output
20212025
most citedAutomated data processing and feature engineering for deep learning and big data applications: a survey

150 citations

6 papers

cs.DB2025

FastER: On-Demand Entity Resolution in Property Graphs

Shujing Wang, Sibo Zhao, Shiqi Miao +5

Entity resolution (ER) is the problem of identifying and linking database records that refer to the same real-world entity. Traditional ER methods use batch processing, which becom…

cs.LG2024★ 150 cited

Automated data processing and feature engineering for deep learning and big data applications: a survey

Alhassan Mumuni, Fuseini Mumuni

Modern approach to artificial intelligence (AI) aims to design algorithms that learn directly from data. This approach has achieved impressive results and has contributed significa…

cs.CV2024★ 110 cited

A survey of synthetic data augmentation methods in computer vision

Alhassan Mumuni, Fuseini Mumuni, Nana Kobina Gerrar

The standard approach to tackling computer vision problems is to train deep convolutional neural network (CNN) models using large-scale image datasets which are representative of t…

cs.LG2024★ 26 cited

Improving deep learning with prior knowledge and cognitive models: A survey on enhancing explainability, adversarial robustness and zero-shot learning

Fuseinin Mumuni, Alhassan Mumuni

We review current and emerging knowledge-informed and brain-inspired cognitive systems for realizing adversarial defenses, eXplainable Artificial Intelligence (XAI), and zero-shot…

cs.LG2024★ 29 cited

Data augmentation with automated machine learning: approaches and performance comparison with classical data augmentation methods

Alhassan Mumuni, Fuseini Mumuni

Data augmentation is arguably the most important regularization technique commonly used to improve generalization performance of machine learning models. It primarily involves the…

cs.CV2021★ 3 cited

MiNet: A Convolutional Neural Network for Identifying and Categorising Minerals

Emmanuel Asiedu Brempong, Millicent Agangiba, Daniel Aikins

Identification of minerals in the field is a task that is wrought with many challenges. Traditional approaches are prone to errors where there is no enough experience and expertise…