alex/temperature-based-fertility-prediction-thesis
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fixes and improvements

Browse Source
This commit is contained in:
Alex Blank
2025-09-09 13:44:45 +00:00
parent bf2e79cc4c
commit e71f1cd2e3
10 changed files with 354 additions and 234 deletions
Download Patch File Download Diff File Expand all files Collapse all files
thesis/sections/appendix.tex
+13 -13
View File
@@ -2,12 +2,12 @@
\appendixpage % prints "Appendices"
\section{Supplementary Results: Prediction of Ovulation-Over Indicator}\label{sec:appendix_ov_over_results}
\section{Supplementary Results: Prediction of OV-over Indicator}\label{sec:appendix_ov_over_results}
\subsection{Comparative Study of Model Architectures and Parameters}\label{subsec:appendix_ov_over_architecture_results}
We evaluate prediction of a binary indicator denoting whether ovulation has already occurred.
We examine the influence of input window length, input resolution, and model capacity.
I will evaluate prediction of a binary indicator denoting whether ovulation has already occurred and
examine the influence of input window length, input resolution, and model capacity.
\paragraph{Impact of input window length.}
For predicting whether ovulation has occurred (OV-over),
@@ -57,7 +57,7 @@ See Table~\ref{tab:ovover_windows_compact_mse} for a summary.
\end{table}
\paragraph{Impact of input resolution.}
Fixing the input window to 20 days, we compare input resolutions for LSTM and Transformer models.
Fixing the input window to 20 days, I have compared input resolutions for LSTM and Transformer models.
For the \textbf{LSTM}, the lowest overall MSE (0.0633) occurs at 24/day,
with best before-OV and after-OV MSEs at 12/day (0.0212) and 48/day (0.0550), respectively.
@@ -96,7 +96,7 @@ full resolution grids are in Appendix Table~\ref{tab:ov_over_results_by_resoluti
\end{table}
\paragraph{Impact of model parameters.}
Using fixed input settings (160 days at 12/day for LSTM/Transformer; 40 days for convolutional models), we evaluate model scaling.
Using fixed input settings (160 days at 12/day for LSTM/Transformer; 40 days for convolutional models), I have evaluated model scaling.
The \textbf{Transformer} achieves the lowest overall (0.0543) and after-ovulation MSE (0.0410) at a large configuration (512×8×8).
Before-OV MSE is lowest at 256×4×4 (0.0293).
@@ -177,7 +177,7 @@ full comparisons are included in Appendix Tables~\ref{tab:ov_over_results_by_mod
User Mean Baseline & 0.180702 & 0.088884 & 0.217144 \\
\bottomrule
\end{tabularx}
\caption{MSEs for ovulation-over target across different model architectures for regular and irregular cycle groups. Bold values denote the best scores per column.}
\caption{MSEs for OV-over target across different model architectures for regular and irregular cycle groups. Bold values denote the best scores per column.}
\label{tab:ov_over_mse_regular_irregular}
\end{table}
@@ -447,7 +447,7 @@ The full table with MSE and MAE for all models can be found in the appendix, Tab
\bottomrule
\end{tabularx}
\caption{Evaluation Metrics for the Ovulation-Over Target across Different Model Architectures and Input Lengths at a fixed Input Resolution of 12 Values per Day.
\caption{Evaluation Metrics for the OV-over Target across Different Model Architectures and Input Lengths at a fixed Input Resolution of 12 Values per Day.
\underline{Underlined} values represent the best value for each metric within a model.
\textbf{\underline{Bold + Underlined}} values represent the global best values across all models for a given metric.}
\label{tab:ov_over_results_by_window_length}
@@ -486,7 +486,7 @@ The full table with MSE and MAE for all models can be found in the appendix, Tab
288 & 0.1319 & 0.1879 & 0.1097 & 0.0617 & 0.0769 & \underline{0.0578}\\
\bottomrule
\end{tabularx}
\caption{Evaluation Metrics for the Ovulation-Over Target across Different Model Architectures and Input Resolutions at a fixed Input-Window-Length of 20 Days.
\caption{Evaluation Metrics for the OV-over Target across Different Model Architectures and Input Resolutions at a fixed Input-Window-Length of 20 Days.
\underline{Underlined} values represent the best value for each metric within a model.
\textbf{\underline{Bold + Underlined}} values represent the global best values across all models for a given metric.}
\label{tab:ov_over_results_by_resolution}
@@ -517,7 +517,7 @@ The full table with MSE and MAE for all models can be found in the appendix, Tab
512 & 4 & \textbf{0.1120} & 0.1358 & \textbf{0.0983} & \textbf{0.0616} & 0.0603 & \textbf{0.0613} \\
\bottomrule
\end{tabularx}
\caption{Evaluation Metrics for the Ovulation-Over Target across Different Model Parameters for the LSTM model with
\caption{Evaluation Metrics for the OV-over Target across Different Model Parameters for the LSTM model with
a fixed input window length of 160 days and an input resolution of 12 values per day.
\textbf{Bold} values represent the best value for each metric within a model.}
\label{tab:ov_over_results_by_model_parameters_lstm}
@@ -547,7 +547,7 @@ The full table with MSE and MAE for all models can be found in the appendix, Tab
512 & 8 & 8 & 0.1126 & 0.1965 & \textbf{0.0753} & \textbf{0.0543} & 0.0868 & \textbf{0.0410} \\
\bottomrule
\end{tabularx}
\caption{Evaluation Metrics for the Ovulation-Over Target across Different Model Parameters for the Transformer model with
\caption{Evaluation Metrics for the OV-over Target across Different Model Parameters for the Transformer model with
a fixed input window length of 160 days and an input resolution of 12 values per day.
\textbf{Bold} values represent the best value for each metric within a model.}
\label{tab:ov_over_results_by_model_parameters_transformer}
@@ -576,7 +576,7 @@ The full table with MSE and MAE for all models can be found in the appendix, Tab
512 & 4 & 0.1436 & \textbf{0.1166} & 0.1523 & 0.0699 & 0.0382 & 0.0820 \\
\bottomrule
\end{tabularx}
\caption{Evaluation Metrics for the Ovulation-Over Target across Different Model Parameters for the convolutional LSTM model with
\caption{Evaluation Metrics for the OV-over Target across Different Model Parameters for the convolutional LSTM model with
a fixed input window length of 40 days.
\textbf{Bold} values represent the best value for each metric within a model.}
\label{tab:ov_over_results_by_model_parameters_conv_lstm}
@@ -606,7 +606,7 @@ The full table with MSE and MAE for all models can be found in the appendix, Tab
512 & 8 & 8 & 0.1576 & \textbf{0.1025} & 0.1848 & 0.0825 & 0.0339 & 0.1066 \\
\bottomrule
\end{tabularx}
\caption{Evaluation Metrics for the Ovulation-Over Target across Different Model Parameters for the convolutional Transformer model with
\caption{Evaluation Metrics for the OV-over Target across Different Model Parameters for the convolutional Transformer model with
a fixed input window length of 40 days.
\textbf{Bold} values represent the best value for each metric within a model.}
\label{tab:ov_over_results_by_model_parameters_conv_transformer}
@@ -679,7 +679,7 @@ The full table with MSE and MAE for all models can be found in the appendix, Tab
User Mean Baseline & 0.180702 & 0.088884 & 0.217144 & 0.180702 & 0.088884 & 0.217144 \\
\bottomrule
\end{tabularx}
\caption{Evaluation Metrics for the Ovulation-Over Target across Different Model Architectures for the Regular and Irregular Cycle Groups.
\caption{Evaluation Metrics for the OV-over Target across Different Model Architectures for the Regular and Irregular Cycle Groups.
\textbf{Bold} values represent the best values across all models for a given metric.}
\label{tab:regular_vs_irregular_ov_over_results}
\end{table}