Titulo Estágio
Programmer 2.0: shape a new S/W development paradigm using biofeedback: EEG Module
Áreas de especialidade
Sistemas Inteligentes
Engenharia de Software
Local do Estágio
DEI
Enquadramento
The proposed thesis is part of the on-going FCT-funded project BASE. The main goal is to research software bugs in a new perspective using neuro-physiological response and software reliability engineering in a tight interdisciplinary approach to understand the brain mechanisms involved in software error making and error discovery, in particular code errors due to lack of attention during logical reasoning.
This biosensing approach will allow the establishment of predictive relationships between brain activity related to bug making/discovery and measurable body response monitored by current wearable devices, in order to identifying conditions (and corresponding code locations) that may precipitate programmers making bugs or bugs escaping human attention.
The overall BASE Biofeedback Augmented Software Engineering approach will allow online bug warning, calling programmers’ attention to code areas that need a second look, and will establish radically new software testing strategies and bug prediction models.
Intellectual activities such as code comprehension and bug discovery invoke cognitive control (researched in the project using mainly fMRI, fNIRS and EEG) that induce physiologic responses driven by the Autonomic Nervous System (ANS) that triggers variations in the heart rate, blood pressure, breathing rhythm and skin electrical characteristics.
Objetivo
The objective of this thesis is to uncover neural mechanisms involved in code comprehension and bug detection by analysing scalp EEG recordings. Other objective is the understanding of the relations between the identified neural mechanisms and the triggered autonomic changes. The ultimate goal is to find relations between EEG biomarkers and ANS responses that lead us to trust in minimally invasive measurements, such as those obtained with commercial smart watches and wearable devices that can monitor ANS response.
In summary, the overall research goal of this thesis involves the development and validation of existent and new EEG biomarkers that allow to correlate them with the information gathered from the wearable devices that aim to measure ANS response. These correlations can be validated by simultaneous EEG/fMRI recordings.
This project will be initially supported by a database of 30 subjects (already measured) and is expected that the student will help to increase this number.
The detailed goals are:
- Support data collection studies related to synchronised fMRI/fNIRS/EEG/ECG/PPG/EDA acquisition during code inspection and programming tasks
- Develop feature extraction solutions to assess brain patterns form EEG and their relations with sympathetic and parasympathetic activity of the autonomic nervous system during code inspection and programming tasks
- Compare different algorithm setups and multi-parametric models to assess neuro-autonomic relations during code inspection and programming tasks
Plano de Trabalhos - Semestre 1
- Technical background on software faults (bugs) classification, software complexity metrics, and cognitive models of human error in software development
- Psycho-physiological background
- Technical background in EEG pre-processing and feature extraction, such as Independent Component Analysis, Source Localization, time-frequency descriptors, among others.
- State-of-the-art on EEG feature extraction for assessing stress, cognitive load and attention.
- Support data collection studies during code inspection and programming tasks.
Plano de Trabalhos - Semestre 2
- Develop feature extraction solutions to assess stress levels, cognitive load and attention during code inspection and programming tasks using EEG.
- Traditional feature extraction techniques as well as more modern techniques such as autoencoders and deep learning may be applied.
- Correlate EEG features (biomarkers) with features extracted to assess stress levels, cognitive load and attention based on minimally invasive wearable sensors to evaluate ANS response during code inspection and programming tasks.
- Conclude about ANS response and brain patterns during code inspection and programming tasks.
- Writing the thesis.
Condições
Student will have access to facilities available in the AC and SSE group, such as computers and cloud services.
Observações
This thesis might be allocated a grant from the BASE project. This thesis will have a strong cooperation with another thesis that will evaluate the ANS response by recording easy-to-measure biosignals (PPG, ECG, etc).
This thesis is co-supervised by:
• Paulo de Carvalho, PhD, Associate Professor, FCTUC
• Henrique Madeira, PhD, Full Professor, FCTUC
Orientador
Cesar Teixeira
cteixei@dei.uc.pt 📩