Self-Tuning Varri Method in Preparing Fatigue Segment

Authors

  • M. H. Osman Faculty of Engineering and Built Environment, Universiti Kebangsaan Malaysia, 43600 UKM Bangi, Selangor, Malaysia
  • Z. M. Nopiah Faculty of Engineering and Built Environment, Universiti Kebangsaan Malaysia, 43600 UKM Bangi, Selangor, Malaysia
  • S. Abdullah Centre for Automotive Research, Universiti Kebangsaan Malaysia, 43600 UKM Bangi, Selangor, Malaysia
  • A. Lennie Faculty of Engineering and Built Environment, Universiti Kebangsaan Malaysia, 43600 UKM Bangi, Selangor, Malaysia

DOI:

https://doi.org/10.11113/jt.v63.1911

Keywords:

Fatigue segment, fatigue signal, classification, segmentation, Varri method

Abstract

An overlapping segmentation method on time series data is often used for preparing training dataset i.e. the population of instance, for classification data mining. Having large number of redundant instances would burden the training process with heavy computational operation. This would happen if practitioners fail to acknowledge an appropriate amount of overlap when performing the time series segmentation. Fortunately, the risk could be decreased if knowledge preferences can be determined to guide on overlapping criteria in the segmentation algorithm. Thus, this study aims to investigate how the Varri method is able to contribute for better understanding in preparing training dataset consists of irredundant fatigue segment from the loading history (fatigue signal). Generally, the method locates segment boundaries based on local maxima in the difference function which are above the assigned threshold. In the present study, the mean and standard deviation have been used to define the function due to the fact that predicting attributes are the key components in defining instance redundancy. The resulting dataset from the proposed method is trained by three classification algorithms under the supervision of the Genetic algorithms-based feature selection wrapper approach. The average performance index shows an additional advantage of the proposed method as compared to the conventional procedure in preparing training dataset.

References

Czarnowski, I. and P. Jędrzejowicz. 2006. Instance Reduction Approach to Machine Learning and Multi-Database Mining. Annales UMCS Inform. AI. 4: 60–71.

Niamut, O.A. and R. Heusdens. 2005. Optimal Time Segmentation for Overlap-Add Systems with Variable Amount of Window Overlap. Signal Processing Letters, IEEE. 12(10): 665–668.

Brain, D. and G. Webb. 1999. On The Effect of Data Set Size on Bias and Variance in Classification Learning. Proc. 4th Australian Knowl. Acquis. Workshop. 117–128.

Albalate, M.T.L., Data Reduction Techniques in Classification Processes. 2007. Ph. D., Llenguatges I Sistemses Informatics, Universitat Jaume I.

Niyogi, P. and N. Karmarkar. 2000. An Approach to Data Reduction and Clustering with Theoretical Guarantees. Proc. Int. Conf. Machine Learning. 679–686.

Vaari, A., Digital Orocessing of The EEG in Epilepsy, 1998, Licentiate Thesis, Tampere University of Technology, Tempere, Finland.

Azami, H., K. Mohammadi and B. Bozorgtabar. 2012. An Improved Signal Segmentation Using Moving Average and Savitzky-Golay Filter. J. Signal Inf. Processing. 3(1): 39–44.

Kirlangic, M.E., D. Perez, S. Kudryavtseva, G. Griessbach and G. Henning. 2001. Fractal Dimension as a Feature for Adaptive Electroencephalogram Segmentation in Epilepsy. 2001 Proc. 23rd Annu. EMBS Int. Conf. 2: 1573–1576.

Anisheh, S.M. and H. Hassanpour. 2009. Adaptive Segmentation with Optimal Window Length Scheme Using Fractal Dimension And Wavelet Transform. Transactions B: Applications. 22(3): 257–268.

Nopiah, Z.M., M.H. Osman, S. Abdullah and M.N. Baharin. 2011. The Identification of Low Fatigue Damage Using Fuzzy Double Clustering Framework. 2011 IEEE 7th Int. Colloq. Signal Processing and its Applications. 181–186.

Osman, M.H., Z.M. Nopiah and S. Abdullah. 2012. Feature Selection for Fatigue Segment Classification System Using Elitist Non-dominated Sorting in Genetic Algorithm. Appl. Mech. Mater. 165: 232–236.

Nopiah, Z.M., M.I. Khairir and S. Abdullah. 2008. Segmentation and Scattering of Fatigue Damage Time Series Data by Kurtosis And Root Mean Square. Proc. 7th WSEAS Int. Conf. Signal Process. 64–68.

Kotsiantis, S.B. 2007. Supervised Machine Learning: A Review of Classification Techniques. Inform. 31: 249–268.

Nopiah, Z.M., M.N. Baharin, S. Abdullah, M.I. Khairir and A. Ariffin. 2010. Running Damage Extraction Technique for Identifying Fatigue Damaging Events. WSEAS Trans. Math. 9(5): 324–333.

García, V., J.S. Sánchez and R.A. Mollineda. 2012. On The Effectiveness of Preprocessing Methods When Dealing with Different Levels of Class Imbalance. Knowl-Based Syst. 25(1): 13–21.

Karegowda, A.G., M.A. Jayaram and A.S. Manjunath. 2010. Feature Subset Selection Problem Using Wrapper Approach in Supervised Learning. Int. J. Computer Applications. 1(7): 13–17.

Hall, M., E. Frank, G. Holmes, B. Pfahringer, P. Reutemann and I.H. Witten. 2009. The WEKA Data Mining Software: An Update. SIGKDD Explor. Newsl. 11(1): 10–18.

Stephens, R.I., P.M. Dindinger and J.E. Gunger. 1997. Fatigue Damage Editing for Accelerated Durability Testing Using Strain Range and SWT Parameter Criteria. Int. J. Fatigue. 19(8–9): 599–606.

Downloads

Published

2013-06-15

Issue

Section

Science and Engineering

How to Cite

Self-Tuning Varri Method in Preparing Fatigue Segment. (2013). Jurnal Teknologi (Sciences & Engineering), 63(2). https://doi.org/10.11113/jt.v63.1911