An improved PSO-BP neural network and its application to earthquake prediction

Cao, Li; Liu, Xiaoyu

doi:10.1109/ccdc.2016.7531576

Cited by 33 publications

(19 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A comparison between a non-linear forecasting technique and the ANN for regions of Northeast India was performed in [22]. They obtained similar results with both methods although slightly better for the ANN.…”

Section: Earthquake Prediction By Means Of Annmentioning

confidence: 96%

“…Zone Comparison [3] Azores (Portugal) [30] South California (USA) LM-BP, RBF [31] South California (USA) LM-BP, RBF [23] Sichuan (China) [39] Yunnan (China) BPNN [35] Northeast India BPNN [34] North California (USA) BPNN [27] Greece [2] Northern Red Sea Statistical predictors [33] Chile SVM, NB [25] Iberian Peninsula M5P, NB, SVM [24] Iberian Peninsula, Chile SVM, NB [42] Qeshm (Iran) [4] Alaska (USA) BPNN [45] Southwest Chine BPNN [7] Tokyo (Japan) KNN, SVM, NB, J48 [41] Tabriz (Iran) [6] Chile [22] China BPNN, PSO-BPNN [8] Hindukush (Pakistan) Random Forest, LPBoost ensemble Table 1: Summary of zones studied and algorithms used for comparative purposes…”

Section: Earthquake Prediction By Means Of Annmentioning

confidence: 99%

See 1 more Smart Citation

Untitled

2016

CRORR

View full text Add to dashboard Cite

Abstract. The occurrence of earthquakes has been studied from many aspects. Apparently, earthquakes occur without warning and can devastate entire cities in just a few seconds, causing numerous casualties and huge economic loss. Great eort has been directed towards being able to predict these natural disasters, and taking precautionary measures. However, simultaneously predicting when, where and the magnitude of the next earthquake, within a limited region and time, seems an almost impossible task. Techniques from the eld of data mining are providing new and important information to researchers. This article reviews the use of articial neural networks for earthquake prediction in response to the increasing amount of recently published works and presenting claims of being eective. Based on an analysis and discussion of recent results, data mining practitioners are encouraged to apply their own techniques in this emerging eld of research.

show abstract

Section: Earthquake Prediction By Means Of Annmentioning

confidence: 96%

Section: Earthquake Prediction By Means Of Annmentioning

confidence: 99%

Untitled

2016

CRORR

View full text Add to dashboard Cite

show abstract

“…(13)). It can avoid being trapped in the local minimum and slow down the convergence compared to the LDIW model [24]…”

Section: Nonlinear Decreasing Inertia Weight (Ndiw)mentioning

confidence: 99%

“…At the same time, the particle velocity drops faster so that when the particles are close to the global optimal solution, it can be achieved. This results in the particles not losing their optimal solution [24].…”

Section: Proposed Inertia Weightsmentioning

confidence: 99%

PSO-ELM with Time-varying Inertia Weight for Classification of SMILES Codes

Ratnawati¹,

Marjono²,

Widodo³

et al. 2020

IJIES

View full text Add to dashboard Cite

Classification of active compounds is necessary to trivialize their properties and activities and can be carried out by identifying functional groups and their structures based on the simplified molecular input line entry system (SMILES) code. This study classified active compounds based on the SMILES structure using a combination of the machine learning techniques, extreme learning machine (ELM), and particle swarm optimization (PSO). ELM facilitates learning very quickly and at with high predictive accuracy. The PSO covers the limitations of the ELM, i.e., randomly determining the weight and bias, trial, and error in determining the number of hidden neurons. PSO optimizes the weight, bias, and number of hidden neurons. This study’s results indicate that the classification of active compounds’ function based on the SMILES code can be done by the ELM and PSO-ELM with high accuracy. The PSO-ELM can improve the accuracy performance of the ELM classification by optimizing the weight, bias, and number of hidden neurons automatically. Moreover, the proposed PSO-ELM is better than the PSO-ELM for average accuracy, computation time, and standard deviation. The proposed algorithm has the highest average accuracy compared to the ELM by increasing the accuracy to 2.54%, 6.43%, and 3.85% for 2, 3, and 4 classes, respectively. A comparison with other machine algorithms shows that the proposed is superior.

show abstract

“…However, the performance of RBF neural network depends on the selection of network parameters. The traditional RBF neural network parameters are usually selected by experience or random, so the performance of RBF neural network has strong randomicity [3,4].…”

Section: Introductionmentioning

confidence: 99%

Application of Swarm Intelligent Algorithm Optimization Neural Network in Network Security

Xia¹

2016

Proceedings of the 2016 4th International Conference on Machinery, Materials and Information Technology Applications

View full text Add to dashboard Cite

A network traffic detection model based on swarm intelligent optimization neural network algorithm is proposed in this paper. QAPSO algorithm is used to optimize the basis function center and base function width of RBF neural network, and the connection weights of the output layer and the hidden layer as well. This paper analyzes the detection model studied in this paper by an example,and use the collected data to train the network traffic identification system and test its performance. The comparison between the proposed method and the conventional PSO algorithm based on the HPSO algorithm shows that the proposed method has faster recognition speed and better recognition accuracy, and avoids the problem of falling into the local optimal solution. Situation.

show abstract

An improved PSO-BP neural network and its application to earthquake prediction

Cited by 33 publications

References 4 publications

Untitled

Untitled

PSO-ELM with Time-varying Inertia Weight for Classification of SMILES Codes

Application of Swarm Intelligent Algorithm Optimization Neural Network in Network Security

Contact Info

Product

Resources

About