Multivariate Datenanalyse

Kessler, Waltraud

doi:10.1002/9783527610037

Cited by 88 publications

(62 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The resampled TIR and the VNIR-SWIR laboratory soil spectra were transformed from reflectance (R) to absorbance (log 10 (1/R)), as input to the statistical analyses, to be consistent with the Beer-Lambert law [28].…”

Section: Spectral Resampling To Operational Hyperspectral Remote Sensorsmentioning

confidence: 99%

Applicability of the Thermal Infrared Spectral Region for the Prediction of Soil Properties Across Semi-Arid Agricultural Landscapes

et al. 2012

View full text Add to dashboard Cite

In this study we tested the feasibility of the thermal infrared (TIR) wavelength region (within the atmospheric window between 8 and 11.5 µm) together with the traditional solar reflective wavelengths for quantifying soil properties for coarse-textured soils from the Australian wheat belt region. These soils have very narrow ranges of texture and organic carbon contents. Soil surface spectral signatures were acquired in the laboratory, using a directional emissivity spectrometer (µFTIR) in the TIR, as well as a bidirectional reflectance spectrometer (ASD FieldSpec) for the solar reflective wavelengths (0.4-2.5 µm). Soil properties were predicted using multivariate analysis techniques (partial least square regression). The spectra were resampled to operational imaging spectroscopy sensor characteristics (HyMAP and TASI-600). To assess the relevance of specific wavelength regions in the prediction, the drivers of the PLS models were interpreted with respect to the spectral characteristics of the soils' chemical and physical composition. The study

show abstract

Section: Spectral Resampling To Operational Hyperspectral Remote Sensorsmentioning

confidence: 99%

Applicability of the Thermal Infrared Spectral Region for the Prediction of Soil Properties Across Semi-Arid Agricultural Landscapes

et al. 2012

View full text Add to dashboard Cite

show abstract

“…where a i is the absorbance at the wavelength λ i and a is the arithmetic mean of all a i (28). & The region above 7,226 cm −1 does not contain any of the constituents' chemical signatures and was, therefore, neglected.…”

Section: Spectral Acquisition and Pretreatmentmentioning

confidence: 99%

“…Under PCA, the investigated data variables (the spectra in our case) are projected onto a space, whose axes are the principal components (PCs); PCs are linear combinations of the measured variables, and each PC captures the directions of maximum variance in the measured data (28). These projected values, termed scores, are shown in Fig.…”

Section: Spectral Acquisition and Pretreatmentmentioning

confidence: 99%

See 1 more Smart Citation

Monitoring Blending of Pharmaceutical Powders with Multipoint NIR Spectroscopy

et al. 2012

View full text Add to dashboard Cite

Abstract. Blending of powders is a crucial step in the production of pharmaceutical solid dosage forms. The active pharmaceutical ingredient (API) is often a powder that is blended with other powders (excipients) in order to produce tablets. The blending efficiency is influenced by several external factors, such as the desired degree of homogeneity and the required blending time, which mainly depend on the properties of the blended materials and on the geometry of the blender. This experimental study investigates the mixing behavior of acetyl salicylic acid as an API and α-lactose monohydrate as an excipient for different filling orders and filling levels in a blender. A multiple near-infrared probe setup on a laboratoryscale blender is used to observe the powder composition quasi-simultaneously and in-line in up to six different positions of the blender. Partial least squares regression modeling was used for a quantitative analysis of the powder compositions in the different measurement positions. The end point for the investigated mixtures and measurement positions was determined via moving block standard deviation. Observing blending in different positions helped to detect good and poor mixing positions inside the blender that are affected by convective and diffusive mixing.

show abstract

“…Wrongly presumed uniformity can result in a classification of unsimilar features as similar and vice versa. Some approaches try to improve the matching of features in the non-uniform feature space by using dimensionality reduction techniques such as Principal Component Analyses (PCA) [4]. For example Ke and Sukthankar showed in [5] that using PCA can improve the matching of features in SIFT space.…”

Section: Introductionmentioning

confidence: 99%

A Topology-Independent Similarity Measure for High-Dimensional Feature Spaces

Kerdels

Peters

2007

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. In the field of computer vision feature matching in high dimensional feature spaces is a commonly used technique for object recognition. One major problem is to find an adequate similarity measure for the particular feature space, as there is usually only little knowledge about the structure of that space. As a possible solution to this problem this paper presents a method to obtain a similarity measure suitable for the task of feature matching without the need for structural information of the particular feature space. As the described similarity measure is based on the topology of the feature space and the topology is generated by a growing neural gas, no knowledge about the particular structure of the feature space is needed. In addition, the used neural gas quantizes the feature vectors and thus reduces the amount of data which has to be stored and retrieved for the purpose of object recognition.

show abstract

Multivariate Datenanalyse

Cited by 88 publications

References 0 publications

Applicability of the Thermal Infrared Spectral Region for the Prediction of Soil Properties Across Semi-Arid Agricultural Landscapes

Applicability of the Thermal Infrared Spectral Region for the Prediction of Soil Properties Across Semi-Arid Agricultural Landscapes

Monitoring Blending of Pharmaceutical Powders with Multipoint NIR Spectroscopy

A Topology-Independent Similarity Measure for High-Dimensional Feature Spaces

Contact Info

Product

Resources

About