P
Pradnya Kulkarni
Researcher at Massachusetts Institute of Technology
Publications - 25
Citations - 122
Pradnya Kulkarni is an academic researcher from Massachusetts Institute of Technology. The author has contributed to research in topics: Contextual image classification & Image retrieval. The author has an hindex of 4, co-authored 22 publications receiving 54 citations. Previous affiliations of Pradnya Kulkarni include Maharashtra Institute of Technology & Federation University Australia.
Papers
More filters
Book ChapterDOI
Recommender System in eLearning: A Survey
TL;DR: This paper reviews the main paradigms of recommendation systems using explicit and implicit feedback and the various methodologies that have been implemented to design recommender systems to enhance learning.
Proceedings ArticleDOI
Conversational AI: An Overview of Methodologies, Applications & Future Scope
TL;DR: This study is intended to shed light on the latest research in Conversational AI architecture development and also to highlight the improvements that these novel innovations have achieved over their traditional counterparts.
Proceedings ArticleDOI
Analysis of Classifiers for Prediction of Type II Diabetes Mellitus
Rahul Barhate,Pradnya Kulkarni +1 more
TL;DR: This paper analyzes the different classification algorithms based on a patient's health history to aid doctors identify the presence of type II diabetes as well as promote early diagnosis and treatment.
Proceedings ArticleDOI
Diabetic Retinopathy Classification using a Combination of EfficientNets
Sagar Karki,Pradnya Kulkarni +1 more
TL;DR: In this article, the authors proposed a method for classifying the severity of diabetic retinopathy using deep learning and achieved a quadratic kappa score of 0.924377 on the APTOS test dataset.
Journal ArticleDOI
Visual character n-grams for classification and retrieval of radiological images
TL;DR: It is argued that Classifying regions of interests would reduce the number of comparisons necessary for finding similar images from the database and hence would reduced the time required for retrieval of past similar cases.