polito.it
Politecnico di Torino (logo)

The Readiness Potential: a systematic review about the influencing factors and the development of an algorithm for automatic features extraction

Leonardo Cardinali

The Readiness Potential: a systematic review about the influencing factors and the development of an algorithm for automatic features extraction.

Rel. Gabriella Olmo, Vito De Feo. Politecnico di Torino, Corso di laurea magistrale in Ingegneria Biomedica, 2019

[img]
Preview
PDF (Tesi_di_laurea) - Tesi
Licenza: Creative Commons Attribution Non-commercial No Derivatives.

Download (2MB) | Preview
Abstract:

The goals that this thesis work wants to achieve are two: one objective is to redact a schematic review of the Readiness Potential, the components it is made of (early BP, late BP and also LRP) and the factors modulating its waveform; the other is to write a program that performs onsets and amplitudes measurements using methods found in literature and to compare these results to observe the robustness of the different algorithms. These methods include peak and mean amplitude measurements using different parameters, as well as many onsets measurements, divided in criterion-based, baseline-based and regression-based methods. To understand the robustness of these techniques we divided our dataset in three categories: high-quality, medium-quality and low-quality data. For high-quality data, as expected, no problem arises and the measurements are correctly performed, while for lower quality data many measurements are impossible or produce implausible results. For amplitudes methods, the less reliable is the method based on the work from Wright et al., while the other two produce reliable results in medium and and high-quality conditions. For onset measurements, the method that revealed to be less reliable is the criterion-based method, while the most reliable methods are the regression-based methods. The cleanliness of the data on which the proposed algorithms are performed is crucial for the goodness of the measurements. One of the most problematic issue in dirty data is the noise present in the baseline period.

Relatori: Gabriella Olmo, Vito De Feo
Anno accademico: 2019/20
Tipo di pubblicazione: Elettronica
Numero di pagine: 70
Soggetti:
Corso di laurea: Corso di laurea magistrale in Ingegneria Biomedica
Classe di laurea: Nuovo ordinamento > Laurea magistrale > LM-21 - INGEGNERIA BIOMEDICA
Aziende collaboratrici: NON SPECIFICATO
URI: http://webthesis.biblio.polito.it/id/eprint/12262
Modifica (riservato agli operatori) Modifica (riservato agli operatori)