Improvement of Auto-Regressive Integrated Moving Average models using Fuzzy logic and Artificial Neural Networks (ANNs)

Khashei, Mehdi; Bijari, Mehdi; Ardali, Gholam Ali Raissi

doi:10.1016/j.neucom.2008.04.017

Cited by 260 publications

(130 citation statements)

References 58 publications

Supporting

Mentioning

125

Contrasting

Unclassified

Order By: Relevance

“…The comparison presented in [13] shows that FARIMA processes and ANNs have similar approximation errors. However, the best results are achieved for hybrid solutions which employ both FARIMA and ANNs simultaneously [13,32,33].…”

Section: Related Workmentioning

confidence: 99%

Traffic prediction methods for quality improvement of adaptive video

Biernacki

2017

Multimedia Systems

View full text Add to dashboard Cite

During the past years, adaptive video based on HTTP has become very popular. Streaming of the adaptive video relies heavily on an estimation of end-to-end network throughput, which can be challenging especially in mobile networks, where the capacity highly fluctuates. In this work, we propose to predict the network throughput using its past measurements. As the analysis shows, the network throughput forms a long range-dependent process; thus, for the throughput prediction, we apply a fractional ARIMA process and artificial neural networks. Our approach does not require any modifications to the network infrastructure or the TCP stack. The predictions are performed for data traces obtained from measurements of throughput of a real mobile network. As the experiment shows, the obtained traffic models are able to enhance the performance of an adaptive streaming algorithm. Compared to the throughput predictors employed in contemporary systems dedicated to adaptive video streaming, the proposed technique obtains better results when taking into account effectiveness of network capacity utilisation and stability of video play-out.

show abstract

Section: Related Workmentioning

confidence: 99%

Traffic prediction methods for quality improvement of adaptive video

Biernacki

2017

Multimedia Systems

View full text Add to dashboard Cite

show abstract

“…However, unlike linear ARIMA and FARIMA, ANNs can handle also non-linear phenomena in time series [26,27]. Thus, ANNs have been also widely applied for network traffic modelling and prediction [28,29].…”

Section: Artificial Neural Networkmentioning

confidence: 99%

Analysis and modelling of traffic produced by adaptive HTTP-based video

Biernacki

2016

Multimed Tools Appl

View full text Add to dashboard Cite

The increase of HTTP-based video popularity causes that broadband and Internet service providers' links transmit mainly multimedia content. Network planning, traffic engineering or congestion control requires an understanding of the statistical properties of network traffic; therefore, it is desirable to investigate the characteristic of traffic traces generated by systems which employ adaptive bit-rate streaming. Our first contribution is an investigation of traffic originating from 120 client-server pairs, situated in an emulated content distribution network, and multiplexed onto a single network link. We show that the structure of the traffic is distinct from the structure generated by the first and second generation of HTTP video systems, and furthermore, not similar to the structure of general Internet traffic. The obtained traffic exhibits negative and positive correlations, anti-persistence, and its distribution function is skewed to the right. Our second contribution is an approximation of the traffic by ARIMA/FARIMA processes blue and artificial neural networks. As we show, the obtained traffic models are able to enhance the performance of an adaptive streaming algorithm.

show abstract

“…Sebenarnya, fluktuasi harga minyak mentah cenderung nonlinear, sehingga kurang cocok menggunakan pemodelan ARIMA [8]. Untuk mengakomodasi fluktuasi nonlinear tersebut, penelitian [9] Seperti yang ditampilkan pada Gambar 1, diagram alir hampir sama dengan penelitian yang dilakukan Latif dan Herawati [9].…”

Section: No 2 November 2016unclassified

Analisis Kinerja Gabungan Metode Ensemble Empirical Mode Decomposition Dan Generalized Regression Neural Network

Herawati

Latif

2016

INFOTEL

View full text Add to dashboard Cite

Abstrak -Metode runtun waktu cocok digunakan ketika akan memeriksa setiap pola data secara sistematis dan memiliki banyak variabel bebas, seperti pada kasus harga minyak mentah. Salah satu penelitian yang memanfaatkan metode runtun waktu adalah integrasi antara Ensemble Empirical Mode Decomposition (EEMD) dan jaringan syaraf berdasarkan algoritma Polak-Ribiére Conjugate Gradient (PCG). Jenis jaringan syaraf menggunakan FeedForward Neural Network (FNN). Namun, FNN memerlukan pengaturan parameter bebas dalam proses pembelajarannya. Sementara, parameter yang sesuai sangat dibutuhkan untuk mendapatkan hasil peramalan yang akurat. Penelitian ini mengusulkan integrasi antara EEMD dan Generalized Regression Neural Network (GRNN). GRNN memiliki keunggulan, yaitu: tidak memerlukan pengaturan parameter dan proses pembelajaran yang cepat. Untuk evaluasi, kinerja metode EEMD-GRNN dibandingkan dengan GRNN. Hasil eksperimen menunjukkan bahwa metode EEMD-GRNN menghasilkan peramalan yang lebih baik dari GRNN. Metode EEMD-GRNN memiliki nilai MSE dan RMSE lebih kecil daripada GRNN. Nilai MSE dan RMSE menggunakan data pengujian untuk WTI berturut-turut sebesar 0,0032 dan 0,0569. Sementara, Nilai MSE dan RMSE menggunakan data pengujian Brent berturut-turut sebesar 0,0017 dan 0,0415.Kata kunci -Peramalan Harga Minyak Mentah, EEMD, GRNN.Abstract -The method of time series suitable for use when it checks each data patterns systematically and has many variables, such as in the case of crude oil prices. One study that utilizes the methods of time series is the integration between Ensemble Empirical Mode Decomposition (EEMD) and neural network algorithms based on Polak-Ribiere Conjugate Gradient (PCG). Type of neural network using Feedforward Neural Network (FNN). However, FNN requires setting free parameters in the learning process. Meanwhile, the appropriate parameters are needed to get accurate forecasting results. This research proposes the integration between EEMD and Generalized Regression Neural Network (GRNN). GRNN has advantages, such as: does not require any parameter settings and a quick learning process. For the evaluation, the performance of the method EEMD-GRNN compared with GRNN. The experimental results showed that the method EEMD-GRNN produce better forecasting of GRNN. Method of EEMD-GRNN has a value of MSE and RMSE smaller than GRNN. The value of MSE and RMSE used test data for WTI successively equal 0.0032 and 0.0569. While the value of MSE and RMSE used test data for Brent successively equal 0,0017 and 0,0415. Beberapa penelitian telah dilakukan dengan menggunakan metode runtun waktu untuk peramalan harga minyak mentah. Salah satu contohnya, penelitian menggunakan GARCH yang dibandingkan dengan model volatilitas [6]. Kemudian, penelitian mengenai integrasi antara ARIMA dan GARCH [7].

show abstract

Improvement of Auto-Regressive Integrated Moving Average models using Fuzzy logic and Artificial Neural Networks (ANNs)

Cited by 260 publications

References 58 publications

Traffic prediction methods for quality improvement of adaptive video

Traffic prediction methods for quality improvement of adaptive video

Analysis and modelling of traffic produced by adaptive HTTP-based video

Analisis Kinerja Gabungan Metode Ensemble Empirical Mode Decomposition Dan Generalized Regression Neural Network

Contact Info

Product

Resources

About