Recent years have witnessed the rapid development in research topic of WiFi sensing that automatically senses human with commercial devices. This work falls into two major categories, i.e., activity recognition and indoor localization. The former utilizes devices to recognize daily activities such as smoking, walking, dancing. latter one, localization, can be used for navigation, location-based services, through-wall surveillance. key rationale behind this type is people behaviors influence...

Regular free-weight exercise helps to strengthen the body's natural movements and stabilize muscles that are important strength, balance, posture of human beings. Prior works have exploited wearable sensors or RF signal changes (e.g., WiFi Blue tooth) for activity sensing, recognition countingetc.. However, none them incorporate three key factors necessary a practical monitoring system: recognizing activities on site, assessing their qualities, providing useful feedbacks bodybuilder...

With the rapid development of mobile devices and crowdsourcing platforms, spatial has attracted much attention from database community, specifically, refers to sending a location-based request workers according their positions. In this paper, we consider an important problem, namely reliable diversity-based (RDB-SC), in which tasks (such as taking videos/photos landmark or firework shows, checking whether not parking spaces are available) time-constrained, moving towards some directions. Our...

Gesture recognition has emerged recently as a promising application in our daily lives. Owing to low cost, prevalent availability, and structural simplicity, RFID shall become popular technology for gesture recognition. However, the performance of existing RFID-based systems is constrained by unfavorable intrusiveness users, requiring users attach tags on their bodies. To overcome this, we propose GRfid, novel device-free system based phase information output COTS devices. Our work stems...

Fine-grained person perception such as body segmentation and pose estimation has been achieved with many 2D 3D sensors RGB/depth cameras, radars (e.g. RF-Pose), LiDARs. These solutions require images, depth maps or point clouds of bodies input. In this paper, we take one step forward to show that fine-grained is possible even 1D sensors: WiFi antennas. Specifically, used two sets antennas acquire signals, i.e., transmitter set receiver set. Each contains three horizontally lined-up a regular...

Activity monitoring, a crucial task in many applications, is often conducted expensively using video cameras. Effectively monitoring large field by analyzing images from multiple cameras remains challenging issue. Other approaches generally require the tracking objects to attach special devices, which are infeasible scenarios. To address issue, we propose use RF tag arrays for activity where data mining techniques play critical role. The RFID technology provides an economically attractive...

Device-free object tracking provides a promising solution for many localization and systems to monitor non-cooperative objects, such as intruders, which do not carry any transceiver. However, existing device-free solutions mainly use special sensors or active RFID tags, are much more expensive compared passive tags. In this paper, we propose novel motion detection method using named Twins. The leverages newly observed phenomenon called critical state caused by interference among We...

With the rapid development of mobile devices and crowdsourcing platforms, spatial has attracted much attention from database community. Specifically, refers to sending location-based requests workers, based on their current positions. In this paper, we consider a scenario, in which each worker set qualified skills, whereas task (e.g., repairing house, decorating room, performing entertainment shows for ceremony) is time-constrained, under budget constraint, required skills. Under will study...

Physical-layer identification utilizes unique features of wireless devices as their fingerprints, providing authenticity and security guarantee. Prior physical-layer techniques on radio frequency (RFID) tags require nongeneric equipments are not fully compatible with existing standards. In this paper, we propose a novel system, GenePrint, for UHF passive tags. The GenePrint prototype system is implemented by commercial reader, USRP-based monitor, off-the-shelf Our solution generic completely...

Device-to-device communication is important to emerging mobile applications such as Internet of Things and social networks. Authentication key agreement among multiple legitimate devices the first step build a secure channel. Existing solutions put into physical proximity use common radio environment proof identities secret agree on same key. However they experience very slow bit generation rate high errors, requiring several minutes 256-bit In this work, we design implement an...

WiFi-based Human Gesture Recognition (HGR) becomes increasingly promising for device-free human-computer interaction. However, existing approaches have not been ready real-world deployment due to the limited scalability, especially unseen gestures. The reason behind is that when introducing gestures, prior works collect a large number of samples and re-train model. While recent advance few-shot learning has brought new opportunities solve this problem, overhead effectively reduced. This...

With the advance in automatic speech recognition, voice user interface has gained popularity recently. Since COVID-19 pandemic, VUI is increasingly preferred online communication due to its non-contact. Additionally, various ambient noise impedes public applications of interfaces requirement audio-only recognition methods for a high signal-to-noise ratio. In this paper, we present Wavoice, first noise-resistant multi-modal system that fuses two distinct sensing modalities, i.e.,...

The objective of private authentication for radio frequency identification (RFID) systems is to allow valid readers explicitly authenticate their dominated tags without leaking tags' information. To achieve this goal, RFID issue encrypted messages the reader, and reader searches key space locate tags. Due lack efficient updating algorithms, previous schemes are vulnerable many active attacks, especially compromising attack. In paper, we propose a strong lightweight protocol, SPA. By...

Cardinality estimation and tag authentication are two major issues in large-scale Radio Frequency Identification (RFID) systems. While there exist both per-tag probabilistic approaches for the cardinality estimation, RFID-oriented protocols mainly based: reader authenticates one at each time. For a batch of tags, current RFID systems have to identify them then authenticate sequentially, incurring large volume data huge communication cost. We study issue propose first approach, termed as...

Prior work on anti-collision for Radio Frequency IDentification (RFID) systems usually schedule adjacent readers to exclusively interrogate tags avoiding reader collisions. Although such a pattern can effectively deal with collisions, the lack of readers' collaboration wastes numerous time scheduling process and dramatically degrades throughput identification. Even worse, within overlapped interrogation regions (termed as contentious tags), even if number is very small, introduce significant...

Shopping behavior data are of great importance to understand the effectiveness marketing and merchandising efforts. Online clothing stores capable capturing customer shopping by analyzing click stream carts. Retailers with physical stores, however, still lack effective methods identify comprehensive behaviors. In this paper, we show that backscatter signals passive RFID tags can be exploited detect record how customers browse which items clothes they pay attention to, usually match with. The...

Comparing to well protected data frames, Wi-Fi management frames (MFs) are extremely vulnerable various attacks. Since MFs transmitted without encryption or authentication, attackers can easily launch attacks by forging the MFs. In a collaborative environment with many sniffers, such be detected sensing anomaly RSS changes. However, it is quite difficult identify these spoofing assistance from other nodes. By exploiting some unique characteristics (e.g., rapid spatial decorrelation,...

Different from online shopping, in-store shopping has few ways to collect the customer behaviors before purchase. In this paper, we present design and implementation of an on-site Customer Behavior IDentification system based on passive RFID tags, named CBID. By collecting analyzing wireless signal features, CBID can detect track tag movements further infer corresponding behaviors. We model three main objectives behavior identification by concrete problems solve them using novel protocols...

Device to device (D2D) communication is expected become a promising technology of the next-generation wireless systems. Security issues have technical barriers D2D due its "open-air" nature and lack centralized control. Generating symmetric keys individually on different parties without key exchange or distribution desirable but challenging. Recent work has proposed extract from measurement physical layer random variations channel, e.g., channel state information (CSI) orthogonal...

Device-free based object tracking provides a promising solution for many localization and systems to monitor non-cooperative objects which do not carry any transceiver such as intruders. However, existing device-free solutions mainly use sensors active RFID tags, are much more expensive compared passive tags. In this paper, we propose novel motion detection method using named Twins. The leverages phenomenon called critical state caused by interference among We theoretically explain via an...

This paper presents RF-Mehndi, a passive commercial RFID tag array formed identifier. The key RF-Mehndi novelty is that when the user's fingertip touching on surface during communication, backscattered signals by become user-dependent and unique. Hence, if we enhance communication modality of many personal cards nowadays in case card gets lost or stolen, it cannot be used illegally adversaries. To harvest such benefit, have two observations designing RF-Mehndi. first observation tags are...

Regular free-weight exercise helps to strengthen natural movements and stabilize muscles that are important strength, balance, posture of human beings. Prior works have exploited wearable sensors or RF signal changes for activity sensing, recognition, counting, etc.. However, none them incorporated three key factors necessary a practical monitoring system: recognizing activities on site, assessing their qualities, providing useful feedbacks the bodybuilder promptly. Our FEMO system provides...

The technological revolution of long-awaited energy-saving and vision-friendly displays represented by bistable display technology is coming. Here we discuss methods, challenges, opportunities for implementing in terms molecular design, device structure, further expansion, required criteria, hopefully benefiting the light-related community.

Face authentication (FA) schemes are universally adopted. However, current FA systems mainly camera-based and hence susceptible to face occlusion (e.g., facial masks) vulnerable spoofing attacks 3D-printed masks). This paper exploits the penetrability, material sensitivity, fine-grained sensing capability of millimeter wave (mmWave) build an anti-spoofing system, named mmFace. It scans human by moving a commodity off-the-shelf (COTS) mmWave radar along specific trajectory. The signals...

Screen locking/unlocking is important for modern smart phones to avoid the unintentional operations and secure personal stuff. Once phone locked, user should take a specific action or provide some secret information unlock phone. The existing unlocking approaches can be categorized into four groups: motion, password, pattern, fingerprint. Existing do not support well due deficiency of security, high cost, poor usability. We collect 200 users' handwaving actions with their discover an...