Generalized Principal Component Analysis

Kong, Xiangyu; Hu, Changhua; Duan, Zhansheng

doi:10.1007/978-981-10-2915-8_7

Cited by 13 publications

(7 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The matrix of partial correlations, Kaiser Statistic for sampling adequacy (MSA) was used to determine the degree of interrelations between variables and adequacy for use in principal component analyses. Principal components were chosen based on Kaiser's eigenvalue rule which states that only principal components with eigenvalues greater than one should be considered (Kong et al, 2017). The principal components were rotated using varimax rotation.…”

Section: Statistical Analysesmentioning

confidence: 99%

Heat tolerance in Mashona beef cows in semi-arid rangelands: does conformation matter?

MATOPE

Zindove

DHLIWAYO

et al. 2023

aas

View full text Add to dashboard Cite

High temperatures and frequent heat waves raise concerns about heat stress in cattle in grass-based systems, especially in arid and semiarid areas. This study analysed the relationship between conformation traits and physiological parameters associated with heat stress in Mashona cattle. A total of 200 records from fifty cows were used to study the relationships between seven conformation traits and physiological parameters associated with heat stress. Body conformation traits were categorised into three principal components related to body capacity (body depth, flank circumference, chest girth), frame size (stature and body length), and loose skin fold (navel height and dewlap size). As the size of abdominopelvic and thoracic cavities increased, respiratory rate, heart rate, and rectal temperature decreased significantly, while blood triiodothyronine concentration increased. Cattle with deeper bodies, larger flanks, and larger chest girths had significantly lower heart rate, respiratory rate, and rectal temperature but higher blood triiodothyronine concentration than cattle with shallower bodies, smaller flanks, and smaller chest girths. Respiratory rate increased with increasing frame size. Large-framed cattle had significantly higher respiratory rate and lower blood thyroxine concentration. Small-framed cattle with larger chest girth, larger dewlap, and navel farther from the ground surface are better adapted to higher ambient temperatures.

show abstract

Section: Statistical Analysesmentioning

confidence: 99%

Heat tolerance in Mashona beef cows in semi-arid rangelands: does conformation matter?

MATOPE

Zindove

DHLIWAYO

et al. 2023

aas

View full text Add to dashboard Cite

show abstract

“…and as a result variance explained by each principal will be smaller as components increases (John Lu, 2010;Kong et al, 2017).…”

Section: Principal Component Analysismentioning

confidence: 99%

The Impacts of Emerging Mobility Options and Vehicle Technologies on Travel Behavior

Cutr¹

2020

View full text Add to dashboard Cite

This report presents a study that investigated potential travel behavior changes in light of automated, connected, electric, and shared-use vehicle (ACES) technologies. Three main aspects of choice behavior were investigated: AV adoption and willingness to pay (WTP), shared mobility adoption, and mode choice. Particularly, this study focuses on exploring the roles of attitudes in individuals' travel choice behavior. Data collected through a stated preference (SP) survey were used for this study. The survey included a series of attitude-related questions that cover various aspects of user attitudes, which include general mobility preferences, perceived benefits and concerns of shared mobility, reasons against or for private ownership, and motivations for and desired features of AVs. Various modeling techniques were employed to identify influential factors and examine the impacts of attitudes, including error component models, structural equations model, and support vector machine method. The models identified various attitudes that played significant roles in individuals' choice behavior. These include joy of driving, technology-savviness, choice reasoning, trust issues, data privacy concerns, favor for private-vehicle utility, on-demand services, green travel preferences, and desire for efficiency and technology, etc. Model results showed that attitudes played important roles in shaping travelers' choice behavior. Incorporating these factors improved the model performance and prediction accuracy of travel behavior models, which will lead to a more reliable assessment of the likelihood and magnitude of behavioral shifts toward future mobility options. This study provides useful and meaningful insights into users' attitudes and perceptions toward ACES technologies and how these attitudes and other contributing factors may influence travelers' choice behavior. Recognizing that the market will not react homogeneously toward new technologies, the study results contribute to a better understanding of user acceptance and adoption of emerging mobility options and better assessment of their potential impacts. The findings could be helpful for planners and service providers to better plan for and address the needs and concerns of travelers.

show abstract

“…To illustrate the benefits of the APR approach for GLM-PCA, we analyzed two scRNA-seq data sets: 7,193 cells from the tracheal epithelium in wild-type mice (Montoro et al, 2018) and 68,579 cells from peripheral blood mononuclear cells ("68k PBMC") (Zheng et al, 2017). We compared APR, implemented in the R package fastglmpca, to two existing software implementations in R: the Iterative Reweighted SVD (IRSVD) algorithm implemented in the R package scGBM (Miller and Carter, 2020;Nicol and Miller, 2023); and the adaptive stochastic gradient algorithm ("AvaGrad") implemented in the R package glmpca (Savarese et al, 2021;Townes, 2019;.…”

mentioning

confidence: 99%

Accelerated dimensionality reduction of single-cell RNA sequencing data with fastglmpca

Weine,

Carbonetto,

Stephens

2024

Preprint

View full text Add to dashboard Cite

Motivated by theoretical and practical issues that arise when applying Principal Components Analysis (PCA) to count data, Townes et al introduced ''Poisson GLM-PCA'', a variation of PCA adapted to count data, as a tool for dimensionality reduction of single-cell RNA sequencing (RNA-seq) data. However, fitting GLM-PCA is computationally challenging. Here we study this problem, and show that a simple algorithm, which we call ``Alternating Poisson Regression'' (APR), produces better quality fits, and in less time, than existing algorithms. APR is also memory-efficient, and lends itself to parallel implementation on multi-core processors, both of which are helpful for handling large single-cell RNA-seq data sets. We illustrate the benefits of this approach in two published single-cell RNA-seq data sets. The new algorithms are implemented in an R package, fastglmpca.

show abstract

Generalized Principal Component Analysis

Cited by 13 publications

References 48 publications

Heat tolerance in Mashona beef cows in semi-arid rangelands: does conformation matter?

Heat tolerance in Mashona beef cows in semi-arid rangelands: does conformation matter?

The Impacts of Emerging Mobility Options and Vehicle Technologies on Travel Behavior

Accelerated dimensionality reduction of single-cell RNA sequencing data with fastglmpca

Contact Info

Product

Resources

About