I am a doctoral student with the Future Resilient Systems (FRS) programme at the Singapore-ETH Centre, which is part of the Campus for Research Excellence and Technological Enterprise (CREATE) established by Singapore's National Research Foundation. My involvement with FRS began in January 2021 after completing my Master's degree at the Indian Institute of Technology Kharagpur, India. My research primarily focuses on the development of visualization, interaction, and notification frameworks for the communication of predicted disruptions in urban systems. My work is significantly based in the field of Human-Computer Interaction and eye-tracking, where I contribute to enhancing the resilience of urban systems by improving how disruptions are communicated and understood..
I have been aware that to be a student of Human computer interaction (HCI) theoretical study
and coursework is one thing, the development of practical abilities is another thing. In addition
to this, HCI is more an applied subject than a theoretical one. With this realization, I have
made conscious efforts to participate in research projects. I worked alongside a team of researchers
developing a multi-modal approach in estimating the cognitive state of an individual using the
eye tracking data and other sensor acquired during the experiments.
@Google scholar
.
My research seeks to advance decision making support tools
toward more robust and uncertainty-aware solutions through the
intersection of field experiments, numerical simulation, and
human-computer interaction with applications in resilience.
You can check out my recent work below 😉
Recent Work
Estimating Perceived Mental Workload From Eye-Tracking Data Based on Benign Anisocoria
Did you know your left and right pupil sizes are not the same? In a recently accepted article, we introduce two new eye-tracking metrics -- based on the minute differences between left and right pupil diameter -- that can accurately measure cognitive load. By analyzing pupil size asymmetry between the left and right eye, we've developed an effective method for assessing mental workload. Our research shows promising results in a case study using an N-back test.
The influence of uncertainty visualization on cognitive load in a safety- and time-critical decision-making task
**Making spatial decisions under pressure? New research reveals how visualization techniques can significantly reduce cognitive load. **Traffic controllers and other professionals working in safety-critical domains constantly face spatial decision situations under high pressure. But what if there was a simple way to improve their decision-making abilities? This new study at Singapore-ETH Centre explores the impact of different visualization techniques on cognitive load in time-critical tasks using eye tracking. The study also examines the differences in scanning patterns resulting from different decision-making strategies through gaze transition entropy. The results are sure to surprise you! P.S. Want to know which visualization technique reigns supreme? Read the full article here Influence of uncertainty visualization on cognitive load in a safety-critical, time-critical decision-making task
Localization of eye saccadic signatures in electrooculograms using sparse representations with data driven dictionaries
In this paper, we propose two methods for localizing saccadic eye movement signatures from Electrooculograms (EOG). The first approach uses a sparse representation of data-driven dictionaries of saccadic movements. In this approach, we match the EOG subsequence with the dictionary element using distance metrics to identify the saccades. The second approach is to compare a saccadic signature template with the EOG subsequence using Dynamic Time Warping (DTW). We find that the proposed methods have advantages over one another in context specific applications. The first method is significantly faster with considerable accuracy, while the second approach is more accurate.
Modeling and Analysis of Electrodes for Electrooculography
Selection of suitable electrodes for practical applications in electrooculography (EOG) is an open research problem. The present paper compares electrodes made of various materials (Copper, gold, silver and Ag-Ag-Cl) in terms of SNR, shape and surface area and employs statistical analysis to address the issue of choice of electrodes. A low-cost dry electrode assembly for EOG has also been proposed. The preliminary findings suggest that the proposed set of electrodes improve the quality of EOG recordings and are thus suitable for a wide range of EOG studies and BCI applications. Besides, the design of the electrodes has been tested on a number of subjects and found to ensure a more comfortable fit compared to the conventional electrodes and may hence be suitable for use over a long period of time.
Active Sensors for the Acquisition of Physiological Signals
The acquisition of physiological signals from human subjects has been an important research area for quite some time. Common issues involved in standard schemes for acquisition and processing of physiological signals, such as the possibility of the electrodes being easily damaged, or the probability of irritation upon prolonged usage, necessitate the development of active sensors for the acquisition of physiological signals. The present paper proposes the use of gold-plated copper electrodes with active compensation to obtain electroencephalogram (EEG), electrooculogram (EOG), and electrocardiogram (ECG) signals. The quality of the signal obtained has been compared with those obtained with standard sensors. The paper has two significant contributions: the proposal of sensors with active compensation, and preparation of a composite database.
