Neural Network Algorithm Variants for Malaysian Weather Prediction

Siti Nur Kamaliah Kamarudin, Azuraliza Abu Bakar

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper studies the performance of a newly prepared time-series rainfall data by a previous researcher. The issues related are; (i) the large amount of data, and (ii) the accuracy of the prediction. In this study, the data set was obtained from Institute of Climate Change UKM, pre-processed using improved Symbolic Aggregate approximation (iSAX) and verified by experts. Five neural network algorithms were tested with the data set, namely standard Back-Propagation (BPNN), Back-Propagation with Momentum (BP with Mom), Quick-Propagation (QuickProp), Genetic Algorithm with neural network (GA-NN) and Particle Swarm Optimization with neural network (PSO-NN). The performances of these engines were measured according to the accuracy of prediction and the training time taken. The experimental results showed that while standard BPNN and PSO-NN achieved about the same accuracy prediction, PSO-NN is considered to be better as it showed a faster training time with acceptable prediction accuracy.

Original languageEnglish
Title of host publicationCommunications in Computer and Information Science
PublisherSpringer Verlag
Pages121-134
Number of pages14
Volume378 CCIS
ISBN (Print)9783642405662
DOIs
Publication statusPublished - 2013
Event2nd International Multi-Conference on Artificial Intelligence Technology, M-CAIT 2013 - Shah Alam
Duration: 28 Aug 201329 Aug 2013

Publication series

NameCommunications in Computer and Information Science
Volume378 CCIS
ISSN (Print)18650929

Other

Other2nd International Multi-Conference on Artificial Intelligence Technology, M-CAIT 2013
CityShah Alam
Period28/8/1329/8/13

Fingerprint

Neural networks
Particle swarm optimization (PSO)
Backpropagation
Climate change
Rain
Time series
Momentum
Genetic algorithms
Engines

Keywords

  • data mining
  • neural network
  • rainfall prediction

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Kamarudin, S. N. K., & Abu Bakar, A. (2013). Neural Network Algorithm Variants for Malaysian Weather Prediction. In Communications in Computer and Information Science (Vol. 378 CCIS, pp. 121-134). (Communications in Computer and Information Science; Vol. 378 CCIS). Springer Verlag. https://doi.org/10.1007/978-3-642-40567-9_11

Neural Network Algorithm Variants for Malaysian Weather Prediction. / Kamarudin, Siti Nur Kamaliah; Abu Bakar, Azuraliza.

Communications in Computer and Information Science. Vol. 378 CCIS Springer Verlag, 2013. p. 121-134 (Communications in Computer and Information Science; Vol. 378 CCIS).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kamarudin, SNK & Abu Bakar, A 2013, Neural Network Algorithm Variants for Malaysian Weather Prediction. in Communications in Computer and Information Science. vol. 378 CCIS, Communications in Computer and Information Science, vol. 378 CCIS, Springer Verlag, pp. 121-134, 2nd International Multi-Conference on Artificial Intelligence Technology, M-CAIT 2013, Shah Alam, 28/8/13. https://doi.org/10.1007/978-3-642-40567-9_11
Kamarudin SNK, Abu Bakar A. Neural Network Algorithm Variants for Malaysian Weather Prediction. In Communications in Computer and Information Science. Vol. 378 CCIS. Springer Verlag. 2013. p. 121-134. (Communications in Computer and Information Science). https://doi.org/10.1007/978-3-642-40567-9_11
Kamarudin, Siti Nur Kamaliah ; Abu Bakar, Azuraliza. / Neural Network Algorithm Variants for Malaysian Weather Prediction. Communications in Computer and Information Science. Vol. 378 CCIS Springer Verlag, 2013. pp. 121-134 (Communications in Computer and Information Science).
@inproceedings{0e1305bce43e42779d82ddc621d31cb8,
title = "Neural Network Algorithm Variants for Malaysian Weather Prediction",
abstract = "This paper studies the performance of a newly prepared time-series rainfall data by a previous researcher. The issues related are; (i) the large amount of data, and (ii) the accuracy of the prediction. In this study, the data set was obtained from Institute of Climate Change UKM, pre-processed using improved Symbolic Aggregate approximation (iSAX) and verified by experts. Five neural network algorithms were tested with the data set, namely standard Back-Propagation (BPNN), Back-Propagation with Momentum (BP with Mom), Quick-Propagation (QuickProp), Genetic Algorithm with neural network (GA-NN) and Particle Swarm Optimization with neural network (PSO-NN). The performances of these engines were measured according to the accuracy of prediction and the training time taken. The experimental results showed that while standard BPNN and PSO-NN achieved about the same accuracy prediction, PSO-NN is considered to be better as it showed a faster training time with acceptable prediction accuracy.",
keywords = "data mining, neural network, rainfall prediction",
author = "Kamarudin, {Siti Nur Kamaliah} and {Abu Bakar}, Azuraliza",
year = "2013",
doi = "10.1007/978-3-642-40567-9_11",
language = "English",
isbn = "9783642405662",
volume = "378 CCIS",
series = "Communications in Computer and Information Science",
publisher = "Springer Verlag",
pages = "121--134",
booktitle = "Communications in Computer and Information Science",

}

TY - GEN

T1 - Neural Network Algorithm Variants for Malaysian Weather Prediction

AU - Kamarudin, Siti Nur Kamaliah

AU - Abu Bakar, Azuraliza

PY - 2013

Y1 - 2013

N2 - This paper studies the performance of a newly prepared time-series rainfall data by a previous researcher. The issues related are; (i) the large amount of data, and (ii) the accuracy of the prediction. In this study, the data set was obtained from Institute of Climate Change UKM, pre-processed using improved Symbolic Aggregate approximation (iSAX) and verified by experts. Five neural network algorithms were tested with the data set, namely standard Back-Propagation (BPNN), Back-Propagation with Momentum (BP with Mom), Quick-Propagation (QuickProp), Genetic Algorithm with neural network (GA-NN) and Particle Swarm Optimization with neural network (PSO-NN). The performances of these engines were measured according to the accuracy of prediction and the training time taken. The experimental results showed that while standard BPNN and PSO-NN achieved about the same accuracy prediction, PSO-NN is considered to be better as it showed a faster training time with acceptable prediction accuracy.

AB - This paper studies the performance of a newly prepared time-series rainfall data by a previous researcher. The issues related are; (i) the large amount of data, and (ii) the accuracy of the prediction. In this study, the data set was obtained from Institute of Climate Change UKM, pre-processed using improved Symbolic Aggregate approximation (iSAX) and verified by experts. Five neural network algorithms were tested with the data set, namely standard Back-Propagation (BPNN), Back-Propagation with Momentum (BP with Mom), Quick-Propagation (QuickProp), Genetic Algorithm with neural network (GA-NN) and Particle Swarm Optimization with neural network (PSO-NN). The performances of these engines were measured according to the accuracy of prediction and the training time taken. The experimental results showed that while standard BPNN and PSO-NN achieved about the same accuracy prediction, PSO-NN is considered to be better as it showed a faster training time with acceptable prediction accuracy.

KW - data mining

KW - neural network

KW - rainfall prediction

UR - http://www.scopus.com/inward/record.url?scp=84904625871&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84904625871&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-40567-9_11

DO - 10.1007/978-3-642-40567-9_11

M3 - Conference contribution

AN - SCOPUS:84904625871

SN - 9783642405662

VL - 378 CCIS

T3 - Communications in Computer and Information Science

SP - 121

EP - 134

BT - Communications in Computer and Information Science

PB - Springer Verlag

ER -