Integrating Heterogeneous Classifier Ensembles for EMG Signal Decomposition Based on Classifier Agreement

Abstract

In this paper, we present a design methodology for integrating heterogeneous classifier ensembles by employing a diversity-based hybrid classifier fusion approach, whose aggregator module consists of two classifier combiners, to achieve an improved classification performance for motor unit potential classification during electromyographic (EMG) signal decomposition. Following the so-called overproduce and choose strategy to classifier ensemble combination, the developed system allows the construction of a large set of base classifiers, and then automatically chooses subsets of classifiers to form candidate classifier ensembles for each combiner. The system exploits kappa statistic diversity measure to design classifier teams through estimating the level of agreement between base classifier outputs. The pool of base classifiers consists of different kinds of classifiers: the adaptive certainty-based, the adaptive fuzzy k -NN, and the adaptive matched template filter classifiers; and utilizes different types of features. Performance of the developed system was evaluated using real and simulated EMG signals, and was compared with the performance of the constituent base classifiers. Across the EMG signal datasets used, the developed system had better average classification performance overall, especially in terms of reducing classification errors. For simulated signals of varying intensity, the developed system had an average correct classification rate CCr of 93.8% and an error rate Er of 2.2% compared to 93.6% and 3.2%, respectively, for the best base classifier in the ensemble. For simulated signals with varying amounts of shape and/or firing pattern variability, the developed system had a CCr of 89.1% with an Er of 4.7% compared to 86.3% and 5.6%, respectively, for the best classifier. For real signals, the developed system had a CCr of 89.4% with an Er of 3.9% compared to 84.6% and 7.1%, respectively, for the best classifier.

EMG Signal Decomposition Using Motor Unit Potential Train Validity

“…A MUP begins when its sample values exceed a threshold and ends when they fall below this threshold [54], [55], [59], [70], [71]. If a fixed-length window is chosen for analysis, the length of the window is set to include a fixed duration, typically 2.5 ms [1], [7], [19], [26], [27], [72], [74], [76][77][78], [81][82][83] or 6 ms [58], [66], [67]. Longer windows improve MUP representation, but will increase decomposition time.…”

“…Raw-data (time samples) and first-or second -derivative of time samples [1], [5][6][7], [19], [25], [27], [72], [74], [76][77][78][79][80], [82], [86], [87], power spectrum and Fourier transform coefficients [45], [49], [50], [62], wavelet coefficients [53][54][55], [59], [59], [79], [81], [83], [88][89][90][91][92][93][94], and principal components of wavelet coefficients [95] are features that have been used to represent and assign MUPs to MUPTs. Using power spectrum coefficients [62] or wavelet coefficients of MUPs decreases the dimensionality of the feature space and hence may improve the processing time.…”

“…For diagnostic purposes it is useful to get detailed temporal and spatial information about the fibers of a MU. [27] and [28]). …”

Motor Unit Potential Train Validation and Its Application in EMG Signal Decomposition

“…The MU discharges corresponding to a valid MUPT occur at regular intervals and in general, have a Gaussian-shaped IDI histogram while for invalid MUPTs the IDIs have large variations and will not have a Gaussian-shaped IDI histogram. Even though some researchers have demonstrated that the IDI distribution of a MU may not actually be Gaussian (De Luca & Forrest,1973;Matthews, 1996), for MUPTs of MUs that are consistently recruited, the Gaussian density is an appropriate approximation (Clamann, 1969;Stashuk, 1999;Moritz et al, 2005;Rasheed et al, 2010;. If an extracted MUPT represents the firing of a single MU and has suitably low percentage of FCEs (FCE rate), it has MU firing pattern validity.…”

Aggregating Fuzzy QL- and (S,N)-Subimplications: Conjugate and Dual Constructions

“…The study of aggregation operators is a large domain, supported by using aggregation concepts modeling uncertainty in distinct fields such as social, engineering or economical problems which are based on fuzzy logic (FL) [1,2,3,4]. Consequently, they have been applied to many fields of approximate reasoning [5], e.g.…”