Currently I am working towards understanding the qualitative nature of sleep physiology in an aging cohort using signal processing and machine learning tools.
Areas of specialism
- Sleep Electrophysiology
- Wearable devices
- Signal Processing and Machine learning
- Brain computer interfaces
Indicators of esteem
Awarded the ‘Prof S Radhakrishnan Award for best PhD Thesis in Biomedical Engineering, Oct 2020’ during the 57th Convocation of Indian Institute of Technology (IIT) Madras.
Awarded the ‘Institute Research Award 2019-20’ as a recognition of Quality and Quantity of Research work done during my MS-PhD degree at the Indian Institute of Technology (IIT) Madras.
Nocturnal disturbance is frequently observed in dementia and is a major contributor to institutionalisation. Unobtrusive technology that can quantify sleep/wake and determine bed occupancy during the major nocturnal sleep episode may be beneficial for long-term clinical monitoring and the carer. Such technologies have, however, not been validated in older people. Here we assessed the performance of the Withings Sleep Mattress (WSM) in a heterogenous older population to ensure external validity.
Objective. This study introduces and evaluates a novel target identification method, latent common source extraction (LCSE), that uses subject-specific training data for the enhancement of detection of steady-state visual evoked potential (SSVEP). Approach. LCSE seeks to construct a common latent representation of the SSVEP signal subspace that is stable across multiple trials of electroencephalographic (EEG) data. The spatial filter thus obtained improves the signal-to-noise ratio (SNR) of the SSVEP components by removing nuisance signals that are irrelevant to the generalized signal representation learnt from the given data. In this study a comparison of SSVEP identification performance between the proposed method, extended canonical correlation analysis (ExtCCA) and multiset canonical correlation analysis (MsetCCA) was conducted using SSVEP benchmark data of 40 targets recorded from 35 subjects to validate the effectiveness of the LCSE framework. Main results. The results indicate that the LCSE framework significantly outperforms the other two methods in terms of both classification accuracy and information transfer rates (ITRs). Significance. The significant improvement in the target identification performance demonstrates that the proposed LCSE method can be seen as a promising potential candidate for efficient SSVEP detection in brain-computer interface (BCI) systems.
This study illustrates and evaluates a novel subject-specific target detection framework, sum of squared correlations (SSCOR), for improving the performance of steady-state visual evoked potential (SSVEP) based brain-computer interfaces (BCIs). The SSCOR spatial filter learns a common SSVEP representation space through the optimization of the individual SSVEP templates. The projection onto this SSVEP response subspace improves the signal to noise ratio (SNR) of the SSVEP components embedded in the recorded electroencephalographic (EEG) data. To demonstrate the effectiveness of the proposed framework, the target detection performance of the SSCOR method is compared with the state of the art task-related component analysis (TRCA). The evaluation is conducted on a 40 target SSVEP benchmark data collected from 35 subjects. The results of the extensive comparisons of the performance metrics show that the proposed SSCOR method outperforms the TRCA method. The ensemble version of the SSCOR framework provides an offline simulated information transfer rate (ITR) of 387 ± 9 bits/min which is much higher than that of the ensemble TRCA approach (max. ITR 216 ± 27 bits/min). The significant improvement in the detection accuracy and simulated ITR demonstrates the efficacy of the proposed framework for target detection in SSVEP based BCI applications.
Traditional spatial filters used for steady-state visual evoked potential (SSVEP) extraction such as minimum energy combination (MEC) require the estimation of the background electroencephalogram (EEG) noise components. Even though this leads to improved performance in low signal to noise ratio (SNR) conditions, it makes such algorithms slow compared to the standard detection methods like canonical correlation analysis (CCA) due to the additional computational cost. In this paper, Periodic component analysis (πCA) is presented as an alternative spatial filtering approach to extract the SSVEP component effectively without involving extensive modelling of the noise. The πCA can separate out components corresponding to a given frequency of interest from the background electroencephalogram (EEG) by capturing the temporal information and does not generalize SSVEP based on rigid templates. Data from ten test subjects were used to evaluate the proposed method and the results demonstrate that the periodic component analysis acts as a reliable spatial filter for SSVEP extraction. Statistical tests were performed to validate the results. The experimental results show that πCA provides significant improvement in accuracy compared to standard CCA and MEC in low SNR conditions. The results demonstrate that πCA provides better detection accuracy compared to CCA and on par with that of MEC at a lower computational cost. Hence πCA is a reliable and efficient alternative detection algorithm for SSVEP based brain-computer interface (BCI).
Recently, filter bank analysis has been used in several detection methods to extract selective frequency features across multiple brain computer interface (BCI) modalities due to its effectiveness and simple structure. In this work, we propose filter bank technique as a standard preprocessing method for popular training free multi-channel steady-state visual evoked potential (SSVEP) detection methods to overcome subject-specific performance differences and a general improvement in detection accuracy. Our study validates the effectiveness of filter bank extensions by comparing performance differences of multichannel methods with their filter bank counterparts using a forty target SSVEP benchmark dataset collected across thirty five subjects. The results demonstrate that the proposed two stage (a filter bank stage followed by SSVEP detection) implementation of popular multichannel algorithms provide significant improvement in performance at short datalengths of < 2.75 s (p < 0.001) and can be viewed as a potential standard detection approach across all SSVEP identification problems.
•A novel approach that maps EEG data onto an exactly periodic subspace is proposed.•EPSD employs the periodic characteristics of the SSVEP response to enhance its SNR.•EPSD exhibits robust performance compared to the other commonly used spatial filters.•The study confirms that EPSD is promising detection algorithm for SSVEP based BCI. A novel exactly periodic spatial filtering (EPSD) approach, that provides a robust detection performance, is introduced and evaluated in this study. The proposed method exploits the temporal properties of the steady-state visual evoked potential (SSVEP) response to construct an orthogonal and exactly periodic mapping that enhances the signal to noise ratio (SNR) of the SSVEP embedded in the electroencephalogram (EEG) data. The subspace of interest is constructed via the elimination of the signals spaces that does not constitute the exact period of the target frequency. The EPSD is evaluated on a 35 subject benchmark dataset collected using a 40 target SSVEP BCI system. The results reveal that the proposed EPSD spatial filter significantly enhances the performance of target detection. Further statistical tests also confirm that the EPSD is a potential alternative to the existing SSVEP spatial filters for realizing an efficient BCI system.