The Experts below are selected from a list of 309 Experts worldwide ranked by ideXlab platform
Peter Kleinebudde - One of the best experts on this subject based on the ideXlab platform.
-
evaluation of in line raman Data for end point determination of a coating process comparison of science based calibration pls regression and Univariate Data analysis
European Journal of Pharmaceutics and Biopharmaceutics, 2017Co-Authors: Shirin Barimani, Peter KleinebuddeAbstract:A multivariate analysis method, Science-Based Calibration (SBC), was used for the first time for endpoint determination of a tablet coating process using Raman Data. Two types of tablet cores, placebo and caffeine cores, received a coating suspension comprising a polyvinyl alcohol-polyethylene glycol graft-copolymer and titanium dioxide to a maximum coating thickness of 80µm. Raman spectroscopy was used as in-line PAT tool. The spectra were acquired every minute and correlated to the amount of applied aqueous coating suspension. SBC was compared to another well-known multivariate analysis method, Partial Least Squares-regression (PLS) and a simpler approach, Univariate Data Analysis (UVDA). All developed calibration models had coefficient of determination values (R2) higher than 0.99. The coating endpoints could be predicted with root mean square errors (RMSEP) less than 3.1% of the applied coating suspensions. Compared to PLS and UVDA, SBC proved to be an alternative multivariate calibration method with high predictive power.
-
evaluation of in line raman Data for end point determination of a coating process comparison of science based calibration pls regression and Univariate Data analysis
European Journal of Pharmaceutics and Biopharmaceutics, 2017Co-Authors: Shirin Barimani, Peter KleinebuddeAbstract:A multivariate analysis method, Science-Based Calibration (SBC), was used for the first time for endpoint determination of a tablet coating process using Raman Data. Two types of tablet cores, placebo and caffeine cores, received a coating suspension comprising a polyvinyl alcohol-polyethylene glycol graft-copolymer and titanium dioxide to a maximum coating thickness of 80µm. Raman spectroscopy was used as in-line PAT tool. The spectra were acquired every minute and correlated to the amount of applied aqueous coating suspension. SBC was compared to another well-known multivariate analysis method, Partial Least Squares-regression (PLS) and a simpler approach, Univariate Data Analysis (UVDA). All developed calibration models had coefficient of determination values (R2) higher than 0.99. The coating endpoints could be predicted with root mean square errors (RMSEP) less than 3.1% of the applied coating suspensions. Compared to PLS and UVDA, SBC proved to be an alternative multivariate calibration method with high predictive power.
Shirin Barimani - One of the best experts on this subject based on the ideXlab platform.
-
evaluation of in line raman Data for end point determination of a coating process comparison of science based calibration pls regression and Univariate Data analysis
European Journal of Pharmaceutics and Biopharmaceutics, 2017Co-Authors: Shirin Barimani, Peter KleinebuddeAbstract:A multivariate analysis method, Science-Based Calibration (SBC), was used for the first time for endpoint determination of a tablet coating process using Raman Data. Two types of tablet cores, placebo and caffeine cores, received a coating suspension comprising a polyvinyl alcohol-polyethylene glycol graft-copolymer and titanium dioxide to a maximum coating thickness of 80µm. Raman spectroscopy was used as in-line PAT tool. The spectra were acquired every minute and correlated to the amount of applied aqueous coating suspension. SBC was compared to another well-known multivariate analysis method, Partial Least Squares-regression (PLS) and a simpler approach, Univariate Data Analysis (UVDA). All developed calibration models had coefficient of determination values (R2) higher than 0.99. The coating endpoints could be predicted with root mean square errors (RMSEP) less than 3.1% of the applied coating suspensions. Compared to PLS and UVDA, SBC proved to be an alternative multivariate calibration method with high predictive power.
-
evaluation of in line raman Data for end point determination of a coating process comparison of science based calibration pls regression and Univariate Data analysis
European Journal of Pharmaceutics and Biopharmaceutics, 2017Co-Authors: Shirin Barimani, Peter KleinebuddeAbstract:A multivariate analysis method, Science-Based Calibration (SBC), was used for the first time for endpoint determination of a tablet coating process using Raman Data. Two types of tablet cores, placebo and caffeine cores, received a coating suspension comprising a polyvinyl alcohol-polyethylene glycol graft-copolymer and titanium dioxide to a maximum coating thickness of 80µm. Raman spectroscopy was used as in-line PAT tool. The spectra were acquired every minute and correlated to the amount of applied aqueous coating suspension. SBC was compared to another well-known multivariate analysis method, Partial Least Squares-regression (PLS) and a simpler approach, Univariate Data Analysis (UVDA). All developed calibration models had coefficient of determination values (R2) higher than 0.99. The coating endpoints could be predicted with root mean square errors (RMSEP) less than 3.1% of the applied coating suspensions. Compared to PLS and UVDA, SBC proved to be an alternative multivariate calibration method with high predictive power.
Evgeny Burnaev - One of the best experts on this subject based on the ideXlab platform.
-
Conformal k-NN Anomaly Detector for Univariate Data Streams
arXiv: Machine Learning, 2017Co-Authors: Vladislav Ishimtsev, Ivan Nazarov, Alexander Bernstein, Evgeny BurnaevAbstract:Anomalies in time-series Data give essential and often actionable information in many applications. In this paper we consider a model-free anomaly detection method for Univariate time-series which adapts to non-stationarity in the Data stream and provides probabilistic abnormality scores based on the conformal prediction paradigm. Despite its simplicity the method performs on par with complex prediction-based models on the Numenta Anomaly Detection benchmark and the Yahoo! S5 Dataset.
Mikhail D. Prokhorov - One of the best experts on this subject based on the ideXlab platform.
-
Detection of synchronization from Univariate Data using wavelet transform
Physical Review E, 2007Co-Authors: Alexander E. Hramov, Alexey A. Koronovskii, Vladimir I. Ponomarenko, Mikhail D. ProkhorovAbstract:A method is proposed for detecting from Univariate Data the presence of synchronization of a self-sustained oscillator by external driving with varying frequency. The method is based on the analysis of difference between the oscillator instantaneous phases calculated using continuous wavelet transform at time moments shifted by a certain constant value relative to each other. We apply our method to a driven asymmetric van der Pol oscillator, experimental Data from a driven electronic oscillator with delayed feedback and human heartbeat time series. In the latest case, the analysis of the heart rate variability Data reveals synchronous regimes between the respiration and slow oscillations in blood pressure.
-
Detecting Synchronization of Self-Sustained Oscillators Using Wavelet Analysis of Univariate Data for Variable External Drive Frequency
Technical Physics Letters, 2006Co-Authors: A. A. Koronovskiĭ, Mikhail D. Prokhorov, Vladimir I. Ponomarenko, Alexander E. HramovAbstract:A new method based on the continuous wavelet transform of Univariate Data is proposed for detecting the synchronization of a self-sustained oscillator under external drive action with linear frequency modulation. The efficacy of the proposed method is demonstrated in application to a model van der Pol oscillator and experimental physiological Data.
Mickael L. Perrin - One of the best experts on this subject based on the ideXlab platform.
-
Benchmark and application of unsupervised classification approaches for Univariate Data
Communications Physics, 2021Co-Authors: Maria El Abbassi, Jan Overbeck, Oliver Braun, Michel Calame, Herre S. J. Van Der Zant, Mickael L. PerrinAbstract:Unsupervised machine learning, and in particular Data clustering, is a powerful approach for the analysis of Datasets and identification of characteristic features occurring throughout a Dataset. It is gaining popularity across scientific disciplines and is particularly useful for applications without a priori knowledge of the Data structure. Here, we introduce an approach for unsupervised Data classification of any Dataset consisting of a series of Univariate measurements. It is therefore ideally suited for a wide range of measurement types. We apply it to the field of nanoelectronics and spectroscopy to identify meaningful structures in Data sets. We also provide guidelines for the estimation of the optimum number of clusters. In addition, we have performed an extensive benchmark of novel and existing machine learning approaches and observe significant performance differences. Careful selection of the feature space construction method and clustering algorithms for a specific measurement type can therefore greatly improve classification accuracies. In the field of nanoscience, clustering methods have gained momentum for the analysis of experimental Datasets with the aim of uncovering new physical properties. Here, the authors describe an unsupervised machine learning methodology that selects the optimal combination of feature space, clustering method, and number of clusters for the analysis of a range of experimental Datasets, including break-junction traces, I-V curves, and Raman spectra.
-
Universal approach for unsupervised classification of Univariate Data
arXiv: Mesoscale and Nanoscale Physics, 2020Co-Authors: Maria El Abbassi, Jan Overbeck, Oliver Braun, Michel Calame, Herre S. J. Van Der Zant, Mickael L. PerrinAbstract:Unsupervised machine learning, and in particular Data clustering, is a powerful approach for the analysis of Datasets and identification of characteristic features occurring throughout a Dataset. It is gaining popularity across scientific disciplines and is particularly useful for applications without a priori knowledge of the Data structure. Here, we introduce a universal approach for unsupervised Data classification relevant for any Dataset consisting of a series of Univariate measurements. It is therefore ideally suited for a wide range of measurement types. Here, we apply it to the field of nanoelectronics and spectroscopy to identify meaningful structures in Data sets, providing physically relevant information about the system under study. An important step in our approach is the guidelines for the estimation of the optimum number of clusters. In addition, we have performed an extensive benchmark of ML approaches found in literature for the classification of molecular break junction traces. We find that several feature space construction methods we have introduced and clustering algorithms yield accuracies up to 20% higher than methods reported so far, increasing the Fowlkes-Mallows index from 0.77 up to 0.91
-
benchmark and application of unsupervised classification approaches for Univariate Data
arXiv: Mesoscale and Nanoscale Physics, 2020Co-Authors: Maria El Abbassi, Jan Overbeck, Oliver Braun, Michel Calame, Herre S. J. Van Der Zant, Mickael L. PerrinAbstract:Unsupervised machine learning, and in particular Data clustering, is a powerful approach for the analysis of Datasets and identification of characteristic features occurring throughout a Dataset. It is gaining popularity across scientific disciplines and is particularly useful for applications without a priori knowledge of the Data structure. Here, we introduce an approach for unsupervised Data classification of any Dataset consisting of a series of Univariate measurements. It is therefore ideally suited for a wide range of measurement types. We apply it to the field of nanoelectronics and spectroscopy to identify meaningful structures in Data sets. We also provide guidelines for the estimation of the optimum number of clusters. In addition, we have performed an extensive benchmark of novel and existing machine learning approaches and observe significant performance differences. Careful selection of the feature space construction method and clustering algorithms for a specific measurement type can therefore greatly improve classification accuracies.
