Self-organized Operational Neural Networks with Generative Neurons

Kıranyaz, Serkan; Malik, Junaid; Abdallah, Habib Ben; İnce, Türker; Iosifidis, Alexandros; Gabbouj, Moncef

doi:10.1016/j.neunet.2021.02.028

Cited by 67 publications

(53 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Owing to this, unlike ONNs, the generative neurons inside a Self-ONN layer can be parallelized more efficiently, leading to a considerable reduction in computational complexity and time. The generalized formulations of the forward-propagation through a Self-ONN neuron and back-propagation training of the Self-ONNs are described in [25], [29].…”

Section: Ii1d Self-organized Operational Neural Networkmentioning

confidence: 99%

“…Recent studies [19]- [21] have pointed out that CNNs having homogenous network configuration based on a firstorder neuron model cannot adequately learn problems with a complex and highly nonlinear solution space [19]- [21] unless a sufficiently high network depth and complexity (variants of CNN) are accommodated. Recently, Self-Organized Operational Neural Networks (Self-ONN) have been proposed to achieve a high heterogeneity level with self-organized operator optimization capability to maximize the learning performance [25]. The superior regression capability of Self ONNs over image segmentation, restoration, and denoising was demonstrated in recent studies [25], [29].…”

Section: Introductionmentioning

confidence: 99%

“…Recently, Self-Organized Operational Neural Networks (Self-ONN) have been proposed to achieve a high heterogeneity level with self-organized operator optimization capability to maximize the learning performance [25]. The superior regression capability of Self ONNs over image segmentation, restoration, and denoising was demonstrated in recent studies [25], [29].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Early Bearing Fault Diagnosis of Rotating Machinery by 1D Self-Organized Operational Neural Networks

İnce¹,

Malik

Devecioğlu

et al. 2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

Preventive maintenance of modern electric rotating machinery (RM) is critical for ensuring reliable operation, preventing unpredicted breakdowns and avoiding costly repairs. Recently many studies investigated machine learning monitoring methods especially based on Deep Learning networks focusing mostly on detecting bearing faults; however, none of them addressed bearing fault severity classification for early fault diagnosis with high enough accuracy. 1D Convolutional Neural Networks (CNNs) have indeed achieved good performance for detecting RM bearing faults from raw vibration and current signals but did not classify fault severity. Furthermore, recent studies have demonstrated the limitation in terms of learning capability of conventional CNNs attributed to the basic underlying linear neuron model. Recently, Operational Neural Networks (ONNs) were proposed to enhance the learning capability of CNN by introducing non-linear neuron models and further heterogeneity in the network configuration. In this study, we propose 1D Self-organized ONNs (Self-ONNs) with generative neurons for bearing fault severity classification and providing continuous condition monitoring. Experimental results over the benchmark NSF/IMS bearing vibration dataset using both x-and y-axis vibration signals for inner race and rolling element faults demonstrate that the proposed 1D Self-ONNs achieve significant performance gap against the state-of-the-art (1D CNNs) with similar computational complexity.

show abstract

Section: Ii1d Self-organized Operational Neural Networkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Early Bearing Fault Diagnosis of Rotating Machinery by 1D Self-Organized Operational Neural Networks

İnce¹,

Malik

Devecioğlu

et al. 2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…To address these limitations, Operational Neural Networks (ONNs) [21]- [24] have recently been proposed as a heterogeneous network model encapsulating distinct nonlinear neurons. ONNs are derived from the Generalized Operational Perceptrons (GOPs) [14], [20] that can learn those problems where MLPs entirely fail.…”

Section: Introductionmentioning

confidence: 99%

“…Instead, during the training of the network, to maximize the learning performance, each generative neuron in a Self-ONN can customize the nodal operators, 𝚿, of each kernel connection. This yields a heterogeneity level that is far beyond that of ONNs, and the traditional "weight optimization" becomes an "operator generation" process as the details can be found in [24]. The superior regression capability of Self ONNs over image segmentation, restoration, and denoising was demonstrated in recent studies; however, they have not been evaluated for a classification problem.…”

Section: Introductionmentioning

confidence: 99%

Real-Time Glaucoma Detection From Digital Fundus Images Using Self-ONNs

Devecioğlu¹,

Malik

İnce

et al. 2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

Glaucoma leads to permanent vision disability by damaging the optical nerve that transmits visual images to the brain. The fact that glaucoma does not show any symptoms as it progresses and cannot be stopped at the later stages, makes it critical to be diagnosed in its early stages. Although various deep learning models have been applied for detecting glaucoma from digital fundus images, due to the scarcity of labeled data, their generalization performance was limited along with high computational complexity and special hardware requirements. In this study, compact Self-Organized Operational Neural Networks (Self-ONNs) are proposed for early detection of glaucoma in fundus images and their performance is compared against the conventional (deep) Convolutional Neural Networks (CNNs) over three benchmark datasets: ACRIMA, RIM-ONE, and ESOGU. The experimental results demonstrate that Self-ONNs not only achieve superior detection performance but can also significantly reduce the computational complexity making it a potentially suitable network model for biomedical datasets especially when the data is scarce.

show abstract

Bearing fault detection in adjustable speed drives via self-organized operational neural networks

Kilickaya,

Eren

2024

Electr Eng

View full text Add to dashboard Cite

Adjustable speed drives (ASDs) are widely used in industry for controlling electric motors in applications such as rolling mills, compressors, fans, and pumps. Condition monitoring of ASD-fed induction machines is very critical for preventing failures. Motor current signature analysis offers a non-invasive approach to assess motor condition. Application of conventional convolutional neural networks provides good results in detecting and classifying fault types for utility line-fed motors, but the accuracy drops considerably in the case of ASD-fed motors. This work introduces the use of self-organized operational neural networks to enhance the accuracy of detecting and classifying bearing faults in ASD-fed induction machines. Our approach leverages the nonlinear neurons and self-organizing capabilities of self-organized operational neural networks to better handle the non-stationary nature of ASD operations, providing more reliable fault detection and classification with minimal preprocessing and low complexity, using raw motor current data.

show abstract

Self-organized Operational Neural Networks with Generative Neurons

Cited by 67 publications

References 26 publications

Early Bearing Fault Diagnosis of Rotating Machinery by 1D Self-Organized Operational Neural Networks

Early Bearing Fault Diagnosis of Rotating Machinery by 1D Self-Organized Operational Neural Networks

Real-Time Glaucoma Detection From Digital Fundus Images Using Self-ONNs

Bearing fault detection in adjustable speed drives via self-organized operational neural networks

Contact Info

Product

Resources

About