J
Jennifer G. Dy
Researcher at Northeastern University
Publications - 253
Citations - 9588
Jennifer G. Dy is an academic researcher from Northeastern University. The author has contributed to research in topics: Cluster analysis & Feature selection. The author has an hindex of 41, co-authored 238 publications receiving 7712 citations. Previous affiliations of Jennifer G. Dy include Dana Corporation & Purdue University.
Papers
More filters
Journal ArticleDOI
Feature Selection for Unsupervised Learning
Jennifer G. Dy,Carla E. Brodley +1 more
TL;DR: This paper explores the feature selection problem and issues through FSSEM (Feature Subset Selection using Expectation-Maximization (EM) clustering) and through two different performance criteria for evaluating candidate feature subsets: scatter separability and maximum likelihood.
Journal ArticleDOI
Monitoring Motor Fluctuations in Patients With Parkinson's Disease Using Wearable Sensors
Shyamal Patel,Konrad Lorincz,R. Hughes,N. Huggins,John H. Growdon,David G. Standaert,Metin Akay,Jennifer G. Dy,Matt Welsh,Paolo Bonato +9 more
TL;DR: This paper presents the results of a pilot study to assess the feasibility of using accelerometer data to estimate the severity of symptoms and motor complications in patients with Parkinson's disease, and a support vector machine (SVM) classifier was implemented to estimateThe severity of tremor, bradykinesia and dyskinesian symptoms from accelerometers data features.
Journal ArticleDOI
Automated Diagnosis of Plus Disease in Retinopathy of Prematurity Using Deep Convolutional Neural Networks
James M. Brown,J. Peter Campbell,Andrew Beers,Ken Chang,Susan Ostmo,R.V. Paul Chan,Jennifer G. Dy,Deniz Erdogmus,Stratis Ioannidis,Jayashree Kalpathy-Cramer,Jayashree Kalpathy-Cramer,Michael F. Chiang +11 more
TL;DR: This fully automated algorithm diagnosed plus disease in ROP with comparable or better accuracy than human experts, which has potential applications in disease detection, monitoring, and prognosis in infants at risk of ROP.
Journal ArticleDOI
Impact of imputation of missing values on classification error for discrete data
TL;DR: It is shown that imputation with the tested methods on average improves classification accuracy when compared to classification without imputation, and some classifiers such as C4.5 and Nai@?ve-Bayes were found to be missing data resistant, i.e., they can produce accurate classification in the presence of missing data.
Proceedings Article
Active Learning from Crowds
TL;DR: In this article, the authors employ a probabilistic model for learning from multiple annotators that can also learn the annotator expertise even when their expertise may not be consistently accurate across the task domain.