Recently Wi-Fi positioning systems are gaining popularity in pervasive computing and machine learning community. However, collecting a sufficient amount of calibration data is rather tedious and time consuming, especially indoor scenarios where GPS coverage is unavailable. To alleviate this problem, we present a semi-supervised learning from “route-annotated data”, where a human walks to collect radio signal strength (RSS) values while route information is annotated independently. The basic idea is to allocate temporary location information to each RSS values by using route information as dynamic programming, thereby many conventional machine learning methods become adaptable. Experimental results with real-world deployment demonstrate the practical utility of the method.
Projects Frustratingly Simplified Deployment in Wi-Fi Localization via Route Annotation.
Frustratingly Simplified Deployment in Wi-Fi Localization via Route Annotation.
Comments are disabled for this post
- Presenting our paper on data-driven Bluetooth RSSI simulation with neural generative models at IPIN2023 2023/09/14
- Device-Free Multi-Person Indoor Localization Using the Change of ToF 2023/03/03
- Presenting our paper on Device-Free Multi-Person Indoor Localization Using the Change of ToF at PerCom2023 2023/02/28
- Our paper on Efficient Adaptive Beacon Deployment Optimization for Indoor Crowd Monitoring has been published in IMWUT. 2023/01/24
- Presenting our paper on Robust Continuous MaxEnt IRL with RRT at IV2022 2022/06/09
- Presenting our paper on Efficient Indoor Localization Model Construction by Sequential Recommendation of Data Gathering Position based on Bayesian Optimization at IPIN2021 2021/11/29
- Adaptive incremental beacon placement optimization for crowd density monitoring applications 2021/11/01
- Presenting 2 papers at ACM SIGSPATIAL 2021 2021/11/01
- Fine-grained Urban Dynamics Prediction using Large-Scale Mobile Phone Location Data 2021/10/05
- Robustifying Wi-Fi localization by Between-Location data augmentation 2021/09/28