1 |
FFT and Neural Networks for Identifying and Classifying Heart ArrhythmiasKegel, Johan, Zetterblad, Carolina January 2024 (has links)
The rise of machine learning has seen an increase in digital methods for use within health care. Arrythmia detection is one of the areas where this increase is obvious. However, many machine learning methods for arrythmia detection utilise models that are computationally expensive, such as convolutional neural networks, CNNs. This thesis examines whether it is viable to use the Fast Fourier Transform to transform an Electrocardiogram, ECG, signal into its frequency components before training a neural network, NN, on the data. This could allow for a lower computational cost and wider availability of arrythmia detection technology. The results from the model were compared to that of a CNN trained on time domain data. The results show that the CCN model outperforms the NN trained on FFT transformed data but the performance of the model still indicates that valuable information about heart arrythmias does exist within the frequency space. This suggests a potential for future work on the subject.
|
2 |
Heartbeat detection, classification and coupling analysis using Electrocardiography dataLi, Yelei 02 September 2014 (has links)
No description available.
|
3 |
EKG-analys och presentation / ECG analysis and presentationEngström, Magnus, Soheily, Nadia January 2014 (has links)
Tolkningen av EKG är en viktig metod vid diagnostisering av onormala hjärttillstånd och kan användas i förebyggande syfte att upptäcka tidigare okända hjärtproblem. Att enkelt kunna mäta sitt EKG och få det analyserat och presenterat på ett pedagogiskt sätt utan att behöva rådfråga en läkare är något det finns ett konsumentbehov av. Denna rapport beskriver hur en EKG-signal behandlas med olika algoritmer och metoder i syfte att detektera hjärtslag och dess olika parametrar. Denna information används till att klassificera varje hjärtslag för sig och därmed avgöra om användaren har en normal eller onormal hjärtfunktion. För att nå dit har en mjukvaruprototyp utvecklats där algoritmerna implementerats. En enkätundersökning gjordes i syfte att undersöka hur utdata från mjukvaruprototypen skulle presenteras för en vanlig användare utan medicinsk utbildning. Sju filer med EKG-signaler från MIT-BIH Arrhythmia Database användes för testning av mjukvaruprototypen. Resultatet visade att prototypen kunde detektera en rad olika hjärtfel som låg till grund vid fastställning om hjärtat slog normalt eller onormalt. Resultatet presenterades på en mobilapp baserad på enkätundersökningen. / The interpretation of the ECG is an important method in the diagnosis of abnormal heart conditions and can be used proactively to discover previ-ously unknown heart problems. Being able to easily measure the ECG and get it analyzed and presented in a clear manner without having to consult a doctor is improtant to satisfy consumer needs. This report describes how an ECG signal is treated with different algo-rithms and methods to detect the heartbeat and its various parameters. This information is used to classify each heartbeat separately and thus determine whether the user has a normal or abnormal cardiac function. To achieve this a software prototype was developed in which the algorithms were implemented. A questionnaire survey was done in order to examine how the output of the software prototype should be presented for a user with no medical training. Seven ECG files from MIT-BIH Arrhythmia database were used for validation of the algorithms. The developed algorithms could detect of if any abnormality of heart function occurred and informed the users to consult a physician. The presentation of the heart function was based on the result from the questioner.
|
Page generated in 0.1026 seconds