Improving Time Series Prediction with Deep Belief Network

In this paper, the time series data prediction is done using Deep Belief Network (DBN). The time series data chosen are stock price data, exchange rate data, and electricity consumption data. DBN predicts these three datasets. Particle Swarm Optimization and Local Linear Wavelet Neural Network are a...

Full description

Saved in:
Bibliographic Details
Published in:Journal of the Institution of Engineers (India). Series B, Electrical Engineering, Electronics and telecommunication engineering, Computer engineering Electrical Engineering, Electronics and telecommunication engineering, Computer engineering, 2023-10, Vol.104 (5), p.1103-1118
Main Authors: Das, Soumya, Nayak, Monalisa, Senapati, Manas Ranjan
Format: Article
Language:English
Subjects:
Algorithms
Belief networks
Communications Engineering
Datasets
Electricity consumption
Engineering
Errors
Fault tolerance
Machine learning
Networks
Neural networks
Original Contribution
Parallel processing
Particle swarm optimization
Time series
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, the time series data prediction is done using Deep Belief Network (DBN). The time series data chosen are stock price data, exchange rate data, and electricity consumption data. DBN predicts these three datasets. Particle Swarm Optimization and Local Linear Wavelet Neural Network are also used for prediction of these three datasets. The Root Mean Square Error and Mean Absolute Percentage Error parameters are used to validate the performance of the algorithm. DBNs are more efficient than other machine learning algorithms because they generate less error. They are fault tolerant and use parallel processing. They avoid over fitting and increase the model generalization.
ISSN:2250-2106
2250-2114
DOI:10.1007/s40031-023-00912-0