Search results for "linear discriminant analysis"
showing 10 items of 163 documents
Molecular connectivity to find β-blockers with low toxicity
1997
Abstract Molecular connectivity has been used to find new β-blocker drugs using linear discriminant analysis and connectivity functions with different topological descriptors. Among the selected compounds stands out the probucol and the β-carotene. Both of them interact with β adrenoceptors.
Predictability and prediction of lowest observed adverse effect levels in a structurally heterogeneous set of chemicals
2005
A database of chronic lowest observed adverse effect levels (LOAELs) for 234 compounds, previously compiled from different sources (Toxicology Letters79, 131-143 (1995)), was modelled using graph theoretical descriptors. This study reveals that data are not homogeneous. Only those data originating from the U.S. Environmental Protection Agency (EPA) reports could be well modelled by multilinear regression (MLR) and linear discriminant analysis (LDA). In contrast, data available from the specific procedures of the National Toxicology Program (NTP) database introduced noise and did not render good models either alone, or in combination with the EPA data.
Application of molecular topology for the prediction of the reaction times and yields under solvent-free conditions
2010
Ball milling and conventional magnetic stirring can be used to support different laboratory techniques with a highly efficient mixing of reagents under solvent-free conditions. By using multilinear regression and linear discriminant analysis, topological-mathematical models have been built to predict the yield and the reaction time for organocatalytic reactions, Suzuki reactions and reactions of synthesis of heterocyclic compounds. The results from the in silico predictions confirm the usefulness of the approach followed.
Diagnosis of damage to Norway spruce (Picea abies) through biochemical criteria
1995
Bioindication can be carried out at different hierarchical levels, eg. cell, organism, and ecosystem. While the monitoring of damage by visible criteria (e.g. loss of needles) is connected with the organism as a whole, the monitoring of damage by biochemical indicators is above all connected with cell metabolism. The degree of vitality of a tree can be ascertained through the integration of a number of biochemical parameters. Furthermore, a differential diagnosis of a particular stress pattern can be carried out because of the feedback pattern of several biochemical indicators. In order to describe and interpret biochemical or physiological changes that have been caused by a number of facto…
A multivariate approach to the study of orichalcum ingots from the underwater Gela's archaeological site
2017
Abstract In this work a careful ICP-OES and ICP-MS investigation of 38 ancient ingots has been performed to determine both major components and trace elements content to find a correlation between the observed different features and the composition. The ingots, recovered in an underwater archaeological site of various finds near Gela (CL, Italy), were previously investigated by X-Ray Fluorescence (XRF) spectroscopy to know the composition of the alloy and it was found that the major elements were copper and zinc, in a ratio compatible with the famous orichalcum similar to the contemporary brass that was considered a precious metal in ancient times. The discovery of huge amount this alloy is…
Automated facies identification by Direct Push-based sensing methods (CPT, HPT) and multivariate linear discriminant analysis to decipher geomorpholo…
2021
In ad 1362, a major storm surge drowned wide areas of cultivated medieval marshland along the north‐western coast of Germany and turned them into tidal flats. This study presents a new methodological approach for the reconstruction of changing coastal landscapes developed from a study site in the Wadden Sea of North Frisia. Initially, we deciphered long‐term as well as event‐related short‐term geomorphological changes, using a geoscientific standard approach of vibracoring, analyses of sedimentary, geochemical and microfaunal palaeoenvironmental parameters and radiocarbon dating. In a next step, Direct Push (DP)‐based Cone Penetration Testing (CPT) and the Hydraulic Profiling Tool (HPT) wer…
Contribution to the taxonomy of the family Campulidae Odhner, 1926 (Digenea) by means of a morphometric multivariate analysis
1996
Digeneans of the family Campulidae occur exclusively in marine mammals, particularly in cetaceans. Their taxonomy is confused, being based on adult morphology only. We used a multivariate discriminant analysis of morphometric data to provide new evidence on the taxonomy of the Campulidae. Measurements of 217 specimens from 21 species of all seven genera of the family were taken. The percentage of specimens correctly assigned into their own species was 96.3%. The first three discriminant functions accounted for most of the variation between the species, which were grouped together in suprageneric groups along the first and the second function. The ordination pattern observed conforms partly …
Hyperspectral system for early detection of rottenness caused by Penicillium digitatum in mandarins
2008
Abstract Nowadays, the detection of fruit infected with Penicillium sp. fungi on packing lines is carried out manually under ultraviolet illumination. Ultraviolet sources induce visible fluorescence of essential oils, present in the skin of citrus and which are released by the action of fungi, thus increasing the contrast between sound and rotten skin. This work analyses a set of techniques aimed at detecting rotten citrus without the use of UV lighting. The techniques used include hyperspectral image acquisition, pre-processing and calibration, feature selection and segmentation using linear and non-linear methods for classification of fruits. Different methods such as correlation analysis…
Decoding Emotional Valence from Electroencephalographic Rhythmic Activity
2017
We attempt to decode emotional valence from electroencephalographic rhythmic activity in a naturalistic setting. We employ a data-driven method developed in a previous study, Spectral Linear Discriminant Analysis, to discover the relationships between the classification task and independent neuronal sources, optimally utilizing multiple frequency bands. A detailed investigation of the classifier provides insight into the neuronal sources related with emotional valence, and the individual differences of the subjects in processing emotions. Our findings show: (1) sources whose locations are similar across subjects are consistently involved in emotional responses, with the involvement of parie…
Identification In Silico and In Vitro of Novel Trypanosomicidal Drug-Like Compounds
2012
Atom-based bilinear indices and linear discriminant analysis are used to discover novel trypanosomicidal compounds. The obtained linear discriminant analysis-based quantitative structure–activity relationship models, using non-stochastic and stochastic indices, provide accuracies of 89.02% (85.11%) and 89.60% (88.30%) of the chemicals in the training (test) sets, respectively. Later, both models were applied to the virtual screening of 18 in-house synthesized compounds to find new pro-lead antitrypanosomal agents. The in vitro antitrypanosomal activity of this set against epimastigote forms of Trypanosoma cruzi is assayed. Predictions agree with experimental results to a great extent (16/18…