Skip to content
Hot storiesContinuously updated

研究人员推出5G Open RAN无监督干扰检测基准

1 reports1 reporting sourcesUpdated 11 hours ago

Start here

AI overview

针对 5G Open RAN 射频干扰检测缺乏标注数据的问题,研究人员对统计与重构类无监督检测器开展了基准评测。评测基于 10 个异构 5G 环境的 KPI 遥测数据进行,结果显示,统计集成方法(SEM)在留一法评估中取得 0.906 的平均综合得分,在真实标签验证中的平均 F1-score 达到 0.918,表现全面优于 LSTM 与 VAE 等自编码器基线模型。

AI-generated from reports · Updated 11 hours ago

Report timeline

Follow the reports to see different sides of the story.

Nov 4
  1. arXiv 人工智能
    5G Open RAN 无监督干扰检测基准评测

    该研究针对 5G Open RAN 射频干扰检测缺乏标注数据的问题,对统计与重构类无监督检测器开展基准评测。基于 10 个异构 5G 环境的 KPI 遥测数据,统计集成方法(SEM)在留一法评估中取得 0.906 的平均综合得分,真实标签验证平均 F1-score 达 0.918,全面优于 LSTM 与 VAE 等自编码器基线。

Story heat trend

Current heat 7·Comparable peak 10(Nov 4 14:00)·Comparable change, last 24 hours–

02.557.510Nov4Nov4Nov4Nov5

Trends compare only the same parties observed continuously, so the scope can be narrower than current heat counts. Move the pointer or tap the chart to see hourly heat; use the left and right arrow keys on a keyboard.