Harisu Abdullahi Shehu
Victoria University of Wellington, Queensland University of Technology
Papers
7
Total Citations
54
H-Index
5
About
Harisu Abdullahi Shehu is a researcher specializing in affective computing, computer vision, and machine learning, with a particular focus on the challenging problem of emotion categorization from facial expressions. His work addresses a critical real-world limitation: the degradation of emotion recognition accuracy when faces are partially obscured by coverings such as face masks and sunglasses — a concern made increasingly relevant by the COVID-19 pandemic and the growing deployment of intelligent systems in shared human environments. Shehu's most notable contributions include developing robust emotion categorization frameworks that remain effective under adverse conditions, employing attention-based deep learning methods and evolutionary optimization techniques such as Particle Swarm Optimization for feature selection. His comparative studies between human and machine classifier performance provide valuable benchmarks for the field, revealing how both struggle with facial coverings. He has also explored adversarial robustness, proposing anti-attack methods to improve system resilience against malicious inputs. With a growing body of work accumulating over 50 citations across publications since 2021, Shehu is an emerging voice in human-robot interaction and intelligent systems research. His contributions are particularly valuable for researchers designing emotion-aware AI systems intended to function reliably in diverse, real-world conditions.
Research Focus
Key Achievements
Top Papers
- 1
- 2An anti-attack method for emotion categorization from images11 citations · 2022
- 3Particle Swarm Optimization for Feature Selection in Emotion Categorization10 citations · 2021
- 4
- 5
- 6
- 7