The enhanced BPNN-NAR and BPNN-NARMA models for Malaysian aggregate cost indices with outlying data
Neurocomputing have been adapted in time series forecasting arena, but the presence of outliers that usually occur in data time series may be harmful to the data network training. This is because the ability to automatically find out any patterns without prior assumptions and loss of generality....
| Main Authors: | , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English English |
| Published: |
IEEE
2015
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/50812/ http://irep.iium.edu.my/50812/ http://irep.iium.edu.my/50812/ http://irep.iium.edu.my/50812/1/50812.pdf http://irep.iium.edu.my/50812/2/50812-The%20enhanced%20BPNN-NAR%20and%20BPNN-NARMA%20models%20for%20Malaysian%20aggregate%20cost%20indices%20with%20outlying%20data_SCOPUS.pdf |
| id |
iium-50812 |
|---|---|
| recordtype |
eprints |
| spelling |
iium-508122017-03-31T01:51:30Z http://irep.iium.edu.my/50812/ The enhanced BPNN-NAR and BPNN-NARMA models for Malaysian aggregate cost indices with outlying data Ahmad Kamaruddin, Saadi Md Ghani, Nor Azura Mohamed Ramli, Norazan T Technology (General) Neurocomputing have been adapted in time series forecasting arena, but the presence of outliers that usually occur in data time series may be harmful to the data network training. This is because the ability to automatically find out any patterns without prior assumptions and loss of generality. In theory, the most common training algorithm for Backpropagation algorithms leans on reducing ordinary least squares estimator (OLS) or more specifically, the mean squared error (MSE). However, this algorithm is not fully robust when outliers exist in training data, and it will lead to false forecast future value. Therefore, in this paper, we present a new algorithm that manipulate algorithms firefly on least median squares estimator (FFA-LMedS) for Backpropagation neural network nonlinear autoregressive (BPNN-NAR) and Backpropagation neural network nonlinear autoregressive moving (BPNN-NARMA) models to reduce the impact of outliers in time series data. The performances of the proposed enhanced models with comparison to the existing enhanced models using M-estimators, Iterative LMedS (ILMedS) and Particle Swarm Optimization on LMedS (PSO-LMedS) are done based on root mean squared error (RMSE) values which is the main highlight of this paper. In the meanwhile, the real-industrial monthly data of Malaysian Aggregate cost indices data set from January 1980 to December 2012 (base year 1980=100) with different degree of outliers problem is adapted in this research. At the end of this paper, it was found that the enhanced BPNN-NARMA models using Mestimators, ILMedS and FFA-LMedS performed very well with RMSE values almost zero errors. It is expected that the findings would assist the respected authorities involve in Malaysian construction projects to overcome cost overruns. IEEE 2015 Conference or Workshop Item PeerReviewed application/pdf en http://irep.iium.edu.my/50812/1/50812.pdf application/pdf en http://irep.iium.edu.my/50812/2/50812-The%20enhanced%20BPNN-NAR%20and%20BPNN-NARMA%20models%20for%20Malaysian%20aggregate%20cost%20indices%20with%20outlying%20data_SCOPUS.pdf Ahmad Kamaruddin, Saadi and Md Ghani, Nor Azura and Mohamed Ramli, Norazan (2015) The enhanced BPNN-NAR and BPNN-NARMA models for Malaysian aggregate cost indices with outlying data. In: 2015 IIEEE Conference on e-Learning, e- Management and e-Services (IC3e), 24th-26th August 2015, Melaka, Malaysia. http://ieeexplore.ieee.org/document/7403484/?section=abstract 10.1109/IC3e.2015.7403484 |
| repository_type |
Digital Repository |
| institution_category |
Local University |
| institution |
International Islamic University Malaysia |
| building |
IIUM Repository |
| collection |
Online Access |
| language |
English English |
| topic |
T Technology (General) |
| spellingShingle |
T Technology (General) Ahmad Kamaruddin, Saadi Md Ghani, Nor Azura Mohamed Ramli, Norazan The enhanced BPNN-NAR and BPNN-NARMA models for Malaysian aggregate cost indices with outlying data |
| description |
Neurocomputing have been adapted in time series
forecasting arena, but the presence of outliers that usually occur
in data time series may be harmful to the data network training.
This is because the ability to automatically find out any patterns
without prior assumptions and loss of generality. In theory, the
most common training algorithm for Backpropagation
algorithms leans on reducing ordinary least squares estimator
(OLS) or more specifically, the mean squared error (MSE).
However, this algorithm is not fully robust when outliers exist in
training data, and it will lead to false forecast future value.
Therefore, in this paper, we present a new algorithm that
manipulate algorithms firefly on least median squares estimator
(FFA-LMedS) for Backpropagation neural network nonlinear
autoregressive (BPNN-NAR) and Backpropagation neural
network nonlinear autoregressive moving (BPNN-NARMA)
models to reduce the impact of outliers in time series data. The
performances of the proposed enhanced models with comparison
to the existing enhanced models using M-estimators, Iterative
LMedS (ILMedS) and Particle Swarm Optimization on LMedS
(PSO-LMedS) are done based on root mean squared error
(RMSE) values which is the main highlight of this paper. In the
meanwhile, the real-industrial monthly data of Malaysian
Aggregate cost indices data set from January 1980 to December
2012 (base year 1980=100) with different degree of outliers
problem is adapted in this research. At the end of this paper, it
was found that the enhanced BPNN-NARMA models using Mestimators,
ILMedS and FFA-LMedS performed very well with
RMSE values almost zero errors. It is expected that the findings
would assist the respected authorities involve in Malaysian
construction projects to overcome cost overruns. |
| format |
Conference or Workshop Item |
| author |
Ahmad Kamaruddin, Saadi Md Ghani, Nor Azura Mohamed Ramli, Norazan |
| author_facet |
Ahmad Kamaruddin, Saadi Md Ghani, Nor Azura Mohamed Ramli, Norazan |
| author_sort |
Ahmad Kamaruddin, Saadi |
| title |
The enhanced BPNN-NAR and BPNN-NARMA models for Malaysian aggregate cost indices with outlying data |
| title_short |
The enhanced BPNN-NAR and BPNN-NARMA models for Malaysian aggregate cost indices with outlying data |
| title_full |
The enhanced BPNN-NAR and BPNN-NARMA models for Malaysian aggregate cost indices with outlying data |
| title_fullStr |
The enhanced BPNN-NAR and BPNN-NARMA models for Malaysian aggregate cost indices with outlying data |
| title_full_unstemmed |
The enhanced BPNN-NAR and BPNN-NARMA models for Malaysian aggregate cost indices with outlying data |
| title_sort |
enhanced bpnn-nar and bpnn-narma models for malaysian aggregate cost indices with outlying data |
| publisher |
IEEE |
| publishDate |
2015 |
| url |
http://irep.iium.edu.my/50812/ http://irep.iium.edu.my/50812/ http://irep.iium.edu.my/50812/ http://irep.iium.edu.my/50812/1/50812.pdf http://irep.iium.edu.my/50812/2/50812-The%20enhanced%20BPNN-NAR%20and%20BPNN-NARMA%20models%20for%20Malaysian%20aggregate%20cost%20indices%20with%20outlying%20data_SCOPUS.pdf |
| first_indexed |
2023-09-18T21:11:54Z |
| last_indexed |
2023-09-18T21:11:54Z |
| _version_ |
1777411307908104192 |