Deep active learning framework for chest-abdominal CT scans segmentation

L Rokach, Y Aperstein, A Akselrod-Ballin - Expert Systems with Applications, 2024‏ - Elsevier
State-of-the-art deep learning approaches for segmentation require large, high-quality
annotated datasets for training and evaluation. However, the manual processes for creating …

Deuce: Dual-diversity Enhancement and Uncertainty-awareness for Cold-start Active Learning

J Guo, CL Philip Chen, S Li, T Zhang - Transactions of the Association …, 2024‏ - direct.mit.edu
Cold-start active learning (CSAL) selects valuable instances from an unlabeled dataset for
manual annotation. It provides high-quality data at a low annotation cost for label-scarce text …

Tracking and handling behavioral biases in active learning frameworks

D Agarwal, B Natarajan - Information Sciences, 2023‏ - Elsevier
The computational capabilities of AI engines integrated with human knowledge and
experience can help create intelligent human-in-the-loop (HITL) decision systems. Such …

Active Foundational Models for Fault Diagnosis of Electrical Motors

S Anbalagan, SS GP, D Agarwal, B Natarajan… - arxiv preprint arxiv …, 2023‏ - arxiv.org
Fault detection and diagnosis of electrical motors are of utmost importance in ensuring the
safe and reliable operation of several industrial systems. Detection and diagnosis of faults at …

Impacts of behavioral biases on active learning strategies

D Agarwal, O Covarrubias-Zambrano… - … in Information and …, 2022‏ - ieeexplore.ieee.org
Cyber-Physical-Human Systems (CPHS) interconnect humans, physical plants and cyber
infrastructure across space and time. Industrial processes, electromechanical systems …

An Active Regression Learning Method for Quality Evaluation of Molecular Dynamics Data

Y Huang, D Zhao, H Shen - 2024 4th International Conference …, 2024‏ - ieeexplore.ieee.org
Training deep potentials for molecular dynamics simulations via active learning methods is a
prevalent technique. However, a significant drawback of this method is its tendency to get …

Active Learning for Node Classification using a Convex Optimization approach

D Agarwal, B Natarajan - … on Big Data Computing Service and …, 2022‏ - ieeexplore.ieee.org
The recent advancements related to big data analytics in the era of Industry 4.0 are fueled by
development and deployment of decision models based on neural network (NN) …

[PDF][PDF] Introduction to Computer Engineering: Evidence-Based Inclusive Teaching Practices

Z Zhou - 2023‏ - aquila.usm.edu
1. State Clear Learning Goals repeatedly, so students have a clear idea of where they are
going and what it will look like when they get there. This is a practice that creates …

[PDF][PDF] Investigating Core Set-based Active Learning for Text Classification

Y Brenning‏ - downloads.webis.de
Following the exponential growth in the number of readily available documents and texts in
recent years, the need for efficient methods of classification has become increasingly …

Feature Enhancement with Deep Generative Models in Deep Bayesian Active Learning

PE Duymuş - 2022‏ - search.proquest.com
Data-intensive models emerge as new advances in Deep Learning take place. However,
access to annotated datasets with many data points is not constantly prevalent. This …