- This event has passed.
Ph.D. Proposal: Badar Almarri
December 16, 2020 @ 9:30 am - 11:00 am EST
Doctoral Dissertation Proposal
Title: A BCI Framework for Affection Recognition: Channel and Feature Selection, and Subjective Label Dichotomization
Student: Badar Almarri
Major Advisor: Dr. Chun-Hsi Huang
Associate Advisors: Dr. Sanguthevar Rajasekaran and Dr. Sheida Nabavi
Date/Time: Wednesday, December 16th, 2020, 09:30 AM
Meeting number: 120 495 9782
Affective computing has become a vital component in the evolvement of artificial intelligence humanization. Compared to various sources of reading human emotions, brain signals are considered to be more objective and accurate in the perspective of brain-computer interaction. Brain imaging and recording solutions such as fMRI and EEG are feasible considering the massive number of neurons (i.e. quantified in tens of billions) and the rapid and unanticipated interactivity among them, yet there are challenges that are multifaceted and complex. In particular, the dimensionality of the spatially-distributed channels in EEG-based brain-computer interface (BCI) undermines the prediction power of human affections. EEG is known for its decent temporal resolution, however, neural interactivities are subjective and their synchronization patterns vary spontaneously. Thus, prior to modeling such data, as the final stage of the learning pipeline, adequate preprocessed signals’ features of the stimuli-related electrode channels are of the essence to predict underlying human emotions.
In this proposal, we investigate and propose a framework that tackles two problems in EEG-related affective computing studies. More specifically, the first pipeline is stimulus-dependent in which we implement subject-specific unsupervised learning to select the most stimulus-subject-relevant EEG features and channels. Also, we embed unsupervised algorithms for feature extraction and selection in the time and frequency domains. The second pipeline is to solve the problem of subjective labeling and label imbalance in such experiments. In BCI applications, ground truth labels are expected to be certain – their existence is a vital component of supervised learning problems. In certain cases, however, they can prove to be obstacles. They can lead to two possible issues: class imbalances (i.e. skewed label distribution), and unreliability due to the uncertainty of subjects’ underlying emotional states. Since the labels are continuous, they need to be dichotomized for a classification task. Dichotomization is typically decided statistically or based on a subject matter expert. However, the subjectivity of participants and its impact is neglected. To improve the prediction pipeline, we investigate the effect of thresholding on EEG emotional self-assessment in order to minimize subjectivity, improve model outcomes as well as alleviating the effect of label imbalance.
Our preliminary results outperform other methods in the EEG-based subject-independent emotion recognition studies when applied to real datasets. The main components of this algorithmic framework are unsupervised and based solely on neural data. Therefore, automatic emotion analysis and recognition are possible in both experimental trials and real-life applications. In our ongoing work, we will investigate more about the connectivity of brain regions-of-interest (ROIs) using several methods (e.g. phase synchronization and coherence). Also, derivations of feature extraction methods such as alpha and beta waves are to be embedded and measured. Lastly, we will study the subjective labeling behavior in different real datasets.