ETD system

Electronic theses and dissertations repository

 

Tesi etd-03312020-175857


Thesis type
Tesi di laurea magistrale
Author
RESTA, MICHELE
URN
etd-03312020-175857
Title
Increasing the Interpretability of Deep Recurrent Models for Biomedical Signals Analysis
Struttura
INFORMATICA
Corso di studi
INFORMATICA
Supervisors
relatore Prof. Bacciu, Davide
correlatore Prof.ssa Monreale, Anna
relatore Prof. Vellido, Alfredo
Parole chiave
  • interpretability
  • recurrent neural networks
  • deep-learning
  • biomedical signals
  • gated recurrent units
Data inizio appello
08/05/2020;
Consultabilità
Secretata d'ufficio
Riassunto analitico
A large research effort is spent in the field of biomedical signal analysis. Great progresses have been made recently in the field by applying novel Machine Learning techniques, especially in classification tasks.
The adoption of new models is however slowed down by their lack of interpretability, a key requirement in the medical domain.
While some interpretability approaches have been proposed for models and architectures dealing with images data and classification tasks, little to none work exists for biomedical signal regression.
This work present results obtained by adapting well-established interpretability techniques to deep learning models dealing with arterial blood pressure estimation.
Different models have been trained on Electrocardiogram (ECG) and Photoplethysmogram (PPG) data to predict arterial blood pressure (ABP).
First we describe our analysis on filters learned by models using convolutional layers.
Then we focus on gated recurrent models to analyze the effects of input signals occlusion on both output and gates activations.
Experiments with different types of occlusion have been performed to explore the behaviour of different architectures.
Both a qualitative and a quantitative evaluation is presented.
File