Yuqin-wang123
sweet
Recently Published
Plot
# ====================================================
# Figure 1: Technological Evolution Curve (2016-2030)
# ====================================================
# 1. 检查并安装必要的包
required_packages <- c("ggplot2", "dplyr", "tidyr", "scales")
for(pkg in required_packages) {
if(!require(pkg, character.only = TRUE)) {
install.packages(pkg)
library(pkg, character.only = TRUE)
}
}
# 2. 创建数据框
df <- data.frame(
Year = 2016:2030,
EI_Score = c(0.32, 0.36, 0.41, 0.45, 0.52, 0.58, 0.65, 0.71, 0.82, 0.94, 0.97, 0.99, 1.01, 1.02, 1.03),
Accuracy = c(75, 77, 80, 82, 86, 88, 90, 92, 94, 95, 96, 97, 98, 98.5, 98.5),
Type = c(rep("Actual", 10), rep("Predicted", 5))
)
# 3. 创建区域数据框用于背景色
regions <- data.frame(
xmin = c(2016, 2018.5, 2020.5, 2022.5, 2024.5),
xmax = c(2018.5, 2020.5, 2022.5, 2024.5, 2030.5),
Era = c("Early CNNs", "Hybrid Models", "Transformer Era",
"Personalization Era", "Clinical Translation Era")
)
# 4. 创建标注数据框
annotations <- data.frame(
Year = c(2020, 2021, 2023),
EI = c(0.58, 0.65, 0.71),
EI_label = c(0.65, 0.72, 0.78),
Label = c("ViT (2020)", "MAE (2021)", "DINOv2 (2023)")
)
# 5. 分割数据为实际值和预测值
df_actual <- df[1:10, ]
df_pred <- df[10:15, ]
# 6. 使用ggplot2创建图形
p <- ggplot() +
# 添加背景区域
geom_rect(data = regions,
aes(xmin = xmin, xmax = xmax, ymin = -Inf, ymax = Inf, fill = Era),
alpha = 0.2, inherit.aes = FALSE) +
# 添加EI曲线 - 实际值
geom_line(data = df_actual, aes(x = Year, y = EI_Score, color = "EI Score"),
linetype = "solid", size = 1) +
geom_point(data = df_actual, aes(x = Year, y = EI_Score, color = "EI Score"),
shape = 16, size = 3) +
# 添加EI曲线 - 预测值
geom_line(data = df_pred, aes(x = Year, y = EI_Score, color = "EI Score"),
linetype = "dashed", size = 1) +
geom_point(data = df_pred, aes(x = Year, y = EI_Score, color = "EI Score"),
shape = 1, size = 3) +
# 添加Accuracy曲线 - 实际值
geom_line(data = df_actual, aes(x = Year, y = Accuracy/83.33, color = "Accuracy"),
linetype = "solid", size = 1) +
geom_point(data = df_actual, aes(x = Year, y = Accuracy/83.33, color = "Accuracy"),
shape = 15, size = 3) +
# 添加Accuracy曲线 - 预测值
geom_line(data = df_pred, aes(x = Year, y = Accuracy/83.33, color = "Accuracy"),
linetype = "dashed", size = 1) +
geom_point(data = df_pred, aes(x = Year, y = Accuracy/83.33, color = "Accuracy"),
shape = 0, size = 3) +
# 添加垂直线
geom_vline(xintercept = 2025, linetype = "dashed", color = "black", alpha = 0.5) +
# 添加标注
geom_segment(data = annotations,
aes(x = Year, xend = Year, y = EI, yend = EI_label),
arrow = arrow(length = unit(0.2, "cm")), color = "black") +
geom_text(data = annotations,
aes(x = Year, y = EI_label + 0.02, label = Label),
size = 3, hjust = 0.5) +
# 添加区域文本标签
geom_text(data = data.frame(x = c(2017.25, 2019.5, 2021.5, 2023.5, 2027.5),
y = rep(1.15, 5),
label = c("Early CNNs", "Hybrid Models", "Transformer Era",
"Personalization", "Clinical Translation")),
aes(x = x, y = y, label = label), size = 3.5, fontface = "italic") +
# 设置坐标轴
scale_x_continuous(breaks = seq(2016, 2030, 2), limits = c(2016, 2030)) +
scale_y_continuous(
name = "Evolution Index (EI)",
sec.axis = sec_axis(~.*83.33, name = "Accuracy (%)", breaks = seq(70, 100, 5)),
limits = c(0, 1.2),
breaks = seq(0, 1.2, 0.2)
) +
# 设置颜色
scale_color_manual(
name = "",
values = c("EI Score" = "#2563EB", "Accuracy" = "#DC2626"),
labels = c("EI Score (Actual)", "Accuracy (Actual)")
) +
# 设置填充色
scale_fill_manual(
name = "Technological Eras",
values = c("Early CNNs" = "gray80",
"Hybrid Models" = "lightblue",
"Transformer Era" = "lightgreen",
"Personalization Era" = "lightyellow",
"Clinical Translation Era" = "orange")
) +
# 添加主题设置
theme_minimal() +
theme(
plot.title = element_text(size = 14, face = "bold", hjust = 0.5, margin = margin(b = 20)),
axis.title.x = element_text(size = 12, face = "bold"),
axis.title.y.left = element_text(color = "#2563EB", size = 12, face = "bold"),
axis.title.y.right = element_text(color = "#DC2626", size = 12, face = "bold"),
axis.text.y.left = element_text(color = "#2563EB"),
axis.text.y.right = element_text(color = "#DC2626"),
legend.position = "bottom",
legend.box = "vertical",
legend.margin = margin(t = 10),
panel.grid.minor = element_blank(),
panel.grid.major = element_line(color = "gray90"),
plot.margin = margin(1, 1, 1, 1, "cm")
) +
# 添加标题
labs(
title = "Figure 1: Technological Evolution of Pain Expression Recognition (2016-2030)",
x = "Year",
caption = "Predicted values (2025-2030) shown with dashed lines. Actual data (2016-2025) shown with solid lines. Predictions generated from exponential growth model (α=0.25, β=0.15, γ=0.12, δ=0.08, ω=2.1)."
) +
# 添加图例说明
annotate("text", x = 2027, y = 0.2, label = "Solid: Actual\nDashed: Predicted",
size = 3, hjust = 0, fontface = "italic")
# 7. 显示图形
print(p)
# 8. 保存为高分辨率PNG
ggsave("figure1_evolution_curve.png", plot = p, width = 12, height = 6, dpi = 600, bg = "white")
# 9. 保存为SVG矢量格式（用于出版物）
ggsave("figure1_evolution_curve.svg", plot = p, width = 12, height = 6, bg = "white")
Plot
# ====================================================
# Figure 1: Technological Evolution Curve (2016-2030)
# ====================================================
# 1. 检查并安装必要的包
required_packages <- c("ggplot2", "dplyr", "tidyr", "scales")
for(pkg in required_packages) {
if(!require(pkg, character.only = TRUE)) {
install.packages(pkg)
library(pkg, character.only = TRUE)
}
}
# 2. 创建数据框
df <- data.frame(
Year = 2016:2030,
EI_Score = c(0.32, 0.36, 0.41, 0.45, 0.52, 0.58, 0.65, 0.71, 0.82, 0.94, 0.97, 0.99, 1.01, 1.02, 1.03),
Accuracy = c(75, 77, 80, 82, 86, 88, 90, 92, 94, 95, 96, 97, 98, 98.5, 98.5),
Type = c(rep("Actual", 10), rep("Predicted", 5))
)
# 3. 创建区域数据框用于背景色
regions <- data.frame(
xmin = c(2016, 2018.5, 2020.5, 2022.5, 2024.5),
xmax = c(2018.5, 2020.5, 2022.5, 2024.5, 2030.5),
Era = c("Early CNNs", "Hybrid Models", "Transformer Era",
"Personalization Era", "Clinical Translation Era")
)
# 4. 创建标注数据框
annotations <- data.frame(
Year = c(2020, 2021, 2023),
EI = c(0.58, 0.65, 0.71),
EI_label = c(0.65, 0.72, 0.78),
Label = c("ViT (2020)", "MAE (2021)", "DINOv2 (2023)")
)
# 5. 分割数据为实际值和预测值
df_actual <- df[1:10, ]
df_pred <- df[10:15, ]
# 6. 使用ggplot2创建图形
p <- ggplot() +
# 添加背景区域
geom_rect(data = regions,
aes(xmin = xmin, xmax = xmax, ymin = -Inf, ymax = Inf, fill = Era),
alpha = 0.2, inherit.aes = FALSE) +
# 添加EI曲线 - 实际值
geom_line(data = df_actual, aes(x = Year, y = EI_Score, color = "EI Score"),
linetype = "solid", size = 1) +
geom_point(data = df_actual, aes(x = Year, y = EI_Score, color = "EI Score"),
shape = 16, size = 3) +
# 添加EI曲线 - 预测值
geom_line(data = df_pred, aes(x = Year, y = EI_Score, color = "EI Score"),
linetype = "dashed", size = 1) +
geom_point(data = df_pred, aes(x = Year, y = EI_Score, color = "EI Score"),
shape = 1, size = 3) +
# 添加Accuracy曲线 - 实际值
geom_line(data = df_actual, aes(x = Year, y = Accuracy/83.33, color = "Accuracy"),
linetype = "solid", size = 1) +
geom_point(data = df_actual, aes(x = Year, y = Accuracy/83.33, color = "Accuracy"),
shape = 15, size = 3) +
# 添加Accuracy曲线 - 预测值
geom_line(data = df_pred, aes(x = Year, y = Accuracy/83.33, color = "Accuracy"),
linetype = "dashed", size = 1) +
geom_point(data = df_pred, aes(x = Year, y = Accuracy/83.33, color = "Accuracy"),
shape = 0, size = 3) +
# 添加垂直线
geom_vline(xintercept = 2025, linetype = "dashed", color = "black", alpha = 0.5) +
# 添加标注
geom_segment(data = annotations,
aes(x = Year, xend = Year, y = EI, yend = EI_label),
arrow = arrow(length = unit(0.2, "cm")), color = "black") +
geom_text(data = annotations,
aes(x = Year, y = EI_label + 0.02, label = Label),
size = 3, hjust = 0.5) +
# 添加区域文本标签
geom_text(data = data.frame(x = c(2017.25, 2019.5, 2021.5, 2023.5, 2027.5),
y = rep(1.15, 5),
label = c("Early CNNs", "Hybrid Models", "Transformer Era",
"Personalization", "Clinical Translation")),
aes(x = x, y = y, label = label), size = 3.5, fontface = "italic") +
# 设置坐标轴
scale_x_continuous(breaks = seq(2016, 2030, 2), limits = c(2016, 2030)) +
scale_y_continuous(
name = "Evolution Index (EI)",
sec.axis = sec_axis(~.*83.33, name = "Accuracy (%)", breaks = seq(70, 100, 5)),
limits = c(0, 1.2),
breaks = seq(0, 1.2, 0.2)
) +
# 设置颜色
scale_color_manual(
name = "",
values = c("EI Score" = "#2563EB", "Accuracy" = "#DC2626"),
labels = c("EI Score (Actual)", "Accuracy (Actual)")
) +
# 设置填充色
scale_fill_manual(
name = "Technological Eras",
values = c("Early CNNs" = "gray80",
"Hybrid Models" = "lightblue",
"Transformer Era" = "lightgreen",
"Personalization Era" = "lightyellow",
"Clinical Translation Era" = "orange")
) +
# 添加主题设置
theme_minimal() +
theme(
plot.title = element_text(size = 14, face = "bold", hjust = 0.5, margin = margin(b = 20)),
axis.title.x = element_text(size = 12, face = "bold"),
axis.title.y.left = element_text(color = "#2563EB", size = 12, face = "bold"),
axis.title.y.right = element_text(color = "#DC2626", size = 12, face = "bold"),
axis.text.y.left = element_text(color = "#2563EB"),
axis.text.y.right = element_text(color = "#DC2626"),
legend.position = "bottom",
legend.box = "vertical",
legend.margin = margin(t = 10),
panel.grid.minor = element_blank(),
panel.grid.major = element_line(color = "gray90"),
plot.margin = margin(1, 1, 1, 1, "cm")
) +
# 添加标题
labs(
title = "Figure 1: Technological Evolution of Pain Expression Recognition (2016-2030)",
x = "Year",
caption = "Predicted values (2025-2030) shown with dashed lines. Actual data (2016-2025) shown with solid lines. Predictions generated from exponential growth model (α=0.25, β=0.15, γ=0.12, δ=0.08, ω=2.1)."
) +
# 添加图例说明
annotate("text", x = 2027, y = 0.2, label = "Solid: Actual\nDashed: Predicted",
size = 3, hjust = 0, fontface = "italic")
# 7. 显示图形
print(p)
# 8. 保存为高分辨率PNG
ggsave("figure1_evolution_curve.png", plot = p, width = 12, height = 6, dpi = 600, bg = "white")
# 9. 保存为SVG矢量格式（用于出版物）
ggsave("figure1_evolution_curve.svg", plot = p, width = 12, height = 6, bg = "white")