The Experts below are selected from a list of 174 Experts worldwide ranked by ideXlab platform
Royston Goodacre - One of the best experts on this subject based on the ideXlab platform.
-
Use of Pyrolysis Mass Spectrometry with Supervised Learning for the Assessment of the Adulteration of Milk of Different Species
Applied Spectroscopy, 1997Co-Authors: Royston GoodacreAbstract:Binary mixtures of 0-20% cows' milk with ewes' milk, 0-20% cows' milk with goats' milk, and 0-5% cows' milk with goats' milk were subjected to pyrolysis mass spectrometry (PyMS). For analysis of the pyrolysis mass spectra so as to determine the percentage adulteration of either caprine or ovine milk with bovine milk, partial least-squares regression (PLS), principal components regression (PCR) and fully interconnected feed-forward artificial neural networks (ANNs) were studied. In the latter case, the weights were modified by using the standard back-propagation algorithm, and the nodes used a sigmoidal Squashing Function. It was found that each of the methods could be used to provide calibration models which gave excellent predictions for the percentage adulteration with cows' milk to < 1% for samples, with an accuracy of +/- 0.5%, on which they had not been trained. Scaling the individual nodes on the input layer of ANNs significantly decreased the time taken for the ANNs to learn, compared with scaling across the whole mass range; however in one case this approach resulted in poor generalization for the estimates of percentage cows' milk in ewes' milk. To assess whether the calibration models had learned the differences between the milk species or the differences due to the different fat content of in each of the milk types, we also analyzed pure milk samples varying in fat content by PyMS. Cluster analysis showed unequivocally that the major variation between the different milk species was not due to variable fat content. Since any biological material can be pyrolyzed in this way, the combination of PyMS with supervised learning constitutes a rapid, powerful, and novel approach to the quantitative assessment of food adulteration generally.
-
Rapid and quantitative analysis of metabolites in fermentor broths using pyrolysis mass spectrometry with supervised learning: application to the screening of Penicillium chrysogenum fermentations for the overproduction of penicillins☆
Analytica Chimica Acta, 1995Co-Authors: Royston Goodacre, Mark Neal, Sally Trew, Carys A. Wrigley-jones, Neil Porter, Gunter Saunders, Douglas B. KellAbstract:Abstract The combination of pyrolysis mass spectrometry (PyMS) and artificial neural networks (ANNs) can be used to quantify levels of penicillins in strains of Penicillium chrysogenum and ampicillin in spiked samples of Escherichia coli. Four P. chrysogenum strains (NRRL 1951, Wis Q176, P1, and P2) were grown in submerged culture to produce penicillins, and fermentation samples were taken aseptically and subjected to PyMS. To deconvolute the pyrolysis mass spectra so as to obtain quantitative information on the titre of penicillins, fully-interconnected feedforward artificial neural networks (ANNs) were studied; the weights were modified using the standard back-propagation algorithm, and the nodes used a sigmoidal Squashing Function. In addition the multivariate linear regression techniques of partial least squares regression (PLS), principal components regression (PCR) and multiple linear regression (MLR) were applied. The ANNs could be trained to give excellent estimates for the penicillin titre, not only from the spectra that had been used to train the ANN but more importantly from previously unseen pyrolysis mass spectra. All the linear regression methods failed to give accurate predictions, because of the very variable biological backgrounds (the four different strains) in which penicillin was produced and also of the inability of models using linear regression accurately to map non-linearities. Comparisons of Squashing Functions on the output nodes of identical 150-8-1 neural networks revealed that networks employing linear Functions gave more accurate estimates of ampicillin in E. coli near the edges of the concentration range than did those using sigmoidal Functions. It was also shown that these neural networks could be successfully used to extrapolate beyond the concentration range on which they had been trained. PyMS with the multivariate clustering technique of principal components analysis was able to differentiate between four strains of P. chrysogenum studied, and was also able to detect phenotypic differences at five, seven, nine or 11 days growth. A crude smapling procedure consisting of homogenised agar plugs proved applicable for rapid analysis of a large number of samples.
-
Rapid screening for metabolite overproduction in fermentor broths, using pyrolysis mass spectrometry with multivariate calibration and artificial neural networks.
Biotechnology and Bioengineering, 1994Co-Authors: Royston Goodacre, Mark Neal, Sally Trew, Carys A. Wrigley-jones, John Maddock, Thomas W. Ottley, Neil Porter, Douglas B. KellAbstract:Binary mixtures of model systems consisting of the antibiotic ampicillin with either Escherichia coli or Staphylococcus aureus were subjected to pyrolysis mass spectrometry (PyMS). To deconvolute the pyrolysis mass spectra, so as to obtain quantitative information on the concentration of ampicillin in the mixtures, partial least squares regression (PLS), principal components regression (PCR), and fully interconnected feedforward artificial neural networks (ANNs) were studied. In the latter case, the weights were modified using the standard backpropagation algorithm, and the nodes used a sigmoidal Squashing Function. It was found that each of the methods could be used to provide calibration models which gave excellent predictions for the concentrations of ampicillin in samples on which they had not been trained. Furthermore, ANNs trained to predict the amount of ampicillin in E. coli were able to generalise so as to predict the concentration of ampicillin in a S. aureus background, illustrating the robustness of ANNs to rather substantial variations in the biological background. The PyMS of the complex mixture of ampicillin in bacteria could not be expressed simply in terms of additive combinations of the spectra describing the pure components of the mixtures and their relative concentrations. Intermolecular reactions took place in the pyrolysate, leading to a lack of superposition of the spectral components and to a dependence of the normalized mass spectrum on sample size. Samples from fermentations of a single organism in a complex production medium were also analyzed quantitatively for a drug of commercial interest. The drug could also be quantified in a variety of mutant-producing strains cultivated in the same medium. The combination of PyMS and ANNs constitutes a novel, rapid, and convenient method for exploitation in strain improvement screening programs. 0 1994
-
Rapid and Quantitative Analysis of the Pyrolysis Mass Spectra of Complex Binary and Tertiary Mixtures Using Multivariate Calibration and Artificial Neural Networks
Analytical Chemistry, 1994Co-Authors: Royston Goodacre, Mark Neal, Douglas B. KellAbstract:Binary mixtures of the protein lysozyme with glycogen, of DNA or RNA in glycogen, and the tertiary mixture of cells of the bacteria Bacillus subtilh, Escherichia coli, and Staphylococcusaurecls were subjected to pyrolysis mass spectrometry. To analyze the pyrolysis mass spectra so as to obtain quantitative information representative of the complex components of the mixtures, partial least-squares regression (PLS), principal components regression (PCR), and fully interconnected feedforward artificial neural networks (ANNs) were studied. In the latter case, the weights were modified using the standard back-propagation algorithm, and the nodes used a sigmoidal Squashing Function. It was found that each of the methods could be used to provide calibration models which gave excellent predictions for the concentrations of determinands in samples on which they had not been trained. Neural networks were found to provide the most accurate predictions. We also report that scaling the individual nodes on the input layer of ANNs significantly decreased the time taken for the ANNs to learn. Removing masses of low intensity, which perhaps mainly contributed noise to the pyrolysis mass spectra, had little effect on the accuracy of the ANN predictions though could dramatically speed up the learning process (by more than 100-fold) and slightly improved the accuracy of PLS calibrations.
Douglas B. Kell - One of the best experts on this subject based on the ideXlab platform.
-
Rapid and quantitative analysis of metabolites in fermentor broths using pyrolysis mass spectrometry with supervised learning: application to the screening of Penicillium chrysogenum fermentations for the overproduction of penicillins☆
Analytica Chimica Acta, 1995Co-Authors: Royston Goodacre, Mark Neal, Sally Trew, Carys A. Wrigley-jones, Neil Porter, Gunter Saunders, Douglas B. KellAbstract:Abstract The combination of pyrolysis mass spectrometry (PyMS) and artificial neural networks (ANNs) can be used to quantify levels of penicillins in strains of Penicillium chrysogenum and ampicillin in spiked samples of Escherichia coli. Four P. chrysogenum strains (NRRL 1951, Wis Q176, P1, and P2) were grown in submerged culture to produce penicillins, and fermentation samples were taken aseptically and subjected to PyMS. To deconvolute the pyrolysis mass spectra so as to obtain quantitative information on the titre of penicillins, fully-interconnected feedforward artificial neural networks (ANNs) were studied; the weights were modified using the standard back-propagation algorithm, and the nodes used a sigmoidal Squashing Function. In addition the multivariate linear regression techniques of partial least squares regression (PLS), principal components regression (PCR) and multiple linear regression (MLR) were applied. The ANNs could be trained to give excellent estimates for the penicillin titre, not only from the spectra that had been used to train the ANN but more importantly from previously unseen pyrolysis mass spectra. All the linear regression methods failed to give accurate predictions, because of the very variable biological backgrounds (the four different strains) in which penicillin was produced and also of the inability of models using linear regression accurately to map non-linearities. Comparisons of Squashing Functions on the output nodes of identical 150-8-1 neural networks revealed that networks employing linear Functions gave more accurate estimates of ampicillin in E. coli near the edges of the concentration range than did those using sigmoidal Functions. It was also shown that these neural networks could be successfully used to extrapolate beyond the concentration range on which they had been trained. PyMS with the multivariate clustering technique of principal components analysis was able to differentiate between four strains of P. chrysogenum studied, and was also able to detect phenotypic differences at five, seven, nine or 11 days growth. A crude smapling procedure consisting of homogenised agar plugs proved applicable for rapid analysis of a large number of samples.
-
Rapid screening for metabolite overproduction in fermentor broths, using pyrolysis mass spectrometry with multivariate calibration and artificial neural networks.
Biotechnology and Bioengineering, 1994Co-Authors: Royston Goodacre, Mark Neal, Sally Trew, Carys A. Wrigley-jones, John Maddock, Thomas W. Ottley, Neil Porter, Douglas B. KellAbstract:Binary mixtures of model systems consisting of the antibiotic ampicillin with either Escherichia coli or Staphylococcus aureus were subjected to pyrolysis mass spectrometry (PyMS). To deconvolute the pyrolysis mass spectra, so as to obtain quantitative information on the concentration of ampicillin in the mixtures, partial least squares regression (PLS), principal components regression (PCR), and fully interconnected feedforward artificial neural networks (ANNs) were studied. In the latter case, the weights were modified using the standard backpropagation algorithm, and the nodes used a sigmoidal Squashing Function. It was found that each of the methods could be used to provide calibration models which gave excellent predictions for the concentrations of ampicillin in samples on which they had not been trained. Furthermore, ANNs trained to predict the amount of ampicillin in E. coli were able to generalise so as to predict the concentration of ampicillin in a S. aureus background, illustrating the robustness of ANNs to rather substantial variations in the biological background. The PyMS of the complex mixture of ampicillin in bacteria could not be expressed simply in terms of additive combinations of the spectra describing the pure components of the mixtures and their relative concentrations. Intermolecular reactions took place in the pyrolysate, leading to a lack of superposition of the spectral components and to a dependence of the normalized mass spectrum on sample size. Samples from fermentations of a single organism in a complex production medium were also analyzed quantitatively for a drug of commercial interest. The drug could also be quantified in a variety of mutant-producing strains cultivated in the same medium. The combination of PyMS and ANNs constitutes a novel, rapid, and convenient method for exploitation in strain improvement screening programs. 0 1994
-
Rapid and Quantitative Analysis of the Pyrolysis Mass Spectra of Complex Binary and Tertiary Mixtures Using Multivariate Calibration and Artificial Neural Networks
Analytical Chemistry, 1994Co-Authors: Royston Goodacre, Mark Neal, Douglas B. KellAbstract:Binary mixtures of the protein lysozyme with glycogen, of DNA or RNA in glycogen, and the tertiary mixture of cells of the bacteria Bacillus subtilh, Escherichia coli, and Staphylococcusaurecls were subjected to pyrolysis mass spectrometry. To analyze the pyrolysis mass spectra so as to obtain quantitative information representative of the complex components of the mixtures, partial least-squares regression (PLS), principal components regression (PCR), and fully interconnected feedforward artificial neural networks (ANNs) were studied. In the latter case, the weights were modified using the standard back-propagation algorithm, and the nodes used a sigmoidal Squashing Function. It was found that each of the methods could be used to provide calibration models which gave excellent predictions for the concentrations of determinands in samples on which they had not been trained. Neural networks were found to provide the most accurate predictions. We also report that scaling the individual nodes on the input layer of ANNs significantly decreased the time taken for the ANNs to learn. Removing masses of low intensity, which perhaps mainly contributed noise to the pyrolysis mass spectra, had little effect on the accuracy of the ANN predictions though could dramatically speed up the learning process (by more than 100-fold) and slightly improved the accuracy of PLS calibrations.
John T. Rickard - One of the best experts on this subject based on the ideXlab platform.
-
WCSC - Preliminary Results on a New Fuzzy Cognitive Map Structure
Advance Trends in Soft Computing, 2020Co-Authors: John T. Rickard, Janet Aisbett, Ronald R. Yager, Greg GibbonAbstract:We introduce a new structure for fuzzy cognitive maps (FCM) where the traditional fan-in structure involving an inner product followed by a Squashing Function to describe the causal influences of antecedent nodes to a particular consequent node is replaced with a weighted mean type operator. In this paper, we employ the weighted power mean (WPM). Through appropriate selection of the weights and exponents in the WPM operators, we can both account for the relative importance of different antecedent nodes in the dynamics of a particular node, as well as take a perspective ranging continuously from the most pessimistic (minimum) to the most optimistic (maximum) on the normalized aggregation of antecedents for each node. We consider this FCM structure to be more intuitive than the traditional one, as the nonlinearity involved in the WPM is more scrutable with regard to the aggregation of its inputs. We provide examples of this new FCM structure to illustrate its behavior, including convergence.
-
A New Fuzzy Cognitive Map Structure Based on the Weighted Power Mean
IEEE Transactions on Fuzzy Systems, 2015Co-Authors: John T. Rickard, Janet Aisbett, Ronald R. YagerAbstract:We introduce a new structure for fuzzy cognitive maps (FCM) where the traditional fan-in structure involving an inner product followed by a Squashing Function to describe the causal influences of antecedent nodes to a particular consequent node is replaced with a weighted mean type operator. In this paper, we employ the weighted power mean (WPM). Through appropriate selection of the weights and exponents in the WPM operators, we can both account for the relative importance of different antecedent nodes in the dynamics of a particular node, as well as take a perspective ranging continuously from the most pessimistic (minimum) to the most optimistic (maximum) on the normalized aggregation of antecedents for each node. We consider this FCM structure to be more intuitive than the traditional one, as the nonlinearity involved in the WPM is more scrutable with regard to the aggregation of its inputs. We provide examples of this new FCM structure to illustrate its behavior, including its convergence, and compare it with a traditional FCM architecture on a scenario presented in previous works.
-
A perceptual fuzzy neural model
2014 IEEE Symposium on Computational Intelligence in Multi-Criteria Decision-Making (MCDM), 2014Co-Authors: John T. Rickard, Janet AisbettAbstract:We introduce a fuzzy neural model which is more intuitive and general than the traditional weighted sum/Squashing Function neuron model. Positively and negatively causal inputs are separately aggregated using operators that are selected to suit the particular application. The aggregations are then combined using a simple arithmetic transformation. We outline the computational process when inputs and importance weights are vocabulary words modelled as interval type-2 fuzzy sets, and illustrate on predictions of gold price changes.
József Dombi - One of the best experts on this subject based on the ideXlab platform.
-
Rule based fuzzy classification using Squashing Functions
2020Co-Authors: József Dombi, Zsolt GeraAbstract:In this paper we are dealing with the construction of a fuzzy rule based classifier. A three-step method is proposed based on Lukasiewicz logic for the description of the rules and the fuzzy memberships to construct concise and highly comprehensible fuzzy rules. In our method, a genetic algorithm is applied to evolve the structure of the rules and then a gradient based optimization to fine tune the fuzzy membership Functions. The introduced Squashing Function allows us not only to handle the approximation of the operators and the memberships in the same way, but also to efficiently calculate the derivatives of the membership Functions. We also show applications of the model on the UCI machine learning database.
-
Interpretable neural networks based on continuous-valued logic and multicriteria decision operators
Knowledge Based Systems, 2020Co-Authors: O. Csiszár, Gábor Csiszár, József DombiAbstract:Abstract Combining neural networks with continuous logic and multicriteria decision-making tools can reduce the black-box nature of neural models. In this study, we show that nilpotent logical systems offer an appropriate mathematical framework for hybridization of continuous nilpotent logic and neural models, helping to improve the interpretability and safety of machine learning. In our concept, perceptrons model soft inequalities; namely membership Functions and continuous logical operators. We design the network architecture before training, using continuous logical operators and multicriteria decision tools with given weights working in the hidden layers. Designing the structure appropriately leads to a drastic reduction in the number of parameters to be learned. The theoretical basis offers a straightforward choice of activation Functions (the cutting Function or its differentiable approximation, the Squashing Function), and also suggests an explanation to the great success of the rectified linear unit (ReLU). In this study, we focus on the architecture of a hybrid model and introduce the building blocks for future applications in deep neural networks.
-
Interpretable neural networks based on continuous-valued logic and multicriteria decision operators.
arXiv: Artificial Intelligence, 2020Co-Authors: O. Csiszár, Gábor Csiszár, József DombiAbstract:Combining neural networks with continuous logic and multicriteria decision making tools can reduce the black box nature of neural models. In this study, we show that nilpotent logical systems offer an appropriate mathematical framework for a hybridization of continuous nilpotent logic and neural models, helping to improve the interpretability and safety of machine learning. In our concept, perceptrons model soft inequalities; namely membership Functions and continuous logical operators. We design the network architecture before training, using continuous logical operators and multicriteria decision tools with given weights working in the hidden layers. Designing the structure appropriately leads to a drastic reduction in the number of parameters to be learned. The theoretical basis offers a straightforward choice of activation Functions (the cutting Function or its differentiable approximation, the Squashing Function), and also suggests an explanation to the great success of the rectified linear unit (ReLU). In this study, we focus on the architecture of a hybrid model and introduce the building blocks for future application in deep neural networks. The concept is illustrated with some toy examples taken from an extended version of the tensorflow playground.
Ronald R. Yager - One of the best experts on this subject based on the ideXlab platform.
-
WCSC - Preliminary Results on a New Fuzzy Cognitive Map Structure
Advance Trends in Soft Computing, 2020Co-Authors: John T. Rickard, Janet Aisbett, Ronald R. Yager, Greg GibbonAbstract:We introduce a new structure for fuzzy cognitive maps (FCM) where the traditional fan-in structure involving an inner product followed by a Squashing Function to describe the causal influences of antecedent nodes to a particular consequent node is replaced with a weighted mean type operator. In this paper, we employ the weighted power mean (WPM). Through appropriate selection of the weights and exponents in the WPM operators, we can both account for the relative importance of different antecedent nodes in the dynamics of a particular node, as well as take a perspective ranging continuously from the most pessimistic (minimum) to the most optimistic (maximum) on the normalized aggregation of antecedents for each node. We consider this FCM structure to be more intuitive than the traditional one, as the nonlinearity involved in the WPM is more scrutable with regard to the aggregation of its inputs. We provide examples of this new FCM structure to illustrate its behavior, including convergence.
-
A New Fuzzy Cognitive Map Structure Based on the Weighted Power Mean
IEEE Transactions on Fuzzy Systems, 2015Co-Authors: John T. Rickard, Janet Aisbett, Ronald R. YagerAbstract:We introduce a new structure for fuzzy cognitive maps (FCM) where the traditional fan-in structure involving an inner product followed by a Squashing Function to describe the causal influences of antecedent nodes to a particular consequent node is replaced with a weighted mean type operator. In this paper, we employ the weighted power mean (WPM). Through appropriate selection of the weights and exponents in the WPM operators, we can both account for the relative importance of different antecedent nodes in the dynamics of a particular node, as well as take a perspective ranging continuously from the most pessimistic (minimum) to the most optimistic (maximum) on the normalized aggregation of antecedents for each node. We consider this FCM structure to be more intuitive than the traditional one, as the nonlinearity involved in the WPM is more scrutable with regard to the aggregation of its inputs. We provide examples of this new FCM structure to illustrate its behavior, including its convergence, and compare it with a traditional FCM architecture on a scenario presented in previous works.