Package 'SOPC'

Heart failure

Description

Heart failure

Usage

data("Heart")

Format

A data frame with 299 observations on the following 13 variables.

age

a numeric vector

anaemia

a numeric vector

creatinine_phosphokinase

a numeric vector

diabetes

a numeric vector

ejection_fraction

a numeric vector

high_blood_pressure

a numeric vector

platelets

a numeric vector

serum_creatinine

a numeric vector

serum_sodium

a numeric vector

sex

a numeric vector

smoking

a numeric vector

time

a numeric vector

DEATH_EVENT

a numeric vector

Details

This dataset contains the medical records of 299 patients who had heart failure, collected during their follow-up period, where each patient profile has 13 clinical features.

Source

The Heart failure data set comes from the UCI database.

References

Davide Chicco, Giuseppe Jurman. (2020). Machine learning can predict survival of patients with heart failure from serum creatinine and ejection fraction alone. BMC Medical Informatics and Decision Making.

Examples

data(Heart)
## maybe str(Heart) ; plot(Heart) ...

---

Hugging

Description

The EMG Physical Action-Hugging data set.

Usage

data("Hugging")

Format

A data frame with 9752 observations on the following 8 variables.

A

a numeric vector

B

a numeric vector

C

a numeric vector

D

a numeric vector

E

a numeric vector

F

a numeric vector

G

a numeric vector

H

a numeric vector

Details

The data set is a body movement data set, including 10 normal and 10 aggressive body movements. The data frame with 9752 observations on the following 8 variables.

Source

The Hugging data set comes from the UCI database.

References

Demir et al. (2019). Surface emg signals and deep transfer learning-based physical action classification. Neural Computing and Applications.

Examples

data(Hugging)
## maybe str(Hugging) ; plot(Hugging) ...

---

The incremental principal component can handle online data sets with highly correlated.

Description

The incremental principal component can handle online data sets with highly correlated.

Usage

IPC(data, m, eta)

Arguments

data	is a highly correlated online data set
m	is the number of principal component
eta	is the proportion of online data to total data

Value

Ai,Di

Examples

IPC(data=PSA,m=3,eta=0.8)

---

The online principal component method refers to the IPC method with the best performance among the IPC, the PPC and the SAPC methods.

Description

The online principal component method refers to the IPC method with the best performance among the IPC, the PPC and the SAPC methods.

Usage

OPC(data, m, eta)

Arguments

data	is a highly correlated online data set
m	is the number of principal component
eta	is the proportion of online data to total data

Value

Ao,Do

Examples

OPC(data=PSA,m=3,eta=0.8)

---

The traditional principal component method. This method can estimate the eigen space of the data set.

Description

The traditional principal component method. This method can estimate the eigen space of the data set.

Usage

PC(data, m = m)

Arguments

data	is a highly correlated data set
m	is the number of principal component

Value

Ahat, Dhat

Examples

PC(data=PSA,m=3)

---

The perturbation principal component can handle online data sets with highly correlated.

Description

The perturbation principal component can handle online data sets with highly correlated.

Usage

PPC(data, m, eta)

Arguments

data	is a highly correlated online data set
m	is the number of principal component
eta	is the proportion of online data to total data

Value

Ap,Dp

Examples

PPC(data=PSA,m=3,eta=0.8)

---

Prostate Specific Antigen

Description

The prostate specific antigen (PSA) data set.

Usage

data("PSA")

Format

lcavol

a numeric vector

lweight

a numeric vector

age

a numeric vector

lbph

a numeric vector

svi

a numeric vector

lcp

a numeric vector

gleason

a numeric vector

pgg45

a numeric vector

lpsa

a numeric vector

Details

The data set comes from the prostate specific antigen (PSA) data of 96 patients collected by Stanford University Medical Center. These patients all underwent radical prostatectomy.

Source

The Stanford University Medical Center.

References

NA

Examples

data(PSA)
## maybe str(PSA) ; plot(PSA) ...

---

The stochastic approximation principal component can handle online data sets with highly correlated.

Description

The stochastic approximation principal component can handle online data sets with highly correlated.

Usage

SAPC(data, m, eta)

Arguments

data	is a highly correlated online data set
m	is the number of principal component
eta	is the proportion of online data to total data

Value

Asa,Dsa

Examples

SAPC(data=PSA,m=3,eta=0.8)

---

The sparse online principal component can not only process online data sets, but also obtain a sparse solution of online data sets.

Description

The sparse online principal component can not only process online data sets, but also obtain a sparse solution of online data sets.

Usage

SOPC(data, m, gamma, eta)

Arguments

data	is a highly correlated online data set
m	is the number of principal component
gamma	is a sparse parameter
eta	is the proportion of online data to total data

Value

Aso,Dso

Examples

require(elasticnet)
SOPC(PSA,3,0.03,0.6)

---

The sparse principal component can obtain sparse solutions of the eigenmatrix to better explain the relationship between principal components and original variables.

Description

The sparse principal component can obtain sparse solutions of the eigenmatrix to better explain the relationship between principal components and original variables.

Usage

SPC(data, m, gamma)

Arguments

data	is a highly correlated data set
m	is the number of principal component
gamma	is a sparse parameter

Value

As,Ds

Examples

require(elasticnet)
SPC(data=PSA,m=3,gamma=0.03)

---