GMMs similarity measure based on LPP-like projection of the parameter space. (30th December 2016)

• Record Type: Journal Article
• Authors: Krstanović, Lidija; Ralević, Nebojsa M.; Zlokolica, Vladimir; Obradović, Ratko; Mišković, Dragiša; Janev, Marko; Popović, Branislav
• Is Part Of: Expert systems with applications. Volume 66(2016)
• Page Start: 136
• Page End: 148
• Publication Date: 2016-12-30
• Subjects: Gaussian mixture model -- Similarity measures -- Dimensionality reduction -- KL-divergence; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2016.09.014
• Languages: English
• ISSNs: 0957-4174

Abstract

Highlights: We propose the novel more efficient similarity measure between GMMs. It is done by projecting GMMs from high dimensional to a lower dimensional space. GMMs distance is reduced to the distance between lower dimensional euclidian vectors. Greater discriminativity and lower computational cost is obtained. We confirm our results on artificial and real experimental data. Abstract: The need for a comparison between two Gaussian Mixture Models (GMMs) plays a crucial role in various pattern recognition tasks and is involved as a key components in many expert and artificial intelligence (AI) systems dealing with real-life problems. As those system often operate on large data-sets and use high dimensional features, it is crucial for their recognition component to be computationally efficient in addition to its good recognition accuracy. In this work we deliver the novel similarity measure between GMMs, by LPP-like projecting the components of a particular GMM, from the high dimensional original parameter space, to a much lower dimensional space. Thus, finding the distance between two GMMs in the original space is reduced to finding the distance between sets of lower dimensional Euclidian vectors, pondered by corresponding weights. By doing so, we manage to obtain much better trade-off between the recognition accuracy and the computational complexity, in comparison to the measures between GMMs utilizing distances between Gaussian components evaluated in the original parameter space. Thus, the GMM measure that we propose is suitable for applications in AI systems that use GMMs in their recognition tasks and operate on large data sets, as the required number of overall Gaussian components involved in such systems is always large. We evaluate the proposed GMM measure on artificial, as well as real-world experimental data obtaining a much better trade-off between recognition accuracy and the computational complexity, in comparison to all baseline GMM similarity measures tested.