Modified Baum Welch Algorithm for Hidden Markov Models with Known Structure
Hidden Markov Models (HMMs) are widely used in speech and handwriting recognition, behavior prediction in traffic, time series analysis, biostatistics, image and signal processing, and many other fields. For some applications in those real world problems, a-priori knowledge about the structure of the HMM is available. For example the shape of the state transition matrix and/or the observation matrix might be given. We might know that some entries in these matrices are equal and others are zero. For training such a model, we have two options: use the common Baum Welch Algorithm (BWA) and enforce the given structure after training or modify the BWA to enforce it during training. This paper shows several approaches for modifying the BWA and compares the results of all training methods.
KeywordsHidden Markov Model HMM Baum Welch Algorithm Multiple sequence learning A-priori knowledge
This research was supported by the European Social Fund and the Free State of Saxony under Grant No. 100269974.
- 3.Kuge, N., Yamamura, T., Shimoyama, O., Liu, A.: A driver behavior recognition method based on a driver model framework. SAE Technical Paper, Technical report (2000)Google Scholar
- 4.Streubel, T., Hoffmann, K.H.: Prediction of driver intended path at intersections. In: Intelligent Vehicles Symposium Proceedings, 8–11 June 2014, pp. 134–139. IEEE, Dearborn (2014)Google Scholar
- 5.Knab, B.: Erweiterung von Hidden-Markov-Modellen zur Analyse ökonomischer Zeitreihen. Ph.D. dissertation, Universit ̈at zu Köln (2000)Google Scholar
- 6.Hassan, M.R., Nath, B.: Stock market forecasting using hidden Markov model: a new approach. In: 5th International Conference on Intelligent Systems Design and Applications (ISDA 2005), pp. 192–196 (2005)Google Scholar
- 10.Dash, D.P., Kolekar, M.H.: Epileptic seizure detection based on EEG signal analysis using hierarchy based Hidden Markov Model. In: 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI), pp. 1114–1120 (2017)Google Scholar