further work on methodology

thesis/sections/background.tex

@@ -239,6 +239,8 @@ Figure~\ref{fig:background_menstruation_data_gap} shows an example cycle with a
     \label{fig:background_menstruation_data_gap}
 \end{figure}
 
+%TODO: more stats!
+
 \subsubsection{Privacy}
 The dataset used in this study contains sensitive personal health information and is handled with strict privacy safeguards.
 All data is pseudonymized and processed exclusively on encrypted devices, ensuring that no identifiable information can be traced back to individual users.

thesis/sections/methodology.tex

@@ -4,6 +4,17 @@
 
 \section{Methodology}\label{sec:methodology}
 
+While prior studies have demonstrated the promise of physiological signals for ovulation detection and phase classification,
+many are limited by small sample sizes, rigid inclusion criteria, or non-transparent methodologies.
+Temperature has emerged as a potentially predictive signal, but existing work often lacks scalability or generalizability.
+This study extends previous approaches by leveraging a large, heterogeneous real-world dataset of high-resolution core body temperature
+readings to develop and evaluate machine learning models for real-time ovulation prediction.
+In addition to model development, special emphasis is placed on evaluating performance across irregular cycles and assessing
+the predictive value of low-noise, high-resolution temperature data.
+
+The following section outlines the methodology used, including data preprocessing,
+feature extraction, input encoding, and model architectures.
+
 % why did I select tft over other methods -> include examples of time series and why I belief a complex model could help
 % you did I apply it
 % implementation details
@@ -368,6 +379,15 @@ fertility probability and ovulation-over indicator.
 Figure~\ref{fig:methodology_transformer_architecture} shows the overall architecture.
 The stacked inputs and outputs indicate batch processing.
 
+Model-specific architectural parameters are:
+\begin{itemize}
+    \item \textbf{Input Length} — Number of time steps included in each input sequence.
+    \item \textbf{Embedding dimension} — Dimensionality of the Transformer internal token representation.
+    \item \textbf{Number of Encoder-Layers} — Number of encoder layers to stack
+    \item \textbf{Number of Attention-Heads} — Number of attention heads to use in each layer
+\end{itemize}
+The specific values and tuning ranges for these parameters are discussed in Section~\ref{subsubsec:hyperparameter_tuning}.
+
 \subsubsection{Temporal Convolution Layer}
 \label{subsubsec:temporal_convolution_layer}
 
@@ -439,7 +459,7 @@ Hyperparameter tuning was divided into two stages:
 (1) tuning of input-related parameters such as resampling rate, and
 (2) tuning of model-specific architectural parameters such as hidden size or attention heads.
 
-\paragraph{Input Parameter Tuning}% \mbox{}\\
+\paragraph{Input Parameter Tuning:}
 This stage involved identifying optimal settings for data preprocessing and input representation.
 Key variables included the resampling rate (temporal resolution) and historical context length (input window size).
 These parameters strongly influence the structure of the input signal and can significantly affect model performance.
@@ -480,10 +500,48 @@ while Table~\ref{tab:input_hyperparameters_conv} lists those for the convolution
 Note that convolutional models do not require an explicit resampling parameter, as they perform learned downsampling internally
 (see Section~\ref{subsubsec:temporal_convolution_layer}).
 
-\paragraph{Model Parameter Tuning}% \mbox{}\\
-Once suitable input configurations were established, model-specific hyperparameters were tuned.
-For LSTM-based models, this included hidden layer size and number of recurrent layers.
-For Transformer models, relevant parameters included the number of attention heads and encoder depth.
+\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.
+
+\begin{table}[htbp]
+    \centering
+    \setlength{\tabcolsep}{8pt} % adjust column spacing
+    \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} \\
+        \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                   \\
+        \bottomrule
+    \end{tabular}
+    \caption{Model hyperparameters for the LSTM and convolutional-LSTM hybrid architectures.}
+    \label{tab:lstm_model_hyperparameters}
+\end{table}
+
+
+\begin{table}[htbp]
+    \centering
+    \setlength{\tabcolsep}{8pt} % adjust column spacing
+    \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}    \\
+        \midrule
+        Embedding Dimension       & Size of the internal token embedding & 16, 32, 64, 128, 256, 512 \\
+        Number of Encoder Layers  & Number of stacked encoder layers     & 1, 2, 4, 8                \\
+        Number of Attention Heads & Number of attention heads per layer  & 1, 2, 4, 8                \\
+        \bottomrule
+    \end{tabular}
+    \caption{Model-related hyperparameters for the Transformer and Convolutional-Transformer-Hybrid architectures.}
+    \label{tab:transformer_model_hyperparameters}
+\end{table}
+
+Tables~\ref{tab:lstm_model_hyperparameters} and~\ref{tab:transformer_model_hyperparameters} summarize the tested hyperparameters and value ranges
+for the LSTM-based and Transformer-based models, respectively.
+Note that the same settings were used for the hybrid models, as their architecture beyond the convolutional front end is structurally identical.
+
 
 \vspace{0.5em}
 We acknowledge that interactions between input and model parameters may influence final model performance,
@@ -501,3 +559,16 @@ joint parameter space in a more efficient and principled manner.
 
 \subsubsection{Baseline Comparisons}\label{subsubsec:baseline_comparisons}
 
+\subsection{Ethical Considerations}\label{subsec:ethical_considerations}
+
+This study was conducted using pseudonymized data collected in accordance with the terms of service and privacy policy of the data provider, VivoSensMedical GmbH (Leipzig, Germany).
+All users whose data were included had consented to the use of their recordings for analytical purposes at the time of data collection.
+
+The study protocol was reviewed and approved by the provider's internal legal and scientific advisory team,
+which is responsible for ensuring ethical and regulatory compliance.
+
+All data used in this study were pseudonymized prior to access.
+No personal identifiers or sensitive metadata were included.
+Additional safeguards were implemented to ensure data confidentiality and integrity,
+including restricted access and use solely for the purposes of model development and evaluation.
+No compensation was provided to participants, as the data were originally collected as part of routine usage under the agreed terms.

thesis/sections/related_work.tex

@@ -3,13 +3,30 @@
 
 
 \section{Related Work}\label{sec:related_work}
-There has been a variety of works in menstrual cycle analysis and ovulation prediction based on different physiological signs.
+
+A variety of approaches have historically been explored for ovulation detection and prediction,
+ranging from hormonal assays to physiological signal tracking.
+
+In~\citeyear{wallach_prediction_1980}, \citeauthor{wallach_prediction_1980} identified several physiological indicators for ovulation timing,
+including salivary ferning and viscosity, serum levels of progesterone and estrogen,
+and urinary luteinizing hormone (LH) concentrations~\cite{wallach_prediction_1980}.
+These indicators showed strong correlation with ovulation timing as measured via transvaginal ultrasound.
+\citeauthor{noauthor_monitoring_1987} later expanded on this work by focusing specifically on LH and estradiol,
+confirming that LH surges reliably indicate an imminent ovulation event.
+
+Despite their diagnostic value, many of these biomarkers are difficult to measure continuously and reliably in everyday settings,
+limiting their practicality for real-time or large-scale applications.
 
 \subsection{Temperature-Based Approaches}\label{subsec:temperature_based_approaches}
+Body temperature has emerged as a more accessible physiological signal for ovulation tracking,
+given the feasibility of continuous and non-invasive measurement.
+As outlined in Section~\ref{subsubsec:physiological_signs}, basal body temperature (BBT) exhibits a biphasic pattern across
+the menstrual cycle that correlates with ovulation.
 
-Several studies have questioned the utility of BBT (Basal Body Temperature) for reliable ovulation prediction.
-For example \citeauthor{bauman_basal_1981} concluded, that BBT is not a robust standalone marker due to its
-retrospective nature and sensitivity to external factors and thus must be used with extreme caution clinical or research evaluations~\cite{bauman_basal_1981}.
+However, several studies have raised concerns about its reliability as a predictive marker.
+\citeauthor{bauman_basal_1981} concluded that BBT alone is insufficiently robust due to its retrospective nature and
+high susceptibility to external confounders, recommending caution in its clinical or research use~\cite{bauman_basal_1981}.
+Similarly, \citeauthor{moghissi_accuracy_1976} emphasized its limited accuracy, particularly in cycles with irregularities~\cite{moghissi_accuracy_1976}.
 
 However, such conclusions were largely based on the standard BBT method, which relies on a single-point measurement taken
 immediately upon waking—typically reflecting the body's lowest resting temperature.
@@ -72,7 +89,6 @@ These findings suggest that electrical resistance is a strong physiological mark
 A related modern implementation is the commercial product \textit{kegg}~\cite{noauthor_kegg_nodate}, which measures the electrical resistance of cervical mucus.
 The device uses an undisclosed algorithm to estimate fertility status based on these readings, although no peer-reviewed validation studies are currently available.
 
-
 \citeauthor{masuda_machine_2025} developed a machine learning algorithm to classify phases of the menstrual cycle
 (follicular vs. luteal) based on sleeping heart rate, as recorded by a fitness tracker~\cite{masuda_machine_2025}.
 They used an XGBoost classifier for this binary task and additionally performed ovulation day prediction,
@@ -100,8 +116,7 @@ waking—they report classification accuracies between 0.843 and 0.864, dependin
 with very similar numbers for precision, recall, specificity and F1 score.
 Ovulation day prediction yielded an average absolute error between 3.6 and 4.1 days.
 
-When models are trained on highly constrained datasets with predictable patterns and clear ovulatory signals,
-complex methods often show limited gains over naive or rule-based approaches—as will be demonstrated in Section~\ref{sec:methodology}.
+
 
 \paragraph{Summary:}
 While various physiological signals and modeling strategies have been explored for ovulation prediction,