An Enhanced Artificial Bee Colony-Based Support Vector Machine for Image-Based Fault Detection

Chen, Guijun; Zhang, Xueying; Wang, Zizhong John; Li, Fenglian

doi:10.1155/2015/638926

Cited by 12 publications

(7 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper, we have analyzed the significant differences of active source regions and frequency bands for pairs of emotions-based reconstructed EEG sources using sLORETA, and 26 Brodmann areas are selected as the regions of interest (ROI). The selected ROI sets include BA3, 5,6,9,10,13,18,19,23,29,30,39 and 40 with bilateral hemispheres, which involve postcentral gyrus, prefrontal cortex, parietal cortex, temporal cortex and occipital cortex. Most significant differences between pairs of emotions occur in γ , θ and α bands.…”

Section: Discussionmentioning

confidence: 99%

“…The goal of SVM is to find a separating hyper-plane with maximum margins and classify the data accurately. There are two parameters, including penalty parameter and the kernel parameter, that need to be optimized to improve the classification accuracy [39]. The grid search method was utilized to tune the parameters, which were searched in the range from 2 −8 to 2 8 .…”

Section: Classifier and Evaluationmentioning

confidence: 99%

See 1 more Smart Citation

Emotion Feature Analysis and Recognition Based on Reconstructed EEG Sources

et al. 2020

Self Cite

View full text Add to dashboard Cite

Emotion plays a significant role in perceiving external events or situations in daily life. Due to ease of use and relative accuracy, Electroencephalography (EEG)-based emotion recognition has become a hot topic in the affective computing field. However, scalp EEG is a mixed-signal and cannot directly indicate the exact information about active cortex sources of different emotions. In this paper, we analyze the significant differences of active source regions and frequency bands for pairs of emotions-based reconstructed EEG sources using sLORETA, and 26 Brodmann areas are selected as the regions of interest (ROI). And then, six kinds of time-and frequency-domain features from significant active regions and frequency bands are extracted to classify different emotions using support vector machines. Furthermore, we compare the classification performances of emotion features extracted from active source regions and EEG sensors. We have demonstrated that the features from selected source regions can improve the classification accuracy by extensive experiments on the DEAP and TYUT 2.0 EEG-based datasets. INDEX TERMS Emotion recognition, EEG source reconstruction, inverse solution, difference analysis of active source, time-and frequency-domain features.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Classifier and Evaluationmentioning

confidence: 99%

Emotion Feature Analysis and Recognition Based on Reconstructed EEG Sources

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…33 Chen et al proposed an improved artificial swarm algorithm to optimize the weight of the penalty function, which improved the recognition accuracy and convergence performance of the model for fault diagnosis from images. 34 …”

Section: Introductionmentioning

confidence: 99%

Prediction Model for Coal Spontaneous Combustion Based on SA-SVM

et al. 2021

View full text Add to dashboard Cite

Accurate predictions of the coal temperature in coal spontaneous combustion (CSC) are important for ensuring coal mine safety. Gas coal (the Zhaolou coal mine in Shandong Province, China) was used in this paper. A large CSC experimental device was adopted to obtain its characteristic temperatures from the macroscopic characteristics of gas production. A simulated annealing-support vector machine (SA-SVM) prediction model was proposed to reflect the complex nonlinear mapping between characteristic gases and the coal temperature. The risk degree of CSC was estimated in the time domain, and the model was verified by using in situ data from an actual working face. Furthermore, back-propagation neural network (BPNN) and single SVM methods were adopted for comparison. The results showed that the BPNN could not adapt to the small-sample problem due to overfitting and the output of a single SVM was unstable due to its strong dependence on the setting of hyperparameters. Through the SA global optimization process, the optimal combination of hyperparameters was obtained. Therefore, SA-SVM had higher prediction accuracy, robustness, and error tolerance rate and better environmental adaptability. These findings have certain practical significances for eliminating the hidden danger of CSC in the gob and providing timely warnings about potential danger.

show abstract

“…The indentation rolling resistance is the largest, and the energy consumed by it accounts for about 60% of the total energy consumption of the belt conveyor [3]. So accurately predicting and reducing IRR is the focus and hot spot of current research [4][5][6].…”

Section: Introductionmentioning

confidence: 99%

Research on Indentation Rolling Resistance Based on Viscoelasticity of Cover Rubber under a Conveyor Belt

Zhao

Meng

Zhou

2019

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Minimizing the power consumption of the belt conveyor is the common wish of all enterprises and even countries. Among all the resistances generated by the belt conveyor during the operation, the indentation rolling resistance accounts for the largest proportion and the power consumed is the largest. Therefore, accurately predicting and reducing the rolling resistance of indentation is the focus of current research. Firstly, based on the three-element Maxwell solid model, the dynamic loading experiments of cylindrical rubber made of conveyor belt cover material were carried out at different temperatures. The identification models of elastic moduli E2 and E3 and viscosity coefficient η2 in the three-element Maxwell model were obtained, and then the fitting functions of the three parameters were gotten, which can intuitively reflect the influence of temperature. Secondly, the mathematical model of the indentation rolling resistance was derived. The mathematical model is characterized by the direct parameters such as belt speed v, thickness of backing material h, the idler radius R, and the rubber viscoelastic parameters E2, E3, and η2 and the indirect parameters such as normal force P and temperature T. Afterwards, the effects of belt speed, normal force, temperature, idler radius, and thickness of underlay on the indentation rolling resistance were studied under different working conditions. After that, experimental testing and analysis were fulfilled using test equipment and compared with theoretical analysis results. The results prove that the theoretical results are basically consistent with the experimental results, in line with the actual engineering rules. Finally, the application of the results in practical engineering was analyzed superficially.

show abstract

An Enhanced Artificial Bee Colony-Based Support Vector Machine for Image-Based Fault Detection

Cited by 12 publications

References 30 publications

Emotion Feature Analysis and Recognition Based on Reconstructed EEG Sources

Emotion Feature Analysis and Recognition Based on Reconstructed EEG Sources

Prediction Model for Coal Spontaneous Combustion Based on SA-SVM

Research on Indentation Rolling Resistance Based on Viscoelasticity of Cover Rubber under a Conveyor Belt

Contact Info

Product

Resources

About