Intelligent Edge Computing
为解决边缘设备资源限制下的高效数据处理问题，提出了一种基于工作负载预测的WACI-HJ方法，优化了哈希连接操作，提高了查询效率和资源利用率。
0 citationsRead paper
Selected work
Representative Papers
HalluPrism: When Multimodal Uncertainty Should Diagnose, Not Decide
研究提出HalluPrism方法，通过视觉干扰等手段诊断多模态大语言模型的错误类型，以提高故障分类准确性。
0 citationsRead paper
Interpretable statistical feature engineering for early disruption prediction in the short pulse ADITYA tokamak
本文针对短脉冲托卡马克装置的早期扰动预测问题，提出了一种基于统计特征工程和机器学习的方法，通过提取等离子体诊断数据中的统计描述符，并使用决策树进行特征选择及随机森林分类器训练，实现了稳定且高效的预测性能。
0 citationsRead paper
Data-Driven Reconstruction of Spatially Resolved Electron and Ion Energy Distributions from Macroscopic Plasma Quantities with Deep Neural Networks
This study addresses the challenge of measuring kinetic energy distributions in low-temperature plasmas by proposing a deep learning-based nonlinear inverse mapping method. Utilizing 2D-3V PIC-MCC data, U-Net, FNO, and MeshGraphNet models were trained to reconstruct microscopic energy distributions from macroscopic observables. This work validates for the first time that macroscopic quantities contain sufficient information to infer kinetic properties, establishing a new paradigm for surrogate kinetic modeling. Results demonstrate that the reconstructed distributions accurately reproduce bulk and sheath characteristics, with FNO exhibiting superior performance and key physical parameters aligning closely with reference data. These findings offer a novel pathway for next-generation plasma diagnostics.
0 citationsRead paper
ChainLearn: A Blockchain-Based Capacity-Aware Framework for Federated Ensemble Learning
This work addresses the challenge of heterogeneous computational resources across hospitals in medical imaging federated learning, which often renders standard algorithms ineffective. The authors propose a heterogeneous federated ensemble learning framework that does not require a unified model architecture. By evaluating each participant’s computational throughput, the system dynamically assigns tailored models—such as MobileNetV3-Small, EfficientNet-B0, or ResNet-50—and performs weighted ensemble inference off-chain. A blockchain-based mechanism, implemented via Solidity smart contracts, manages participant registration, performance metrics, and ensemble weights, while only uploading hashes and scalar values to preserve privacy and efficiency. Experiments on PneumoniaMNIST and DermaMNIST demonstrate that the method achieves calibration error no worse than uniform-weight ensembles and accuracy comparable to FedAvg, with a per-round communication overhead of merely 224 bytes—over 910,000 times lower than FedAvg.
0 citationsRead paper
Recent publications
Latest Papers
Intelligent Edge Computing
为解决边缘设备资源限制下的高效数据处理问题，提出了一种基于工作负载预测的WACI-HJ方法，优化了哈希连接操作，提高了查询效率和资源利用率。
0 citationsRead paper
HalluPrism: When Multimodal Uncertainty Should Diagnose, Not Decide
研究提出HalluPrism方法，通过视觉干扰等手段诊断多模态大语言模型的错误类型，以提高故障分类准确性。
0 citationsRead paper
Interpretable statistical feature engineering for early disruption prediction in the short pulse ADITYA tokamak
本文针对短脉冲托卡马克装置的早期扰动预测问题，提出了一种基于统计特征工程和机器学习的方法，通过提取等离子体诊断数据中的统计描述符，并使用决策树进行特征选择及随机森林分类器训练，实现了稳定且高效的预测性能。
0 citationsRead paper
Data-Driven Reconstruction of Spatially Resolved Electron and Ion Energy Distributions from Macroscopic Plasma Quantities with Deep Neural Networks
This study addresses the challenge of measuring kinetic energy distributions in low-temperature plasmas by proposing a deep learning-based nonlinear inverse mapping method. Utilizing 2D-3V PIC-MCC data, U-Net, FNO, and MeshGraphNet models were trained to reconstruct microscopic energy distributions from macroscopic observables. This work validates for the first time that macroscopic quantities contain sufficient information to infer kinetic properties, establishing a new paradigm for surrogate kinetic modeling. Results demonstrate that the reconstructed distributions accurately reproduce bulk and sheath characteristics, with FNO exhibiting superior performance and key physical parameters aligning closely with reference data. These findings offer a novel pathway for next-generation plasma diagnostics.
0 citationsRead paper
ChainLearn: A Blockchain-Based Capacity-Aware Framework for Federated Ensemble Learning
This work addresses the challenge of heterogeneous computational resources across hospitals in medical imaging federated learning, which often renders standard algorithms ineffective. The authors propose a heterogeneous federated ensemble learning framework that does not require a unified model architecture. By evaluating each participant’s computational throughput, the system dynamically assigns tailored models—such as MobileNetV3-Small, EfficientNet-B0, or ResNet-50—and performs weighted ensemble inference off-chain. A blockchain-based mechanism, implemented via Solidity smart contracts, manages participant registration, performance metrics, and ensemble weights, while only uploading hashes and scalar values to preserve privacy and efficiency. Experiments on PneumoniaMNIST and DermaMNIST demonstrate that the method achieves calibration error no worse than uniform-weight ensembles and accuracy comparable to FedAvg, with a per-round communication overhead of merely 224 bytes—over 910,000 times lower than FedAvg.
0 citationsRead paper