ANN

Setting

rm(list=ls(all=TRUE))
setwd('C:/Users/sitdo/Documents/GitHub/IBD-EDA/paper1/')

Loading Data

library(dplyr)

载入程辑包：‘dplyr’

The following objects are masked from ‘package:stats’:

    filter, lag

The following objects are masked from ‘package:base’:

    intersect, setdiff, setequal, union

data <- read.csv("./data_preprocessed/data.csv") %>% select(-1)

Installing Packages

library(neuralnet)

载入程辑包：‘neuralnet’

The following object is masked from ‘package:dplyr’:

    compute

Method I: Splitting Data

set.seed(123)
splitting_ratio <- 0.7

indices <- 1:nrow(data)
shuffled_indices <- sample(indices) 
train_size <- floor(splitting_ratio * length(indices))

train_indices <- shuffled_indices[1:train_size]
test_indices <- shuffled_indices[(train_size + 1):length(indices)]

train_data <- data[train_indices, ]
test_data <- data[test_indices, ]

Building Model

ann_formula <- as.formula("dod ~ .")
ann_model <- neuralnet(ann_formula,
                       data = train_data,
                       hidden = c(32, 16),
                       linear.output = FALSE,
                       act.fct = "logistic")

trained_model <- ann_model

Performance

predictions <- compute(trained_model, 
                       test_data[, -1])$net.result

Confusion Matrix

confusion_matrix <- table(
  as.numeric(test_data$dod), as.numeric(ifelse(predictions > 0.5, 1, 0))
)

TP <- confusion_matrix[1, 1]
TN <- confusion_matrix[2, 2]
FP <- confusion_matrix[2, 1]
FN <- confusion_matrix[1, 2]

## Calculate Accuracy
accuracy <- (TP + TN) / (TP + FP + TN + FN)
cat("Accuracy:", accuracy, "\n")

Accuracy: 0.8443526 

## Calculate Recall
recall <- TP / (TP + FN)
cat("Recall:", recall, "\n")

Recall: 0.9299674 

## Calculate Precision
precision <- TP / (TP + FP)
cat("Precision:", precision, "\n")

Precision: 0.8907956 

## Calculate Specificity
specificity <- TN / (TN + FP)
cat("Specificity:", specificity, "\n")

Specificity: 0.375 

## Calculate F1 Score
f1_score <- 2 * (precision * recall) / (precision + recall)
cat("F1 Score:", f1_score, "\n")

F1 Score: 0.9099602 

ROC Curve

library(pROC)

Type 'citation("pROC")' for a citation.

载入程辑包：‘pROC’

The following objects are masked from ‘package:stats’:

    cov, smooth, var

# Calculate ROC curve using the actual values and predictions
roc_obj <- roc(
  as.numeric(test_data$dod), predictions
)

Setting levels: control = 0, case = 1
Warning: Deprecated use a matrix as predictor. Unexpected results may be produced, please pass a numeric vector.Setting direction: controls < cases

# Plot the ROC curve
plot(
  roc_obj,
  col = "blue",
  main = "ROC Curve - ANN",
  legacy.axes = TRUE,
  print.auc = TRUE,
  print.thres = TRUE,
  grid = c(0.2, 0.2),
  grid.col = c("green", "orange")
)

Method II: Cross Validation

# Perform 10-fold cross-validation
num_folds <- 10
folds <- cut(seq(1, nrow(data)), breaks = num_folds, labels = FALSE)

# Create empty vectors to store the predictions and actual values
all_predictions <- vector()
all_actuals <- vector()

for (i in 1:num_folds) {
  # Split the data into training and test sets for the current fold
  train_data <- data[folds != i, ]
  test_data <- data[folds == i, ]
  
  # ANN
  ann_formula <- as.formula("dod ~ .")
  ann_model <- neuralnet(ann_formula, 
                         data = train_data, 
                         hidden = c(32, 16), 
                         linear.output = FALSE, 
                         act.fct = "logistic")
  trained_model <- ann_model
  
  # Make predictions on the test set
  predictions <- compute(trained_model, 
                         test_data[, -1])$net.result
  
  # Append the predictions and actual values to the vectors
  all_predictions <- c(all_predictions, predictions)
  all_actuals <- c(all_actuals, test_data[, 1])
}

Performance

Confusion Matrix

confusion_matrix <- table(
  as.numeric(all_actuals), 
  as.numeric(ifelse(all_predictions > 0.5, 1, 0))
)

TP <- confusion_matrix[1, 1]
TN <- confusion_matrix[2, 2]
FP <- confusion_matrix[2, 1]
FN <- confusion_matrix[1, 2]

## Calculate Accuracy
accuracy <- (TP + TN) / (TP + FP + TN + FN)
cat("Accuracy:", accuracy, "\n")

Accuracy: 0.836988 

## Calculate Recall
recall <- TP / (TP + FN)
cat("Recall:", recall, "\n")

Recall: 0.9170349 

## Calculate Precision
precision <- TP / (TP + FP)
cat("Precision:", precision, "\n")

Precision: 0.8924988 

## Calculate Specificity
specificity <- TN / (TN + FP)
cat("Specificity:", specificity, "\n")

Specificity: 0.4078947 

## Calculate F1 Score
f1_score <- 2 * (precision * recall) / (precision + recall)
cat("F1 Score:", f1_score, "\n")

F1 Score: 0.9046005 

ROC Curve

# Calculate ROC curve using the actual values and predictions
roc_obj <- roc(
  as.numeric(all_actuals), all_predictions
)

Setting levels: control = 0, case = 1
Setting direction: controls < cases

# Plot the ROC curve
plot(
  roc_obj,
  col = "blue",
  main = "ROC Curve - ANN (Cross Validation)",
  legacy.axes = TRUE,
  print.auc = TRUE,
  print.thres = TRUE,
  grid = c(0.2, 0.2),
  grid.col = c("green", "orange")
)