Usman Roshan

Usman Roshan

New Jersey Institute of Technology

H-index: 17

North America-United States

About Usman Roshan

Usman Roshan, With an exceptional h-index of 17 and a recent h-index of 11 (since 2020), a distinguished researcher at New Jersey Institute of Technology, specializes in the field of Machine learning, Deep learning, Medical AI, Bioinformatics.

His recent articles reflect a diverse array of research interests and contributions to the field:

Accuracy of TextFooler black box adversarial attacks on 01 loss sign activation neural network ensemble

DS 644-005: Introduction to Big Data

An AI system for evaluating pass fail in fundamentals of laparoscopic surgery from live video in realtime with performative feedback

A cascaded neural network system for rating student performance in surgical knot tying simulation

Accuracy of white box and black box adversarial attacks on a sign activation 01 loss neural network ensemble

CS 634: Data Mining

Defense against adversarial attacks based on stochastic descent sign activation networks on medical images

Defending against substitute model black box adversarial attacks with the 01 loss

Usman Roshan Information

University

Position

Associate Professor Department of Computer Science

Citations(all)

1457

Citations(since 2020)

423

Cited By

1157

hIndex(all)

17

hIndex(since 2020)

11

i10Index(all)

29

i10Index(since 2020)

13

Email

University Profile Page

New Jersey Institute of Technology

Google Scholar

View Google Scholar Profile

Usman Roshan Skills & Research Interests

Machine learning

Deep learning

Medical AI

Bioinformatics

Top articles of Usman Roshan

Title

Journal

Author(s)

Publication Date

Accuracy of TextFooler black box adversarial attacks on 01 loss sign activation neural network ensemble

arXiv preprint arXiv:2402.07347

Yunzhe Xue

Usman Roshan

2024/2/12

DS 644-005: Introduction to Big Data

Usman Roshan

2023

An AI system for evaluating pass fail in fundamentals of laparoscopic surgery from live video in realtime with performative feedback

Yunzhe Xue

Andrew Hu

Rohit Muralidhar

Justin W Ady

Advaith Bongu

...

2023/12/5

A cascaded neural network system for rating student performance in surgical knot tying simulation

Yunzhe Xue

Olanrewaju Eletta

Justin W Ady

Nell M Patel

Advaith Bongu

...

2023/6/26

Accuracy of white box and black box adversarial attacks on a sign activation 01 loss neural network ensemble

Yunzhe Xue

Usman Roshan

2023/3/1

CS 634: Data Mining

Usman Roshan

2023

Defense against adversarial attacks based on stochastic descent sign activation networks on medical images

International Journal of Pattern Recognition and Artificial Intelligence

Yanan Yang

Frank Y Shih

Usman Roshan

2022/3/15

Defending against substitute model black box adversarial attacks with the 01 loss

arXiv preprint arXiv:2009.09803

Yunzhe Xue

Meiyan Xie

Usman Roshan

2020/9/1

Two-stage and dual-decoder convolutional U-Net ensembles for reliable vessel and plaque segmentation in carotid ultrasound images

Meiyan Xie

Yunzhu Li

Yunzhe Xue

Lauren Huntress

William Beckerman

...

2020/12/14

Brain tumor classification with tumor segmentations and a dual path residual convolutional neural network from MRI and pathology images

Yunzhe Xue

Yanan Yang

Fadi G Farhat

Frank Y Shih

Olga Boukrina

...

2020

An Ensemble-Based Confidence Score to Increase Accuracy of Carotid Ultrasound Vessel Lumen Segmentation by Convolutional Neural Networks

Journal of Vascular Surgery

Lauren A Huntress

Meiyan Xie

Shih-Yau G Huang

William Beckerman

Saum Rahimi

...

2020/7/1

Towards adversarial robustness with 01 loss neural networks

Yunzhe Xue

Meiyan Xie

Usman Roshan

2020/12/14

A multi-path decoder network for brain tumor segmentation

Yunzhe Xue

Meiyan Xie

Fadi G Farhat

Olga Boukrina

AM Barrett

...

2020

On the transferability of adversarial examples between convex and 01 loss models

IEICE Technical Report; IEICE Tech. Rep.

Miki Tanaka

Isao Echizen

Hitoshi Kiya

2023/1/19

Robust binary classification with the 01 loss

arXiv preprint arXiv:2002.03444

Yunzhe Xue

Meiyan Xie

Usman Roshan

2020/2/9

Accurate and adversarially robust classification of medical images and ECG time-series with gradient-free trained sign activation neural networks

Zhibo Yang

Yanan Yang

Yunzhe Xue

Frank Y Shih

Justin Ady

...

2020/12/16

A multi-path 2.5 dimensional convolutional neural network system for segmenting stroke lesions in brain MRI images

NeuroImage: Clinical

Yunzhe Xue

Fadi G Farhat

Olga Boukrina

AM Barrett

Jeffrey R Binder

...

2020/1/1

Defending against black-box adversarial attacks with gradient-free trained sign activation neural networks

Yunzhe Xue

Meiyan Xie

Zhibo Yang

Usman Roshan

2020/10/2

CS 675-850: Introduction to Machine Learning

Usman Roshan

2020

Challenges in predicting glioma survival time in multi-modal deep networks

Abdulrhman Aljouie

Yunzhe Xue

Meiyan Xie

Usman Roshan

2020/12/16

See List of Professors in Usman Roshan University(New Jersey Institute of Technology)