Derivative-based acceleration of general vector machine

Yong, Binbin; Li, Fucun; Lv, Qingquan; Shen, Jun; Zhou, Qing

doi:10.1007/s00500-017-2808-z

Cited by 4 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since it contains the design risk minimization and Monte Carlo (MC) algorithm, it has strong generalization ability and has been successfully applied in phishing detection [29], Android malware detection [30], groundwater status forecasting [31], electricity demand prediction [32]. Yong et al proposed a derivative-based Monte Carlo algorithm to accelerate the training of GVM based on the GVM [33]. Yong et al applied the Monte Carlo neural network (MCNN) based on the GVM to electricity load forecast.…”

Section: B Alo and Gvmmentioning

confidence: 99%

Using Cost-Sensitive Learning and Feature Selection Algorithms to Improve the Performance of Imbalanced Classification

Feng

Shen

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

Imbalanced data problem is widely present in network intrusion detection, spam filtering, biomedical engineering, finance, science, being a challenge in many real-life data-intensive applications. Classifier bias occurs when traditional classification algorithms are used to deal with imbalanced data. As already known, the General Vector Machine (GVM) algorithm has good generalization ability, though it does not work well for the imbalanced classification. Additionally, the state-of-the-art Binary Ant Lion Optimizer (BALO) algorithm has high exploitability and fast convergence rate. Based on these facts, we have proposed in this paper a Cost-sensitive Feature selection General Vector Machine (CFGVM) algorithm based on GVM and BALO algorithms to tackle the imbalanced classification problem, delivering different cost weights to different classes of samples. In our method, the BALO algorithm determines the cost weights and extract more significant features to improve the classification performance. Experiments conducted on eleven imbalanced data sets have shown that the CFGVM algorithm significantly improves the classification performance of minority class samples. By comparing with similar algorithms and stateof-the-art algorithms, the proposed algorithm significantly outperforms in performance and produces better classification results. INDEX TERMS Imbalanced data, cost-sensitive, general vector machine, binary ant lion optimizer.

show abstract

Section: B Alo and Gvmmentioning

confidence: 99%

Using Cost-Sensitive Learning and Feature Selection Algorithms to Improve the Performance of Imbalanced Classification

Feng

Shen

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, modern computers are adequate for MC training algorithm, and there is also Fig. 3 The process of Monte Carlo algorithm for training MCNN method to optimize MC algorithm [15]. Also, BP often falls into local optimal solution, while MC is prone to avoid local optima because of its global optimization characteristic.…”

Section: Monte Carlo Algorithmmentioning

confidence: 99%

A research of Monte Carlo optimized neural network for electricity load forecast

Yong

Huang

et al. 2019

J Supercomput

Self Cite

View full text Add to dashboard Cite

In this paper, we apply the Monte Carlo Neural Network (MCNN), a type of neural network optimized by Monte Carlo algorithm, to electricity load forecast. Meanwhile, deep MCNNs with one, two and three hidden layers are designed. Results have demonstrated that 3-layers MCNN improves 70.35% accuracy for 7 weeks electricity load forecast, compared with traditional neural network. And 5-layers MCNN improves 17.24% accuracy for 7 weeks forecast. This proves that MCNN has great potential in electricity load forecast. Keywords Monte Carlo • neural network • electricity load forecast • deep MCNNs

show abstract

“…General Vector Machine (GVM) [10,11], which has a basic structure of threelayer neural network, is designed as a mixer model of neural network and SVM. In fact, GVM is applicable to cases of lacking samples [12,13], and it has been successfully applied in time series forecast problem, such as electricity demand forecast [14].…”

Section: Introductionmentioning

confidence: 99%

Combined General Vector Machine for Single Point Electricity Load Forecast

Yong

Wei

Shen

et al. 2020

Lecture Notes in Electrical Engineering

Self Cite

View full text Add to dashboard Cite

General Vector Machine (GVM) is a newly proposed machine learning model, which is applicable to small samples forecast scenarios. In this paper, the GYM is applied into electricity load forecast based on single point modeling method. Meanwhile, traditional time series forecast models, including back propagation neural network (BPNN), Support Vector Machine (SVM) and Autoregressive Integrated Moving Average Model (ARIMA), are also experimented for single point electricity load forecast. Further, the combined model based on GYM, BPNN, SVM and ARIMA are proposed and verified. Results show that GYM performs better than these traditional models, and the combined model outperforms any other single models for single point electricity load forecast.

show abstract

Derivative-based acceleration of general vector machine

Cited by 4 publications

References 10 publications

Using Cost-Sensitive Learning and Feature Selection Algorithms to Improve the Performance of Imbalanced Classification

Using Cost-Sensitive Learning and Feature Selection Algorithms to Improve the Performance of Imbalanced Classification

A research of Monte Carlo optimized neural network for electricity load forecast

Combined General Vector Machine for Single Point Electricity Load Forecast

Contact Info

Product

Resources

About