A5083046363- EEG and Brain-Computer Interfaces
- Advanced Text Analysis Techniques
- Neural and Behavioral Psychology Studies
- Gaze Tracking and Assistive Technology
- Heart Rate Variability and Autonomic Control
- Emotion and Mood Recognition
- Intelligent Tutoring Systems and Adaptive Learning
- Data Visualization and Analytics
- Multimedia Communication and Technology
- Online Learning and Analytics
- Explainable Artificial Intelligence (XAI)
- Dementia and Cognitive Impairment Research
- Human-Automation Interaction and Safety
- Visual and Cognitive Learning Processes
- Personal Information Management and User Behavior
- Genetics, Bioinformatics, and Biomedical Research
- Information Retrieval and Search Behavior
- Musculoskeletal pain and rehabilitation
- Non-Invasive Vital Sign Monitoring
- Retinal Imaging and Analysis
- Privacy, Security, and Data Protection
- Cognitive Science and Mapping
- Cybercrime and Law Enforcement Studies
- Deception detection and forensic psychology
- Data Quality and Management
University of British Columbia
2019-2021
Okanagan University College
2021
Helsinki Institute for Information Technology
2014-2019
University of Helsinki
2014-2019
Term-Relevance Prediction from Brain Signals (TRPB) is proposed to automatically detect relevance of text information directly brain signals. An experiment with forty participants was conducted record neural activity while providing judgments stimuli for a given topic. High-precision scientific equipment used quantify across 32 electroencephalography (EEG) channels. A classifier based on multi-view EEG feature representation showed improvement up 17% in prediction signals alone. Relevance...
Wearable sensors are quickly making their way into psychophysiological research, as they allow collecting data outside of a laboratory and for an extended period time. The present tutorial considers fidelity physiological measurement with wearable sensors, focusing on reliability. We elaborate why ensuring reliability wearables is important offer statistical tools assessing between participants within-participant designs. framework offered here illustrated using several brands commercially...
Peripheral physiological signals, as obtained using electrodermal activity and facial electromyography over the corrugator supercilii muscle, are explored indicators of perceived relevance in information retrieval tasks. An experiment with 40 participants is reported, which these signals recorded while perform Appropriate feature engineering defined, space explored. The results indicate that features window 4 to 6 seconds after judgment for activity, from 1 second before 2 associated users'...
Finding relevant information from large document collections such as the World Wide Web is a common task in our daily lives. Estimation of user's interest or search intention necessary to recommend and retrieve these collections. We introduce brain-information interface used for recommending by relevance inferred directly brain signals. In experiments, participants were asked read Wikipedia documents about selection topics while their EEG was recorded. Based on prediction word relevance,...
Primary chronic pain is that persists for over 3 months without associated measurable tissue damage. One of the most consistent findings in primary its association with autonomic hyperactivation. Yet whether hyperactivation causes or results from it still unclear. It also unclear to what extent related experienced intensity different subtypes pain.
The use of implicit relevance feedback from neurophysiology could deliver effortless information retrieval. However, both computing neurophysiologic responses and retrieving documents are characterized by uncertainty because noisy signals incomplete or inconsistent representations the data. We present first‐of‐its‐kind, fully integrated retrieval system that makes online generated brain activity as measured through electroencephalography (EEG), eye movements. findings evaluation experiment...
Alzheimer’s disease (AD) is a progressive neurodegenerative condition that results in impaired performance multiple cognitive domains. Preclinical changes eye movements and language can occur with the disease, progress alongside worsening cognition. In this article, we present from machine learning analysis of novel multimodal dataset for AD classification. The cohort includes data two tasks not previously assessed classification models (pupil fixation description pleasant past experience),...
We explore electroencephalography (EEG), electrodermal activity (EDA), and electrocardiography (ECG) as valid sources to infer humor appraisal in a realistic environment. report on an experiment which 25 participants browsed popular user-generated humorous content website while their physiological responses were recorded. build predictive models the participants’ of humorousness demonstrate that fusion several signals can lead classification performances up 0.73 terms area under ROC curve...
We study the effectiveness of adaptive guidance at helping users process textual documents with embedded visualizations, known as narrative visualizations. do so by leveraging eye tracking to analyze in depth effect that adaptations meant guide user's gaze relevant parts visualizations has on different levels visualization literacy. Results indicate succeed guiding attention salient components especially generating more transitions between key (i.e., datapoints, labels and legend). also show...
We leverage eye-tracking data to predict user performance and levels of cognitive abilities while reading magazine-style narrative visualizations (MSNV), a widespread form multimodal documents that combine text visualizations. Such predictions are motivated by recent interest in devising user-adaptive MSNVs can dynamically adapt user's needs. Our results provide evidence for the feasibility real-time modeling MSNV, as we first consider eye tracking predicting task comprehension processing...
Motivational intensity has been previously linked to information processing. In particular, it argued that affects which are high in motivational tend narrow cognitive scope. A similar effect attributed negative affect, narrowing of this paper, we investigated how these phenomena manifest themselves during visual word search. We conducted three studies participants were instructed perform category identification. manipulated by controlling reward expectations and affect via outcomes....
We study the effectiveness of adaptive interventions at helping users process textual documents with embedded visualizations, a form multimodal known as Magazine-Style Narrative Visualizations (MSNVs). The are meant to dynamically highlight in visualization datapoints that described sentence currently being read by user, captured eye-tracking. These were previously evaluated two user studies involved 98 participants reading excerpts real-world MSNVs during 1-hour session. Participants’...
Chronic pain is devastating and its measurement elusive, making intervention difficult for sufferers practitioners alike. The present study explores the possibility of tracking fluctuations in over time with wearable sensors heart-based metrics. We measured mean heart rate variability a wrist-worn sensor persons without chronic one month. Mixed model regressions were used to test associations, revealing that at night was predictive intensity on next day participants (p < .05), but not...
Abstract Background Clinical trials of disease‐modifying therapies for Alzheimer’s disease (AD) are increasingly focused on recruiting individuals with preclinical or early‐stage disease. Artificial intelligence may help in enriching clinical trial populations high‐risk individuals. We analyzed prospectively‐collected speech and eye‐tracking data to distinguish mild‐moderate AD, mild cognitive impairment (MCI), subjective memory complaints (SMC) from age sex‐matched healthy volunteers....
Automatic annotation of media content has become a critically important task for many digital services as the quantity available online grown exponentially. One approach is to annotate using physiological responses consumer. In present paper, we reflect on three case studies that use brain signals implicit text discuss challenges faced when bringing passive brain-computer interfaces real world.