8 papers
Designing Automation Boundaries for Trustworthy Smart Medication Support
Liqian You, Jianlong Zhou
Smart medication systems increasingly automate medication recognition, reminders, and logging. However, automation in home medication routines should be carefully bounded, as users…
A Survey of TinyML Applications in Beekeeping for Hive Monitoring and Management
Willy Sucipto, Jianlong Zhou, Ray Seung Min Kwon +1
Honey bee colonies are essential for global food security and ecosystem stability, yet they face escalating threats from pests, diseases, and environmental stressors. Traditional h…
ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability
Zhiyu Zhu, Jiayu Zhang, Zhibo Jin +2
Attribution algorithms are essential for enhancing the interpretability and trustworthiness of deep learning models by identifying key features driving model decisions. Existing fr…
Can LLM Assist in the Evaluation of the Quality of Machine Learning Explanations?
Bo Wang, Yiqiao Li, Jianlong Zhou +1
EXplainable machine learning (XML) has recently emerged to address the mystery mechanisms of machine learning (ML) systems by interpreting their 'black box' results. Despite the de…
Narrowing Information Bottleneck Theory for Multimodal Image-Text Representations Interpretability
Zhiyu Zhu, Zhibo Jin, Jiayu Zhang +4
The task of identifying multimodal image-text representations has garnered increasing attention, particularly with models such as CLIP (Contrastive Language-Image Pretraining), whi…
E-LENS: User Requirements-Oriented AI Ethics Assurance
Jianlong Zhou, Fang Chen
Despite the much proliferation of AI ethical principles in recent years, there is a challenge of assuring AI ethics with current AI ethics frameworks in real-world applications. Wh…