arXiv · Machine Learning Theory· Talha Ansar (University of Engineering and Technology, Lahore, Pakistan), Waqar Muhammad Ashraf (The Alan Turing Institute, London, UK), Alejandro Coca-Castro (The Alan Turing Institute, London, UK), Manvendra Janmaijaya (The Alan Turing Institute, London, UK), Ramit Debnath (University of Cambridge, Cambridge, UK), J. Scott Hosking (The Alan Turing Institute, London, UK)·· 4 hr agoAI score20
数据驱动的英国气溶胶监测传感器最优选址
Data-driven Optimal Sensor Placement for Aerosol Monitoring in the UK
AI brief
研究提出数据驱动的传感器选址框架，将卷积高斯神经过程嵌入 DeepSensor，用于英国气溶胶监测。遗传优化结合惰性评估与缓存使平均计算时间降低 60%（10±3 对 25±7 分钟），序列选址性能接近贪心求解器；以 CAMS 参考场构建回溯 oracle 基准，Joint-MI 驱动的遗传选址在确定 5 个站点后 Joint NLL 提升约 22%。
Source: arXiv · Machine Learning Theory · arxiv.org