PSO based Neural Networks vs. traditional statistical models for seasonal time series forecasting

Adhikari, Ratnadip; Agrawal, R. K.; Kant, Laxmi

doi:10.1109/iadcc.2013.6514315

Cited by 22 publications

(15 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The experiments were run using an improved deterministic PSO variant from [30], which is among the most popular versions of the PSO algorithm [31]. We are interested in assessing the quality of predictions for OIDW and compare them with the traditional grid search IDW (denoted, in the following.…”

Section: Experimental Settingsmentioning

confidence: 99%

Optimizing Inverse Distance Weighting with Particle Swarm Optimization

Bărbulescu

Băutu

2020

Applied Sciences

View full text Add to dashboard Cite

Spatial analysis of hydrological data often requires the interpolation of a variable from point samples. Commonly used methods for solving this problem include Inverse Distance Weighting (IDW) and Kriging (KG). IDW is easily extensible, has a competitive computational cost with respect to KG, hence it is usually preferred for this task. This paper proposes the optimization of finding the IDW parameter using a nature-inspired metaheuristic, namely Particle Swarm Optimization (PSO). The performance of the improved algorithm is evaluated in a complex scenario and benchmarked against the KG algorithm for 51 precipitation series from the Dobrogea region (Romania). Apart from facilitating the process of applying IDW, the PSO implementation for Optimizing IDW (OIDW) is computationally lighter than the traditional IDW approach. Compared to Kriging, OIDW is straightforward to be implemented and does not require the difficult process of identification of the most appropriate variogram for the given data.The interpolation method often chosen by geoscientists is IDW, implemented in many Geographic Information Systems (GIS) packages [4]. Its popularity is mainly due to its straightforward interpretability, easy computability and good prediction results. Still, the No Free Lunch theorem for optimization [5] stands also in the case of spatial interpolation: no method stands out as being the best in all situations [6]. In a study about the rainfall data in the Indian Himalayas, Kumari et al. [7] performed a comparison of several interpolation methods, among which there were several variants of multivariate Kriging and IDW. It was shown that none of the methods performs best in all the studied cases. Principal Component Regression with the Residual correction (PCRR) method, IDW and the Multiple Linear Regression (MLR) methods were used to compare interpolated annual, daily and hourly precipitation and the spatial distribution of precipitation in the Xinxie catchment [8], while the spatial distribution of precipitation deficit over Seyhan River basin using IDW is reported in [9].The basic IDW method is successfully employed in [10] to estimate the rainfall distribution in a region of Iraq. The scenario uses incremental values for the power parameter, in the range from 1 to 5. A modified IDW method is investigated in [11], where the elevation is also considered for estimating the values at unknown locations. A new method for estimating the regional precipitation (MPPM) has been introduced in [12] and its performance has been tested against that of IDW and kriging. It was reported that MPPM avoids the problems that could appear in the application of kriging methods, as (i) the invertibility of the distance matrix, (ii) the high computational cost related to building the inverse of the distance matrix in the case of a high number of stations, (iii) the choice of the model for the estimation of theoretical variogram and (iv) the selection of the optimal parameters of the variogram model. It was shown that deterministic methods could b...

show abstract

Section: Experimental Settingsmentioning

confidence: 99%

Optimizing Inverse Distance Weighting with Particle Swarm Optimization

Bărbulescu

Băutu

2020

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…After illustrating the result of different applications, they concluded that the hybrid algorithm integrating BP and PSO improved the performance, and exceeded the individual BP or PSO in terms of the convergence rate and error level. Adhikari et al [24] investigated a PSO approach which improve the predicting ability of feed-forward artificial neural network optimized by particle swarm optimizations to predict uniaxial compressive strength and achieved good results. Wang et al [18] used the BP model optimized by cuckoo search algorithm, which is superior to the traditional BP neural network in lightning prediction.…”

Section: Prediction Modelmentioning

confidence: 99%

Prediction of Significant Wave Heights Based on CS-BP Model in the South China Sea

et al. 2019

View full text Add to dashboard Cite

Forecasting the significant wave heights (Hs) is indispensable in H S -related engineering studies and is exceedingly important in the assessment of wave energy in future. As a technique essential for the future of clean energy systems, reducing the forecasting errors related to Hs has always been a vital research subject. In this paper, an optimized hybrid method based on the back propagation neural network (BP) and the cuckoo search algorithm (CS) is proposed to forecast the Hs in the South China Sea. This approach employs the CS as an intelligent optimization algorithm to optimize the parameters of the BP model, which develop a hybrid model that is suit for the data set, reducing the forecasting errors. The proposed method is subsequently tested based on nine prediction points selected in the South China Sea, where the proposed hybrid model is proved to perform effectively and steadily.INDEX TERMS CS-BP, significant wave heights, South China sea, predication performance.

show abstract

“…, y t−d+1 . This procedure, characterized by functional relationship (1), is called auto-regressive approach to time series modeling. The objective of the training phase is to adjust the behavior (parameters) of f until all of its predictionsŷ tp+s get sufficiently close to corresponding target values y tp+s .…”

Section: Time Series Modeling: the Problem Of Predicting The Futurementioning

confidence: 99%

“…Recently, PSO has been employed as a FFNN training algorithm; it is easy to adapt the basic PSO algorithm in order to minimize mean squared error loss function (5); simply identify vector W , whose components are all the weights in a FFNN, with basic PSO's position vector x. Numerous particular applications involving some sort of FFNN-PSO hybrid model for time series prediction can be found in the literature; see for example [1], [12] and [20]. In this paper, we adapt FFNN ensemble models to quarterly time series data, training individual FFNN elements with either BP or basic PSO; individual predictions from an ensemble are averaged out, producing a final prediction for the whole ensemble.…”

Section: Particle Swarm Optimizationmentioning

confidence: 99%

A comparison between SARIMA models and Feed Forward Neural Network Ensemble Models for Time Series Data

Alba

Muñoz-Zavala²

2015

RCS

View full text Add to dashboard Cite

In this paper, we investigate the robustness of Feed Forward Neural Network (FFNN) ensemble models applied to quarterly time series forecasting tasks, by comparing their prediction ability with that of Seasonal Auto-regressive Integrated Moving Average (SARIMA) models. We obtained adequate SARIMA models which required statistical knowledge and considerable effort. On the other hand, FFNN ensemble models were readily constructed from a single FFNN template, and they produced competitive forecasts, at the level of well-constructed SARIMA models. The single template approach for adapting FFNN ensembles to multiple time series datasets can be an economic and sensible alternative if fitting individual models for each time series turns out to be very time consuming. Additionally, FFNN ensembles were able to produce accurate interval estimations, in addition to good point forecasts.

show abstract

PSO based Neural Networks vs. traditional statistical models for seasonal time series forecasting

Cited by 22 publications

References 27 publications

Optimizing Inverse Distance Weighting with Particle Swarm Optimization

Optimizing Inverse Distance Weighting with Particle Swarm Optimization

Prediction of Significant Wave Heights Based on CS-BP Model in the South China Sea

A comparison between SARIMA models and Feed Forward Neural Network Ensemble Models for Time Series Data

Contact Info

Product

Resources

About