Comparing NARX and NARMAX models using ANN and SVM for cash demand forecasting for ATM

Acuña, Gonzalo; Ramírez, Cristián; Curilem, Millaray

doi:10.1109/ijcnn.2012.6252476

Cited by 16 publications

(14 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Non-linear Auto Regressive with Exogenous (NARX) input is a time series non-linear model derived from the Autoregressive exogenous (ARX) linear model and have been widely used for modelling and prediction purposes [19][20][21][22][23][24][25]. The model consists of structure which is repeated in the dynamic network with feedback connections.…”

Section: Narx-ann Modelmentioning

confidence: 99%

Energy consumption prediction through linear and non-linear baseline energy model

Mustapa

Dahlan

Yassin

et al. 2020

IJEECS

View full text Add to dashboard Cite

<span>Accurate baseline energy models demand increase significantly as it lower the risk of energy savings quantification. It is achieved by performing energy consumption prediction with its respective independent variables through linear or non-linear modelling technique. Developing such model through linear modelling technique provide certain disadvantages due to the fact that the behavior of certain independent variables with respect to the energy consumption is non-linear in nature. Furthermore, linear modelling technique requires prior studies upon modelling to achieve accurate energy consumption prediction. Thus, to apprehend this situation, this paper main intention is to perform energy consumption prediction through a non-linear modelling technique to provide alternative option for developing a good and accurate baseline energy models. This study proposes energy consumption prediction based on Non-linear Auto Regressive with Exogenous Input – Artificial Neural Network (NARX-ANN) as a non-linear modelling technique that will be compared with Multiple Linear Regression Model (MLR) as linear modelling technique. A case study in Malaysian educational buildings during lecture week will be used for this purpose. The results demonstrate that NARX-ANN shows a higher accuracy through statistical error measurement.</span>

show abstract

Section: Narx-ann Modelmentioning

confidence: 99%

Energy consumption prediction through linear and non-linear baseline energy model

Mustapa

Dahlan

Yassin

et al. 2020

IJEECS

View full text Add to dashboard Cite

show abstract

“…The combined method showed a better performance than ARX and NARX separately due to ability of combined model structure to model nonlinear dynamical systems [11]. Although NARX models have proved to be a powerful approach to identification of nonlinear phenomena [10][11][12][13], as far as the authors know, no gait events detection with NARX have been reported.…”

Section: Nonlinear Autoregressive Models With Exogenousmentioning

confidence: 99%

Comparison between Classical and Intelligent Identification Systems for Classification of Gait Events

Galván-Duque¹,

Zavala-Yoé²,

Rodríguez-Reyes³

et al. 2015

JCSE

View full text Add to dashboard Cite

Gait event detection is important for diagnosis and evaluation. This is a challenging endeavor due to subjectivity, high amount of data, among other problems. ANFIS (Artificial Neural Fuzzy Inference Systems), ARX (Autoregressive Models with Exogenous Variables), OE (Output Error models), NARX (Nonlinear Autoregressive Models with Exogenous Variables) and models based on NN (neural networks) were developed in order to detect gait events without the problems mentioned. The objective was to compare developed models' performance and determinate the most suitable model for gait events detection. Knee joint angle, heel foot switch and toe foot switch during normal walking in a treadmill were collected from a healthy volunteer. Gait events were classified by three experts in human motion. Experts' mean classification was obtained and all models were trained and tested with the collected data and experts' mean classification. Fit percentage was obtained to evaluate models performance. Fit percentages were: ANFIS: 79.49%, ARX: 68.8%, OE: 71.39%, NARX: 88.59%, NNARX: 67.66%, NNRARX: 68.25% and NNARMAX: 54.71%. NARX had the best performance for gait events classification. For ARX and OE, previous filtering is needed. NN's models showed the best performance for high frequency components. ANFIS and NARX were able to integrate criteria from three experts for gait analysis. NARX and ANFIS are suitable for gait event identification. Test with additional subjects is needed.

show abstract

“…A number of recent studies, e.g. Acuna et al (2012), Dandekar and Ranade (2015), Mishra and Dehuri (2014), Venkatesh et al (2014), utilise ANN models as a cash forecasting tool. These studies support the superiority of ANN models as forecasting tools.…”

Section: Introductionmentioning

confidence: 99%

The development of a government cash forecasting model

Iskandar

Willett

2018

JPBAFM

View full text Add to dashboard Cite

Purpose Government cash forecasting is central to achieving effective government cash management but research in this area is scarce. The purpose of this paper is to address this shortcoming by developing a government cash forecasting model with an accuracy acceptable to the cash manager in emerging economies. Design/methodology/approach The paper follows “top-down” approach to develop a government cash forecasting model. It uses the Indonesian Government expenditure data from 2008 to 2015 as an illustration. The study utilises ARIMA, neural network and hybrid models to investigate the best procedure for predicting government expenditure. Findings The results show that the best method to build a government cash forecasting model is subject to forecasting performance measurement tool and the data used. Research limitations/implications The study uses the data from one government only as its sample, which may limit the ability to generalise the results to a wider population. Originality/value This paper is novel in developing a government cash forecasting model in the context of emerging economies.

show abstract

Comparing NARX and NARMAX models using ANN and SVM for cash demand forecasting for ATM

Cited by 16 publications

References 16 publications

Energy consumption prediction through linear and non-linear baseline energy model

Energy consumption prediction through linear and non-linear baseline energy model

Comparison between Classical and Intelligent Identification Systems for Classification of Gait Events

The development of a government cash forecasting model

Contact Info

Product

Resources

About