DNN-based Outdoor NLOS Human Detection Using IEEE 802.11ac WLAN Signal

Takahashi, Ryo; Ishida, Shigemi; Fukuda, Akira; Murakami, Tomoki; Otsuki, Shoichiro

doi:10.1109/sensors43011.2019.8956943

Cited by 12 publications

(23 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Desain WLAN yang aman dengan menggunakan firewall packet filtering juga telah dikaji pada penelitian [2]. Pada penelitian [3], alat untuk mendeteksi manusia luar ruang non-line-of-sight (NLOS) berbasis deep neural network (DNN) menggunakan sinyal WLAN IEEE 802.11ac telah dirancang. Ada pula yang membuat antena WLAN multi-input multi-output (MIMO) dengan antena global positioning system (GPS) untuk aplikasi jam tangan pintar [4].…”

Section: Pendahuluanunclassified

Sistem bandwidth WiFi jaringan ad-hoc menggunakan metode class based queue

Hariyanto

Rahayu

2021

JITEL

View full text Add to dashboard Cite

Mobile ad-hoc network (MANET) merupakan jaringan ad-hoc yang dibangun oleh perangkat-perangkat bergerak, salah satunya adalah laptop. Jaringan tersebut merupakan jaringan nirkabel yang bersifat infrastructureless. Jaringan ini mampu mengkomunikasikan node secara peer-to-peer tanpa basic service set (BSS). Ketidakberadaan BSS pada jaringan ini menyulitkan para pengguna dalam mengalokasikan uplink bandwidth bagi node/link kritikal dan mencegah terjadinya flooding pada jaringan. Penelitian ini bertujuan untuk merancang sebuah bandwidth management tool berupa program yang diimplementasikan untuk mengalokasikan uplink bandwidth pada jaringan ad-hoc. Program yang dirancang menggunakan metode CBQ untuk classifying dan scheduling paket. Dari hasil pengujian, sistem bandwidth WiFi jaringan ad-hoc menggunakan metode CBQ ini memiliki kinerja throughput 513,24 Kbps yang diperoleh melalui perhitungan average rounded trip time.

show abstract

Section: Pendahuluanunclassified

Sistem bandwidth WiFi jaringan ad-hoc menggunakan metode class based queue

Hariyanto

Rahayu

2021

JITEL

View full text Add to dashboard Cite

show abstract

“…To alleviate this restriction, a new WiFi sensing framework, called beamforming feedback (BFF)-based sensing, has been proposed [4], [5]. BFF-based sensing performs without explicitly extracting CSI from the PHY layer components but leveraged BFF frames [6], which contain a compressed version of the CSI.…”

Section: Introductionmentioning

confidence: 99%

“…Instead of the BFF-based sensing's benefits of wide applicability, a critical issue remains; to the best of our knowledge, there are no model-driven algorithms, which geometrically estimate the surrounding environment based on mathematical modeling. The existing BFF-based sensing methods [4], [5] are referred to as data-driven methods. The sensing tasks are conducted via pattern matching to a database consisting of a pre-obtained training dataset, which comprises the BFF and corresponding actual-measured target labels (e.g., human locations or device locations).…”

Section: Introductionmentioning

confidence: 99%

Beamforming Feedback-based Model-Driven Angle of Departure Estimation Toward Legacy Support in WiFi Sensing: An Experimental Study

Itahara¹,

Kondo²,

Yamashita³

et al. 2021

Preprint

View full text Add to dashboard Cite

This paper proves that the angle of departure (AoD) estimation using the multiple signal classification (MUSIC) with only WiFi control frames for beamforming feedback (BFF), defined in IEEE 802.11ac/ax, is possible. Although channel state information (CSI) enables model-driven AoD estimation, most BFF-based sensing techniques are data-driven because they only contain the right singular vectors of CSI and subcarrier-averaged stream gain. Specifically, we find that right singular vectors with a subcarrier-averaged stream gain of zero have the same role as the noise subspace vectors in the CSI-based MUSIC algorithm. Numerical evaluations confirm that the proposed BFFbased MUSIC successfully estimates the AoDs and gains for all propagation paths. Meanwhile, this result implies a potential privacy risk; a malicious sniffer can carry out AoD estimation only with unencrypted BFF frames.

show abstract

“…To alleviate this restriction, few studies [3], [4] performed WiFi sensing without explicitly extracting CSI from PHY layer components, but rather leveraged a beamforming feedback matrix (BFM) [5], which is referred to as a compressed version of CSI. However, WiFi access points (APs) and stations (STAs) are mandated to exchange the BFM without encryption to perform OFDM-MIMO transmissions using the IEEE 802.11ac/ax standard [5], [6].…”

Section: Introductionmentioning

confidence: 99%

“…However, existing BFM-based WiFi sensing studies [3], [4] have addressed only a few sensing tasks, while CSI-based WiFi sensing has addressed several tasks [7], [8]. Specifically, studies related to BFM-based WiFi sensing are limited to human detection and localization [3], [4], whereas the CSIbased WiFi sensing acquires various usage models, e.g., human activity recognition [9]- [11], device localization [12], and human vital sensing [13].…”

Section: Introductionmentioning

confidence: 99%

Frame-Capture-Based CSI Recomposition Pertaining to Firmware-Agnostic WiFi Sensing

Hanahara,

Itahara,

Yamashita

et al. 2021

Preprint

View full text Add to dashboard Cite

With regard to the implementation of WiFi sensing agnostic according to the availability of channel state information (CSI), we investigate the possibility of estimating a CSI matrix based on its compressed version, which is known as beamforming feedback matrix (BFM). Being different from the CSI matrix that is processed and discarded in physical layer components, the BFM can be captured using a medium-access-layer framecapturing technique because this is exchanged among an access point (AP) and stations (STAs) over the air. This indicates that WiFi sensing that leverages the BFM matrix is more practical to implement using the pre-installed APs. However, the ability of BFM-based sensing has been evaluated in a few tasks, and more general insights into its performance should be provided. To fill this gap, we propose a CSI estimation method based on BFM, approximating the estimation function with a machine learning model. In addition, to improve the estimation accuracy, we leverage the inter-subcarrier dependency using the BFMs at multiple subcarriers in orthogonal frequency division multiplexing transmissions. Our simulation evaluation reveals that the estimated CSI matches the ground-truth amplitude. Moreover, compared to CSI estimation at each individual subcarrier, the effect of the BFMs at multiple subcarriers on the CSI estimation accuracy is validated.

show abstract

DNN-based Outdoor NLOS Human Detection Using IEEE 802.11ac WLAN Signal

Cited by 12 publications

References 13 publications

Sistem bandwidth WiFi jaringan ad-hoc menggunakan metode class based queue

Sistem bandwidth WiFi jaringan ad-hoc menggunakan metode class based queue

Beamforming Feedback-based Model-Driven Angle of Departure Estimation Toward Legacy Support in WiFi Sensing: An Experimental Study

Frame-Capture-Based CSI Recomposition Pertaining to Firmware-Agnostic WiFi Sensing

Contact Info

Product

Resources

About