For notebook computer companies, managing component inventory for repair service centers is vital. While there are many works performed forecast in repair time and repair volume of components, there is a limited number of research performs the pattern recognition for component failure in notebook computers. This work, in the quest of providing valuable inputs for the inventory management practice of repair service center, will focus recognizing the pattern of component failure in notebook computers. Sequential repair history was gathered from a notebook computer repair service center in Taiwan and treated as sets of observations sequences of a hidden Markov model (HMM). Meanwhile, the component failure is treated as the hidden states. The pre-processing of raw data is carried out and revealed an imbalanced HMM structure. To tackle this, a cellular Genetic Algorithm (cGA) with dominance chromosome mechanism is proposed to train the HMM. Furthermore, to enhance the performance of the proposed algorithm, an adaptive feature to switch the dominance chromosome ratio and a feature to re-estimate the fitness value using Baum-Welch Algorithm is proposed. This proposed algorithm is then called Adaptive cGA-BW and, subsequently trained the HMM for 2099 observation sequence instances. A comparative study among conventional algorithm to train the HMM and other variants of cGA is employed. This study shows Adaptive cGA-BW performed significantly better than Baum-Welch Algorithm. This result is verified by Kruskal-Wallis test. To understand the most probable component failure pattern, Viterbi Algorithm based on the HMM trained by Adaptive cGA-BW is implemented. The algorithm decoded the 70% most occurring observation sequences to component failure patterns. These patterns are ranked by their probability of happening.

For notebook computer companies, managing component inventory for repair service centers is vital. While there are many works performed forecast in repair time and repair volume of components, there is a limited number of research performs the pattern recognition for component failure in notebook computers. This work, in the quest of providing valuable inputs for the inventory management practice of repair service center, will focus recognizing the pattern of component failure in notebook computers. Sequential repair history was gathered from a notebook computer repair service center in Taiwan and treated as sets of observations sequences of a hidden Markov model (HMM). Meanwhile, the component failure is treated as the hidden states. The pre-processing of raw data is carried out and revealed an imbalanced HMM structure. To tackle this, a cellular Genetic Algorithm (cGA) with dominance chromosome mechanism is proposed to train the HMM. Furthermore, to enhance the performance of the proposed algorithm, an adaptive feature to switch the dominance chromosome ratio and a feature to re-estimate the fitness value using Baum-Welch Algorithm is proposed. This proposed algorithm is then called Adaptive cGA-BW and, subsequently trained the HMM for 2099 observation sequence instances. A comparative study among conventional algorithm to train the HMM and other variants of cGA is employed. This study shows Adaptive cGA-BW performed significantly better than Baum-Welch Algorithm. This result is verified by Kruskal-Wallis test. To understand the most probable component failure pattern, Viterbi Algorithm based on the HMM trained by Adaptive cGA-BW is implemented. The algorithm decoded the 70% most occurring observation sequences to component failure patterns. These patterns are ranked by their probability of happening.

REFERENCE
Alba, E. et al., 2005. A cellular multiobjective genetic algorithm for optimal broadcasting strategy in metropolitan MANETs. Denver, International Parallel and Distributed Processing Simposium (IPDPS).
Alba, E. & Dorronsoro, B., 2005. The Exploration/Exploitation Tradeoff in Dynamic Cellular Genetic Algorithms. IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION, Volume 9.
Alba, E. & Dorronsoro, B., 2008. Cellular Genetic Algorithm. 1st ed. s.l.:Springer Publishing.
Arabas, J., Michalewicz, Z. & Mulawka, J., 1994. GAVaPS - a genetic algorithm with varying population size. s.l., In Proceedings of the First IEEE Conference on Evolutionary Computation.
Aupetit, S., Monarche, N. & Slimane, M., 2007. Hidden Markov Models Training by a Particle Swarm Optimization Algorithm. Journal of Mathematical Modelling and Algorithms, Volume 6, pp. 175-193.
Baum, L., Petrie, T., Soules, G. & Weiss, N., 1970. A Maximization Technique Occurring in the Statistical Analysis of Probabilistic Functions of Markov Chains. The Annals of Mathematical Statistics, Volume 41, p. 164.
Bilmies, J. A., 1998. A Gentle Tutorial of the EM Algorithm and its Application to Parameter Estimation for Gaussian Mixture and Hidden Markov Models. s.l.:Berkeley Press..
Bjerkeseth, M., 2010. Using Hidden Markov Models for fault diagnostics and prognostics in Condition Based Maintenance System, s.l.: Thesis Dissertation of Faculty of Engineering of University of Agder.
Chau, C., Kwong, S., Diu, C. & Fahrner, W., 1997. Optimization of HMM by a genetic algorithm. Muncih, IEEE.
Dahi, Z. A., Alba, E. & Draa, A., 2018. A Stop-and-Start Adaptive Cellular Genetic Algorithm for Mobility Management of GSM-LTE Cellular Network Users. Expert Systems with Applications, Volume (Accepted Manuscript 1 March 2018).
Danven, P. & Yao, X., 1996. Every niching mehtod has its niche: Fitness sharing and implicit sharing compared. Problem Solving from Nature - PPSV IV, Volume 1141, p. 398.
Deb, K., 2008. Multi-Objective Optimization. 1st ed. s.l.:John Wiley & Sons.
Durret, R., 2013. Probability: Theory and Examples. 4th ed. s.l.:Cambridge University Press.
Fogarty, T., 1989. Varying the probability of mutation in the genetic. Proceedings of the 3rd International Conference on Genetic Algorithms, pp. 104-109.
Fogel, L., Owens, A. & Walsh, M., 1966. Artificial Intelligence through Simulated Evolution. New York: John Wiley & Sons.
Garg, A. & Warmuth, M., 2003. Inline updates for HMMs. Eurospeech 2003, Volume 1005-1008.
Hinterding, R., Michalewicz, Z. & Eiben, A., 1997. Adaptation in evolutionary. Proc. IEEE Conf. Evolutionary Computation, pp. 65-69.
Holland, J., 1975. Adaption in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control and Artificial Systems. Ann Arbor: The University Press of Michigan.
Jaarsveld, W. v., Dollevoet, T. & Dekker, R., 2015. Improving spare parts inventory control at a repair shop. Omega, Volume 57, pp. 217-229.
Jeong, Y. W., 2014. Joint speaker and environment adaptation using TensorVoice for robust speech recognition. Speech Communication, Volume 58, pp. 1-10.
Julstorm, B., 1995. Adapting operator probabilities in a steady-state genetic algorithm. Proceedings of the Sixth International Conference on Genetic Algorithms, pp. 81-87.
Jurafsky, D. & Martin, J. H., 2016. An Introduction to Natural Languange Processing, Computational Linguistics and Speech Recognition. 2nd ed. s.l.:Pearson Education.
Karr, A. F., 1990. Handbooks in Oprations Research and Management Science - Markov Processes. Handbooks in Operations Research and Management Science, Volume 2, pp. 95-123.
Khater, F., Mohamed, I., El-Sebah, A. & Osama, M., 2017. Fault diagnostics in an inverter feeding an induction motor using fuzzy logic. Journal of Electrical Systems and Information Technology, Volume 4, pp. 10-17.
Khreich, W., Granger, E., Miri, A. & Sabourin, R., 2012. A survey of techniques for incremental learning of HMM parameters. Information Sciences, Volume 197, pp. 105-130.
Ko, K.-E., Park, S.-M., Park, J. & Sim, K.-B., 2012. Training HMM Structure and Parameters with Genetic Algorithm. Journal of Electrical Engineering & Technology, Volume 7, pp. 109-114.
Koza, J., 1992. Genetic Programming. 1st ed. s.l.:MIT Press.
Kumar, S., Chow, T. W. & Pecht, M., 2007. Approach to Fault Identification for Electronic Products Using Mahalanobis Distance. IEEE Transactions on Instrumentation and Measurement , Volume 59, pp. 2055-2064.
Kwan, C. et al., 2005. An integrated approach to bearing fault diagnostics and prognostics. Proceedings of the American Control Conference, Volume 4, pp. 2750-2755.
Kwong, S., Chau, C., Man, K. & Tang, K., 2001. Optimisation of HMM topology and its model parameters by genetic algorithms. Pattern Recognition, Volume 34, pp. 509-522.
Lasfar, M. & Bouden, H., 2018. A method of data mining using Hidden Markov Models (HMMs) for protein secondary structure prediction. Procedia Computer Science, Volume 127, pp. 42-51.
Lee, J. & Kim, D.-W., 2016. An effective initialization method for genetic algorithm-based robot path planning using a directed acyclic graph. Information Sciences, Volume 332, pp. 1-18.
Leite, N., Fernandes, C. M., Melício, F. & Rosac, A. C., 2018. A cellular memetic algorithm for the examination timetabling problem. Computers & Operations Research, Volume 94, pp. 118-138.
Lin, C.-c., 2018. Repair Duty Process Flow in Notebook Computer Service Center, s.l.: Electronic Laboratory, National Taiwan University of Science and Technology, Unpublished.
Li, R. & Zhao, Q.-S., 2017. An improved particle swarm-ant colony hybrid algorithm for HMM training. International Journal of Wireless and Mobile Computing (IJWMC), Volume 12.
Liu, F. & Zeng, G., 2009. Study of genetic algorithm with reinforcement learning to solve the TSP. Expert Systems with Applications, Volume 36, pp. 6995-7001.
Liu, L., Huo, H. & Wang, B., 2005. A Novel Optimization of Profile HMM by a Hybrid Genetic Algorithm. COmputational Intelligence and Bioinspired Systems, pp. 734-741.
Liu, N., Davis, R. I., Lovell, B. C. & Kootsookos, P. J., 2004. Effect of Initial HMM Choices in Multiple Sequence Training for Gesture Recognition, Brinsbane: Intelligent Real-Time Imaging and Sensing (IRIS) Group School of Information Technology and Electrical Engineering.
Lopez, V. et al., 2013. An insight into classification with imbalanced data: Empirical results and current trends on using data. Information Sciences, Volume 250, pp. 113-141.
Lynn, C., Goodman, D., Kunst, N. & Judkins, J., 2009. Damage propagation analysis methodology for electromechanical actuator prognostics. Aerospace Conference, IEEE.
Maghsoudlou, Z., Merhani, H. & Azam, F., 2014. The Role of After-Sales Service in Customer. International Research Journal of Management Sciences, Volume 2, pp. 175-179.
Manderic, B. & Spiessens, P., 1989. Fine-grained parallel genetic algorithm. Proc. of the Third International Conference on Genetic Algorithms (ICGA), pp. 428-433.
Miller, B. & Goldberg, D., 1995. Genetic Algorithms, Tournament Selection, and the Effects of Noise. Complex Systems, Volume 9, pp. 193-212.
Murali, S., Pugazendhi, S. & Muralidharan, C., 2016. Modelling and Investigating the relationship of after sales service quality with customer satisfaction, retention and loyalty – A case study of home appliances business. Journal of Retailing and Consumer Services, Volume 30, pp. 67-83.
Nilsson, M., 2005. First Order Hidden Markov Model: Theory and Implementation Issues, Sweden: Department of Signal Precessing, Blekinge Institute of Technology.
Pathan, M., Patsias, S. & Tagarielli, V., 2018. A real-coded genetic algorithm for optimizing the damping response of composite laminates. Computers & Structures, Volume 198, pp. 51-60.
Pecht, M., 2012. Nvidia’s GPU failures: A case for prognostics and health management. Microelectronics Reliability, Volume 52, pp. 953-957.
Pecht, M. & Jaai, R., 2010. A prognostics and health management roadmap for information and electronics-rich systems. Microelectronics Reliability, Volume 50, pp. 317-323.
Rabiner, L. & Juang, B., 1993. Fundamentals of Speech Recognition. Englewood Cliff: Prentice-Hall.
Rabiner, L. R., 1989. A tutorial on Hidden Markov Models and selected applications in. Proceedings of the IEEE, Volume 77, pp. 257-286.
Renooij, S., 2012. Efficient sensitivity analysis in hidden markov model. International Journal of Approximate Reasoning, 53(9), pp. 1397-1414.
Sabbagha, O. et al., 2016. Impact of Quality Management Systems and After-sales Key Performance Indicators on Automotive Industry: A Literature Review. Procedia - Social and Behavioral Sciences, Volume 224, pp. 68-75.
Saha, B., Goebel, K., Poll, S. & Christophersen, J., 2009. Prognostics Methods for Battery Health Monitoring Using a Bayesian Framework. IEEE Transactions on Instrumentation and Measurement, Volume 58, pp. 291-296.
Samanta, O., Roy, A., Parui, S. K. & Bhattacharya, U., 2018. An HMM framework based on spherical-linear features for online cursive handwriting recognition. Information Sciences, Volume 441, pp. 133-151.
Schlierkamp-Voosen, D. & Miihlenbein, 1996. Adaption of population sizes by competing subpopulations. Piscataway, In Proceedings of the 1996 IEEE Conference on Evolutionary Computation.
Selak, L., Butala, P. & Sluga, A., 2014. Condition monitoring and fault diagnostics for hydropower plants. Computers in Industry, Volume 65, pp. 924-936.
Somarin, A. R., Chen, S., Asian, S. & Wang, D. Z., 2017. A heuristic stock allocation rule for repairable service parts. International Journal of Production Economics, Volume 184, pp. 131-140.
Song, G.-B. & Martynovich, P., 2009. A study of HMM-based bandwith extension of speech signals. Signal Processing, Volume 89, pp. 2036-2044.
Srivathsan, S. & Viswanathan, S., 2016. A queueing-based optimization model for planning inventory of repaired components in a service center. Computers & Industrial Engineering, Volume 106, pp. 375-385.
Streichert, F., 2002. Introduction to Evolutionary Algorithms. s.l.:University of Tuebingen.
Tang, K., Man, K., Kwong, S. & He, Q., 1996. Genetic algorithms and their applications. IEEE Signal Processing Magazine, Volume 22-37, p. 13.
Wagner, C., Saalmann, P. & Hellingrath, B., 2016. Machine Condition Monitoring and Fault Diagnostics with Imbalanced Data Sets based on the KDD Process. IFAC-PapersOnLine, Volume 49, pp. 196-301.
Warakagoda, N. D., 1996. A Hybrid ANN-HMM ASR system with NN based adaptive preprocessing, s.l.: M.Sc. Thesis Norges Tekniske Høgskole Institutt for Teleteknikk Transmisjonsteknikk.
Whitney, D., 1994. A genetic algorithm tutorial. Statistics and Computing, Volume 4, pp. 65-85.
Won, K., Prugel-Bennett, A. & Krogh, A., 2004. Training HMM Structure with Genetic Algorithm for Biological Sequence Analysis. Bioinformatics, Volume 20, pp. 3613-2619.
Xue, L., Yin, J., Ji, Z. & Jiang, L., 2006. A Particle Swarm Optimization for Hidden Markov Model Training. 8th International Conference of Signal Processing, IEEE.
Yang, Y. & Jiang, J., 2018. Bi-weighted ensemble via HMM-based approaches for temporal data clustering. Pattern Recognition, Volume 76, pp. 391-403.