Institution profile

Queen's University Belfast

Academic institutioneurope · gb
Official website
Research library226linked papers
Opportunities0open roles
Selected work

Representative Papers

k-fold Subsampling based Sequential Backward Feature Elimination

Feb 24, 2016International Conference on Pattern Recognition Applications and Methods

To address the redundancy and insufficient discriminability of shape features in human detection, this paper proposes a novel feature selection method integrating filter- and wrapper-based strategies. We innovatively design a k-fold subsampling-driven Sequential Backward Elimination (SBE) framework that simultaneously optimizes feature robustness and discriminability while preserving essential shape representation capability, thereby significantly reducing feature dimensionality. Coupled with a linear SVM classifier, our method is evaluated on the INRIA and ETH pedestrian datasets. Results show that it achieves over 50% faster detection speed and a 2% improvement in mean Average Precision (mAP) compared to the current state-of-the-art approaches; relative to the Deformable Parts Model (DPM), it yields approximately a 9% mAP gain. The proposed framework establishes an interpretable, reusable paradigm for lightweight and efficient human detection through principled feature selection.

5 citationsRead paper

Simultaneously Transmitting and Reflecting Surfaces (STARS) for Multi-Functional 6G

Jan 01, 2025IEEE Network

Emerging 6G multimodal networks demand seamless integration of communication, sensing, computing, and caching—challenging conventional reconfigurable intelligent surfaces (RISs), which support only unidirectional communication. Method: This paper proposes simultaneous transmitting-and-reflecting intelligent surfaces (STARS), capable of both transmission and reflection, thereby enabling integrated functionalities. We establish the first systematic STARS taxonomy, pioneer single-/dual-baseline sensing architectures, and introduce a target-end STARS sensing paradigm. Furthermore, we integrate electromagnetic reconfigurable metasurface design, multi-domain channel modeling, and joint beamforming with edge-coordinated scheduling algorithms. Contribution/Results: The proposed framework achieves a paradigm shift from communication-only to full-stack 6G capabilities, significantly improving spectrum-energy-hardware efficiency: sensing latency is reduced by over 30%, content delivery delay by 40%, and the work actively supports ongoing 3GPP/ITU standardization efforts for STARS.

2 citationsRead paper

Defending against Model Inversion Attacks via Random Erasing

Sep 02, 2024arXiv.org

To address privacy leakage from model inversion (MI) attacks, this paper pioneers the adaptation of Random Erasing (RE)—originally a data augmentation technique—into a data-level privacy defense mechanism. During training, RE probabilistically erases random rectangular regions in input images, thereby actively degrading the model’s capacity to encode fine-grained private details. The method requires no architectural modifications or loss-function alterations, ensuring orthogonality and compatibility with existing defenses, and effectively alleviates the privacy–utility trade-off. Evaluated across 23 diverse experimental settings, our approach achieves state-of-the-art privacy–utility balance: reconstructed images suffer a substantial PSNR degradation of 12.6 dB, while classification accuracy drops by less than 1.2%. It consistently outperforms mainstream defense strategies in both privacy preservation and task performance.

1 citationsRead paper

Is Intelligence Artificial?

Mar 05, 2014arXiv.org

This paper addresses the limitation of existing intelligence definitions—being anthropocentric and lacking cross-species and AI generality—by proposing a consciousness-free, non-quantitative, passive intelligence framework. Methodologically, it decouples intelligence from consciousness for the first time, centering instead on “autonomous goal achievement capability,” and constructs a unified, subjectivity- and algorithm-agnostic evaluation criterion through mechanical process modeling, behaviorally verifiable logic, and philosophical conceptual reconstruction. Key contributions include: (1) establishing a universal intelligence assessment standard applicable to both biological and artificial systems; (2) designing an empirically testable “acid test” for AI as a benchmark for free-thinking systems; and (3) introducing a novel paradigm and operationally feasible validation pathway for investigating the ontological nature of artificial intelligence. (138 words)

1 citationsRead paper
Recent publications

Latest Papers

School Choice with Appeals

Sep 06, 2026

研究探讨了学校选择中的申诉机制如何影响家长报告偏好及分配结果,通过理论分析和实验表明申诉使即时接受法更不易被操纵且效率更高。

0 citationsRead paper