Time-delay neural networks for time series prediction: an application to the monthly wholesale price of oilseeds in India

Jha, Girish Kumar; Sinha, Kishore

doi:10.1007/s00521-012-1264-z

Cited by 71 publications

(37 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A TDNN has multiple layers and sufficient inter-connection between units in each layer to ensure the ability to learn complex nonlinear decision surfaces. In addition, the actual abstraction learned by the TDNN should be invariant under in time translation [40][41][42]. Figure 1 shows the architecture of a TDNN.…”

Section: Time-delay Neural Networkmentioning

confidence: 99%

Using a Time Delay Neural Network Approach to Diagnose the Out-of-Control Signals for a Multivariate Normal Process with Variance Shifts

Shao

Lin

2019

Mathematics

View full text Add to dashboard Cite

With the rapid development of advanced sensor technologies, it has become popular to monitor multiple quality variables for a manufacturing process. Consequently, multivariate statistical process control (MSPC) charts have been commonly used for monitoring multivariate processes. The primary function of MSPC charts is to trigger an out-of-control signal when faults occur in a process. However, because two or more quality variables are involved in a multivariate process, it is very difficult to diagnose which one or which combination of quality variables is responsible for the MSPC signal. Though some statistical decomposition methods may provide possible solutions, the mathematical difficulty could confine the applications. This study presents a time delay neural network (TDNN) classifier to diagnose the quality variables that cause out-of-control signals for a multivariate normal process (MNP) with variance shifts. To demonstrate the effectiveness of our proposed approach, a series of simulated experiments were conducted. The results were compared with artificial neural network (ANN), support vector machine (SVM) and multivariate adaptive regression splines (MARS) classifiers. It was found that the proposed TDNN classifier was able to accurately recognize the contributors of out-of-control signal for MNPs.

show abstract

Section: Time-delay Neural Networkmentioning

confidence: 99%

Using a Time Delay Neural Network Approach to Diagnose the Out-of-Control Signals for a Multivariate Normal Process with Variance Shifts

Shao

Lin

2019

Mathematics

View full text Add to dashboard Cite

show abstract

“…The input signal propagates through the network in a forward direction ensuring that the network outputs are calculated as explicit functions of the inputs and their weights. Neural network with a single hidden layer and sufficiently large number of neurons approximates any nonlinear function (Jha and Sinha, 2014). Hence, neural network model with single hidden layer was designed in the present study and it signified a multilayer perceptron network model with 6 input variables, 6 neurons in the hidden layers with one output variable.…”

Section: Of S Litura On Groundnut By Annmentioning

confidence: 99%

Artificial neural network techniques for predicting severity of Spodoptera litura(Fabricius) on groundnut

Vennila¹,

Singh²,

Jha³

et al. 2017

JEB

View full text Add to dashboard Cite

Aim :Methodology : Results :Interpretation :Approaches to modelling pest populations range from simple empirical models to advanced soft computing techniques that have advantages as well as limitations.A comparative analyses of modelling approaches result in selection of betterpest forecast model with a higher prediction accuracy. Artificial neural network (ANN) techniques, multi-layer perceptron neural network (MLP-NN) and polynomial neural networks (PNN) were used along with the multiple and polynomial regressions to predict the moth population of tobacco caterpillar (Fabricius) in groundnut cropping system. pheromone trap catch and weather data of twenty five years (1990-2014) for season (26 to 44 standard meteorological weeks (SMW)) was used for predictive modelling. The weekly male moth catches of (numbers/trap/week) during maximum severity period (34 SMW) was modelled using weather variables maximum and minimum temperature (°C), rainfall (mm), morning and evening relative humidity (%) lagged by two weeks. The performance of the models was evaluated using coefficient of determination (R ), root mean square error (RMSE) and mean absolute percentage error (MAPE) estimates.The study clearly demonstrated the superiority of MLP-NN (R :0.89) over all other models for predicting the peak severity of . Sensitivity analysis of MLP-NN model indicated that the maximum temperature lagged by two weeks and evening relative humidity of the previous week was two most important factors influencing the peak population of . Validation also demonstrated the effectiveness of MLP-NN followed by PNN in dealing with non-linear relation between population and weather variables.All model equations developed in the present study can be used to predict peak (34 SMW) in conjunction with weather of 32 and 33 SMW during season, and in issuing need based advisories for its effective management on groundnut.

show abstract

“…Third, the actual features or abstraction learned by the network should be invariant under translation in time. Forth, the number of weights in the network should be sufficiently compared the training data [15]- [17].…”

Section: B Time-delay Neural Networkmentioning

confidence: 99%

Computational Intelligence Approaches for Determination of Process Disturbance Patterns in an SPC-EPC System

Shao¹,

Wang²

2016

JIII

View full text Add to dashboard Cite

In recent years, the integration of Statistical Process Control (SPC) and Engineering Process Control (EPC) has received considerable attentions due to the superiority for the process improvement. However, a drawback of the integration of SPC and EPC may be encountered for monitoring a process. Because EPC would compensate for the effects of underlying disturbances, the disturbance patterns could be embed and hard to be identified. However, the determination of Disturbance Patterns (DP) is crucial for process improvement due to the fact that DP would be associated with certain root causes for an unstable process. In this study, we propose three computational intelligence approaches to effectively determine the mixture patterns of process disturbances in a SPC-EPC system. Those three computational intelligence approaches include the artificial neural network, Time-Delay Neural Network (TDNN) and Rough Set (RS) techniques. Experimental results show that the proposed TDNN approach has the best performance of Accurate Identification rate (AIC) for determining the DP of an SPC/EPC system.  Index Terms-disturbance patterns, artificial neural network, time-delay neural network, rough set, SPC, EPC

show abstract

Time-delay neural networks for time series prediction: an application to the monthly wholesale price of oilseeds in India

Cited by 71 publications

References 19 publications

Using a Time Delay Neural Network Approach to Diagnose the Out-of-Control Signals for a Multivariate Normal Process with Variance Shifts

Using a Time Delay Neural Network Approach to Diagnose the Out-of-Control Signals for a Multivariate Normal Process with Variance Shifts

Artificial neural network techniques for predicting severity of Spodoptera litura(Fabricius) on groundnut

Computational Intelligence Approaches for Determination of Process Disturbance Patterns in an SPC-EPC System

Contact Info

Product

Resources

About