WiMi: Target Material Identification with Commodity Wi-Fi Devices

Feng, Chao; Xiong, Jie; Chang, Liqiong; Wang, Ju; Liu, Chen; Fang, Dingyi; Tang, Zhanyong

doi:10.1109/icdcs.2019.00075

Cited by 44 publications

(8 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such noise can manifest in the CSI amplitude and phase readings ś both are essential for obtaining accurate DFS spectrograms. For example, prior studies show that the CSI phase readings can vary from 0 to 2𝜋 across different wireless packets, and the CSI amplitude readings contain much impulse noise [8]. Such a noise level can severely affect the accuracy of gesture recognition.…”

Section: Takedownmentioning

confidence: 99%

See 1 more Smart Citation

Wi-Learner

Feng

Wang

Jiang

et al. 2022

Proc. ACM Interact. Mob. Wearable Ubiquitous Technol.

Self Cite

View full text Add to dashboard Cite

Contactless RF-based sensing techniques are emerging as a viable means for building gesture recognition systems. While promising, existing RF-based gesture solutions have poor generalization ability when targeting new users, environments or device deployment. They also often require multiple pairs of transceivers and a large number of training samples for each target domain. These limitations either lead to poor cross-domain performance or incur a huge labor cost, hindering their practical adoption. This paper introduces Wi-Learner, a novel RF-based sensing solution that relies on just one pair of transceivers but can deliver accurate cross-domain gesture recognition using just one data sample per gesture for a target user, environment or device setup. Wi-Learner achieves this by first capturing the gesture-induced Doppler frequency shift (DFS) from noisy measurements using carefully designed signal processing schemes. It then employs a convolution neural network-based autoencoder to extract the low-dimensional features to be fed into a downstream model for gesture recognition. Wi-Learner introduces a novel meta-learner to "teach" the neural network to learn effectively from a small set of data points, allowing the base model to quickly adapt to a new domain using just one training sample. By so doing, we reduce the overhead of training data collection and allow a sensing system to adapt to the change of the deployed environment. We evaluate Wi-Learner by applying it to gesture recognition using the Widar 3.0 dataset. Extensive experiments demonstrate Wi-Learner is highly efficient and has a good generalization ability, by delivering an accuracy of 93.2% and 74.2% - 94.9% for in-domain and cross-domain using just one sample per gesture, respectively.

show abstract

Section: Takedownmentioning

confidence: 99%

“…6(a). To alleviate this impact, we first adopt the DWT algorithm [8] to decompose the raw signal into different level's detail coefficients and approximation coefficients. Then, a detail coefficient threshold is applied to each level for discarding the clutter.…”

Section: Signal Pre-processingmentioning

confidence: 99%

Wi-Learner

Feng

Wang

Jiang

et al. 2022

Proc. ACM Interact. Mob. Wearable Ubiquitous Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Ubiquitous Sensing-based Solutions. Recent research studies techniques that utilize wireless signals to identify the liquid types utilizing interactions between liquid content and radio waves [13,16,26,27,74,75,79,81,84]. However, these solutions also require specialized equipment and setup such as large antennas which are not portable.…”

Section: Related Workmentioning

confidence: 99%

Detecting counterfeit liquid food products in a sealed bottle using a smartphone camera

Sun

Tan

Ren

et al. 2022

Proceedings of the 20th Annual International Conference on Mobile Systems, Applications and Services

View full text Add to dashboard Cite

We are witnessing a surge in the reported cases of counterfeit liquid products in the market including olive oil, honey, and alcohol. Counterfeiters often adulterate the liquid products by replacing a large portion of the authentic content with cheaper substitutes (e.g., mixing vodka with cheaper alcohol or potentially toxic methanol). Exacerbating the problem, the counterfeits are packaged and sealed to factory standards, rendering it extremely difficult for an average consumer to identify them. While solutions exist, they are often impractical for the general public as they require specialized and costly equipment. To overcome these limitations, we propose Liq-uidHash, a novel counterfeit liquid food product detection system. LiquidHash is a practical solution that only requires the use of a commodity smartphone to detect adulterated liquid products without opening the bottles. LiquidHash works by detecting and tracking the shape and movement of air bubbles that form inside the bottles. We implement LiquidHash and evaluate its feasibility with real-world experiments under varying conditions with a total of more than 500 minutes of video recording and observe an overall detection accuracy of up to 95%. CCS CONCEPTS• Human-centered computing → Smartphones; Mobile phones; • Computing methodologies → Computer vision.

show abstract

“…Model-based Wi-Fi sensing [18] has made remarkable advancement after 10 years of development, and has led to many new research areas of fine-grained sensing, including indoor localization [19], [20], [21], [22], trajectory tracking [23], [24], [25], material identification [26], hand gesture recognition [27], inertial measurements [28], etc. mDTrack [22] proposes a joint approach to estimate angle of arrival (AoA), time of flight (ToF) and Doppler effect simultaneously, achieving the decimeter-level resolution for indoor localization.…”

Section: A Wi-fi Sensing Model-based Vs Learning-basedmentioning

confidence: 99%

“…Nopphon et al [23] extract Doppler frequency from CSI, and use it to track the hand trajectory with centimeter-level accuracy. WiMi [26] proposes a sophisticated system that can identify the type of materials regardless of its motion state. WiWrite [27] observes the different signal reflection patterns caused by different hand gestures, and proposes a method to realize precise character recognition and word estimation.…”

Section: A Wi-fi Sensing Model-based Vs Learning-basedmentioning

confidence: 99%

Eliminating the Barriers: Demystifying Wi-Fi Baseband Design and Introducing the PicoScenes Wi-Fi Sensing Platform

Jiang¹,

Luan²,

Ren³

et al. 2020

Preprint

View full text Add to dashboard Cite

Research on Wi-Fi sensing over the past decade has been thriving, but not smooth. Three major barriers severely hamper the research, namely, the unknown baseband design and its influence on CSI, inability to access the low-level hardware controls and the lack of a flexible and versatile software toolkit for hardware control. This paper tries to break the above three barriers from the following aspects. First, an in-depth study on the baseband design of QCA9300, the popular CSI-enabled Wi-Fi NIC, is presented. The lessons learned is of great guiding significance for understanding what other commercial off-theshelf NICs. Second, several valuable features of QCA9300 are unlocked for research, such as the arbitrary tuning for both the carrier frequency and baseband sampling rate. By leveraging the unlocked features, we identify three important types of CSI distortion, and pinpoint their origin through extensive evaluations. Last, we develop and release PicoScenes, a powerful, hardwareunified and extensible Wi-Fi sensing system. PicoScenes allows direct access to the unlocked features of QCA9300 and IWL5300, and therefore greatly facilitate the research on Wi-Fi sensing. It also supports the SDR-based Wi-Fi sensing by embedding a 802.11a/g/n/ac/ax software baseband implementation. We release PicoScenes at https://zpj.io/ps.

show abstract

WiMi: Target Material Identification with Commodity Wi-Fi Devices

Cited by 44 publications

References 18 publications

Wi-Learner

Wi-Learner

Detecting counterfeit liquid food products in a sealed bottle using a smartphone camera

Eliminating the Barriers: Demystifying Wi-Fi Baseband Design and Introducing the PicoScenes Wi-Fi Sensing Platform

Contact Info

Product

Resources

About