My name is Kushal Borkar. I am pursuing my Masters' by Research (MS) in Computer Vision at HAI, IIIT Hyderabad under the guidance of Prof. C V Jawahar (IIIT Hyderabad). Prior to this, I obtained my bachelor’s degrees in Electronics and Communication Engineering from IIIT, SriCity, Chittoor.
My primary research interest lies in the space of Computer Vision and AI, especially in understanding the interaction between vision, language, and applied Healthcare in AI.
I am actively looking for intuitive opportunities to work on challenging real-world problems where I can apply my acquired knowledge and learn, construct, develop, and evolve.
Every so often, while considered not occupied with academics or work, I set aside out some time for reading a novel or a blog post, watching anime, tuning in to podcasts, playing Evony or sharing moments with my family.
I am still figuring out what I am doing with my life. But hey, nice to meet you!
Research work involves developing new AI based solutions in Healthcare domain as part of the Intel Applied Center (INAI) initiative.
Designed and improved the accessibility of multi-sourced data for AR-VR product by automating the data scraping process from 5 various data sources & built the regression model.
Designed and implemented the content-based filtering algorithm to generate personalised product recommendations by utilizing word2vec to analyze product title and various similarity metrics to form a hybrid model.
Selected for Master of Science by Research in Computer Science and Engineering under the guidance of Prof. C V Jawahar.
Accepted as an research fellow under the Applied AI in Healthcare(HAI) at IIIT Hyderabad.
Interned at Varidus in Spring, 2020.
Paper on Image Dehazing by approximating and eliminating the additional airlight component accepted to Neurocomputing, 2020.
Paper on Video Dehazing using temporal and spatial coherence of the hazy video accepted to ICVGIP, 2018.
Anusha Chaturvedi, Kushal Borkar, U Deva Priyakumar, Vinod P.K.
Kushal Borkar, Anusha Chaturvedi, Vinod P.K., Raju Surampudi Bapi.
Kushal Borkar and Snehasis Mukherjee, Neurocomputing, 2020.
Kushal Borkar and Snehasis Mukherjee, Proc. of ICVGIP 2018, IIIT Hyderabad, ACM, pp. 42:1-42:9.
Kushal Borkar and Snehasis Mukherjee, arXiv:1808.08610, 2018
Interactive Machine Learning
Current machine learning based systems mostly work in inference mode, which implies that one gives an input to the system, and gets an output. Thereafter, the only choice is to accept or reject the output. We have developed a new algorithm, which allows “human in the loop” design. Here an ML system produces an output (possibility highly erroneous), a doctor sees it and provide quick and limited corrections. The ML model takes the feedback into account, retrains itself in real time, and produces a new output. The doctor sees the new output and corrects again. The iterations continue until a doctor is mostly satisfied with the output.
Ayu - Characterization of Healthy Ageing from Neuroimaging Data with Deep Learning and rsfMRI
In this work, we propose an age prediction pipeline Ayu which consists of data preprocessing, feature selection and an attention-based model for deep learning architecture for brain age assessment on a dataset (N = 638, age-range 20-88) comprising rsfMRI images from the Cambridge Centre for Ageing and Neuroscience (Cam-CAN) repository of a healthy population.
Covid Cough Detector
In this work, I worked on a Covid-19 Cough Detector using MFCCs and Chroma based features from 10 seconds cough audio recording of the person and applying a CNN based Architecture to classify COVID-19 positive patient or not.
This work was done on IISc ”Co-Swara” Dataset.