Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2509.12870 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911157529346048 |
|---|---|
| author | Wang, Ruichen Ni, Zhikang Wang, Pengzhou Cao, Xiya Li, Zhi Zhang, Bao |
| author_facet | Wang, Ruichen Ni, Zhikang Wang, Pengzhou Cao, Xiya Li, Zhi Zhang, Bao |
| contents | Accurate and personalized environment recognition is essential for seamless indoor positioning and optimized connectivity, yet traditional fingerprinting requires costly site surveys and lacks user-level adaptation. We present a survey-free, on-device sensor-fusion framework that builds a personalized, lightweight multi-source fingerprint (FP) database from pedestrian dead reckoning (PDR), WiFi/cellular, GNSS, and interaction time tags. Matching is performed by an AI-enhanced dynamic time warping module (AIDTW) that aligns noisy, asynchronous sequences. To turn perception into continually improving actions, a cloud-edge online Reinforcement Learning from Human Feedback (RLHF) loop aggregates desensitized summaries and human feedback in the cloud to optimize a policy via proximal policy optimization (PPO), and periodically distills updates to devices. Across indoor/outdoor scenarios, our system reduces network-transition latency (measured by time-to-switch, TTS) by 32-65% in daily environments compared with conventional baselines, without site-specific pre-deployment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_12870 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards personalized, precise and survey-free environment recognition: AI-enhanced sensor fusion without pre-deployment Wang, Ruichen Ni, Zhikang Wang, Pengzhou Cao, Xiya Li, Zhi Zhang, Bao Signal Processing Accurate and personalized environment recognition is essential for seamless indoor positioning and optimized connectivity, yet traditional fingerprinting requires costly site surveys and lacks user-level adaptation. We present a survey-free, on-device sensor-fusion framework that builds a personalized, lightweight multi-source fingerprint (FP) database from pedestrian dead reckoning (PDR), WiFi/cellular, GNSS, and interaction time tags. Matching is performed by an AI-enhanced dynamic time warping module (AIDTW) that aligns noisy, asynchronous sequences. To turn perception into continually improving actions, a cloud-edge online Reinforcement Learning from Human Feedback (RLHF) loop aggregates desensitized summaries and human feedback in the cloud to optimize a policy via proximal policy optimization (PPO), and periodically distills updates to devices. Across indoor/outdoor scenarios, our system reduces network-transition latency (measured by time-to-switch, TTS) by 32-65% in daily environments compared with conventional baselines, without site-specific pre-deployment. |
| title | Towards personalized, precise and survey-free environment recognition: AI-enhanced sensor fusion without pre-deployment |
| topic | Signal Processing |
| url | https://arxiv.org/abs/2509.12870 |