From 09b77a82f774b2e80e429a66b8b5154319265b7a Mon Sep 17 00:00:00 2001 From: Alex Blank Date: Tue, 15 Jul 2025 17:20:21 +0200 Subject: [PATCH] further work on methodology --- thesis/sections/methodology.tex | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/thesis/sections/methodology.tex b/thesis/sections/methodology.tex index 01ee1a4..f497f01 100644 --- a/thesis/sections/methodology.tex +++ b/thesis/sections/methodology.tex @@ -501,8 +501,10 @@ Note that convolutional models do not require an explicit resampling parameter, (see Section~\ref{subsubsec:temporal_convolution_layer}). \paragraph{Model Parameter Tuning} -To identify the most suitable configuration for each model architecture, model-specific hyperparameters were tuned for optimal predictive performance. -The goal was to balance model complexity and expressiveness in relation to the given input configuration. +To identify suitable configurations for each model architecture, model-specific hyperparameters were tuned with the goal of optimizing predictive performance. +The selected value ranges were intentionally broad to explore the trade-off between model complexity and generalization. +This allowed assessment of whether increased architectural depth and capacity contribute meaningfully to performance, +or whether simpler models are sufficient for the task. \begin{table}[htbp] \centering @@ -510,10 +512,10 @@ The goal was to balance model complexity and expressiveness in relation to the g \renewcommand{\arraystretch}{1.2} % more row spacing \begin{tabular}{@{}p{0.28\textwidth}p{0.45\textwidth}p{0.20\textwidth}@{}} \toprule - \textbf{Parameter} & \textbf{Description} & \textbf{Values Tested} \\ + \textbf{Parameter} & \textbf{Description} & \textbf{Values Tested} \\ \midrule - Hidden Layer Size & Size of the LSTM hidden layer & 16, 32, 64, 128, 256, 512 \\ - Number of LSTM Layers & Number of stacked LSTM layers & 1, 2, 4 \\ + Hidden Layer Size & Size of the LSTM hidden layer & 16, 32, 64, 128, 256, 512 \\ + Number of LSTM Layers & Number of stacked LSTM layers & 1, 2, 4 \\ \bottomrule \end{tabular} \caption{Model hyperparameters for the LSTM and convolutional-LSTM hybrid architectures.} @@ -555,6 +557,9 @@ joint parameter space in a more efficient and principled manner. \subsection{Evaluation}\label{subsec:evaluation} +A variety of evaluation metrics have been defined, to best capture each aspect of the performance of an ovulation prediction. +The evaluation is divided into two subgroups for the two prediction targets, fertility and past-ovulation indicator. + \subsubsection{Evaluation Metrics}\label{subsubsec:evaluation_metrics} \subsubsection{Baseline Comparisons}\label{subsubsec:baseline_comparisons}