Multi-Position Object Material Recognition Based on Circular–Fresnel Hybrid WiFi Sensing Model

View at publisher Summarise with VIRAT
Authors: Chuxin Kong, Fangya Jia, Min Peng
Cited by: 0
References: 15

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Object recognition is essential in intelligent applications such as smart security and warehouse logistics. Traditional WiFi-based methods often show low sensitivity at certain positions due to multipath effects. This paper proposes a Circular–Fresnel Hybrid (CFH) propagation model to improve detection sensitivity at specific positions. A Dynamic-to-Static Power Ratio (DPR) method is introduced to select motion-sensitive subcarriers, reducing static environmental influence. A CNN-LSTM network is employed to extract spatiotemporal features from multiple receiving antennas. Experiments demonstrate that the proposed approach achieves high sensitivity and reliable recognition at targeted positions, offering an effective solution for indoor WiFi-based object recognition.

Fields of Study & Subjects

Indoor and Outdoor Localization Technologies Wireless Signal Modulation Classification Radar Systems and Signal Processing

Publication details

Journal / source
International Conference on Communication Networks and Machine Learning (CNML)
Pages
600–604
Publication date
30 January 2026
Language
EN