A New Approach to Plant Diversity Assessment Combining HPLC Data, Simplex Mixture Design and Discriminant Analysis

2007 ◽  
Vol 13 (1) ◽  
pp. 17-33 ◽  
Author(s):  
Nabil Semmar ◽  
Maurice Jay ◽  
Muhammad Farman ◽  
Maurice Roux
Keyword(s):  
Discriminant Analysis ◽  
Plant Diversity ◽  
Mixture Design ◽  
New Approach ◽  
Diversity Assessment ◽  
Hplc Data

scholarly journals Sparse Functional Linear Discriminant Analysis

Biometrika ◽  
2021 ◽  
Author(s):  
Juhyun Park ◽  
Jeongyoun Ahn ◽  
Yongho Jeon
Keyword(s):  
Discriminant Analysis ◽  
Linear Discriminant Analysis ◽  
Real Data ◽  
New Approach ◽  
Linear Discriminant ◽  
Finite Samples ◽  
Regularization Problem ◽  
Bayes Error ◽  
Functional Setting ◽  
Regularized Solution

Abstract Functional linear discriminant analysis offers a simple yet efficient method for classification, with the possibility of achieving a perfect classification. Several methods are proposed in the literature that mostly address the dimensionality of the problem. On the other hand, there is a growing interest in interpretability of the analysis, which favors a simple and sparse solution. In this work, we propose a new approach that incorporates a type of sparsity that identifies nonzero sub-domains in the functional setting, offering a solution that is easier to interpret without compromising performance. With the need to embed additional constraints in the solution, we reformulate the functional linear discriminant analysis as a regularization problem with an appropriate penalty. Inspired by the success of ℓ1-type regularization at inducing zero coefficients for scalar variables, we develop a new regularization method for functional linear discriminant analysis that incorporates an L1-type penalty, ∫ |f|, to induce zero regions. We demonstrate that our formulation has a well-defined solution that contains zero regions, achieving a functional sparsity in the sense of domain selection. In addition, the misclassification probability of the regularized solution is shown to converge to the Bayes error if the data are Gaussian. Our method does not presume that the underlying function has zero regions in the domain, but produces a sparse estimator that consistently estimates the true function whether or not the latter is sparse. Numerical comparisons with existing methods demonstrate this property in finite samples with both simulated and real data examples.

scholarly journals Plant diversity in sedimentary DNA obtained from high-latitude (Siberia) and high-elevation lakes (China)

2020 ◽  
Vol 8 ◽  
Author(s):  
Kathleen Stoof-Leichsenring ◽  
Sisi Liu ◽  
Weihan Jia ◽  
Kai Li ◽  
Luidmila Pestryakova ◽  
...  
Keyword(s):  
Lake Sediments ◽  
Plant Diversity ◽  
Environmental Conditions ◽  
Environmental Changes ◽  
The Arctic ◽  
Mean Annual Precipitation ◽  
Reference Database ◽  
Mean Annual Temperature ◽  
Diversity Assessment ◽  
Recent Climate

Plant diversity in the Arctic and at high altitudes strongly depends on and rebounds to climatic and environmental variability and is nowadays tremendously impacted by recent climate warming. Therefore, past changes in plant diversity in the high Arctic and high-altitude regions are used to infer climatic and environmental changes through time and allow future predictions. Sedimentary DNA (sedDNA) is an established proxy for the detection of local plant diversity in lake sediments, but still relationships between environmental conditions and preservation of the plant sedDNA proxy are far from being fully understood. Studying modern relationships between environmental conditions and plant sedDNA will improve our understanding under which conditions sedDNA is well-preserved helping to a.) evaluate suitable localities for sedDNA approaches, b.) provide analogues for preservation conditions and c.) conduct reconstruction of plant diversity and climate change. This study investigates modern plant diversity applying a plant-specific metabarcoding approach on sedimentary DNA of surface sediment samples from 262 lake localities covering a large geographical, climatic and ecological gradient. Latitude ranges between 25°N and 73°N and longitude between 81°E and 161°E, including lowland lakes and elevated lakes up to 5168 m a.s.l. Further, our sampling localities cover a climatic gradient ranging in mean annual temperature between -15°C and +18°C and in mean annual precipitation between 36­ and 935 mm. The localities in Siberia span over a large vegetational gradient including tundra, open woodland and boreal forest. Lake localities in China include alpine meadow, shrub, forest and steppe and also cultivated areas. The assessment of plant diversity in the underlying dataset was conducted by a specific plant metabarcoding approach. We provide a large dataset of genetic plant diversity retrieved from surface sedimentary DNA from lakes in Siberia and China spanning over a large environmental gradient. Our dataset encompasses sedDNA sequence data of 259 surface lake sediments and three soil samples originating from Siberian and Chinese lakes. We used the established chloroplastidal P6 loop trnL marker for plant diversity assessment. The merged, filtered and assigned dataset includes 15,692,944 read counts resulting in 623 unique plant DNA sequence types which have a 100% match to either the EMBL or to the specific Arctic plant reference database. The underlying dataset includes a taxonomic list of identified plants and results from PCR replicates, as well as extraction blanks (BLANKs) and PCR negative controls (NTCs), which were run along with the investigated lake samples. This collection of plant metabarcoding data from modern lake sediments is still ongoing and additional data will be released in the future.

scholarly journals Sampling with probability proportional to prediction: rethinking rapid plant diversity assessment

2017 ◽  
Vol 91 (1) ◽  
pp. 17-26 ◽  
Author(s):  
Tzeng Yih Lam ◽  
Yung-Han Hsu ◽  
Ting-Ru Yang ◽  
John A Kershaw ◽  
Sheng-Hsin Su
Keyword(s):  
Plant Diversity ◽  
Diversity Assessment

Sex estimation using paranasal sinus discriminant analysis: a new approach via cone beam computerized tomography volume analysis

2019 ◽  
Vol 133 (6) ◽  
pp. 1977-1984 ◽  
Author(s):  
Ana Márcia Viana Wanzeler ◽  
Sergio Melo Alves-Júnior ◽  
Lucas Ayres ◽  
Maria Carolina da Costa Prestes ◽  
Jessica Teixeira Gomes ◽  
...  
Keyword(s):  
Discriminant Analysis ◽  
Paranasal Sinus ◽  
Computerized Tomography ◽  
Cone Beam ◽  
Sex Estimation ◽  
New Approach ◽  
Volume Analysis ◽  
Cone Beam Computerized Tomography

Plant Diversity Assessment on Mount Cameroon: Surveys from 1990 to 2000

2001 ◽  
Vol 71 (2) ◽  
pp. 1017 ◽  
Author(s):  
Nouhou Ndam ◽  
James Acworth ◽  
David Kenfack ◽  
Peguy Tchouto ◽  
John B. Hall
Keyword(s):  
Plant Diversity ◽  
Mount Cameroon ◽  
Diversity Assessment

scholarly journals The role of plants in the formation of species-specific features in grass flies (Diptera, Chloropidae, Meromyza)

2021 ◽  
Vol 9 ◽  
Author(s):  
Tatiana Triseleva ◽  
Varos Petrosyan ◽  
Aleksandra Yatsuk ◽  
Andrey Safonkin
Keyword(s):  
Discriminant Analysis ◽  
Host Plant ◽  
Plant Diversity ◽  
Classification Accuracy ◽  
Host Plants ◽  
Primary Role ◽  
Linear Discriminant ◽  
Anterior Process ◽  
Wide Range

In the current manuscript, we present the results of comparative analysis of seven species of Meromyza flies in the “variegata” cluster and of the evolutionary close species M. inornata, based the following criteria: 1) 14 external key features; 2) shape and area of the anterior processes of postgonites; 3) mtDNA CO1 region and 4) host plant diversity data. We could demonstrate the primary role of host plants in species formation inside genus Meromyza and calculated the timing of the divergence of M. inornata and the species of “variegata” cluster. Based on our estimates of evolution rate for mtDNA CO1 gene, we could conclude that that divergence of herbs happened before the speciation of grass flies Meromyza. Meromyza species, close to the ancestral species of the cluster, are adapted to the wide range of host plants. We revealed the most informative variables h1, S and Plant analysing data with the following statistical methods: linear discriminant analysis - LDA, regularised discriminant analysis - RDA, flexible discriminant analysis – FDA and probabilistic neural network - PNN. The highest classification accuracy was achieved using PNN (99%) and the lowest when using LDA (95.8%). When the Plant trait was excluded, the classification accuracy decreased by 14%. We revealed the significant trends in size change of the anterior process of the postgonite amongst studies species. This morphological structure is an element of male reproductive apparatus critical for the restriction of interspecies mating. We determined three branches of speciation in the “variegata” cluster and five trends in the evolution of this cluster, based on the external morphological features. We showed that M. variegata and especially M. mosquensis, the species closest to the ancestral haplotype, have the largest number of features typical of those of M. inornata. Based on the external features and the area of the anterior process of the postgonite, we reconstructed the phylogenetic position of M. elbergi in the cluster. In accordance with the obtained outcomes, we could conclude that the distribution, species diversity and the adaptation of the grass flies to narrow oligophagy were directly connected to host plant diversity. The adaptation to different host plants could be the main factor in divergence of grass flies and their evolution started later than the diversification in the Pooideae subfamily of grasses.

Sign in / Sign up

Export Citation Format

Share Document