Dr. RuiDong Qi

Publications

Selected Contributions

Density-peak clustering with principled automatic center discovery via curve optimization and inflection-point modeling.
Privacy-aware QoS prediction through personalized federated learning with topology-aware hierarchical aggregation.
Evaluation emphasizes reproducible protocols: standard clustering metrics, baseline-controlled QoS comparisons, and robustness under noisy regimes.

2025

An Adaptive Density Peak Clustering Algorithm Based on N-ary Bézier Reverse Curve Optimization

Le Yang, RuiDong Qi & Jian-tao Zhou

Proceedings of the 21st Annual Meeting of the International Conference on Intelligent Computing (ICIC 2025), 2025. (Conference Paper)

Abstract

Clustering is a fundamental technique in unsupervised learning. This paper proposes an adaptive density peak clustering algorithm using N-ary Bézier inverse-curve optimization for automatic cluster-center selection, with gamma processing and entropy weighting to reduce complexity. Experiments report gains on AMI, ARI, and FMI versus automatic baselines.

DOI

Keywords:

Adaptive density clusteringBézier optimizationCluster center selection

GIDC: A Gaussian Inflection-Based Framework for Automatic Density Peak Clustering

YueQi Wang, RuiDong Qi & Jian-tao Zhou

IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA), 2025. (Conference Paper)

Abstract

GIDC applies contrast-weighted filtering and Gaussian inflection-point analysis on decision-graph γ-curves to stabilize automatic cluster-center detection under noise and smooth densities, improving accuracy and robustness over state-of-the-art methods.

DOI

Keywords:

Density-based clusteringGaussian fittingUnsupervised learning

Personalized Hierarchical Topology-Aware Federated Learning: An Approach for QoS Prediction

CongRong Wu, RuiDong Qi & Jian-tao Zhou

IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA), 2025. (Conference Paper)

Abstract

We propose Personalized Hierarchical Topology-Aware Federated Learning (pHTAFed) for privacy-aware QoS prediction, combining network topology paths with hierarchical aggregation. Results on two real-world datasets show improved accuracy over distributed and centralized baselines.

DOI

Keywords:

QoS predictionFederated learningWeb services