PhD student (Computer Science)

Sitemap

A list of all the posts and pages found on the site. For you robots out there, there is an XML version available for digesting as well.

Pages

Posts

Future Blog Post

less than 1 minute read

Published:

This post will show up by default. To disable scheduling of future posts, edit config.yml and set future: false.

Blog Post number 4

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 3

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 2

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 1

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

awards

AI Fellowship

Fusemachines AI Fellowship Nepal| Fusemachines Nepal | 2019 March

Best Project Award

Assessment of weather anomalies and pollution proxies around Kathmandu valley| Department of Electronics and Computer Engineering, IOE, Tribhuvan University | 2019 November

Second Place

Poster Presentation| Federated Foundation Model for Medical Imaging| WVU AI Symposium | 2025 May

experience

Software Engineering Intern

Industry, Leapfrog Technology, Inc
2019 February - 2019 July

  • Worked on data collection, pre-processing, and development of a model (LSTM) for forecasting weather parameters in Kathmandu Valley, and developed a web-app for data visualization of current weather and pollution statistics and to display predicted weather parameters.

Software Engineering Intern

Industry, UBL R&D Center
2019 July - 2019 September

  • Designed and developed a discussion forum as part of a Learning Management System using Django.
  • Worked on the development of the database, REST APIs, and front-end for the discussion forum

Machine Learning Engineer

Industry, Fusemachines
2019 September - 2021 April

Developed AI applications to adhere to designs that support business requirements by researching and developing machine learning models.

  • Led a team in an intelligent surgery project to develop and deploy an ML pipeline to create 3D bones from multiple views of 2D X-ray images
  • Used pseudolabelling to use a large number of unannotated data to track student status in FuseClassroom, an online learning management system
  • Used Elasticsearch to reduce the search space in text comparisons to detect plagiarism between assignments within a class in FuseClassroom

Research Assistant

Research, NepAl Applied Mathematics and Informatics Institute for Research (NAAMII)
2021 July - 2022 April

Conducted research to assist medical personnel in low-income countries like Nepal.

  • Used UNET architecture for segmentation of fetal head to measure fetal head circumference in the HC18 dataset
  • Used a classification algorithm to detect cancer in ultrasound images of breasts
  • Worked on the exploration of semi-supervised techniques and attention across multiple data points to capture complex relationships between data points

Machine Learning Engineer

Industry, coac GmbH
2022 April - 2023 December

Ideated and implemented AI solutions to meet project requirements.

  • Improved OCR and object detection in PDFs containing scanned schematic diagrams
  • Conducted research on optimization algorithms to minimize lockdown in German counties due to the pandemic, and used AI models to replicate a mathematical model to reduce computation time

Graduate Research Assistant

Research, Lane Department of Computer Science and Electrical Engineering, West Virginia University
2024 January - Present

Working on applying AI and ML to improve healthcare.

  • Used deep learning to estimate heart ejection fraction from ECG signals
  • Trained a foundation model for GI endoscopy images using federated learning
  • Used knockoff framework for feature selection in manufacturing

portfolio

publications

Sentence Ranking and Answer Pinpointing in Online Discussion Forums Utilizing User-generated Metrics and Highlights

Published in NASCOIT, 2018

This work presents a framework for extracting precise answers from online discussion forums by combining sentence ranking with user-generated metrics and highlights. The approach enables accurate answer pinpointing, improving search relevance and supporting better question-answering in forums.

Citation: Gautam, S., Shikha, S., Devkota, A. and Pyakurel, S., 2018. Sentence Ranking and Answer Pinpointing in Online Discussion Forums Utilising User-generated Metrics and Highlights. Proceedings of the NaSCoIT.
Download Paper

Near Real-Time Mobile Profiling and Modeling of Fine-Scale Environmental Proxies Along Major Road Lines of Nepal

Published in ICMSI, 2021

We present a methodology using GPS-enabled mobile sensors to collect and model fine-scale environmental proxies (e.g., temperature, CO₂, PM₂.₅) along major roadways in Nepal, demonstrating the effectiveness of ARIMA and RNNs for real-time and historical climate modeling.

Citation: Adhikari, N.B., Gautam, S., Devkota, A., Shikha, S., Pyakurel, S. and Adhikari, M.P., 2020, January. Near Real-Time Mobile Profiling and Modeling of Fine-Scale Environmental Proxies Along Major Road Lines of Nepal. In International Conference on Mobile Computing and Sustainable Informatics (pp. 605-617). Cham: Springer International Publishing.
Download Paper

Multimodal Federated Learning for Secure and Accurate Healthcare AI

Published in arXiv preprint, 2023

This paper reviews the role of multimodal federated learning in healthcare, highlighting its potential to combine diverse medical data while preserving patient privacy. It surveys state-of-the-art approaches, identifies current challenges and limitations, and outlines future directions for advancing secure and effective healthcare AI.

Citation: Thrasher, J., Devkota, A., Siwakotai, P., Chivukula, R., Poudel, P., Hu, C., Bhattarai, B. and Gyawali, P., 2023. Multimodal federated learning in healthcare: a review. arXiv preprint arXiv:2310.09650.
Download Paper

TE-SSL: Time and Event-aware Self Supervised Learning for Alzheimer’s Disease Progression Analysis

Published in MICCAI 2024, 2024

We introduce TE-SSL, a time and event-aware self-supervised learning framework for Alzheimer’s disease progression analysis. By incorporating time-to-event and event data as supervisory signals, TE-SSL improves representation learning and outperforms existing SSL methods in downstream survival analysis tasks.

Citation: Thrasher, J., Devkota, A., Tafti, A.P., Bhattarai, B., Gyawali, P. and Alzheimer’s Disease Neuroimaging Initiative, 2024, October. TE-SSL: Time and Event-aware Self Supervised Learning for Alzheimer’s Disease Progression Analysis. In International Conference on Medical Image Computing and Computer-Assisted Intervention (pp. 324-333). Cham: Springer Nature Switzerland.
Download Paper

AI analysis for ejection fraction estimation from 12-lead ECG

Published in Scientific Reports, 2025

This study investigates the use of 12-lead ECG signals to estimate heart ejection fraction (EF) in a rural Appalachian population. Using a range of machine learning and deep learning models—including Transformers—our analysis shows deep learning models achieve the highest performance (AUROC ~0.86), with specific multi-lead combinations improving accuracy and model interpretability providing insights into predictive features.

Citation: Devkota, A., Prajapati, R., El-Wakeel, A., Adjeroh, D., Patel, B. and Gyawali, P., 2025. AI analysis for ejection fraction estimation from 12-lead ECG. Scientific Reports, 15(1), p.13502.
Download Paper

Federated Foundation Model for GI Endoscopy Images

Published in arXiv preprint, 2025

We propose a federated learning framework to train foundation models for gastrointestinal endoscopy imaging, allowing hospitals to collaboratively develop general-purpose models while keeping data private. Our approach is evaluated on classification, detection, and segmentation tasks, demonstrating improved performance in a privacy-preserving, federated setting.

Citation: Devkota, A., Amireskandari, A., Palko, J., Thakkar, S., Adjeroh, D., Jiang, X., Bhattarai, B. and Gyawali, P.K., 2025. Federated Foundation Model for GI Endoscopy Images. arXiv preprint arXiv:2505.24108.
Download Paper

talks

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.