AquaCubeAI-Powered Monitoring Turbidity on-board Φsat-2
为解决沿海水质监测延迟问题，提出AquaCubeAI，一种轻量级机器学习方法，在Φsat-2卫星上直接处理多光谱图像以实时估计浊度。
0 citationsRead paper
Selected work
Representative Papers
Sustainability of Open-Source Machine Learning Robustness Assessment Tools: A Repository Mining Study
研究通过GitHub挖掘分析了28个开源机器学习鲁棒性评估工具的维护和持续性问题，发现活跃度不均，强调需将这些工具视为不断发展的软件系统。
0 citationsRead paper
Detection of Christmas tree plantations from high-resolution aerial imagery. A case study in the French Morvan
该研究针对圣诞树种植园在遥感影像中的识别难题，通过引入硬负样本挖掘策略改进深度学习方法，有效提升了识别精度和泛化能力。
0 citationsRead paper
Multi-Sensor Mapping of Vulnerable Urban Settlements Using SAR, Multispectral, and Hyperspectral Imagery: A Case Study in Córdoba, Argentina
本文使用多传感器深度学习框架，结合SAR、多光谱和高光谱影像，解决了阿根廷科尔多瓦非正式定居点的识别问题。
0 citationsRead paper
Studying, Identifying, and Fixing Hidden Technical Debt in AI-Intensive Cyber-Physical Systems
This study addresses the challenges posed by hidden and complex AI-related technical debt in AI-intensive cyber-physical systems (AI-CPS), which is significantly more difficult to identify and manage than in traditional systems. Through empirical analysis of AI ecosystems and code repositories, developer interviews, and static code analysis, this work systematically characterizes AI-CPS-specific forms of technical debt for the first time. It proposes targeted mechanisms for detection and remediation and introduces an innovative agent-driven automated tool to enable continuous monitoring and governance of AI technical debt. The resulting framework advances a systematic understanding of technical debt in AI-CPS and demonstrates the feasibility and effectiveness of the proposed tool in real-world scenarios.
0 citationsRead paper
Recent publications
Latest Papers
AquaCubeAI-Powered Monitoring Turbidity on-board Φsat-2
为解决沿海水质监测延迟问题，提出AquaCubeAI，一种轻量级机器学习方法，在Φsat-2卫星上直接处理多光谱图像以实时估计浊度。
0 citationsRead paper
Sustainability of Open-Source Machine Learning Robustness Assessment Tools: A Repository Mining Study
研究通过GitHub挖掘分析了28个开源机器学习鲁棒性评估工具的维护和持续性问题，发现活跃度不均，强调需将这些工具视为不断发展的软件系统。
0 citationsRead paper
Detection of Christmas tree plantations from high-resolution aerial imagery. A case study in the French Morvan
该研究针对圣诞树种植园在遥感影像中的识别难题，通过引入硬负样本挖掘策略改进深度学习方法，有效提升了识别精度和泛化能力。
0 citationsRead paper
Multi-Sensor Mapping of Vulnerable Urban Settlements Using SAR, Multispectral, and Hyperspectral Imagery: A Case Study in Córdoba, Argentina
本文使用多传感器深度学习框架，结合SAR、多光谱和高光谱影像，解决了阿根廷科尔多瓦非正式定居点的识别问题。
0 citationsRead paper
Studying, Identifying, and Fixing Hidden Technical Debt in AI-Intensive Cyber-Physical Systems
This study addresses the challenges posed by hidden and complex AI-related technical debt in AI-intensive cyber-physical systems (AI-CPS), which is significantly more difficult to identify and manage than in traditional systems. Through empirical analysis of AI ecosystems and code repositories, developer interviews, and static code analysis, this work systematically characterizes AI-CPS-specific forms of technical debt for the first time. It proposes targeted mechanisms for detection and remediation and introduces an innovative agent-driven automated tool to enable continuous monitoring and governance of AI technical debt. The resulting framework advances a systematic understanding of technical debt in AI-CPS and demonstrates the feasibility and effectiveness of the proposed tool in real-world scenarios.
0 citationsRead paper