further work on results

thesis/sections/background.tex

@@ -29,7 +29,7 @@ This process, known as menstruation, marks the beginning of a new cycle.
 
 \begin{figure}[htbp]
     \centering
-    \includegraphics[width=0.6\textwidth]{background_menstrual_cycle_physiology}
+    \includegraphics[width=0.6\textwidth]{resources/figures/background/background_menstrual_cycle_physiology}
     \caption{Physiological changes during the menstrual cycle~\cite{pedroso_menstrual_2022}.
     The figure shows the relationship between hormonal fluctuations, physiological changes, and body temperature, with a clear temperature rise around ovulation.}
 
@@ -42,7 +42,7 @@ Figure~\ref{fig:background_menstrual_cycle_physiology} provides a detailed overv
 
 \begin{figure}[htbp]
     \centering
-    \includegraphics[width=0.9\textwidth]{background_labeled_cycle}
+    \includegraphics[width=0.9\textwidth]{resources/figures/background/background_labeled_cycle}
     \caption{Body core temperature curve across a menstrual cycle. The red line represents a locally smoothed temperature trend.
     Menstruation, ovulation, and the fertile phase are indicated in red, blue, and green, respectively.}
     \label{fig:background_labeled_cycle}
@@ -59,7 +59,7 @@ Anovulation can have various causes, including hormonal imbalances, stress, or u
 
 \begin{figure}[htbp]
     \centering
-    \includegraphics[width=0.9\textwidth]{background_anovulatory_cycle}
+    \includegraphics[width=0.9\textwidth]{resources/figures/background/background_anovulatory_cycle}
     \caption{Example of a cycle without an ovulation and the resulting absence of a temperature rise}
     \label{fig:background_anovulation}
 \end{figure}
@@ -78,14 +78,14 @@ show examples of cycles that are significantly longer or shorter than a normativ
 
 \begin{figure}[htb]
     \centering
-    \includegraphics[width=0.9\textwidth]{background_long_cycle}
+    \includegraphics[width=0.9\textwidth]{resources/figures/background/background_long_cycle}
     \caption{Example of a long cycle with a length of 111 days}
     \label{fig:background_long_cycle}
 \end{figure}
 
 \begin{figure}[htb]
     \centering
-    \includegraphics[width=0.9\textwidth]{background_short_cycle}
+    \includegraphics[width=0.9\textwidth]{resources/figures/background/background_short_cycle}
     \caption{Example of a short cycle with a length of 22 days}
     \label{fig:background_short_cycle}
 \end{figure}
@@ -104,14 +104,14 @@ can reliably be used as the next.
 
 \begin{figure}[htb]
     \centering
-    \includegraphics[width=0.9\textwidth]{background_irregular_cycle_example}
+    \includegraphics[width=0.9\textwidth]{resources/figures/background/background_irregular_cycle_example}
     \caption{Example of a woman with irregular menstrual rhythm}
     \label{fig:background_irregular_cycles}
 \end{figure}
 
 \begin{figure}[htbp]
     \centering
-    \includegraphics[width=0.9\textwidth]{background_regular_cycle_example}
+    \includegraphics[width=0.9\textwidth]{resources/figures/background/background_regular_cycle_example}
     \caption{Example of a woman with regular menstrual rhythm}
     \label{fig:background_regular_cycles}
 \end{figure}
@@ -126,7 +126,7 @@ as illustrated in Figure~\ref{fig:background_pregnancy_chance}.
 
 \begin{figure}[htbp]
     \centering
-    \includegraphics[width=0.7\textwidth]{background_pregnancy_chance_over_time}
+    \includegraphics[width=0.7\textwidth]{resources/figures/background/background_pregnancy_chance_over_time}
     \caption{Chance of fertilization depending on the day of the menstrual cycle.
     The highest chance is around one day before ovulation~\cite{dunson_day-specific_1999}.}
     \label{fig:background_pregnancy_chance}
@@ -173,7 +173,7 @@ Therefore, all user-entered cycle starts undergo manual review to reduce annotat
 
 \begin{figure}[htbp]
     \centering
-    \includegraphics[width=0.3\textwidth]{ovularing}
+    \includegraphics[width=0.3\textwidth]{resources/figures/background/ovularing}
     \caption{The OvulaRing sensor attached to its silicone ring~\cite{noauthor_ringpng_nodate}.}
     \label{fig:background_ovularing}
 \end{figure}
@@ -215,7 +215,7 @@ Distinguishing illness-related changes from cycle-related ones requires models t
 
 \begin{figure}[htbp]
     \centering
-    \includegraphics[width=0.9\textwidth]{background_fever_cycle}
+    \includegraphics[width=0.9\textwidth]{resources/figures/background/background_fever_cycle}
     \caption{Example of a cycle affected by illness, showing a fever-induced temperature rise shortly before the expected ovulatory shift.}
     \label{fig:background_fever_cycle}
 \end{figure}
@@ -228,7 +228,7 @@ Figure~\ref{fig:background_menstruation_data_gap} shows an example cycle with a
 
 \begin{figure}[htbp]
     \centering
-    \includegraphics[width=0.9\textwidth]{background_menstruation_data_gap}
+    \includegraphics[width=0.9\textwidth]{resources/figures/background/background_menstruation_data_gap}
     \caption{Example of a cycle with a data gap at the beginning, caused by sensor removal during menstruation.}
     \label{fig:background_menstruation_data_gap}
 \end{figure}
@@ -287,7 +287,7 @@ outputs at each time step.
 
 \begin{figure}[htbp]
     \centering
-    \includegraphics[width=0.8\textwidth]{recurrent_neural_network_unfold}
+    \includegraphics[width=0.8\textwidth]{resources/figures/background/recurrent_neural_network_unfold}
     \caption{Schematic diagram of the unfolded structure of a recurrent neural network~\cite{fdeloche_english_2017}}
     \label{fig:rnn_unfolded}
 \end{figure}
@@ -308,7 +308,7 @@ allowing LSTMs to preserve and update memory over long sequences.
 
 \begin{figure}[htbp]
     \centering
-    \includegraphics[width=0.6\textwidth]{background_lstm_structure}
+    \includegraphics[width=0.6\textwidth]{resources/figures/background/background_lstm_structure}
     \caption{Architecture of a memory cell \( c_j \) and its gate units \( \text{in}_j \) and \( \text{out}_j \).
     At the center, the self-recurrent linear unit (with weight 1.0) maintains the internal state~\cite{hochreiter_long_1997}.
     See text for more details.}
@@ -376,7 +376,7 @@ linearly projected from the input and used to compute attention scores.
 
 \begin{figure}[htbp]
     \centering
-    \includegraphics[width=0.4\textwidth]{background_transformer_architecture}
+    \includegraphics[width=0.4\textwidth]{resources/figures/background/background_transformer_architecture}
     \caption{The Transformer - architecture for an encoder-decoder model~\cite{vaswani_attention_2017}}
     \label{fig:background_transformer_architecture}
 \end{figure}
@@ -412,7 +412,7 @@ This was done according to the original paper~\cite{vaswani_attention_2017}.
 
 \begin{figure}[htbp]
     \centering
-    \includegraphics[width=0.8\textwidth]{background_attention_mechanism}
+    \includegraphics[width=0.8\textwidth]{resources/figures/background/background_attention_mechanism}
     \caption{(left) Scaled Dot-Product Attention.
         (right) Multi-Head Attention consisting of several attention layers running in parallel~\cite{vaswani_attention_2017}.}
     \label{fig:background_attention_mechanism}
@@ -553,7 +553,7 @@ The stride determines how far the filter moves at each step, affecting both the
 
 \begin{figure}[htbp]
     \centering
-    \includegraphics[width=0.6\textwidth]{background_convolution_example}
+    \includegraphics[width=0.6\textwidth]{resources/figures/background/background_convolution_example}
     \caption{Example of a simple 1-D convolution on an input sequence.}
     \label{fig:background_convolution_example}
 \end{figure}

thesis/sections/methodology.tex

@@ -138,7 +138,7 @@ Except for \textit{time since cycle start}, all features are encoded using sine
 
 \begin{figure}[htbp]
     \centering
-    \includegraphics[width=0.9\textwidth]{methodology_time_feature_sine_encoded}
+    \includegraphics[width=0.9\textwidth]{resources/figures/methodology/methodology_time_feature_sine_encoded}
     \caption{Sine and cosine encoding of the day-of-week feature.}
     \label{fig:methodology_time_feature_encoding}
 \end{figure}
@@ -160,7 +160,7 @@ They represent real-time physiological signals from which the model must infer o
 
 \begin{figure}[htbp]
     \centering
-    \includegraphics[width=0.9\textwidth]{methodology_observable_features}
+    \includegraphics[width=0.9\textwidth]{resources/figures/methodology/methodology_observable_features}
     \caption{Observable features for a cycle.}
     \label{fig:methodology_observable_features}
 \end{figure}
@@ -195,7 +195,7 @@ For this study, the following exogenous variables are used:
 
 \begin{figure}[htbp]
     \centering
-    \includegraphics[width=0.9\textwidth]{methodology_target_features}
+    \includegraphics[width=0.9\textwidth]{resources/figures/methodology/methodology_target_features}
     \caption{
         Target features plotted for a single cycle.
         The ovulation-over indicator switches on the day of ovulation;
@@ -288,7 +288,7 @@ This is used primarily in the convolutional flavours of the models, to allow the
 
 \begin{figure}[htbp]
     \centering
-    \includegraphics[width=0.9\textwidth]{methodology_padding_example}
+    \includegraphics[width=0.9\textwidth]{resources/figures/methodology/methodology_padding_example}
     \caption{
         Padded input window during early cycle phases,
         where historical data is still sparse.
@@ -325,7 +325,7 @@ Ultimately, the models used in this study were selected based on their ability t
 \subsubsection{LSTM-Architecture}\label{subsubsec:lstm_architecture}
 \begin{figure}[htbp]
     \centering
-    \includegraphics[width=0.7\textwidth]{methodology_lstm_architecture}
+    \includegraphics[width=0.7\textwidth]{resources/figures/methodology/methodology_lstm_architecture}
     \caption{
         Schematic overview of the LSTM architecture used in this study.
     }
@@ -354,7 +354,7 @@ as was shown to be an effective value~\cite{pham_dropout_2014}
 
 \begin{figure}[htbp]
     \centering
-    \includegraphics[width=0.7\textwidth]{methodology_transformer_architecture}
+    \includegraphics[width=0.7\textwidth]{resources/figures/methodology/methodology_transformer_architecture}
     \caption{
         Schematic overview of the Transformer architecture used in this study.
     }
@@ -398,7 +398,7 @@ The specific values and tuning ranges for these parameters are discussed in Sect
 
 \begin{figure}[htbp]
     \centering
-    \includegraphics[width=0.7\textwidth]{methodology_convolution_architecture}
+    \includegraphics[width=0.7\textwidth]{resources/figures/methodology/methodology_convolution_architecture}
     \caption{
         Schematic overview of the temporal convolution layer architecture used in this study.
     }

thesis/sections/results.tex

@@ -15,6 +15,14 @@ allowing for a nuanced comparison of approaches and their practical relevance to
 
 \subsection{Overall Model Performance Across Architectures}\label{subsec:overall_model_performance_across_architectures}
 
+
+\begin{figure}
+    \centering
+    \includegraphics[width=0.9\textwidth]{resources/figures/results/model_performance_overview}
+    \caption{Overview of the performances of all model types including the baselines on 4 selected performance metrics.}
+    \label{fig:results_performance_overview_by_model_type}
+\end{figure}
+
 \subsection{Fertility Probability Prediction Accuracy}\label{subsec:fertility_probability_precition_accuracy}
 
 \subsubsection{Performance Across Fertile Window}\label{subsubsec:fert_performance_across_fertile_window}