brain segmentation achieving relevant image segmentation results.…”

Section: Related Workmentioning

confidence: 99%

“…The algorithm's core idea is to map the original space X into a kernelized space, induced by the set of references and the kernel function, where the mapped dataset X become a relatively simple instance for the internal classifier. 1 If memory is scarce, it is also possible to compute X elements online; however, this decision will trade speed by memory. Moreover, some of the steps can be specialized to avoid some computations; for instance, we can avoid the computation of {σ i } for FFT and K-Means, since it is a sideproduct of these algorithms.…”

Section: Learning and Prediction Proceduresmentioning

confidence: 99%