Electromyographic (EMG) signal decomposition is the process of resolving an EMG signal into its component motor unit potential trains (MUPTs). The extracted MUPTs can aid in the diagnosis of neuromuscular disorders and the study of the neural control of movement, but only if they are valid trains. Before using decomposition results and the motor unit potential (MUP) shape and motor unit (MU) firing pattern information related to each active MU for either clinical or research purposes the fact that the extracted MUPTs are valid needs to be confirmed. The existing MUPT validation methods are either time consuming or related to operator experience and skill. More importantly, they cannot be executed during automatic decomposition of EMG signals to assist with improving decomposition results. To overcome these issues, in this thesis the possibility of developing automatic MUPT validation algorithms has been explored. Several methods based on a combination of feature extraction techniques, cluster validation methods, supervised classification algorithms, and multiple classifier fusion techniques were developed. The developed methods, in general, use either the MU firing pattern or MUP-shape consistency of a MUPT, or both, to estimate its overall validity. The performance of the developed systems was evaluated using a variety of MUPTs obtained from the decomposition of several simulated and real intramuscular EMG signals. Based on the results achieved, the methods that use only shape or only firing pattern information had higher generalization error than the systems that use both types of information. For the classifiers that use MU firing pattern information of a MUPT to determine its validity, the accuracy for invalid trains decreases as the number of missed-classification errors in trains increases. Likewise, for the methods that use MUP-shape information of a MUPT to determine its validity, the classification accuracy for invalid trains decreases as the within-train similarity of the invalid trains increase. Of the systems that use both shape and firing pattern information, those that separately estimate MU firing pattern validity and MUP-shape validity and then estimate the overall validity of a train by fusing these two indices using trainable fusion methods performed better than the single classifier scheme that estimates MUPT validity using a single classifier, especially for the real data used. Overall, the multi-classifier constructed using trainable logistic regression to aggregate base classifier outputs had the best performance with overall accuracy of 99.4% and 98.8% for simulated and real data, respectively. The possibility of formulating an algorithm for automated editing MUPTs contaminated with a high number of false-classification errors (FCEs) during decomposition was also investigated. Ultimately, a robust method was developed for this purpose. Using a supervised classifier and MU firing pattern information provided by each MUPT, the developed algorithm first determines whether a given train is contaminated by a high number of FCEs and needs to be edited. For contaminated MUPTs, the method uses both MU firing pattern and MUP shape information to detect MUPs that were erroneously assigned to the train. Evaluation based on simulated and real MU firing patterns, shows that contaminated MUPTs could be detected with 84% and 81% accuracy for simulated and real data, respectively. For a given contaminated MUPT, the algorithm on average correctly classified around 92.1% of the MUPs of the MUPT. The effectiveness of using the developed MUPT validation systems and the MUPT editing methods during EMG signal decomposition was investigated by integrating these algorithms into a certainty-based EMG signal decomposition algorithm. Overall, the decomposition accuracy for 32 simulated and 30 real EMG signals was improved by 7.5% (from 86.7% to 94.2%) and 3.4% (from 95.7% to 99.1%), respectively. A significant improvement was also achieved in correctly estimating the number of MUPTs represented in a set of detected MUPs. The simulated and real EMG signals used were comprised of 3–11 and 3–15 MUPTs, respectively.

Electromyographic (EMG) signal decomposition is the process of resolving an EMG signal into its component motor unit potential trains (MUPTs). The extracted MUPTs can aid in the diagnosis of neuromuscular disorders and the study of the neural control of movement, but only if they are valid trains. Before using decomposition results and the motor unit potential (MUP) shape and motor unit (MU) firing pattern information related to each active MU for either clinical or research purposes the fact that the extracted MUPTs are valid needs to be confirmed. The existing MUPT validation methods are either time consuming or related to operator experience and skill. More importantly, they cannot be executed during automatic decomposition of EMG signals to assist with improving decomposition results. To overcome these issues, in this thesis the possibility of developing automatic MUPT validation algorithms has been explored. Several methods based on a combination of feature extraction techniques, cluster validation methods, supervised classification algorithms, and multiple classifier fusion techniques were developed. The developed methods, in general, use either the MU firing pattern or MUP-shape consistency of a MUPT, or both, to estimate its overall validity. The performance of the developed systems was evaluated using a variety of MUPTs obtained from the decomposition of several simulated and real intramuscular EMG signals. Based on the results achieved, the methods that use only shape or only firing pattern information had higher generalization error than the systems that use both types of information. For the classifiers that use MU firing pattern information of a MUPT to determine its validity, the accuracy for invalid trains decreases as the number of missed-classification errors in trains increases. Likewise, for the methods that use MUP-shape information of a MUPT to determine its validity, the classification accuracy for invalid trains decreases as the within-train similarity of the invalid trains increase. Of the systems that use both shape and firing pattern information, those that separately estimate MU firing pattern validity and MUP-shape validity and then estimate the overall validity of a train by fusing these two indices using trainable fusion methods performed better than the single classifier scheme that estimates MUPT validity using a single classifier, especially for the real data used. Overall, the multi-classifier constructed using trainable logistic regression to aggregate base classifier outputs had the best performance with overall accuracy of 99.4% and 98.8% for simulated and real data, respectively. The possibility of formulating an algorithm for automated editing MUPTs contaminated with a high number of false-classification errors (FCEs) during decomposition was also investigated. Ultimately, a robust method was developed for this purpose. Using a supervised classifier and MU firing pattern information provided by each MUPT, the developed algorithm first determines whether a given train is contaminated by a high number of FCEs and needs to be edited. For contaminated MUPTs, the method uses both MU firing pattern and MUP shape information to detect MUPs that were erroneously assigned to the train. Evaluation based on simulated and real MU firing patterns, shows that contaminated MUPTs could be detected with 84% and 81% accuracy for simulated and real data, respectively. For a given contaminated MUPT, the algorithm on average correctly classified around 92.1% of the MUPs of the MUPT. The effectiveness of using the developed MUPT validation systems and the MUPT editing methods during EMG signal decomposition was investigated by integrating these algorithms into a certainty-based EMG signal decomposition algorithm. Overall, the decomposition accuracy for 32 simulated and 30 real EMG signals was improved by 7.5% (from 86.7% to 94.2%) and 3.4% (from 95.7% to 99.1%), respectively. A significant improvement was also achieved in correctly estimating the number of MUPTs represented in a set of detected MUPs. The simulated and real EMG signals used were comprised of 3–11 and 3–15 MUPTs, respectively.

Neuromuscular disorders change the underlying structure and function of motor units within a muscle, and are detected using needle electromyography. Currently, inferences about the presence or absence of disease are made subjectively and are largely impression-based. Quantitative electromyography (QEMG) attempts to improve upon the status quo by providing greater levels of precision, objectivity and reproducibility through numeric analysis, however, their results must be transparently presented and explained to be clinically viable. The probabilistic muscle characterization (PMC) model is ideally suited for a clinical decision support system (CDSS) and has many analogues to the subjective analysis currently used. To improve disease characterization performance globally, a hierarchical classification strategy is developed that accounts for the wide range of MUP feature values present at different levels of involvement (LOI) of a disorder. To improve utility, methods for detecting LOI are considered that balance the accuracy in reporting LOI with its clinical utility. Finally, several aggregation methods that represent commonly used human decision-making strategies are considered and evaluated for their suitability in a CDSS. Four aggregation measures (Average, Bayes, Adjusted Bayes, and WMLO) are evaluated, that offer a compromise between two common decision making paradigms: conservativeness (average) and extremeness (Bayes). Standard classification methods have high specificity at a cost of poor sensitivity at low levels of disease involvement, but tend to improve with disease progression. The hierarchical model is able to provide a better balance between low-LOI sensitivity and specificity by providing the classifier with more concise definitions of abnormality due to LOI. Furthermore, a method for detecting two discrete levels of disease involvement (low and high) is accomplished with reasonable accuracy. The average aggregation method offers a conservative decision that is preferred when the quality of the evidence is poor or not known, while the more extreme aggregators such as Bayes rule perform optimally when the evidence is accurate, but underperform otherwise due to outlier values that are incorrect. The methods developed offer several improvements to PMC, by providing a better balance between sensitivity and specificity, through the definition of a clinically useful and accurate measure of LOI, and by understanding conditions for which each of the aggregation measures is better suited. These developments will enhance the quality of decision support offered by QEMG techniques, thus improving the diagnosis, treatment and management of neuromuscular disorders.

Neuromuscular disorders change the underlying structure and function of motor units within a muscle, and are detected using needle electromyography. Currently, inferences about the presence or absence of disease are made subjectively and are largely impression-based. Quantitative electromyography (QEMG) attempts to improve upon the status quo by providing greater levels of precision, objectivity and reproducibility through numeric analysis, however, their results must be transparently presented and explained to be clinically viable. The probabilistic muscle characterization (PMC) model is ideally suited for a clinical decision support system (CDSS) and has many analogues to the subjective analysis currently used. To improve disease characterization performance globally, a hierarchical classification strategy is developed that accounts for the wide range of MUP feature values present at different levels of involvement (LOI) of a disorder. To improve utility, methods for detecting LOI are considered that balance the accuracy in reporting LOI with its clinical utility. Finally, several aggregation methods that represent commonly used human decision-making strategies are considered and evaluated for their suitability in a CDSS. Four aggregation measures (Average, Bayes, Adjusted Bayes, and WMLO) are evaluated, that offer a compromise between two common decision making paradigms: conservativeness (average) and extremeness (Bayes). Standard classification methods have high specificity at a cost of poor sensitivity at low levels of disease involvement, but tend to improve with disease progression. The hierarchical model is able to provide a better balance between low-LOI sensitivity and specificity by providing the classifier with more concise definitions of abnormality due to LOI. Furthermore, a method for detecting two discrete levels of disease involvement (low and high) is accomplished with reasonable accuracy. The average aggregation method offers a conservative decision that is preferred when the quality of the evidence is poor or not known, while the more extreme aggregators such as Bayes rule perform optimally when the evidence is accurate, but underperform otherwise due to outlier values that are incorrect. The methods developed offer several improvements to PMC, by providing a better balance between sensitivity and specificity, through the definition of a clinically useful and accurate measure of LOI, and by understanding conditions for which each of the aggregation measures is better suited. These developments will enhance the quality of decision support offered by QEMG techniques, thus improving the diagnosis, treatment and management of neuromuscular disorders.

EMG signal decomposition is the process of resolving a composite EMG signal into its constituent motor unit potential trains (classes) and it can be configured as a classification problem. An EMG signal detected by the tip of an inserted needle electrode is the superposition of the individual electrical contributions of the different motor units that are active, during a muscle contraction, and background interference. <BR>This thesis addresses the process of EMG signal decomposition by developing an interactive classification system, which uses multiple classifier fusion techniques in order to achieve improved classification performance. The developed system combines heterogeneous sets of base classifier ensembles of different kinds and employs either a one level classifier fusion scheme or a hybrid classifier fusion approach. <BR>The hybrid classifier fusion approach is applied as a two-stage combination process that uses a new aggregator module which consists of two combiners: the first at the abstract level of classifier fusion and the other at the measurement level of classifier fusion such that it uses both combiners in a complementary manner. Both combiners may be either data independent or the first combiner data independent and the second data dependent. For the purpose of experimentation, we used as first combiner the majority voting scheme, while we used as the second combiner one of the fixed combination rules behaving as a data independent combiner or the fuzzy integral with the lambda-fuzzy measure as an implicit data dependent combiner. <BR>Once the set of motor unit potential trains are generated by the classifier fusion system, the firing pattern consistency statistics for each train are calculated to detect classification errors in an adaptive fashion. This firing pattern analysis allows the algorithm to modify the threshold of assertion required for assignment of a motor unit potential classification individually for each train based on an expectation of erroneous assignments. <BR>The classifier ensembles consist of a set of different versions of the Certainty classifier, a set of classifiers based on the nearest neighbour decision rule: the fuzzy <em>k</em>-NN and the adaptive fuzzy <em>k</em>-NN classifiers, and a set of classifiers that use a correlation measure as an estimation of the degree of similarity between a pattern and a class template: the matched template filter classifiers and its adaptive counterpart. The base classifiers, besides being of different kinds, utilize different types of features and their performances were investigated using both real and simulated EMG signals of different complexities. The feature sets extracted include time-domain data, first- and second-order discrete derivative data, and wavelet-domain data. <BR>Following the so-called <em>overproduce and choose</em> strategy to classifier ensemble combination, the developed system allows the construction of a large set of candidate base classifiers and then chooses, from the base classifiers pool, subsets of specified number of classifiers to form candidate classifier ensembles. The system then selects the classifier ensemble having the maximum degree of agreement by exploiting a diversity measure for designing classifier teams. The kappa statistic is used as the diversity measure to estimate the level of agreement between the base classifier outputs, i. e. , to measure the degree of decision similarity between the base classifiers. This mechanism of choosing the team's classifiers based on assessing the classifier agreement throughout all the trains and the unassigned category is applied during the one level classifier fusion scheme and the first combiner in the hybrid classifier fusion approach. For the second combiner in the hybrid classifier fusion approach, we choose team classifiers also based on kappa statistics but by assessing the classifiers agreement only across the unassigned category and choose those base classifiers having the minimum agreement. <BR>Performance of the developed classifier fusion system, in both of its variants, i. e. , the one level scheme and the hybrid approach was evaluated using synthetic simulated signals of known properties and real signals and then compared it with the performance of the constituent base classifiers. Across the EMG signal data sets used, the hybrid approach had better average classification performance overall, specially in terms of reducing the number of classification errors.

EMG signal decomposition is the process of resolving a composite EMG signal into its constituent motor unit potential trains (classes) and it can be configured as a classification problem. An EMG signal detected by the tip of an inserted needle electrode is the superposition of the individual electrical contributions of the different motor units that are active, during a muscle contraction, and background interference. <BR>This thesis addresses the process of EMG signal decomposition by developing an interactive classification system, which uses multiple classifier fusion techniques in order to achieve improved classification performance. The developed system combines heterogeneous sets of base classifier ensembles of different kinds and employs either a one level classifier fusion scheme or a hybrid classifier fusion approach. <BR>The hybrid classifier fusion approach is applied as a two-stage combination process that uses a new aggregator module which consists of two combiners: the first at the abstract level of classifier fusion and the other at the measurement level of classifier fusion such that it uses both combiners in a complementary manner. Both combiners may be either data independent or the first combiner data independent and the second data dependent. For the purpose of experimentation, we used as first combiner the majority voting scheme, while we used as the second combiner one of the fixed combination rules behaving as a data independent combiner or the fuzzy integral with the lambda-fuzzy measure as an implicit data dependent combiner. <BR>Once the set of motor unit potential trains are generated by the classifier fusion system, the firing pattern consistency statistics for each train are calculated to detect classification errors in an adaptive fashion. This firing pattern analysis allows the algorithm to modify the threshold of assertion required for assignment of a motor unit potential classification individually for each train based on an expectation of erroneous assignments. <BR>The classifier ensembles consist of a set of different versions of the Certainty classifier, a set of classifiers based on the nearest neighbour decision rule: the fuzzy <em>k</em>-NN and the adaptive fuzzy <em>k</em>-NN classifiers, and a set of classifiers that use a correlation measure as an estimation of the degree of similarity between a pattern and a class template: the matched template filter classifiers and its adaptive counterpart. The base classifiers, besides being of different kinds, utilize different types of features and their performances were investigated using both real and simulated EMG signals of different complexities. The feature sets extracted include time-domain data, first- and second-order discrete derivative data, and wavelet-domain data. <BR>Following the so-called <em>overproduce and choose</em> strategy to classifier ensemble combination, the developed system allows the construction of a large set of candidate base classifiers and then chooses, from the base classifiers pool, subsets of specified number of classifiers to form candidate classifier ensembles. The system then selects the classifier ensemble having the maximum degree of agreement by exploiting a diversity measure for designing classifier teams. The kappa statistic is used as the diversity measure to estimate the level of agreement between the base classifier outputs, i. e. , to measure the degree of decision similarity between the base classifiers. This mechanism of choosing the team's classifiers based on assessing the classifier agreement throughout all the trains and the unassigned category is applied during the one level classifier fusion scheme and the first combiner in the hybrid classifier fusion approach. For the second combiner in the hybrid classifier fusion approach, we choose team classifiers also based on kappa statistics but by assessing the classifiers agreement only across the unassigned category and choose those base classifiers having the minimum agreement. <BR>Performance of the developed classifier fusion system, in both of its variants, i. e. , the one level scheme and the hybrid approach was evaluated using synthetic simulated signals of known properties and real signals and then compared it with the performance of the constituent base classifiers. Across the EMG signal data sets used, the hybrid approach had better average classification performance overall, specially in terms of reducing the number of classification errors.

<p>Signal processing within the neurophysiological field is challenging and requires short processing time and reliable results. In this thesis, three main problems are considered.</p><p>First, a modified line source model for simulation of muscle action potentials (APs) is presented. It is formulated in continuous-time as a convolution of a muscle-fiber dependent transmembrane current and an electrode dependent weighting (impedance) function. In the discretization of the model, the Nyquist criterion is addressed. By applying anti-aliasing filtering, it is possible to decrease the discretization frequency while retaining the accuracy. Finite length muscle fibers are incorporated in the model through a simple transformation of the weighting function. The presented model is suitable for modeling large motor units.</p><p>Second, the possibility of discerning the individual AP components of the concentric needle electromyogram (EMG) is explored. Simulated motor unit APs (MUAPs) are prefiltered using Wiener filtering. The mean fiber concentration (MFC) and jitter are estimated from the prefiltered MUAPs. The results indicate that the assessment of the MFC may well benefit from the presented approach and that the jitter may be estimated from the concentric needle EMG with an accuracy comparable with traditional single fiber EMG.</p><p>Third, automatic, rather than manual, detection and discrimination of recorded C-fiber APs is addressed. The algorithm, detects the Aps reliably using a matched filter. Then, the detected APs are discriminated using multiple hypothesis tracking combined with Kalman filtering which identifies the APs originating from the same C-fiber. To improve the performance, an amplitude estimate is incorporated into the tracking algorithm. Several years of use show that the performance of the algorithm is excellent with minimal need for audit.</p>

Signal processing within the neurophysiological field is challenging and requires short processing time and reliable results. In this thesis, three main problems are considered. First, a modified line source model for simulation of muscle action potentials (APs) is presented. It is formulated in continuous-time as a convolution of a muscle-fiber dependent transmembrane current and an electrode dependent weighting (impedance) function. In the discretization of the model, the Nyquist criterion is addressed. By applying anti-aliasing filtering, it is possible to decrease the discretization frequency while retaining the accuracy. Finite length muscle fibers are incorporated in the model through a simple transformation of the weighting function. The presented model is suitable for modeling large motor units. Second, the possibility of discerning the individual AP components of the concentric needle electromyogram (EMG) is explored. Simulated motor unit APs (MUAPs) are prefiltered using Wiener filtering. The mean fiber concentration (MFC) and jitter are estimated from the prefiltered MUAPs. The results indicate that the assessment of the MFC may well benefit from the presented approach and that the jitter may be estimated from the concentric needle EMG with an accuracy comparable with traditional single fiber EMG. Third, automatic, rather than manual, detection and discrimination of recorded C-fiber APs is addressed. The algorithm, detects the Aps reliably using a matched filter. Then, the detected APs are discriminated using multiple hypothesis tracking combined with Kalman filtering which identifies the APs originating from the same C-fiber. To improve the performance, an amplitude estimate is incorporated into the tracking algorithm. Several years of use show that the performance of the algorithm is excellent with minimal need for audit.