Abstract
Fault prediction is a vital component of proactive maintenance in the telephone access loop. Indication of line problems are found by regularly measuring line parameters such as resistance and voltage. The suggested technique uses preprocessed line measurements as input to a neural network. Line repair records are used as fault indications when creating the training and test data set for the neural network. The collected data is found to be inconsistent and noisy. This limits the achievable correctness of the results. The method uses multiple measurements of the same line. Using hidden layers in the neural network was not found to improve the results significantly. The results show that around 25 – 50 % of the predicted faults are later reported by the customers. Unfortunately, few faults can be predicted with a high correctness.
Preview
Unable to display preview. Download preview PDF.
References
Egan, B.: Data Mining in the Telecommunications Industry, subtopic Network Fault Diagnosis. PKDD'97, Principles of Data Mining and Knowledge Discovery. Tutorial handout notes. First European Symposium, Trondheim, Norway (June 1997)
Thomas, M. R., Bell, P.: Fault rate analysis, modelling and estimation. BT Technical Journal, Vol. 14, No. 2 (April 1996) 133–139
Rumelhart, D., Widrow, B.: The Basic Ideas of Neural Network. Communications of the ACM, Vol.37, No.3 (March 1994) 87–92
Haykin, S.: Neural Networks, A Comprehensive Foundation. Macmillan College Publishing Company, Inc., 696 pages (1994)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1998 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Knudsen, B.R. (1998). Fault prediction in the telephone access loop using a neural network. In: Mercer, R.E., Neufeld, E. (eds) Advances in Artificial Intelligence. Canadian AI 1998. Lecture Notes in Computer Science, vol 1418. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-64575-6_54
Download citation
DOI: https://doi.org/10.1007/3-540-64575-6_54
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-64575-7
Online ISBN: 978-3-540-69349-9
eBook Packages: Springer Book Archive