scholarly journals On the use and abuse of principal component analysis in biomechanics

2019 ◽  
Author(s):  
Daniel Cleather
Keyword(s):  
Principal Component Analysis ◽  
Data Reduction ◽  
Principal Component ◽  
Component Analysis ◽  
Reduction Technique ◽  
The Other ◽  
Philosophical Basis ◽  
Technical Report ◽  
Data Reduction Technique

Principal component analysis (PCA) is a data reduction technique that is increasingly popular within biomechanics. However, a majority of the literature that has used PCA has employed a methodology that is less strongly aligned to the philosophical basis of the technique, and that may not yield the most practically interpretable results. In this technical report I exemplify the two approaches to PCA that have been used in the biomechanics literature, and argue that one method may be superior to the other for the majority of biomechanical applications.

Chemical Structure-Odor Correlation in Series of Synthetic Methylene Interrupted n-Nonadien-1-ols

1996 ◽  
Vol 51 (11-12) ◽  
pp. 841-848 ◽  
Author(s):  
Yasunobu Sakoda ◽  
Kenji Matsui ◽  
Yoshihiko Akakabe ◽  
Jun Suzuki ◽  
Akikazu Hatanaka ◽  
...  
Keyword(s):  
Principal Component Analysis ◽  
Double Bond ◽  
Principal Components ◽  
Chemical Structure ◽  
Principal Component ◽  
Component Analysis ◽  
The Other ◽  
Analysis Method ◽  
In Series ◽  
Natural Characteristic

Abstract Chemical structure-odor correlations in the isomers of n-C9-methylene interrupted dienols were explored using synthetic nine isomers of these alcohols. The synthetic dienols were purified by recrystallization or column chromatography of their 3,5-dinitrobenzoate de­ rivatives. Chemical structure-odor correlations in all the isomers of the purified n-nonadien-1-ols were analyzed by treating the data obtained statistically with the principal component analysis method (Sakoda et al., 1995; Cramer et al., 1988) in comparison with those of n-nonen-1-ols. The odor profiles of the n-nonadien-1-ols were attributable largely to the geometries of the isomers, compared with n-nonen -1-ols (Sakoda et al., 1995). With the principal component analysis, the odor profiles of the series of the dienols were successfully integrated into the first and the second principal components. The first component (PC 1) consisted of combined characteristics of fruity, fresh, sweet, herbal and oily-fatty, and the second component (PC 2) leaf or grassy and vegetable-like. Of the methylene interrupted dienol isomers, (2E ,6Z)-and (3Z,6Z)-nonadien-1-ols which are natural products and have (6Z) in the same, deviated markedly from the other isomers as seen in (6Z)-nonen -1-ol of n-nonen-1-ols. That suggests that the double bond of (ω3Z) was an important factor for natural characteristic odor.

ROBUST ADAPTED PRINCIPAL COMPONENT ANALYSIS FOR FACE RECOGNITION

2009 ◽  
Vol 23 (03) ◽  
pp. 491-520 ◽  
Author(s):  
SHAOKANG CHEN ◽  
BRIAN C. LOVELL ◽  
TING SHAN
Keyword(s):  
Principal Component Analysis ◽  
Recognition Rate ◽  
Principal Component ◽  
Component Analysis ◽  
Face Image ◽  
The Other ◽  
Appearance Model ◽  
Lighting Conditions ◽  
Highly Sensitive ◽  
Gallery Image

Recognizing faces with uncontrolled pose, illumination, and expression is a challenging task due to the fact that features insensitive to one variation may be highly sensitive to the other variations. Existing techniques dealing with just one of these variations are very often unable to cope with the other variations. The problem is even more difficult in applications where only one gallery image per person is available. In this paper, we describe a recognition method, Adapted Principal Component Analysis (APCA), that can simultaneously deal with large variations in both illumination and facial expression using only a single gallery image per person. We have now extended this method to handle head pose variations in two steps. The first step is to apply an Active Appearance Model (AAM) to the non-frontal face image to construct a synthesized frontal face image. The second is to use APCA for classification robust to lighting and pose. The proposed technique is evaluated on three public face databases — Asian Face, Yale Face, and FERET Database — with images under different lighting conditions, facial expressions, and head poses. Experimental results show that our method performs much better than other recognition methods including PCA, FLD, PRM and LTP. More specifically, we show that by using AAM for frontal face synthesis from high pose angle faces, the recognition rate of our APCA method increases by up to a factor of 4.

scholarly journals The earliest record of fossil solid-wood-borer larvae—immature beetles in 99 million-year-old Myanmar amber

2021 ◽  
Vol 4 (4) ◽  
Author(s):  
CAROLIN HAUG ◽  
GIDEON T. HAUG ◽  
ANA ZIPPEL ◽  
SERITA VAN DER WAL ◽  
JOACHIM T. HAUG
Keyword(s):  
Principal Component Analysis ◽  
Shape Analysis ◽  
Fossil Record ◽  
Fourier Transformation ◽  
Principal Component ◽  
Component Analysis ◽  
Solid Wood ◽  
The Body ◽  
The Other ◽  
Wood Borer

Interactions between animals and plants represent an important driver of evolution. Especially the group Insecta has an enormous impact on plants, e.g., by consuming them. Among beetles, the larvae of different groups (Buprestidae, Cerambycidae, partly Eucnemidae) bore into wood and are therefore called wood-borer larvae or borers. While adults of these beetle groups are well known in the fossil record, there are barely any fossils of the corresponding larvae. We report here four new wood-borer larvae from Cretaceous Kachin amber (Myanmar, ca. 99 Ma). To compare these fossils with extant wood-borer larvae, we reconstructed the body outline and performed shape analysis via elliptic Fourier transformation and a subsequent principal component analysis. Two of the new larvae plot closely together and clearly in the same area as modern representatives of Buprestidae. As they furthermore lack legs, they are interpreted as representatives of Buprestidae. The other two new larvae possess legs and plot far apart from each other. They are more difficult to interpret; they may represent larvae of early offshoots of either Cerambycidae or Buprestidae, which still retain longer legs. These findings represent the earliest fossil record of larvae of Buprestidae and possibly of Cerambycidae known to date.

scholarly journals Morphological Variability and Storage Root Productivity of Some Sweet Potato (Ipomoea Batatas (L.) Lam) Genotypes in An Ultisol

2021 ◽  
Vol 2 (6) ◽  
Author(s):  
Gamaliel I. Harry ◽  
Joseph I. Ulasi
Keyword(s):  
Principal Component Analysis ◽  
Sweet Potato ◽  
Ipomoea Batatas ◽  
Principal Component ◽  
Component Analysis ◽  
The Other ◽  
Storage Root ◽  
Root Yield ◽  
Cropping Seasons ◽  
And Storage

Ten sweet potato (Ipomoea batatas (L.) Lam) genotypes sourced from National Root Crops Research Institute, Umudike were evaluated under rainfed condition in 2020 and 2021 cropping seasons at the Teaching and Research Farm of the University of Uyo, Uyo, Akwa Ibom State to ascertain variability among ten sweet potato genotypes and identify traits which are positively and significantly associated with yield and also identify genotypes with high yield potential for cultivation on an ultisol of Akwa Ibom State, Nigeria. The ten genotypes: TIS87/0087, Naspoy-12, Umuspo-4, Umuspo-1, Naspoy-11, Lourdes, Erica, Delvia, Ex-Igbariam and Umuspo-3 were used as treatments and the experiment was laid out in a randomized complete block design with three replications. Data collected were subjected to analysis of variance, correlation and principal component analysis. The genotype differs significantly (P≤ 0.05) for number of marketable roots, weight of marketable roots and fresh roots yield. UMUSPO-3 was superior over all the other genotypes for the following character; number of marketable roots, weight of marketable root yield and fresh root yield. Umuspo-3 produced the highest storage root yield (28.78t/ha, 27.09t/ha) in 2020 and 2021 cropping seasons, respectively. The result of the correlation analysis also revealed that vine length, number of marketable roots, weight of marketable were highly significantly and positively (P<0.01) correlated with fresh root yield. Principal component analysis (PCA) had four main principal components explaining 81.55% of the total variation with number of marketable roots, weight of marketable tuber and storage root yield contributing the most to the first PCA. Umuspo-3 outperformed the other nine sweet potato genotypes in yield and yield related characters. Therefore, Umuspo-3 been a high yielding genotype adaptable to Uyo agro-ecology, could be recommended to sweet potato growers for fresh storage root production.

scholarly journals Rhamnella brachycarpa (Rhamnaceae), a new species from Hainan Island, China

PhytoKeys ◽  
2019 ◽  
Vol 132 ◽  
pp. 19-29
Author(s):  
Zhiqiang Lu ◽  
Yongshuai Sun
Keyword(s):  
Principal Component Analysis ◽  
New Species ◽  
Principal Component ◽  
Woody Species ◽  
Hainan Island ◽  
Component Analysis ◽  
Morphological Characters ◽  
The Other ◽  
A New Species

Rhamnella brachycarpa Z. Qiang Lu &amp; Y. Shuai Sun, a new evergreen woody species from Hainan Island, is described and illustrated. The specimens of this new species have previously been identified and placed under R. rubrinervis (H. Lév.) Rehder, with which it shares evergreen leaves, erect and climbing habits and axillary flowering branches with bracteole leaves. However, the specimens from three distinct Hainan populations significantly differ from those of R. rubrinervis from other regions with smaller length to width ratios of leaves, fruit and seeds, smaller sizes of fruit and seeds and mucronate seed apices. Principal Component Analysis of the closely related taxa, based on multiple morphological characters, further recognised two separated groups. One of them comprises R. tonkinensis and R. rubrinervis, the other merely includes all individuals from these distinct Hainan populations. Therefore, R. brachycarpa, based on these distinct Hainan populations, is here erected as a new species, distinctly different from its published relatives.

scholarly journals Clustering of Cardiovascular Disease Patients Using Data Mining Techniques with Principal Component Analysis and K-Medoids Clustering of Cardiovascular Disease Patients Using Data Mining Techniques with Principal Component Analysis and K-Medoids

2020 ◽  
Author(s):  
Edy Irwansyah ◽  
Ebiet Salim Pratama ◽  
Margaretha Ohyver
Keyword(s):  
Data Mining ◽  
Cardiovascular Disease ◽  
Principal Component Analysis ◽  
Data Reduction ◽  
Clustering Algorithm ◽  
Principal Component ◽  
Component Analysis ◽  
Data Mining Techniques ◽  
The World ◽  
Using Data

Cardiovascular disease is the number one cause of death in the world and Quoting from WHO, around 31% of deaths in the world are caused by cardiovascular diseases and more than 75% of deaths occur in developing countries. The results of patients with cardiovascular disease produce many medical records that can be used for further patient management. This study aims to develop a method of data mining by grouping patients with cardiovascular disease to determine the level of patient complications in the two clusters. The method applied is principal component analysis (PCA) which aims to reduce the dimensions of the large data available and the techniques of data mining in the form of cluster analysis which implements the K-Medoids algorithm. The results of data reduction with PCA resulted in five new components with a cumulative proportion variance of 0.8311. The five new components are implemented for cluster formation using the K-Medoids algorithm which results in the form of two clusters with a silhouette coefficient of 0.35. Combination of techniques of Data reduction by PCA and the application of the K-Medoids clustering algorithm are new ways for grouping data of patients with cardiovascular disease based on the level of patient complications in each cluster of data generated.

Beyond principal component analysis: Canonical component analysis for data reduction in classification of EPs

1984 ◽  
Vol 15 (2) ◽  
pp. 93-111 ◽  
Author(s):  
József Vitrai ◽  
Pál Czobor ◽  
Gábor Simon ◽  
László Varga ◽  
Sándor Marosfi
Keyword(s):  
Principal Component Analysis ◽  
Data Reduction ◽  
Principal Component ◽  
Component Analysis

A Subblock Matrix Approach to Data-Reduction in Gait Recognition

2011 ◽  
Vol 181-182 ◽  
pp. 902-907
Author(s):  
Xian Ye Ben ◽  
Shi An ◽  
Jian Wang ◽  
Hai Yang Liu
Keyword(s):  
Principal Component Analysis ◽  
Data Reduction ◽  
Nearest Neighbor ◽  
Recognition Accuracy ◽  
Gait Recognition ◽  
Principal Component ◽  
Component Analysis ◽  
Two Dimensional ◽  
Redundant Data ◽  
Novel Method

We propose a novel method for data reduction in gait recognition, called Subblock Complete Two Dimensional Principal Component Analysis (SbC2DPCA). GEIs were divided into smaller sub-images and redundant subblocks were adaptively removed. Complete Two Dimensional Principal Component Analysis (C2DPCA) was then applied to every sub-image directly, to acquire a set of projection sub-vectors for both row and column directions and these were synthesized into whole features for subsequent classification using nearest neighbor classifier. We evaluate the proposed gait recognition method on the CASIA gait database. The experimental results and analysis show the recognition accuracy of SbC2DPCA to be superior to C2DPCA, with C2DPCA being a special case of SbC2DPCA. The novelty of the proposed method lies in the adaptive removal of redundant data while extracting local features. This translates to data reduction with very minimal loss of information, as demonstrated by the remarkable recognition accuracy when subjects change clothing or have a backpack.

Sign in / Sign up

Export Citation Format

Share Document