| 1. |
- Kinser, J. M., et al.
(författare)
-
Multidimensional pulse image processing of chemical structure data
- 2000
-
Ingår i: Chemometrics and Intelligent Laboratory Systems. - 0169-7439 .- 1873-3239. ; 51:1, s. 115-124
-
Tidskriftsartikel (refereegranskat)abstract
- Recent advances in the understanding of the mammalian visual cortex have led to new approaches for image processing techniques. As a result of this, computer simulations using the proposed visual cortex model have become very useful in the field of image processing. Models of this kind have the ability to efficiently extract image segments, edges and texture. They operate by generating a set of pulse images (images with binary pixels) for a static input. These pulse images display synchronized activity of neighboring neurons, and it is these images in which the information about segments, edges and texture are displayed. Pulse image generation is dependent on autowaves that travel throughout the image. In order to extend pulse image processing to multidimensional data (i.e., data cubes), the autowaves are designed to expand in all of the cube's dimensions. In this fashion, pulse cubes can be created and the same analysis techniques that have been applied to two-dimensional pulse images can be applied to pulse image cubes. This paper examines and discusses multidimensional pulse image analysis applied to three-dimensional (3D) chemical structural data of 17 beta-estradiol.
|
|
| 2. |
- Verikas, Antanas, et al.
(författare)
-
Using artificial neural networks for process and system modelling
- 2003
-
Ingår i: Chemometrics and Intelligent Laboratory Systems. - Amsterdam : Elsevier. - 0169-7439 .- 1873-3239. ; 67:2, s. 187-191
-
Tidskriftsartikel (refereegranskat)abstract
- This letter concerns several papers, devoted to neural network-based process and system modelling, recently published in the Chemometrics and Intelligent Laboratory Systems journal. Artificial neural networks have proved themselves to be very useful in various modelling applications, because they can represent complex mapping functions and discover the representations using powerful learning algorithms. An optimal set of parameters for defining the functions is learned from examples by minimizing an error functional. In various practical applications, the number of examples available for estimating parameters of the models is rather limited. Moreover, to discover the best model, numerous candidate models must be trained and evaluated. In such thin-data situations, special precautions are to be taken to avoid erroneous conclusions. In this letter, we discuss three important issues, namely network initialization, over-fitting, and model selection, the right consideration of which can be of tremendous help in successful network design and can make neural modelling results more valuable.
|
|
| 3. |
- Öberg, Tomas, 1956-
(författare)
-
Importance of the first design matrix in experimental simplex optimization
- 1998
-
Ingår i: Chemometrics and Intelligent Laboratory Systems. - Amsterdam : Elevier. - 0169-7439 .- 1873-3239. ; 44:1-2, s. 147-151
-
Tidskriftsartikel (refereegranskat)abstract
- The basic and modified simplex methods are efficient optimization techniques applied in many fields of chemistry and engineering. Various first design matrices were evaluated on polynomial models with added noise. D-optimal linear design matrices performed better than regular or cornered first simplices in the normal experimental situation. These findings have been implemented in a new experimental design an optimization software, the MultiSimplex(R).
|
|
| 4. |
|
|
| 5. |
- Abbas, Aamer, 1973, et al.
(författare)
-
Characterization and mapping of carotenoids in the algae Dunaliella and Phaeodactylum using Raman and target orthogonal partial least squares
- 2011
-
Ingår i: Chemometrics and Intelligent Laboratory Systems. - : Elsevier BV. - 0169-7439 .- 1873-3239. ; 107:1, s. 174-177
-
Tidskriftsartikel (refereegranskat)abstract
- A method was developed for the characterisation of carotenoid pigments in algal species using Raman spectroscopy in combination with multivariate hyperspectral analysis. Target orthogonal partial least squares (T-OPLS) operates by designating one known reference spectrum as the target. The target spectrum is put as the single y column in an OPLS regression model where the X matrix consists of the unfolded image spectra as variables in its columns. The spectral shape of the OPLS first orthogonal target score enabled us to verify the peak positions of the standard, and detect new peaks, not present in the reference standard. It was shown that the mixture of carotenoids present in the algae did not fully match the reference spectrum, however, the method provided enough information to make an analysis possible also in this case. The image results were constructed from the OPLS loading vectors that were showing a correlation map for the reference spectrum from the predictive loadings and maps of the occurrence of deviations from the orthogonal loadings.
|
|
| 6. |
- Aftab, Obaid, 1984-, et al.
(författare)
-
Label free quantification of time evolving morphologies using time-lapse video microscopy enables identity control of cell lines and discovery of chemically induced differential activity in iso-genic cell line pairs
- 2015
-
Ingår i: Chemometrics and Intelligent Laboratory Systems. - 0169-7439 .- 1873-3239. ; 141, s. 24-32
-
Tidskriftsartikel (refereegranskat)abstract
- Label free time-lapse video microscopy based monitoring of time evolving cell population morphology has potential to offer a simple and cost effective method for identity control of cell lines. Such morphology monitoring also has potential to offer discovery of chemically induced differential changes between pairs of cell lines of interest, for example where one in a pair of cell lines is normal/sensitive and the other malignant/resistant. A new simple algorithm, pixel histogram hierarchy comparison (PHHC), for comparison of time evolving morphologies (TEM) in phase contrast time-lapse microscopy movies was applied to a set of 10 different cell lines and three different iso-genic colon cancer cell line pairs, each pair being genetically identical except for a single mutation. PHHC quantifies differences in morphology by comparing pixel histogram intensities at six different resolutions. Unsupervised clustering and machine learning based classification methods were found to accurately identify cell lines, including their respective iso-genic variants, through time-evolving morphology. Using this experimental setting, drugs with differential activity in iso-genic cell line pairs were likewise identified. Thus, this is a cost effective and expedient alternative to conventional molecular profiling techniques and might be useful as part of the quality control in research incorporating cell line models, e.g. in any cell/tumor biology or toxicology project involving drug/agent differential activity in pairs of cell line models.
|
|
| 7. |
- Björk, Anders, et al.
(författare)
-
Modeling of pulp quality parameters from distribution curves extracted from process acoustic measurements on a thermo mechanical pulp (TMP) process
- 2007
-
Ingår i: Chemometrics and Intelligent Laboratory Systems. - : Elsevier BV. - 0169-7439 .- 1873-3239. ; 85:1, s. 63-69
-
Tidskriftsartikel (refereegranskat)abstract
- In this paper the feasibility of modeling strength and optical pulp properties from length distribution curves extracted from acoustic data using continuous wavelet transform-fiber length extraction, CWT-FLE (A Björk and L-G Danielsson, 'Extraction of Distribution Curves from Process Acoustic Measurements on a TMP-Process', Pulp and Paper Canada 105 No. 11 (2004), T260-T264) by use of Partial Least Squares (PLS) have been tested. The curves used have earlier been validated against length distribution curves obtained by analyzing pulp samples with a commercial analyzer (FiberMaster). The curves were extracted from acoustic data without any "calibration" against fiber length analyses. The acoustic measurements were performed using an accelerometer affixed to the refiner blow-line during a full-scale trial with a Sunds Defibrator double disc refiner at SCA Ortviken, Sweden. Pulp samples were collected concurrently with the acoustic measurements and extensive physical testing has been made on these samples. For each trial point three pulp samples were collected. PLS1 and PLS2 models were successfully made linking the distribution curves obtained using CWT-FLE to pulp tensile strength properties as well as optical properties. The resulting Root Mean Square Error of Prediction (RMSEP) for all parameters is comparable to what can be obtained by pooling the standard deviations of reference measurements from the different trial points. The results obtained are compared to FiberMaster data modeled in the same fashion, yielding lower prediction errors than the CWT-FLE data. However, this can be partly due to the five-year storage of pulp samples between pulp sampling/acoustic measurement and FiberMaster analyses/sheet testing. The acoustic method is fast and produces results without dead time and could constitute a new tool for improving process control and optimizing the fiber characteristics in a specific process and for a specific purpose. The technique could be implemented in a PC-environment at a fairly low cost.
|
|
| 8. |
- Bouveresse, D. Jouan-Rimbaud, et al.
(författare)
-
Identification of significant factors by an extension of ANOVA-PCA based on multi-block analysis
- 2011
-
Ingår i: Chemometrics and Intelligent Laboratory Systems. - : Elsevier BV. - 0169-7439 .- 1873-3239. ; 106:2, s. 173-182
-
Tidskriftsartikel (refereegranskat)abstract
- A modification of the ANOVA-PCA method, proposed by Harrington et al. to identify significant factors and interactions in an experimental design, is presented in this article. The modified method uses the idea of multiple table analysis, and looks for the common dimensions underlying the different data tables, or data blocks, generated by the "ANOVA-step" of the ANOVA-PCA method, in order to identify the significant factors. In this paper, the "Common Component and Specific Weights Analysis" method is used to analyse the calculated multi-block data set. This new method, called AComDim, was compared to the standard ANOVA-PCA method, by analysing four real data sets. Parameters computed during the AComDim procedure enable the computation of F-values to check whether the variability of each original data block is significantly greater than that of the noise.
|
|
| 9. |
- Carlson, Johan E., et al.
(författare)
-
Estimation of dielectric properties of crude oils based on IR spectroscopy
- 2014
-
Ingår i: Chemometrics and Intelligent Laboratory Systems. - : Elsevier BV. - 0169-7439 .- 1873-3239. ; 139, s. 1-5
-
Tidskriftsartikel (refereegranskat)abstract
- Dielectric properties of crude oils play an important role in characterization and quality control. Measuring permittivity accurately over a wide range of frequencies is, however, a time-consuming task and existing measurement methods are not easily adapted for real-time diagnostics. IR spectroscopy, on the other hand, provides rapid measurements of fundamental molecular properties.In this paper we show that by using multivariate calibration tools such as PLS regression, it is possible to extract dielectric properties of crude oils directly from IR spectra, in addition to conventional interpretation of the spectra, hence reducing the need for direct electrical measurements. Results on 16 different oil samples show that the dielectric parameters obtained with the proposed method agree well with those obtained using direct permittivity measurements. The PLS regression method has also been extended with Monte-Carlo simulation capabilities to account for uncertainties in the data
|
|
| 10. |
- Carlson, Johan E., et al.
(författare)
-
Extracting homologous series from mass spectrometry data by projection on predefined vectors
- 2012
-
Ingår i: Chemometrics and Intelligent Laboratory Systems. - : Elsevier BV. - 0169-7439 .- 1873-3239. ; 114, s. 36-43
-
Tidskriftsartikel (refereegranskat)abstract
- Multivariate statistical methods, such as Principal Component Analysis (PCA), have been used extensively over the past decades as tools for extracting significant information from complex data sets. As such they are very powerful and in combination with an understanding of underlying chemical principles, they have enabled researchers to develop useful models. A drawback with the methods is that they do not have the ability to incorporate any physical / chemical model of the system being studied during the statistical analysis. In this paper we present a method that can be used as a complement to traditional chemometric tools in finding patterns in mass spectrometry data. The method uses a pre-defined set of equally spaced sequences that are assumed to be present in the data. Allowing for some uncertainty in the peak locations due to the uncertainties for the measurement instrumentation, the measured spectra are then projected onto this set. It is shown that the resulting scores can be used to identify homologous series in measured mass spectra that differ significantly between different measured samples. As opposed to PCA, the loading vectors, in this case the pre-defined homologous series, are readily interpretable.
|
|
