Chris Aldrich | Curtin University (original) (raw)
Papers by Chris Aldrich
AIChE Journal, 2005
Statistical pattern-recognition methods are now widely applied in the analysis of process systems... more Statistical pattern-recognition methods are now widely applied in the analysis of process systems to achieve predictable and stable operating conditions. For example, multivariate statistical process control (MSPC) techniques use historical operating data to detect abnormal events, and assist engineers to focus their troubleshooting efforts to reduced subsets of variables in an otherwise broad operational space. Through an iterative process, it is hoped that the system variability remains bounded. Usually only a few samples collected under a state of statistical control are of interest, whereas the rest, which may be used to uncover potential improvement opportunities, are ignored. Beyond statistical control, an additional step is required to reduce the dispersion of process quality variables attributed to common causes. To achieve this goal, common and sustained causes not identified by MSPC must be interrogated. In this paper, a methodology based on kernel-based machine learning concepts is proposed to identify decision boundaries. A sparse set of instances or exemplars is identified that define a linear decision boundary in a feature space, which is equivalent to defining a nonlinear decision function in the associated input space. This is extended to defining operating strategies by integrating inductive learning into a decision support framework. Such an extension is founded on the fact that the success or failure of state-of-the-art approaches are invariably linked to the presence or absence of useful knowledge embedded in the system.
Time Series Analysis - Data, Methods, and Applications
Fault diagnosis in continuous dynamic systems can be challenging, since the variables in these sy... more Fault diagnosis in continuous dynamic systems can be challenging, since the variables in these systems are typically characterized by autocorrelation, as well as time variant parameters, such as mean vectors, covariance matrices, and higher order statistics, which are not handled well by methods designed for steady state systems. In dynamic systems, steady state approaches are extended to deal with these problems, essentially through feature extraction designed to capture the process dynamics from the time series. In this chapter, recent advances in feature extraction from signals or multivariate time series are reviewed. These methods can subsequently be considered in a classical statistical monitoring framework, such as used for steady state systems. In addition, an extension of nonlinear signal processing based on the use of unthresholded or global recurrence quantification analysis is discussed, where two multivariate image methods based on gray level co-occurrence matrices and local binary patterns are used to extract features from time series. When considering the well-known simulated Tennessee Eastman process in chemical engineering, it is shown that time series features obtained with this approach can be an effective means of discriminating between different fault conditions in the system. The approach provides a general framework that can be extended in multiple ways to time series analysis.
The International Journal on the Image, 2012
In this paper, we propose a new method for the motion estimation of flotation froth using mutual ... more In this paper, we propose a new method for the motion estimation of flotation froth using mutual information with a bin size of two as the block matching similarity metric. We also use three-step search-and new-three-step-search as a search strategy. Mean sum of absolute difference (MAD) is widely considered in blocked based motion estimation. The minimum bin size selection of the proposed similarity metric also makes the computational cost of mutual information similar to MAD. Experimental results show that the proposed motion estimation technique improves the motion estimation accuracy in terms of peak signal-to-noise ratio of the reconstructed frame. The computational cost of the proposed method is almost the same as the standard machine vision methods used for the motion estimation of flotation froth.
Froth image analysis has been considered widely in the identification of operational regimes in f... more Froth image analysis has been considered widely in the identification of operational regimes in flotation circuits, the characterisation of froths in terms of bubble size distributions, froth stability and local froth velocity patterns, or as a basis for the development of inferential online sensors for chemical species in the froth. Relatively few studies have considered flotation froth image analysis in unsupervised process monitoring applications. In this study, it is shown that froth image analysis can be combined with traditional multivariate statistical process monitoring methods for reliable monitoring of industrial platinum metal group flotation plants. This can be accomplished with wellestablished methods of multivariate image analysis, such as the Haralick feature set derived from grey level co-occurrence matrices and local binary patterns that were considered in this investigation.
IFAC-PapersOnLine
In this paper, the application of deep learning in the mining and processing of ores is reviewed.... more In this paper, the application of deep learning in the mining and processing of ores is reviewed. Deep learning is strongly impacting the development of sensor systems, particularly computer vision systems used in mining and mineral processing automation, where it is filling a gap not currently achievable by traditional approaches. To a lesser extent, deep learning is also being considered in the automation of decision support systems. There is significant scope for the application of deep learning to improve operations, but access to industrial data and big data infrastructure in operational environments are critical bottlenecks to the development and deployment of the technology.
Minerals
Linear regression is often used as a diagnostic tool to understand the relative contributions of ... more Linear regression is often used as a diagnostic tool to understand the relative contributions of operational variables to some key performance indicator or response variable. However, owing to the nature of plant operations, predictor variables tend to be correlated, often highly so, and this can lead to significant complications in assessing the importance of these variables. Shapley regression is seen as the only axiomatic approach to deal with this problem but has almost exclusively been used with linear models to date. In this paper, the approach is extended to random forests, and the results are compared with some of the empirical variable importance measures widely used with these models, i.e., permutation and Gini variable importance measures. Four case studies are considered, of which two are based on simulated data and two on real world data from the mineral process industries. These case studies suggest that the random forest Shapley variable importance measure may be a mo...
Processes
Grinding circuits typically contribute disproportionately to the overall cost of ore beneficiatio... more Grinding circuits typically contribute disproportionately to the overall cost of ore beneficiation and their optimal operation is therefore of critical importance in the cost-effective operation of mineral processing plants. This can be challenging, as these circuits can also exhibit complex, nonlinear behavior that can be difficult to model. In this paper, it is shown that key time series variables of grinding circuits can be recast into sets of descriptor variables that can be used in advanced modelling and control of the mill. Two real-world case studies are considered. In the first, it is shown that the controller states of an autogenous mill can be identified from the load measurements of the mill by using a support vector machine and the abovementioned descriptor variables as predictors. In the second case study, it is shown that power and temperature measurements in a horizontally stirred mill can be used for online estimation of the particle size of the mill product.
Time Series Analysis - Data, Methods, and Applications, Nov 6, 2019
Fault diagnosis in continuous dynamic systems can be challenging, since the variables in these sy... more Fault diagnosis in continuous dynamic systems can be challenging, since the variables in these systems are typically characterized by autocorrelation, as well as time variant parameters, such as mean vectors, covariance matrices, and higher order statistics, which are not handled well by methods designed for steady state systems. In dynamic systems, steady state approaches are extended to deal with these problems, essentially through feature extraction designed to capture the process dynamics from the time series. In this chapter, recent advances in feature extraction from signals or multivariate time series are reviewed. These methods can subsequently be considered in a classical statistical monitoring framework, such as used for steady state systems. In addition, an extension of nonlinear signal processing based on the use of unthresholded or global recurrence quantification analysis is discussed, where two multivariate image methods based on gray level co-occurrence matrices and local binary patterns are used to extract features from time series. When considering the well-known simulated Tennessee Eastman process in chemical engineering, it is shown that time series features obtained with this approach can be an effective means of discriminating between different fault conditions in the system. The approach provides a general framework that can be extended in multiple ways to time series analysis.
Mineral Processing and Extractive Metallurgy Review
ABSTRACT Gold and copper thiosulfate adsorption from an alkaline gold ore leachate was investigat... more ABSTRACT Gold and copper thiosulfate adsorption from an alkaline gold ore leachate was investigated by using polyethylenimine-coated iron oxide magnetic nanoparticles (NPs). The ore, sourced from a mine in Nevada, USA, was leached with calcium thiosulfate for 48 h in the presence of Cu(II) at a pH of 8 and a temperature of 50°C. A response surface methodology was used to analyze the effect of adsorbent dosage, adsorption time and solution temperature on the recovery of gold and copper from the solution. The results showed that the gold adsorption was nonlinearly dependent on the adsorbent dosage only. In contrast, the recovery of the copper depended on all three predictors, including interaction between the temperature and adsorbent dosage. The optimal conditions for maximal gold adsorption was 35 g/L adsorbent dosage, 55 min time and a temperature of 23°C. The selective elution of loaded metals on the NPs was also successfully achieved.
Minerals Engineering
Deep learning constitutes a significant recent advance in machine learning and has been particula... more Deep learning constitutes a significant recent advance in machine learning and has been particularly successful in applications related to image processing, where it can already surpass human accuracy in some cases. In this paper, the use of a convolutional neural network, AlexNet, pretrained on a database of images of common objects was used as is to extract features from flotation froth images. These features could subsequently be used to predict the conditions or performance of the flotation systems. Two case studies are considered. In the first, froth regimes in an industrial flotation plant could be identified significantly more reliably with the features generated by AlexNet than with previous state-of-the-art approaches, such as wavelets, grey level co-occurrence matrices or local binary patterns. In the second case study, the arsenic concentration in the batch flotation of realgar-orpiment-quartz mixtures could be predicted more accurately than was possible with features extracted by wavelets, grey level co-occurrence matrices, local binary patterns or by use of colour. These results suggest that feature extraction with convolutional neural networks trained on complex data sets from other domains can serve as more reliable methods than previous state-of-the-art approaches to froth image analysis.
Mineral Processing and Extractive Metallurgy
ABSTRACT Multivariate image analysis was used to estimate the arsenic concentrations in froths re... more ABSTRACT Multivariate image analysis was used to estimate the arsenic concentrations in froths resulting from the flotation of different mixtures of realgar and orpiment particles in a laboratory batch flotation cell. The realgar floated rapidly and in excess of 90% of the mineral could be recovered after 2 minutes, whereas only 48–75% of the orpiment could be recovered in the same time. Textural features, based on grey level co-occurrence matrices (GLCMs), local binary patterns (LBPs), steearable pyramids and textons were used in the analysis. Random forest models could explain approximately 71–77% of the variance in the arsenic using either of the texton, steerable pyramid or LBP features. This was considerably better than what could be obtained with the GLCM features. Monitoring of froth flotation cells was simulated with the batch data. The texton textural features were the most discriminatory with regard to detecting changes in the arsenic content of the froth.
Corrosion Science
The corrosion of carbon steel in aqueous media resulting in uniform corrosion, pitting corrosion ... more The corrosion of carbon steel in aqueous media resulting in uniform corrosion, pitting corrosion and passivation was investigated on a laboratory scale. Recurrence quantification analysis was applied to short segments of electrochemical current noise measurements. These segments were converted to recurrence variables, which could be used as reliable predictors in a multilayer perceptron neural network model to identify the type of corrosion. In addition, an automated corrosion monitoring scheme is proposed, based on the principal component scores of the recurrence variables. This approach used the uniform corrosion measurements as reference data and could differentiate between uniform and non-uniform corrosion.
Proceedings of the Genetic and Evolutionary Computation Conference, Jul 9, 2002
Process changes, such as flow disturbances and sensor noise, are common in the chemical and metal... more Process changes, such as flow disturbances and sensor noise, are common in the chemical and metallurgical industries. To maintain optimal performance, the controlling system has to adapt continuously to these changes. This is a difficult problem because the controller also has to perform well while it is adapting. The Adaptive Neural Swarming (ANS) method introduced in this paper satisfies these goals. Using an existing neural network controller as a starting point, ANS modifies the network weights through Particle Swarm Optimisation. The ANS method was tested in a real-world task of controlling a simulated non-linear bioreactor. ANS was able to adapt to process changes while simultaneously avoiding hard operating constraints. This way, ANS balances the need to adapt with the need to preserve generalisation, and constitutes a general tool for adapting neural network controllers online.
Pediatric Neurology, 2016
BACKGROUND: Electroencephalography (EEG) has been used for almost a century to identify seizure-r... more BACKGROUND: Electroencephalography (EEG) has been used for almost a century to identify seizure-related disorders in humans, typically through expert interpretation of multichannel recordings. Attempts have been made to quantify EEG through frequency analyses and graphic representations. These "traditional" quantitative EEG analysis methods were limited in their ability to analyze complex and multivariate data and have not been generally accepted in clinical settings. There has been growing interest in identification of novel EEG biomarkers to detect early risk of autism spectrum disorder, to identify clinically meaningful subgroups, and to monitor targeted intervention strategies. Most studies to date have, however, used quantitative EEG approaches, and little is known about the emerging multivariate analytical methods or the robustness of candidate biomarkers in the context of the variability of autism spectrum disorder. METHODS: Here, we present a targeted review of methodological and clinical challenges in the search for novel resting-state EEG biomarkers for autism spectrum disorder. RESULTS: Three primary novel methodologies are discussed: (1) modified multiscale entropy, (2) coherence analysis, and (3) recurrence quantification analysis. Results suggest that these methods may be able to classify resting-state EEG as "autism spectrum disorder" or "typically developing", but many signal processing questions remain unanswered. CONCLUSIONS: We suggest that the move to novel EEG analysis methods is akin to the progress in neuroimaging from visual inspection, through region-of-interest analysis, to whole-brain computational analysis. Novel restingstate EEG biomarkers will have to evaluate a range of potential demographic, clinical, and technical confounders including age, gender, intellectual ability, comorbidity, and medication, before these approaches can be translated into the clinical setting.
Proceedings of the 19th IFAC World Congress, 2014
All process measurements are corrupted by the presence of measurement error to some degree. The a... more All process measurements are corrupted by the presence of measurement error to some degree. The attenuation of the measurement error, especially large gross errors, can increase the value of the process measurements. Gross error detection has typically been performed through rigorous statistical hypothesis testing. The assumptions required to derive the necessary statistical properties are restrictive, which lead to investigation of alternative approaches, such as artificial neural networks. This paper reports the results of an investigation into the utility of classification trees and linear and quadratic classification functions for resolving the gross error detection and identification problems.
AIChE Journal, 2005
Statistical pattern-recognition methods are now widely applied in the analysis of process systems... more Statistical pattern-recognition methods are now widely applied in the analysis of process systems to achieve predictable and stable operating conditions. For example, multivariate statistical process control (MSPC) techniques use historical operating data to detect abnormal events, and assist engineers to focus their troubleshooting efforts to reduced subsets of variables in an otherwise broad operational space. Through an iterative process, it is hoped that the system variability remains bounded. Usually only a few samples collected under a state of statistical control are of interest, whereas the rest, which may be used to uncover potential improvement opportunities, are ignored. Beyond statistical control, an additional step is required to reduce the dispersion of process quality variables attributed to common causes. To achieve this goal, common and sustained causes not identified by MSPC must be interrogated. In this paper, a methodology based on kernel-based machine learning concepts is proposed to identify decision boundaries. A sparse set of instances or exemplars is identified that define a linear decision boundary in a feature space, which is equivalent to defining a nonlinear decision function in the associated input space. This is extended to defining operating strategies by integrating inductive learning into a decision support framework. Such an extension is founded on the fact that the success or failure of state-of-the-art approaches are invariably linked to the presence or absence of useful knowledge embedded in the system.
Time Series Analysis - Data, Methods, and Applications
Fault diagnosis in continuous dynamic systems can be challenging, since the variables in these sy... more Fault diagnosis in continuous dynamic systems can be challenging, since the variables in these systems are typically characterized by autocorrelation, as well as time variant parameters, such as mean vectors, covariance matrices, and higher order statistics, which are not handled well by methods designed for steady state systems. In dynamic systems, steady state approaches are extended to deal with these problems, essentially through feature extraction designed to capture the process dynamics from the time series. In this chapter, recent advances in feature extraction from signals or multivariate time series are reviewed. These methods can subsequently be considered in a classical statistical monitoring framework, such as used for steady state systems. In addition, an extension of nonlinear signal processing based on the use of unthresholded or global recurrence quantification analysis is discussed, where two multivariate image methods based on gray level co-occurrence matrices and local binary patterns are used to extract features from time series. When considering the well-known simulated Tennessee Eastman process in chemical engineering, it is shown that time series features obtained with this approach can be an effective means of discriminating between different fault conditions in the system. The approach provides a general framework that can be extended in multiple ways to time series analysis.
The International Journal on the Image, 2012
In this paper, we propose a new method for the motion estimation of flotation froth using mutual ... more In this paper, we propose a new method for the motion estimation of flotation froth using mutual information with a bin size of two as the block matching similarity metric. We also use three-step search-and new-three-step-search as a search strategy. Mean sum of absolute difference (MAD) is widely considered in blocked based motion estimation. The minimum bin size selection of the proposed similarity metric also makes the computational cost of mutual information similar to MAD. Experimental results show that the proposed motion estimation technique improves the motion estimation accuracy in terms of peak signal-to-noise ratio of the reconstructed frame. The computational cost of the proposed method is almost the same as the standard machine vision methods used for the motion estimation of flotation froth.
Froth image analysis has been considered widely in the identification of operational regimes in f... more Froth image analysis has been considered widely in the identification of operational regimes in flotation circuits, the characterisation of froths in terms of bubble size distributions, froth stability and local froth velocity patterns, or as a basis for the development of inferential online sensors for chemical species in the froth. Relatively few studies have considered flotation froth image analysis in unsupervised process monitoring applications. In this study, it is shown that froth image analysis can be combined with traditional multivariate statistical process monitoring methods for reliable monitoring of industrial platinum metal group flotation plants. This can be accomplished with wellestablished methods of multivariate image analysis, such as the Haralick feature set derived from grey level co-occurrence matrices and local binary patterns that were considered in this investigation.
IFAC-PapersOnLine
In this paper, the application of deep learning in the mining and processing of ores is reviewed.... more In this paper, the application of deep learning in the mining and processing of ores is reviewed. Deep learning is strongly impacting the development of sensor systems, particularly computer vision systems used in mining and mineral processing automation, where it is filling a gap not currently achievable by traditional approaches. To a lesser extent, deep learning is also being considered in the automation of decision support systems. There is significant scope for the application of deep learning to improve operations, but access to industrial data and big data infrastructure in operational environments are critical bottlenecks to the development and deployment of the technology.
Minerals
Linear regression is often used as a diagnostic tool to understand the relative contributions of ... more Linear regression is often used as a diagnostic tool to understand the relative contributions of operational variables to some key performance indicator or response variable. However, owing to the nature of plant operations, predictor variables tend to be correlated, often highly so, and this can lead to significant complications in assessing the importance of these variables. Shapley regression is seen as the only axiomatic approach to deal with this problem but has almost exclusively been used with linear models to date. In this paper, the approach is extended to random forests, and the results are compared with some of the empirical variable importance measures widely used with these models, i.e., permutation and Gini variable importance measures. Four case studies are considered, of which two are based on simulated data and two on real world data from the mineral process industries. These case studies suggest that the random forest Shapley variable importance measure may be a mo...
Processes
Grinding circuits typically contribute disproportionately to the overall cost of ore beneficiatio... more Grinding circuits typically contribute disproportionately to the overall cost of ore beneficiation and their optimal operation is therefore of critical importance in the cost-effective operation of mineral processing plants. This can be challenging, as these circuits can also exhibit complex, nonlinear behavior that can be difficult to model. In this paper, it is shown that key time series variables of grinding circuits can be recast into sets of descriptor variables that can be used in advanced modelling and control of the mill. Two real-world case studies are considered. In the first, it is shown that the controller states of an autogenous mill can be identified from the load measurements of the mill by using a support vector machine and the abovementioned descriptor variables as predictors. In the second case study, it is shown that power and temperature measurements in a horizontally stirred mill can be used for online estimation of the particle size of the mill product.
Time Series Analysis - Data, Methods, and Applications, Nov 6, 2019
Fault diagnosis in continuous dynamic systems can be challenging, since the variables in these sy... more Fault diagnosis in continuous dynamic systems can be challenging, since the variables in these systems are typically characterized by autocorrelation, as well as time variant parameters, such as mean vectors, covariance matrices, and higher order statistics, which are not handled well by methods designed for steady state systems. In dynamic systems, steady state approaches are extended to deal with these problems, essentially through feature extraction designed to capture the process dynamics from the time series. In this chapter, recent advances in feature extraction from signals or multivariate time series are reviewed. These methods can subsequently be considered in a classical statistical monitoring framework, such as used for steady state systems. In addition, an extension of nonlinear signal processing based on the use of unthresholded or global recurrence quantification analysis is discussed, where two multivariate image methods based on gray level co-occurrence matrices and local binary patterns are used to extract features from time series. When considering the well-known simulated Tennessee Eastman process in chemical engineering, it is shown that time series features obtained with this approach can be an effective means of discriminating between different fault conditions in the system. The approach provides a general framework that can be extended in multiple ways to time series analysis.
Mineral Processing and Extractive Metallurgy Review
ABSTRACT Gold and copper thiosulfate adsorption from an alkaline gold ore leachate was investigat... more ABSTRACT Gold and copper thiosulfate adsorption from an alkaline gold ore leachate was investigated by using polyethylenimine-coated iron oxide magnetic nanoparticles (NPs). The ore, sourced from a mine in Nevada, USA, was leached with calcium thiosulfate for 48 h in the presence of Cu(II) at a pH of 8 and a temperature of 50°C. A response surface methodology was used to analyze the effect of adsorbent dosage, adsorption time and solution temperature on the recovery of gold and copper from the solution. The results showed that the gold adsorption was nonlinearly dependent on the adsorbent dosage only. In contrast, the recovery of the copper depended on all three predictors, including interaction between the temperature and adsorbent dosage. The optimal conditions for maximal gold adsorption was 35 g/L adsorbent dosage, 55 min time and a temperature of 23°C. The selective elution of loaded metals on the NPs was also successfully achieved.
Minerals Engineering
Deep learning constitutes a significant recent advance in machine learning and has been particula... more Deep learning constitutes a significant recent advance in machine learning and has been particularly successful in applications related to image processing, where it can already surpass human accuracy in some cases. In this paper, the use of a convolutional neural network, AlexNet, pretrained on a database of images of common objects was used as is to extract features from flotation froth images. These features could subsequently be used to predict the conditions or performance of the flotation systems. Two case studies are considered. In the first, froth regimes in an industrial flotation plant could be identified significantly more reliably with the features generated by AlexNet than with previous state-of-the-art approaches, such as wavelets, grey level co-occurrence matrices or local binary patterns. In the second case study, the arsenic concentration in the batch flotation of realgar-orpiment-quartz mixtures could be predicted more accurately than was possible with features extracted by wavelets, grey level co-occurrence matrices, local binary patterns or by use of colour. These results suggest that feature extraction with convolutional neural networks trained on complex data sets from other domains can serve as more reliable methods than previous state-of-the-art approaches to froth image analysis.
Mineral Processing and Extractive Metallurgy
ABSTRACT Multivariate image analysis was used to estimate the arsenic concentrations in froths re... more ABSTRACT Multivariate image analysis was used to estimate the arsenic concentrations in froths resulting from the flotation of different mixtures of realgar and orpiment particles in a laboratory batch flotation cell. The realgar floated rapidly and in excess of 90% of the mineral could be recovered after 2 minutes, whereas only 48–75% of the orpiment could be recovered in the same time. Textural features, based on grey level co-occurrence matrices (GLCMs), local binary patterns (LBPs), steearable pyramids and textons were used in the analysis. Random forest models could explain approximately 71–77% of the variance in the arsenic using either of the texton, steerable pyramid or LBP features. This was considerably better than what could be obtained with the GLCM features. Monitoring of froth flotation cells was simulated with the batch data. The texton textural features were the most discriminatory with regard to detecting changes in the arsenic content of the froth.
Corrosion Science
The corrosion of carbon steel in aqueous media resulting in uniform corrosion, pitting corrosion ... more The corrosion of carbon steel in aqueous media resulting in uniform corrosion, pitting corrosion and passivation was investigated on a laboratory scale. Recurrence quantification analysis was applied to short segments of electrochemical current noise measurements. These segments were converted to recurrence variables, which could be used as reliable predictors in a multilayer perceptron neural network model to identify the type of corrosion. In addition, an automated corrosion monitoring scheme is proposed, based on the principal component scores of the recurrence variables. This approach used the uniform corrosion measurements as reference data and could differentiate between uniform and non-uniform corrosion.
Proceedings of the Genetic and Evolutionary Computation Conference, Jul 9, 2002
Process changes, such as flow disturbances and sensor noise, are common in the chemical and metal... more Process changes, such as flow disturbances and sensor noise, are common in the chemical and metallurgical industries. To maintain optimal performance, the controlling system has to adapt continuously to these changes. This is a difficult problem because the controller also has to perform well while it is adapting. The Adaptive Neural Swarming (ANS) method introduced in this paper satisfies these goals. Using an existing neural network controller as a starting point, ANS modifies the network weights through Particle Swarm Optimisation. The ANS method was tested in a real-world task of controlling a simulated non-linear bioreactor. ANS was able to adapt to process changes while simultaneously avoiding hard operating constraints. This way, ANS balances the need to adapt with the need to preserve generalisation, and constitutes a general tool for adapting neural network controllers online.
Pediatric Neurology, 2016
BACKGROUND: Electroencephalography (EEG) has been used for almost a century to identify seizure-r... more BACKGROUND: Electroencephalography (EEG) has been used for almost a century to identify seizure-related disorders in humans, typically through expert interpretation of multichannel recordings. Attempts have been made to quantify EEG through frequency analyses and graphic representations. These "traditional" quantitative EEG analysis methods were limited in their ability to analyze complex and multivariate data and have not been generally accepted in clinical settings. There has been growing interest in identification of novel EEG biomarkers to detect early risk of autism spectrum disorder, to identify clinically meaningful subgroups, and to monitor targeted intervention strategies. Most studies to date have, however, used quantitative EEG approaches, and little is known about the emerging multivariate analytical methods or the robustness of candidate biomarkers in the context of the variability of autism spectrum disorder. METHODS: Here, we present a targeted review of methodological and clinical challenges in the search for novel resting-state EEG biomarkers for autism spectrum disorder. RESULTS: Three primary novel methodologies are discussed: (1) modified multiscale entropy, (2) coherence analysis, and (3) recurrence quantification analysis. Results suggest that these methods may be able to classify resting-state EEG as "autism spectrum disorder" or "typically developing", but many signal processing questions remain unanswered. CONCLUSIONS: We suggest that the move to novel EEG analysis methods is akin to the progress in neuroimaging from visual inspection, through region-of-interest analysis, to whole-brain computational analysis. Novel restingstate EEG biomarkers will have to evaluate a range of potential demographic, clinical, and technical confounders including age, gender, intellectual ability, comorbidity, and medication, before these approaches can be translated into the clinical setting.
Proceedings of the 19th IFAC World Congress, 2014
All process measurements are corrupted by the presence of measurement error to some degree. The a... more All process measurements are corrupted by the presence of measurement error to some degree. The attenuation of the measurement error, especially large gross errors, can increase the value of the process measurements. Gross error detection has typically been performed through rigorous statistical hypothesis testing. The assumptions required to derive the necessary statistical properties are restrictive, which lead to investigation of alternative approaches, such as artificial neural networks. This paper reports the results of an investigation into the utility of classification trees and linear and quadratic classification functions for resolving the gross error detection and identification problems.