diff --git a/main.bib b/main.bib index bb258d6..15e377a 100644 --- a/main.bib +++ b/main.bib @@ -1840,3 +1840,19 @@ Conclusion: {SWS} is a useful tool for confirming the fertile window and absenc langid = {english}, file = {PDF:/home/alex/Zotero/storage/GHT5UMNX/Wu et al. - Deep Transformer Models for Time Series ForecastingThe Influenza Prevalence Case.pdf:application/pdf}, } + +@online{noauthor_ovularing_nodate, + title = {{OvulaRing} Startseite}, + url = {https://ovularing.com/}, + abstract = {Erfahre hier mehr zu {OvulaRing} Startseite}, + titleaddon = {{OvulaRing}}, + urldate = {2025-06-25}, + langid = {german}, + file = {Snapshot:/home/alex/Zotero/storage/PD5DBIS4/ovularing.com.html:text/html}, +} + +@online{noauthor_ringpng_nodate, + title = {ring.png (800×800)}, + url = {https://ovularing.com/wp-content/uploads/2021/07/ring.png}, + urldate = {2025-06-25}, +} diff --git a/thesis/sections/background.tex b/thesis/sections/background.tex index 9621c64..54a113a 100644 --- a/thesis/sections/background.tex +++ b/thesis/sections/background.tex @@ -53,7 +53,7 @@ Anovulation can have various causes, including hormonal imbalances, stress, or u \begin{figure}[htbp] \centering \includegraphics[width=0.9\textwidth]{background_anovulatory_cycle} - \caption{Example of a cycle without an ovulation and the resulting temperature rise} + \caption{Example of a cycle without an ovulation and the resulting absence of a temperature rise} \label{fig:background_anovulation} \end{figure} @@ -100,7 +100,7 @@ rather than relying on population-wide assumptions. \label{fig:background_irregular_cycles} \end{figure} -\begin{figure}[htbp]] +\begin{figure}[htbp] \centering \includegraphics[width=0.9\textwidth]{background_regular_cycle_example} \caption{Example of a woman with regular menstrual rhythm} @@ -117,7 +117,7 @@ the fertile window is typically defined as the five days before ovulation until Research by~\citeauthor{dunson_day-specific_1999} has shown that the highest chance of fertilization is around one day before ovulation, as illustrated in Figure~\ref{fig:background_pregnancy_chance}. -\begin{figure} +\begin{figure}[htbp] \centering \includegraphics[width=0.7\textwidth]{background_pregnancy_chance_over_time} \caption{Chance of fertilization depending on the day of the menstrual cycle. @@ -147,7 +147,52 @@ detecting the slight temperature rise that follows ovulation. Advances in wearable technology have further enabled continuous and automated temperature monitoring, improving accessibility and usability~\cite{alexander_fertilitatsmonitoring_2014, luo_detection_2020, yu_tracking_2022}. -\subsection{Data and Measurement}\label{subsec:data_background} +\subsection{Data Source and Characteristics}\label{subsec:data_background} +This study is based on a dataset collected from users of the \emph{OvulaRing}~\cite{noauthor_ovularing_nodate}, +an intravaginal wearable sensor developed by VivoSensMedical GmbH, located in Leipzig, Germany~\cite{noauthor_vivosens_nodate}. +The device continuously records intravaginal core body temperature at 5-minute intervals. +The sensor itself measures approximately 1\,cm $\times$ 1\,cm $\times$ 2\,cm and is embedded in a silicone ring with a diameter of 5\,cm for ease of use. +It pairs with a smartphone via Bluetooth to synchronize and upload recorded data to a secure database. + +The product has been on the market for over a decade, resulting in an extensive longitudinal dataset of menstrual cycles. +Cycle boundaries are defined by self-reported menstruation, which users manually log in the accompanying app to mark the beginning of each cycle. + +Thanks to a battery life of at least six months, the device supports continuous monitoring of long and irregular cycles, enabling the capture of highly variable menstrual patterns. + +A known limitation of manual cycle annotations is the potential for misalignment. +Intermediate bleeding events unrelated to menstruation (e.g., ovulatory spotting or irregular shedding) or missing menstruation entries can lead to ambiguous cycle definitions. +Therefore, all user-entered cycle starts undergo manual review to reduce annotation errors. + +\begin{figure}[htbp] + \centering + \includegraphics[width=0.3\textwidth]{ovularing} + \caption{The OvulaRing sensor attached to its silicone ring~\cite{noauthor_ringpng_nodate}.} + \label{fig:background_ovularing} +\end{figure} + +In addition to temperature measurements, the database includes contextual metadata such as age, height, weight, and optional user-entered markers. +These markers provide further physiological context and may include information about intermediate bleeding, sexual intercourse, or positive pregnancy tests. + +At the time of writing, the dataset contains approximately 65{,}000 annotated cycles, comprising more than 350 million individual temperature measurements. + +\subsubsection{Dataset Summary} + +\subsubsection{Irregularities and Confounding Factors} + + +\begin{figure}[htbp] + \centering + \includegraphics[width=0.9\textwidth]{background_fever_cycle} + \caption{An example of a cycle with fever significantly altering the temperature data} + \label{fig:background_fever_cycle} +\end{figure} +Figure~\ref{fig:background_fever_cycle} shows a cycle, where the user had an illness that concluded in a rise of body core temperature. +These anomalies can make analysis hard, as the resulting rise in temperature is hard to distinguish from the rise in temperature triggered by an ovulation. + +\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. +VivoSensMedical does not share user data with third parties; the data is used solely for internal research and product improvement efforts that directly benefit users at no additional cost. \subsection{Technical Background}\label{subsec:technological_background} @@ -194,7 +239,7 @@ Figure~\ref{fig:rnn_unfolded} illustrates the unfolded structure of an RNN acros This technique, known as \emph{unfolding}, clarifies how sequential inputs update the hidden state and generate outputs at each time step. -\begin{figure} +\begin{figure}[htbp] \centering \includegraphics[width=0.8\textwidth]{recurrent_neural_network_unfold} \caption{Schematic diagram of the unfolded structure of a recurrent neural network~\cite{fdeloche_english_2017}} @@ -216,7 +261,7 @@ Each gate employs a sigmoid activation function to regulate the flow of informat allowing LSTMs to preserve and update memory over long sequences. -\begin{figure} +\begin{figure}[htbp] \centering \includegraphics[width=0.6\textwidth]{lstm_cell_diagram} \caption{Diagram of a LSTM cell showing the flow of information \cite{chevalier_english_2018}} @@ -263,7 +308,7 @@ context-aware representations by weighing the importance of different input posi This is achieved through \emph{scaled dot-product attention}, where queries, keys, and values are linearly projected from the input and used to compute attention scores. -\begin{figure} +\begin{figure}[htbp] \centering \includegraphics[width=0.4\textwidth]{background_transformer_architecture} \caption{The Transformer - architecture for an encoder-decoder model~\cite{vaswani_attention_2017}} @@ -354,7 +399,7 @@ These techniques reduce the computational load while maintaining salient informa Figure~\ref{fig:background_convolution_example} illustrates a simple one-dimensional convolution applied to a sequence using a filter of size 3. The stride determines how far the filter moves at each step, affecting both the resolution and length of the resulting feature map. -\begin{figure} +\begin{figure}[htbp] \centering \includegraphics[width=0.6\textwidth]{background_convolution_example} \caption{Example of a simple 1-D convolution on an input sequence.}