Selection of the Order of an Autoregressive Model by Akaike's Information Criterion

Shibata, Ritei

doi:10.2307/2335091

Cited by 102 publications

(115 citation statements)

References 5 publications

(7 reference statements)

Supporting

Mentioning

115

Contrasting

Order By: Relevance

“…This has to be done to mitigate non-consistent estimation and increased variance [26]. The AR model was run for model order numbers in the range of 45 to 65 with the increment of 10.…”

Section: Effect Of Changing Model Ordermentioning

confidence: 99%

Remaining Useful Life Prediction of Gas Turbine Engine using Autoregressive Model

Ahsan

Lemma

2017

MATEC Web Conf.

View full text Add to dashboard Cite

Abstract. Gas turbine (GT) engines are known for their high availability and reliability and are extensively used for power generation, marine and aero-applications. Maintenance of such complex machines should be done proactively to reduce cost and sustain high availability of the GT. The aim of this paper is to explore the use of autoregressive (AR) models to predict remaining useful life (RUL) of a GT engine. The Turbofan Engine data from NASA benchmark data repository is used as case study. The parametric investigation is performed to check on any effect of changing model parameter on modelling accuracy. Results shows that a single sensory data cannot accurately predict RUL of GT and further research need to be carried out by incorporating multi-sensory data. Furthermore, the predictions made using AR model seems to give highly pessimistic values for RUL of GT.

show abstract

“…This has to be done to mitigate non-consistent estimation and increased variance [26]. The AR model was run for model order numbers in the range of 45 to 65 with the increment of 10.…”

Section: Effect Of Changing Model Ordermentioning

confidence: 99%

Remaining Useful Life Prediction of Gas Turbine Engine using Autoregressive Model

Ahsan

Lemma

2017

MATEC Web Conf.

View full text Add to dashboard Cite

show abstract

“…Several criteria are used for this purpose, such as Akaike information criterion (AIC) [9,10], Bayesian information criterion (BIC) [11] and the Hannan-Quinn information criterion (HQ) [12,13]. Considering the limitations of AIC and BIC criteria, in this paper, the number of the nearest neighbor points is calculated by HQ information criterion.…”

Section: Lsvm-hq-sax-dtw-k Algorithmmentioning

confidence: 99%

An improved forecasting algorithm for wireless network traffic

Liu

Hua

Chen

et al. 2011

IEICE Electron. Express

View full text Add to dashboard Cite

Abstract:With the growing application of wireless networks, the forecasting technologies for wireless network traffic have played a significant role in network management, congestion control and network security. Local Support Vector Machine (LSVM) is an effective method to deal with model for wireless network traffic. To further improve the forecast accuracy and the real-time computing capability of LSVM-DTW-K algorithm we previously proposed based on LSVM, HannanQuinn information criterion (HQ) is used to calculate the number of the nearest neighbor points and Symbolic Aggregate Approximation (SAX) is used to symbolic the time series before using Dynamic Time Wrapping (DTW) algorithm to measure the similarity between two points. Keywords: wireless network traffic, Local Support Vector Machine (LSVM), Hannan-Quinn information criterion (HQ), Symbolic Aggregate Approximation (SAX) Classification: Wireless circuits and devices References[1] P. Trimintzios, T. Bauge, G. Pavlou, P. Flegkas, and R. Egan, "Quality of service provisioning through traffic engineering with applicability to IP-based production networks,"

show abstract

“…This extra penalty term makes CL-AIC in favour of smaller K compared to AIC given the same data set. It has been shown that AIC tends to over-fit by both theoretical [7,13] and experimental studies [21,11]. The extra penalty term in CL-AIC thus has the effect of rectifying the over-fitting tendency of AIC.…”

Section: Completed Likelihood Akaike's Information Criterion (Cl-aic)mentioning

confidence: 99%

Unsupervised learning of visual context using completed likelihood AIC

Xiang

Gong

2005

IEE International Conference on Visual Information Engineering (VIE 2005)

View full text Add to dashboard Cite

Learning visual context is a critical step of dynamic scene modelling. This paper addresses the problem of choosing the most suitable probabilistic model selection criterion for learning visual context of a dynamic scene. A Completed Likelihood Akaike's Information Criterion (CL-AIC) is formulated to estimate the optimal model order (complexity) for a given visual scene. CL-AIC is designed to overcome poor model selection by existing popular criteria when the data sample size varies from very small to large. Extensive experiments on learning visual context for dynamic scene modelling are carried out to demonstrate the effectiveness of CL-AIC, compared to that of BIC, AIC and ICL.

show abstract

Selection of the Order of an Autoregressive Model by Akaike's Information Criterion

Cited by 102 publications

References 5 publications

Remaining Useful Life Prediction of Gas Turbine Engine using Autoregressive Model

Remaining Useful Life Prediction of Gas Turbine Engine using Autoregressive Model

An improved forecasting algorithm for wireless network traffic

Unsupervised learning of visual context using completed likelihood AIC

Contact Info

Product

Resources

About