Noshin Ulfat

ORCID: 0000-0003-3883-4433
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Software Engineering Research
  • Software Testing and Debugging Techniques
  • Natural Language Processing Techniques
  • Innovative Approaches in Technology and Social Development
  • Industrial Vision Systems and Defect Detection
  • Smart Cities and Technologies
  • ICT in Developing Communities
  • Image and Object Detection Techniques
  • Software Reliability and Analysis Research
  • Medical Image Segmentation Techniques

Pennsylvania State University
2023

United International University
2023

University of Notre Dame
2023

Bangladesh University of Engineering and Technology
2021-2022

A code generation model generates by taking a prompt from comment, existing code, or combination of both. Although models (e.g., GitHub Copilot) are increasingly being adopted in practice, it is unclear whether they can successfully be used for unit test without fine-tuning strongly typed language like Java. To fill this gap, we investigated how well three (Codex, GPT-3.5-Turbo, and StarCoder) generate tests. We two benchmarks (HumanEval Evosuite SF110) to investigate the effect context on...

10.48550/arxiv.2305.00418 preprint EN cc-by arXiv (Cornell University) 2023-01-01

Bangladesh (a low-income country) has a significant number of people dependent on alms for daily survival. These people, who we address as extremely impoverished (EIP) are deprived even basic healthcare. Their extreme levels poverty, coupled with low literacy skills, and complete lack access to technology means that they unaware existing low-cost/free healthcare services (as arranged by local hospitals) available EIPs. In this paper, gap carefully-crafted solution, Dakter Bari term in...

10.1145/3449118 article EN Proceedings of the ACM on Human-Computer Interaction 2021-04-13

Edge detection is a widely used low-level operation done in computer vision applications and image processing tasks. The primary purpose of edge to discover distinguish sharp discontinuities from an image. Since edges give boundaries between different regions the image, these can be classify objects for segmentation matching purposes. This first step many applications. remarkably reduces amount data filters out undesired or less significant information gives useful There are some algorithms...

10.1145/3542954.3543008 article EN 2022-03-10
Coming Soon ...