Wireless indoor localization using predictive models with received signal strength information (RSSI) requires proper calibration for reliable position estimates. One remedy is to employ synthetic labels produced by a (generally different) predictive model. But fine-tuning an additional predictor, as well as estimating residual bias of the synthetic labels, demands additional data, aggravating calibration data scarcity in wireless environments. This letter proposes an approach that efficiently uses limited calibration data to simultaneously fine-tune a predictor and estimate the bias of synthetic labels, yielding prediction sets with rigorous coverage guarantees. Experiments on a fingerprinting dataset validate the effectiveness of the proposed method.
翻译：利用接收信号强度信息（RSSI）的预测模型进行无线室内定位，需要经过适当的校准才能获得可靠的位置估计。一种解决方案是采用由（通常不同的）预测模型生成的合成标签。然而，微调额外的预测器以及估计合成标签的残余偏差都需要额外的数据，这加剧了无线环境中校准数据稀缺的问题。本文提出一种方法，能高效利用有限的校准数据，同时微调预测器并估计合成标签的偏差，从而产生具有严格覆盖度保证的预测集。在指纹数据集上的实验验证了所提方法的有效性。
相关内容
微信扫码咨询专知VIP会员