Non-Obtrusive Detection of Concealed Metallic Objects Using Commodity WiFi Radios

Hanif, Asif; Chughtai, Muhammad Saad; Qureshi, Abuzar Ahmad; Aleem, Abdullah; Munir, Farasat; Tahir, Muhammad; Uppal, Momin

doi:10.1109/glocom.2018.8647871

Cited by 8 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The suspicious items in this literature refer to the items with material types of metal and liquid. Hanif et al 26 proposed to use of multiple Wi-Fi receiving devices to detect hidden metals on pedestrians in a low-cost and non-interfering way. The principle is that the reflection of radio signals on metal objects is different from that on non-metal objects, resulting in a specific pattern of CSI created by metals.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Environment-independent textile fiber identification using Wi-Fi channel state information

Zhang,

2024

Textile Research Journal

View full text Add to dashboard Cite

Textile fiber identification is a technique that can help identify the type of target textile fiber. Existing methods usually rely on expensive detection instruments, specialized researchers, and complex processing techniques. The large number of textile fibers makes it difficult for researchers to use a stable and fast method for identification. This paper introduces a textile fiber identification method based on Wi-Fi signals, and at the same time, in the actual measurement, the signal characteristics of Wi-Fi are usually interfered with by the hardware noise and multipath propagation of channel state information (CSI) measurement equipment. To eliminate the inherent noise of CSI, we designed a denoising method based on the CSI data acquisition of textile fiber samples in independent environments. Then, the features of Wi-Fi signal wavelet packet decomposition could be extracted more stably, and the principal component analysis (PCA) method was used to reduce the data dimension. Finally, the convolutional neural network (CNN) was used to classify the data features. We conducted extensive experiments to verify the effectiveness of the proposed method. The results show that the proposed method can identify all 14 kinds of common textile fibers used in the experiment, and the average accuracy is 93.25%.

show abstract

Section: Related Workmentioning

confidence: 99%

“…8 Researchers have explored CSI-based applications, such as user identity recognition, 9 physiological index recognition, 10 indoor positioning, 11 and object material recognition. 12 Among them, the material recognition technology based on CSI has been developed rapidly and has shown great potential in the field of textile fiber recognition.…”

mentioning

confidence: 99%

Environment-independent textile fiber identification using Wi-Fi channel state information

Zhang,

2024

Textile Research Journal

View full text Add to dashboard Cite

show abstract

“…Furthermore, captured Wi-Fi signals are utilized to recognize human activity [50]- [53] as well as recognize gestures [54]- [57], and track and classify moving objects [58]. For materials, Wi-Fi sensing experiments are considered to distinguish between metals and insulators [59]- [62], estimate the moisture content in wooden samples and wheat [63], [64], and measure the dielectric properties of liquids [65].…”

Section: Wi-fi Based Techniquesmentioning

confidence: 99%

Measurement of Construction Materials Properties Using Wi-Fi and Convolutional Neural Networks

et al. 2022

View full text Add to dashboard Cite

The process of identifying the physical properties of raw construction materials is vital in several industrial and quality assurance applications. Ideally, this process needs to be performed without damaging the sample and at low-cost, while obtaining high-accurate results. In this work, a novel non-destructive construction materials classification tool is proposed. The proposed method is based on passing Wi-Fi signals through the observed samples, then analyzing the Channel State Information (CSI) magnitude and phase components. The collected CSI data packets are pre-processed by performing an averaging operation. Then, the resulting data are divided into training and validation sets and used to train Convolutional Neural Networks (CNNs). Here, the trained CNN models are formulated either as classifiers or regression models, depending on the material under test. If the objective is to sort materials within specific classes, then the CNN is formulated as a classifier. Alternatively, if the goal is to estimate a continuously varying parameter in a material, then the CNN is formulated as a regression model. Furthermore, as per the collected data, the proposed method is used to identify the construction materials based on their thickness, water content value (moisture), and compaction. The obtained experimental results effectively demonstrate the potential and merits of the proposed method. Overall, the trained CNN models achieved a 100% validation accuracy and a low validation loss, which confirms that the method is valid and highly accurate.INDEX TERMS Channel state information (CSI), classification, construction materials, convolutional neural network (CNN), Wi-Fi sensing.[1], [2]. In this work, we focus on observing and measuring three physical parameters namely, thickness, moisture content, and degree of compaction, in different individual raw construction materials. The conducted experiments were designed to study the internal physical properties of the observed materials, as well as evaluate the proposed method's performance robustness to variations in physical traits such as thickness. These parameters have a substantial significance in the industry and quality assurance processes. Furthermore, the existing material classification methods that investigate the mentioned parameters often have a compromise between accuracy, cost, and deployability in practical setups. In the industry, there is considerable interest in measuring the

show abstract

Chloride detection in concrete using wireless fidelity (Wi-Fi) signal

Paul,

Al Mamun,

Hasan

et al. 2024

Innov. Infrastruct. Solut.

View full text Add to dashboard Cite

Non-Obtrusive Detection of Concealed Metallic Objects Using Commodity WiFi Radios

Cited by 8 publications

References 13 publications

Environment-independent textile fiber identification using Wi-Fi channel state information

Environment-independent textile fiber identification using Wi-Fi channel state information

Measurement of Construction Materials Properties Using Wi-Fi and Convolutional Neural Networks

Chloride detection in concrete using wireless fidelity (Wi-Fi) signal

Contact Info

Product

Resources

About