Antennaria howellii subsp. gaspensis comb, et stat. nov. (Asteraceae : Inuleae): justification for change

1995 ◽  
Vol 73 (9) ◽  
pp. 1366-1370 ◽  
Author(s):  
Jerry G. Chmielewski
Keyword(s):  
Data Analysis ◽  
Discriminant Analysis ◽  
Chromosome Number ◽  
Cross Validation ◽  
Growth Form ◽  
Taxonomic Status ◽  
Canonical Discriminant Analysis ◽  
New Combination ◽  
Quantitative Morphology ◽  
Antennaria Microphylla

Canonical discriminant analysis was used to assess the taxonomic status of Antennaria neodioica Greene var. gaspensis Fernald. Results based on these analyses indicate that Antennaria howellii Greene, Antennaria microphylla Rydberg, A. neodioica var. gaspensis, Antennaria pulvinata Greene, and Antennaria rosea Greene are morphologically distinct. High cross-validation assignment rates as well as high Geisser assignment probabilities for each of the taxa support this statement. Elevating var. gaspensis to the rank of species is in part supported by the data analysis, but doing so would be contrary to the species standard method and inconsistent with recent practice in revisions of the genus. The presence of scarious appendages at the tips of the upper cauline leaves, the open pedicellate inflorescence, the whitish-green capitula, general growth form, agamospermous reproduction, chromosome number, provenance, and quantitative morphology, in addition to the results of the canonical discriminant analysis, support recognition of var. gaspensis at an infraspecific rank. In keeping with the criteria utilized in recent revisions of the genus, var. gaspensis should more appropriately be treated as a subspecies. Recent nomenclatural rearrangements in A. neodioica and A. howellii founded on the priority of the latter lead to the following new combination: Antennaria howellii subsp. gaspensis (Fernald) Chmielewski. Key words: Antennaria howellii var. gaspensis, Asteraceae, Newfoundland flora, Gaspé Bay Peninsula flora.

Taxonomic revision of the genus Tetraglochin (Rosaceae, Rosoideae) and morphometric analysis of its species

Phytotaxa ◽  
2017 ◽  
Vol 296 (3) ◽  
pp. 201 ◽  
Author(s):  
ANA M. CIALDELLA ◽  
CAROLINA L. POMETTI
Keyword(s):  
Discriminant Analysis ◽  
Morphological Differentiation ◽  
Taxonomic Revision ◽  
Canonical Discriminant Analysis ◽  
New Combination ◽  
The Andes ◽  
General Terms ◽  
Morphometric Analyses ◽  
Almost All ◽  
Reproductive Characters

Tetraglochin is a small genus distributed along the Andes from Perú to southern Argentina and central Chile, belonging to the family Rosaceae. Systematic studies in Tetraglochin are scarce, and circumscription of some members of this genus is controversial. In order to evaluate the degree of morphological differentiation between the species of this genus, we performed morphometric analyses using multivariate methods (non parametric ANOVA, phenetic analysis and canonical discriminant analysis) including those specimens with intermediate characteristics between T. alata and T. ameghinoi. The phenogram obtained showed two principal clusters; this picture suggested a clear grouping of the specimens of T. alata, T. ameghinoi, T. aff. alata and T. andina. In the canonical discriminant analysis five groups were found and in general terms all individuals of T. alata, T. aff. alata and T. ameghinoi were grouped together. When multivariate analyses were applied almost all specimens could be correctly assigned to its species. However, specimens of T. alata, T. aff. alata and T. ameghinoi , were not well discriminated. Following recent phylogenetic results on the genus, and morphometric analyses perfomed herein for the first time, we present an updated taxonomic revision of Tetraglochin, based on exomorphological, vegetative and reproductive characters, including a key to identify species and varieties, their associated synonymy, full descriptions, geographical distribution and illustrations. As result, a new combination, T. alata var. ameghinoi is proposed, T. alata var. patagonica is reduced to synonymy of T. alata var. alata, and T. paucijugata and T. tragacantha are reduced to synonymy of T. cristata. Lectotypes for Margyricarpus acanthocarpus, Tetraglochin acanthocarpa var. lasiocarpa, var. dasycarpa, var. macropoda and var. lejocarpa are designated. One species, Tetraglochin buxifolia is excluded from the genus.

Comparative analysis of shape variation in the cone scales of Larix dahurica and L. cajanderi (Pinaceae)

2021 ◽  
pp. 47-67
Author(s):  
Valentina P. Vetrova ◽  
◽  
Alexey P. Barchenkov ◽  
Nadezhda V. Sinelnikova ◽  
◽  
...  
Keyword(s):  
Discriminant Analysis ◽  
Geometric Morphometrics ◽  
Baikal Region ◽  
Canonical Discriminant Analysis ◽  
Shape Variation ◽  
Geometric Morphometric ◽  
The North ◽  
Larch Species ◽  
Geometric Morphometric Analysis ◽  
Cone Scale

Geometric morphometric analysis of shape variation in the cone scales of two closely related larch species, Larix dahurica Laws. (=Larix gmelinii (Rupr.) Rupr) and L. cajanderi Mayr, was carried out. The data on the taxonomy and distribution of L. dahurica and L. cajanderi are contradictory. The taxonomic status of L. cajanderi has been confirmed by the genetic and morphological studies performed in Russia and based on considerable evidence, but the species has not been recognized internationally, being considered as a synonym of Larix gmelinii var. gmelinii. In the systematics of larch, morphological characters of the generative organs are mainly used as diagnostic markers, among the most important being the shape variation of the cone scales. The aim of this study was to test geometric morphometrics as a tool for analyzing differentiation of L. dahurica and L. cajanderi in the shape of their cone scales. Characterization of shape variations in cone scales using geometric morphometric methods consists in digitizing points along an outline of scales followed by analysis of partial warps, describing individual differences in coordinates of the outline points. We studied the populations of L. dahurica from Evenkia and the Trans-Baikal region and six L. cajanderi populations from Yakutia and Magadan Oblast. In each population, we analyzed samples of 100-150 cones collected from 20-30 trees. Scales taken from the middle part of the cones were scanned using an Epson Perfection V500 Photo. On the scanned images, outline points were placed with a TPSDig program (Rolf, 2010), using angular algorithm (Oreshkova et al., 2015). The data were processed and analyzed using Integrated Morphometrics Programs (IMP) software (http://www.canisius.edu/~sheets/ morphsoft.html, Sheets, 2001), following the guidelines on geometric morphometrics in biology (Pavlinov, Mikeshina, 2002; Zelditch et al., 2004). Initial coordinates of the scale landmarks were aligned with the mean structure for L. dahurica and L. cajanderi cone scales using Procrustes superimposition in the CoordGen6 program. PCA based on covariances of partial warp scores was applied to reveal directions of variation in the shape of the cone scales. The relative deformations of the cone scales (PCA scores) were used as shape variables for statistical comparisons of these two larch species with canonical discriminant analysis. Morphotypes of the cone scales were distinguished in L. dahurica populations by pairwise comparison of samples from trees in the TwoGroup6h program using Bootstrap resampling-based Goodall’s F-test (Sheets, 2001). Samples from the trees in which the cone scales differed significantly (p < 0.01) were considered to belong to different morphotypes. Morphotypes distinguished in L. dahurica populations were compared with the morphotypes that we had previously determined in L. cajanderi populations. The composition and the frequency of occurrence of morphotypes were used to determine phenotypic distances between populations (Zhivotovskii, 1991). Multidimensional scaling matrix of the phenotypic distances was applied for ordination of larch populations. In this research, we revealed differentiation of L. dahurica and L. cajanderi using geometric morphometric analysis of the shape variation of cone scales. The results of PCA of partial warp scores exposed four principal components, which account for 90% of total explained variance in the shape of the cone scales in the two larch species. Graphical representations of these shape transformations in the vector form characterized directions of shape variability in scales corresponding to the maximum and minimum values of four principal components (See Fig. 2). PCA-ordination of the larch populations revealed some difference in the shape variation of the cone scales in L. dahurica and L. cajanderi (See Fig. 3). The results of canonical discriminant analysis of relative deformations of scales showed differentiation of the populations of the two larch species (See Fig. 4). Eleven morphotypes were identified in L. dahurica cones from Evenkia and nine morphotypes in the Ingoda population, three of the morphotypes being common for both populations (See Fig. 5). The shape of L. dahurica cone scales varied from spatulate to oval and their apical margins from weakly sinuate to distinctly sinuate. The Trans-Baikal population was dominated by scales with obtuse (truncate) and rounded apexes. The obtained morphotypes were compared with 25 cone scale morphotypes previously distinguished in the Yakut and the Magadan L. cajanderi populations (See Fig. 3). Four similar morphotypes of cone scales were revealed in the North-Yeniseisk population of L. dahurica and the Yakut populations of L. cajanderi. The differences between them in the populations of the two larch species were nonsignificant (p > 0.01). All morphotypes of cone scales from the Ingoda population of L. dahurica differed significantly from L. cajanderi cone scale morphotypes. The results of multidimensional scaling phenotypic distance matrix calculated based on the similarity of morphotypes of L. dahurica and L. cajanderi populations were consistent with the results of their differentiation based on relative deformations of scales obtained using canonical discriminant analysis (See Fig. 4 and Fig. 7). In spite of the differences in the shape of the cone scales between the North-Yeniseisk and the Trans-Baikal populations of L. dahurica, they both differed from L. cajanderi populations. Thus, phenotypic analysis confirmed differentiation of these two larch species. Despite the similarities between a number of morphotypes, the Yakut L. cajanderi populations were differentiated from L. dahurica populations. Significant differences were noted between intraspecific groups: between L. cajanderi populations from Okhotsk-Kolyma Upland and Yakutia and between L. dahurica populations from Evenkia and the Trans-Baikal region (See Fig. 4). The similarities between species and intraspecific differences may be attributed to the ongoing processes of hybridization and species formation in the region where the ranges of the larches overlap with the ranges of L. czekanowskii Szafer and L. dahurica×L. cajanderi hybrids. Geometric morphometrics can be used as an effective tool for analyzing differentiation of L. dahurica and L. cajanderi in the shape of their cone scales.

Αποτίμηση κινδύνων των ευρωπαϊκών τραπεζών και συστήματα έγκαιρης προειδοποίησης

2018 ◽  
Author(s):  
Παντελής Σταυρούλιας
Keyword(s):  
Logistic Regression ◽  
Discriminant Analysis ◽  
Cross Validation ◽  
Multinomial Logistic Regression ◽  
Classification Tree ◽  
Probit Regression ◽  
Macroprudential Policy ◽  
Policy Makers ◽  
Out Of Sample ◽  
Sample Testing

Οι έγκυρες προβλέψεις χρηματοοικονομικών κρίσεων διασφάλιζαν ανέκαθεν την σταθερότητα τόσο ολόκληρου του χρηματοοικονομικού οικοδομήματος γενικότερα, όσο και του τραπεζικού τομέα ειδικότερα. Με την παρούσα διατριβή επιτυγχάνεται η πρόβλεψη συστημικών τραπεζικών κρίσεων για χώρες της EE-14 αρκετά τρίμηνα προτού αυτές γίνουν αντιληπτές με την χρησιμοποίηση των πιο διαδεδομένων μεταβλητών (μακροοικονομικών, τραπεζικών και αγοράς) μέσω δύο προσεγγίσεων, της δυαδικής και της πολυεπίπεδης. Ακολουθώντας τη δυαδική προσέγγιση, εξάγονται μοντέλα ταξινόμησης με την εφαρμογή της Διακριτής Ανάλυσης (Discriminant Analysis), της Γραμμικής Παλινδρόμησης (Linear Regression), της Λογιστικής Παλινδρόμησης (Logistic Regression) και της Παλινδρόμησης Πιθανοομάδας (Probit Regression), για την έγκαιρη πρόβλεψη των κρίσεων -12 έως -7 τρίμηνα πριν την εμφάνισή τους. Επιπροσθέτως, συγκρίνεται η απόδοση της ανωτέρω ανάλυσης χρησιμοποιώντας τις νεότερες και πλέον υποσχόμενες μεθόδους του Δέντρου Ταξινόμησης (Classification Tree), του Τυχαίου Δάσους (Random Forest) και της C5. Ταυτόχρονα προτείνεται ένα νέο μέτρο επιλογής κατωφλίων και απόδοσης προσαρμογής (GoF) των μοντέλων πρόβλεψης και μια νέα συνδυαστική (combined) μέθοδος ταξινόμησης. Προκειμένου να διερευνηθεί η απόδοση της ανωτέρω ανάλυσης, χρησιμοποιείται ο εκτός του δείγματος έλεγχος (out-of-sample testing) με τη μέθοδο της ανά χώρα σταυρωτής επικύρωσης (country-blocked cross validation). Σύμφωνα με τη μέθοδο αυτή, πραγματοποιείται η ανάλυση και εξάγονται τα μοντέλα πρόβλεψης με τη χρήση των δεκατριών από τις δεκατέσσερις χώρες του δείγματος (in-sample), εφαρμόζονται τα εξαγόμενα μοντέλα για την δέκατη τέταρτη χώρα που είχε εξαιρεθεί από το αρχικό δείγμα (out-of-sample) και ελέγχονται τα αποτελέσματα πρόβλεψης με τα πραγματικά δεδομένα της χώρας αυτής. Η παραπάνω διαδικασία επαναλαμβάνεται δεκατέσσερις φορές, αφήνοντας δηλαδή κάθε φορά μια χώρα εκτός δείγματος και τελικά εξάγεται ο μέσος όρος των επαναλήψεων. Στην παρούσα διατριβή, και χρησιμοποιώντας τον εκτός του δείγματος έλεγχο, επιτυγχάνεται η κατά 82.4% σωστή ταξινόμηση (Ακρίβεια – Accuracy), 78.4% ποσοστό Αληθινών Θετικών (Τrue Ρositive Rate - TPR) και 80.6% ποσοστό Θετικής Τιμής Πρόβλεψης (Positive Predictive Value - PPV). Σύμφωνα με την πολυεπίπεδη προσέγγιση, διακρίνονται δύο επίπεδα-περίοδοι πρόβλεψης των Συστημικών Τραπεζικών Κρίσεων. Το πρώτο επίπεδο ονομάζεται έγκαιρη πρόβλεψη (early warning) και αφορά περίοδο -12 έως -7 τρίμηνα πριν την έλευση της κρίσης ενώ το δεύτερο επίπεδο ονομάζεται καθυστερημένη πρόβλεψη (late warning) και αφορά περίοδο -6 έως -1 τρίμηνα πριν την έλευση της κρίσης. Για την πολυεπίπεδη αυτή ταξινόμηση, γίνεται χρήση των Νευρωνικών Δικτύων (Neural Networks), της Πολυωνυμικής Λογιστικής Παλινδρόμησης (Multinomial Logistic Regression) και της Πολυεπίπεδης Γραμμικής Διακριτής Ανάλυσης (Multinomial Discriminant Analysis). Εφαρμόζοντας τον ίδιο εκτός του δείγματος έλεγχο με την πρώτη προσέγγιση επιτυγχάνεται η κατά 85.7% σωστή ταξινόμηση με την βέλτιστη μέθοδο που αποδεικνύεται ότι είναι η Πολυεπίπεδη Γραμμική Διακριτή Ανάλυση. Εφαρμόζοντας την ανωτέρω ανάλυση, οι ενδιαφερόμενοι φορείς άσκησης πολιτικής (policy makers) μπορούν να ανιχνεύσουν την ύπαρξης κρίσης σε βάθος χρόνου έως τριών ετών με τα προτεινόμενα μοντέλα, χρησιμοποιώντας μόνο δεδομένα που υπάρχουν ελεύθερα προσβάσιμα στο κοινό, ασκώντας με τον τρόπο αυτό την κατάλληλη ανά περίπτωση μακροπροληπτική πολιτική (macroprudential policy).

scholarly journals Application of multivariate techniques in the evaluation of pure lines of beans

2016 ◽  
Vol 46 (9) ◽  
pp. 1535-1541 ◽  
Author(s):  
Rodolfo Schmit ◽  
Rita Carolina de Melo ◽  
Thayse Cristine Vieira Pereira ◽  
Mattheus Beck ◽  
Altamir Frederico Guidolin ◽  
...  
Keyword(s):  
Discriminant Analysis ◽  
Discriminant Function ◽  
Block Design ◽  
Original Data ◽  
Inbred Lines ◽  
Canonical Discriminant Analysis ◽  
Multivariate Techniques ◽  
Testing Hypotheses ◽  
Randomized Block Design ◽  
Pure Lines

ABSTRACT: The objective of this study was to apply multivariate techniques, canonical discriminant analysis, and multivariate contrasts, indicating the most favorable inferences in the evaluation of pure lines of beans. The study was conducted at the experimental field of the Institute for Breeding and Molecular Genetics, in Lages, SC, Brazil. The experiment was composed of 24 pure lines of beans from the Santa Catarina test of cultivars. Plant height, numbers of pods and grains per plant, and stem diameter were the variables measured. The complete randomized block design was used with four replications. The data were subjected to multivariate analysis of variance, canonical discriminant analysis, multivariate contrasts and univariate contrasts. The first canonical discriminant function has captured 81% of the total variation in the data. The Scott-Knott test showed two groups of inbred lines at the average -of scores of the first canonical discriminant function. It was considered that testing hypotheses with the canonical scores may result in loss of information obtained from the original data. Multivariate contrasts indicated differences within the group formed by the Scott-Knott test. The canonical discriminant analysis and multivariate contrasts are excellent techniques to be combined in the multivariate assessment, being used to explore and test hypotheses, respectively.

scholarly journals Sorghum Accessions for Use as Cover Crops and Biofuel Feedstocks

2015 ◽  
Vol 3 (2) ◽  
pp. 258
Author(s):  
Abram Jared Bicksler ◽  
John B Masiunas
Keyword(s):  
Discriminant Analysis ◽  
Cover Crops ◽  
Cover Crop ◽  
Germplasm Collection ◽  
Field Studies ◽  
Canonical Discriminant Analysis ◽  
Tiller Number ◽  
Canonical Variates ◽  
Growth Habits ◽  
Landrace Accessions

Phenotypes of sorghum species (Sorghum sp.) have characteristics making them valuable summer annual cover crops and/or biofuel feedstocks for temperate climates. In field studies conducted at Urbana, IL, USA, fourteen USDA sorghum landrace accessions and three commercial sorghum accessions were evaluated for their growth habits and regrowth potential. In Canonical Discriminant Analysis (CDA) analysis, the first two canonical variates were significant and accounted for 86% of the among-accession variability. Unmown tiller number, regrowth tiller number, and regrowth biomass best discriminated between accessions in CDA and scattergrams. The accessions clustered into three subgroups. Three multi-stemmed accessions (two commercial varieties and one USDA accession) with an ability to regrow clustered away from the bulk of the USDA sorghums. Multi-stemmed accessions are useful for breeding improved summer annual cover crops that are tall, produce copious amounts of biomass, and rapidly regrow after defoliation; although propensity to lodging and poor germination of accessions will need attention. Additionally, landrace sorghum accessions in the USDA germplasm collection are useful for breeding cover crop and biofuel feedstocks, due to their great height and biomass production, although it will be necessary to select for improved regrowth potential. Crosses between USDA landraces and the commercially available multi-stemmed accessions could lead to a sorghum cover crop and biofuel plant with great biomass and height and ability to regrow following defoliation.

scholarly journals Discrimination of Mangrove Ecosystem Objects on the Visible Spectrum Using Spectroradiometer HR-1024

2015 ◽  
Vol 29 (1) ◽  
Author(s):  
Amal Arfan
Keyword(s):  
Discriminant Analysis ◽  
Spectral Reflectance ◽  
Reflection Spectrum ◽  
Visible Spectrum ◽  
Mangrove Ecosystem ◽  
Canonical Discriminant Analysis ◽  
Integrated Analysis ◽  
Mangrove Vegetation ◽  
Dry Soil ◽  
Vegetation Water

The study was conducted to determine whether the vegetation in the mangrove ecosystem, can be contrasted with another objectt, using Spectroradiometer HR-1024. The data used is data visible spectrum(400-700 nm)  which resulted in 204 bands. The analysis used is the integrated analysis with three levels. First, using ANOVA to determine significant differences in spectral reflectance between vegetation with water, wet soil and dry soil. Second, using Step wise Canonical Discriminant Analysis to identify the most sensitive band for discrimination reflection spectrum. This analysis which resulted in six bands are considered practical to distinguish vegetation with another object namely  401.5 nm, 416.9 nm, 508.2 nm, 599.3 nm, 660.3nm and 689.2 nm. Third using the Jeffries-Matusita separability index which resulted in the separation index of mangrove vegetation, water, wet soil and dry soil is 1.414.

scholarly journals ORBITOLINA DAVIESI HOFKER, 1966: A FORGOTTEN ORBITOLINIDAE FROM THE THANETIAN OF PAKISTAN AND ITS TAXONOMIC STATUS

2020 ◽  
pp. 41-48
Author(s):  
FELIX SCHLAGINTWEIT
Keyword(s):  
New Species ◽  
Phylogenetic Relationships ◽  
New Genus ◽  
Taxonomic Status ◽  
Original Description ◽  
Junior Synonym ◽  
New Combination ◽  
Linear Arrangement ◽  
Radial Zone

Orbitolina daviesi Hofker, 1966 (family Orbitolinidae) was validly described and thoroughly illustrated from Thanetian limestones of Pakistan. Although its attribution to the genus Orbitolina d’Orbigny and any phylogenetic relationships with the Cretaceous taxa have been refuted shortly afterwards, the species has not been taxonomically revised since then. Karsella hottingeri Sirel, 1999 was established as new genus and new species from the Thanetian of Turkey, without taking into account J. Hofker’s publication. The original description and genus diagnosis of Karsella has meanwhile been emended to include the occurrence of a radial zone with septula that follow a zig-zag pattern and associated linear arrangement of the foramina, as well as a complex embryo. Orbitolina daviesi clearly displays these features and is here considered a species of the genus Karsella Sirel. Karsella hottingeri is regarded as a subjective junior synonym of O. daviesi Hofker and therefore, the only species of the genus is given as a new combination: Karsella daviesi (Hofker). From a suprageneric viewpoint, the two Paleogene genera Karsella Sirel and Cushmania Silvestri display a complex embryo and might belong to a new subfamily of the Orbitolinidae, phylogenetically different and unrelated to the lower-mid Cretaceous Orbitolininae.

scholarly journals A revision of the genus Psammogorgia Verrill, 1868 (Cnidaria, Anthozoa, Octocorallia) in the tropical eastern Pacific Ocean

ZooKeys ◽  
2020 ◽  
Vol 961 ◽  
pp. 1-30
Author(s):  
Odalisca Breedy ◽  
Hector M. Guzman
Keyword(s):  
Taxonomic Status ◽  
Taxonomic Revision ◽  
Eastern Pacific ◽  
New Combination ◽  
Valid Species ◽  
Shallow Waters ◽  
Eastern Pacific Ocean ◽  
Tropical Eastern Pacific ◽  
Character Tables ◽  
Two New Species

The species of the genus Psammogorgia Verrill, 1868 from the shallow waters of the tropical eastern Pacific were mainly described from 1846 to 1870. Very few contributions were published subsequently. Recently, the genus was revisited with the addition of two new species. However, a comprehensive generic study is still missing for the eastern Pacific. Psammogorgia is characterised by having axes cores without mineralisation, mainly coarse irregular spindles and thorny, leafy or tuberculate clubs coenenchymal sclerites and the anthocodial armature with distinct collaret and points arrangements. Herein a taxonomic revision of the genus is presented based on type material which was morphologically analysed and illustrated using optical and scanning electron microscopy. Comparative character tables are provided for comparison among species in the genus, along with a taxonomic key. Moreover, the taxonomic status of each species was analysed. The genus Psammogorgia comprises six valid species and two varieties, and three lectotypes and a new combination are proposed to establish the taxonomic status of these species.

scholarly journals Analisis Metode Pengenalan Wajah Two Dimensial Principal Component Analysis (2DPCA) dan Kernel Fisher Discriminant Analysis Menggunakan Klasifikasi KNN (K- Nearest Neighbor)

2020 ◽  
Vol 2 (2) ◽  
pp. 29-38
Author(s):  
Abdur Rohman Harits Martawireja ◽  
Hilman Mujahid Purnama ◽  
Atika Nur Rahmawati
Keyword(s):  
Principal Component Analysis ◽  
Discriminant Analysis ◽  
Cross Validation ◽  
Nearest Neighbor ◽  
Principal Component ◽  
Component Analysis ◽  
K Nearest Neighbor ◽  
Fisher Discriminant Analysis ◽  
Fisher Discriminant ◽  
Kernel Fisher Discriminant Analysis

Pengenalan wajah manusia (face recognition) merupakan salah satu bidang penelitian yang penting dan belakangan ini banyak aplikasi yang menerapkannya, baik di bidang komersil ataupun di bidang penegakan hukum. Pengenalan wajah merupakan sebuah sistem yang berfungsikan untuk mengidentifikasi berdasarkan ciri-ciri dari wajah seseorang berbasis biometrik yang memiliki keakuratan tinggi. Pengenalan wajah dapat diterapkan pada sistem keamanan. Banyak metode yang dapat digunakan dalam aplikasi pengenalan wajah untuk keamanan sistem, namun pada artikel ini akan membahas tentang dua metode yaitu Two Dimensial Principal Component Analysis dan Kernel Fisher Discriminant Analysis dengan metode klasifikasi menggunakan K-Nearest Neigbor. Kedua metode ini diuji menggunakan metode cross validation. Hasil dari penelitian terdahulu terbukti bahwa sistem pengenalan wajah metode Two Dimensial Principal Component Analysis dengan 5-folds cross validation menghasilkan akurasi sebesar 88,73%, sedangkan dengan 2-folds validation akurasi yang dihasilkan sebesar 89,25%. Dan pengujian metode Kernel Fisher Discriminant dengan 2-folds cross validation menghasilkan akurasi rata rata sebesar 83,10%.

Sign in / Sign up

Export Citation Format

Share Document