Aseem Pratap Subedi

Room 9219, CII

RPI

Troy, NY 12180

I’m a PhD Student in Mechanical Engineering in the Center for Modeling, Simulation, & Imaging in Medicine (CeMSIM) at Rensselaer Polytechnic Institute. My research focuses in neuroimaging and physiological sensing to precisely assess motor-skills in end-to-end fashion, through robust AI-based modelling. I have a 5-year experience leveraging statistical and SoTA AI techniques for time-series data, including wavenet, BERT-based foundation models, unsupervised algorithms, LoRA and others.

My current research aims to assess surgical trainees’ dexterity and cognitive skills more accurately, eliminating both human biases and the need to tailor domain-specific data for clinical applications. I am advised by Prof. Suvranu De, collaborating closely with Prof. Rahul and Prof. Lora Cavuoto.

selected publications

×

Deep learning in fNIRS: a review

Condell Eastmond*, Aseem Subedi*, Suvranu De, and Xavier Intes

Publisher: Society of Photo-Optical Instrumentation Engineers

Abs URL

Significance: Optical neuroimaging has become a well-established clinical and research tool to monitor cortical activations in the human brain. It is notable that outcomes of functional near-infrared spectroscopy (fNIRS) studies depend heavily on the data processing pipeline and classification model employed. Recently, deep learning (DL) methodologies have demonstrated fast and accurate performances in data processing and classification tasks across many biomedical fields. Aim: We aim to review the emerging DL applications in fNIRS studies. Approach: We first introduce some of the commonly used DL techniques. Then, the review summarizes current DL work in some of the most active areas of this field, including brain–computer interface, neuro-impairment diagnosis, and neuroscience discovery. Results: Of the 63 papers considered in this review, 32 report a comparative study of DL techniques to traditional machine learning techniques where 26 have been shown outperforming the latter in terms of the classification accuracy. In addition, eight studies also utilize DL to reduce the amount of preprocessing typically done with fNIRS data or increase the amount of data via data augmentation. Conclusions: The application of DL techniques to fNIRS studies has shown to mitigate many of the hurdles present in fNIRS studies such as lengthy data preprocessing or small sample sizes while achieving comparable or improved classification accuracy.