Portfolio item number 1
Short description of portfolio item number 1
Posts by Collection
portfolio
Portfolio item number 2
Short description of portfolio item number 2
publications
Investigation of multiple frequency recognition from single-channel steady-state visual evoked potential for efficient brain computer interfaces application
Published in IET Signal Processing, 2018
In this study, the authors have examined a single-channel electroencephalogram from Oz for identification of seven visual stimuli frequencies with multivariate synchronisation index (MSI) and canonical correlation analysis (CCA). Authors investigated the feasibility in three case studies with varying overlapped as well as non-overlapped window lengths. The visual stimuli frequencies ≤10 Hz are considered in case study I and >10 Hz in case study II. Case study III contains frequencies of both case studies I and II. All the case studies revealed that CCA outperforms MSI for reference signals constituting fundamental, one subharmonics, and three super-harmonics. The results revealed that the accuracy of identification improves with 50% overlap in both the algorithms. Further, recognition accuracy is studied with varying combination sub- and super-harmonics for case study III with 50% overlap. The results revealed that CCA and MSI perform better with reference signals constituting fundamental and twice fundamental frequency compared with traditional power spectral density analysis (PSDA). In addition to recognition accuracy, the information bit transfer rate is also higher in CCA relative to MSI and PSDA.
Learning to solve the credit assignment problem
Published in International conference for learning representations(ICLR), 2019
Backpropagation is driving today’s artificial neural networks (ANNs). However, despite extensive research, it remains unclear if the brain implements this algorithm. Among neuroscientists, reinforcement learning (RL) algorithms are often seen as a realistic alternative: neurons can randomly introduce change, and use unspecific feedback signals to observe their effect on the cost and thus approximate their gradient. However, the convergence rate of such learning scales poorly with the number of involved neurons. Here we propose a hybrid learning approach. Each neuron uses an RL-type strategy to learn how to approximate the gradients that backpropagation would provide. We provide proof that our approach converges to the true gradient for certain classes of networks. In both feedforward and convolutional networks, we empirically show that our approach learns to approximate the gradient, and can match or the performance of exact gradient-based learning. Learning feedback weights provides a biologically plausible mechanism of achieving good performance, without the need for precise, pre-specified learning rules.
Wearable myoelectric interface enables high-dose, home-based training in severely impaired chronic stroke survivors
Published in Annals of clinical and translational neurology, 2021
High-intensity occupational therapy can improve arm function after stroke, but many people lack access to such therapy. Home-based therapies could address this need, but they don’t typically address abnormal muscle co-activation, an important aspect of arm impairment. An earlier study using lab-based, myoelectric computer interface game training enabled chronic stroke survivors to reduce abnormal co-activation and improve arm function. Here, we assess feasibility of doing this training at home using a novel, wearable, myoelectric interface for neurorehabilitation training (MINT) paradigm.
Myoelectric Interface for Neurorehabilitation (MINT) Conditioning Improves Arm Function in Severely Impaired Chronic Stroke Survivors
Published in ANNALS OF NEUROLOGY, 2022
Cortical sites critical to language function act as connectors between language subnetworks
Published in Nature communications, 2024
Historically, eloquent functions have been viewed as localized to focal areas of human cerebral cortex, while more recent studies suggest they are encoded by distributed networks. We examined the network properties of cortical sites defined by stimulation to be critical for speech and language, using electrocorticography from sixteen participants during word-reading. We discovered distinct network signatures for sites where stimulation caused speech arrest and language errors. Both demonstrated lower local and global connectivity, whereas sites causing language errors exhibited higher inter-community connectivity, identifying them as connectors between modules in the language network. We used machine learning to classify these site types with reasonably high accuracy, even across participants, suggesting that a site’s pattern of connections within the task-activated language network helps determine its importance to function. These findings help to bridge the gap in our understanding of how focal cortical stimulation interacts with complex brain networks to elicit language deficits.
High-gamma activity is coupled to low-gamma oscillations in precentral cortices and modulates with movement and speech
Published in eneuro, 2024
Decoding speech intent from non-frontal cortical areas
Published in Journal of Neural Engineering, 2025
Brain machine interfaces (BMIs) that can restore speech have predominantly focused on decoding speech signals from the speech motor cortices. A few studies have shown some information outside the speech motor cortices, such as in parietal and temporal lobes, that also may be useful for BMIs. The ability to use information from outside the frontal lobe could be useful not only for people with locked-in syndrome, but also to people with frontal lobe damage, which can cause nonfluent aphasia or apraxia of speech. However, temporal and parietal lobes are predominantly involved in perceptive speech processing and comprehension. Therefore, to be able to use signals from these areas in a speech BMI, it is important to ascertain that they are related to production. Here, using intracranial recordings, we sought evidence for whether, when and where neural information related to speech intent could be found in the temporal and parietal cortices
Insights from Implementing Wearable Technologies for Stroke Rehabilitation Outside Research Laboratories
Published in Archives of Physical Medicine and Rehabilitation, 2025
Restoring communication with speech brain–computer interfaces
Published in Neural Interfaces, 2025
Wearable Myoelectric Interface for Neurorehabilitation (MINT) to Recover Arm Function: a Randomized Controlled Trial
Published in medRxiv, 2025
Abnormal muscle co-activation contributes to arm impairment after stroke. This single-blind, randomized, sham-controlled trial evaluated the feasibility and efficacy of home-based, personalized myoelectric interface for neurorehabilitation (MINT) conditioning to reduce abnormal co-activation and enhance arm function and determine the optimal number of abnormally co-activating muscles to target during training.
talks
Talk 1 on Relevant Topic in Your Field
Published:
This is a description of your talk, which is a markdown file that can be all markdown-ified like any other post. Yay markdown!
Conference Proceeding talk 3 on Relevant Topic in Your Field
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
teaching
Teaching experience 1
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Teaching experience 2
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.