TagBooth: Deep shopping data acquisition powered by RFID tags

Liu, Tianci; Yang, Lei; Li, Xiangyang; Huang, Huaiyi

doi:10.1109/infocom.2015.7218547

Cited by 32 publications

(12 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…18. Frogeye [10] and TagBooth [11] can achieve the motion perception accuracy of 92.3 % and 89.2 % respectively. All of these tag motion perception method only consider the scenario of persons walking nearby the target RFID tags and ignore continuous human activities in the surveillance area between the reader and target tag.…”

Section: E Accuracy Comparisonmentioning

confidence: 99%

“…So the system can't distinguish these two scenarios. TagBooth [11] is an effective method based on RFID technology to acquire fine-grained deep shopping data using RSSI and phase features with people moving around and fetching tagged goods, which can recognize customer actions of picking and toggling the clothes hanger. The problem similar to Lei Yang' can't extract different features of the RSSI and phase caused by tag motion and continuous movements of human near the target tag.…”

mentioning

confidence: 99%

See 1 more Smart Citation

TMicroscope: Behavior Perception Based on the Slightest RFID Tag Motion

Wang¹,

Ye²,

Malekian³

et al. 2016

ElAEE

View full text Add to dashboard Cite

Behavior perception with fine granularity can offer much more valuable information, e.g. which and why products people are often interested in will not be purchased in shopping. In this paper, we propose a RFID-based method to perceive slight motion of a target product with RFID tag for mining customer's behaviors. However, the interference from human movements in the reading zone is a challenge to result in false positives. To address this problem, we first compute virtual displacements of the target RFID tag and then adopt Support Vector Machines to recognize absence or presence of human motion near the tag. Next, we divide the surveillance region into mm-level grids to construct similarity matrixes of the tracked tag before and after human motion, which can accurately distinguish absence or presence of tag motion. Indeed, the optimization method based on phase-ambiguity is introduced to reduce computations. The results show that our method can achieve the average scenario classification accuracy of 96.3 % and the average slight tag motion perception accuracy of 100 % with the hypersensitivity of 1 mm.

show abstract

Section: E Accuracy Comparisonmentioning

confidence: 99%

mentioning

confidence: 99%

TMicroscope: Behavior Perception Based on the Slightest RFID Tag Motion

Wang¹,

Ye²,

Malekian³

et al. 2016

ElAEE

View full text Add to dashboard Cite

show abstract

“…CBID [4] adopts a Doppler effectbased protocol to detect tag movements. Tagbooth [5] leverages physical-layer information to exploit the motion of tagged commodities by phase and RSS to recognize customers actions. ShopMiner [6] harnesses the distinct yet stable patterns of phase in the time series when customers move their desired items to detect comprehensive shopping behaviors.…”

Section: Related Workmentioning

confidence: 99%

“…They usually calculate customer behavior by Doppler effect, measuring the phase and received signal strength (RSS) of all tagged commodities [4][5][6], and their experiments show that these indicators can be used to induce user behavior effectively, but they have not taken the large calculation amount and long latency into account. We should notice that in a large shopping mall, the quantity of items is huge, which means there are massive data that need to be calculated.…”

Section: Introductionmentioning

confidence: 99%

Mining shopping data with passive tags via velocity analysis

Zhao

Wang

et al. 2018

J Wireless Com Network

View full text Add to dashboard Cite

Unlike online shopping, it is difficult for the physical store to collect customer shopping data during the process of shopping and conduct in-depth data mining. The existing methods to solve this problem only considered how to collect and analyze the data, but they have not paid attention to the large computation amount, bulk data amount, and long time delay, in which they can not feedback user data timely and effectively. In this paper, we present the received signal strength of passive radio frequency identification (RFID) tags that can be used to carry out on-site shopping data mining, such as which items are popular, which goods are customers interested in, which items are usually bought together, which areas have a large customer flow, and what is the order of items being bought by customers. By exploiting the received signal strength indicator (RSSI) information, we calculate the velocity of the items and then leverage machine learning and hierarchical agglomerative clustering to carry out in-depth analysis of velocity data. We implement a prototype in which all components are built by off-the-shelf devices. Meanwhile, we conduct extensive experiments in the real environment. The experiment results show that our methods have low computation and latency, which demonstrate that our proposed system is quite feasible in practical shopping data analysis.

show abstract

“…Thus, the first priority of preprocessor is to unwrap the raw phase readings. As assumed in TagBooth [16], the absolute difference of two adjacent reading phase value should be smaller than π because of the low frequency of hand movement compared with the reader interrogation. For simplicity, we adopt the approach in TagBooth [16] to solve this problem.…”

Section: Preprocessormentioning

confidence: 99%

TagController

Ding

Zhang

et al. 2017

Proceedings of the 14th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services

View full text Add to dashboard Cite

Innovative Human Machine Interface technologies are fundamentally reshaping the way people live, entertain and work. Passive RFID tags, benefiting from its wireless, inexpensive and battery-free sensing ability, are gradually being applied in new-style interaction interfaces, ranging from virtual touch screen to 3D mouse. This paper presents TagController, a universal wireless and battery-free remote controller with two types of interactive actions. The key insight is that the fine-grained phase information extracted from RF signals is capable of perceiving various actions. TagController can recognize 10 actions without any training or prestored profiles by executing a sequence of functional components, i.e. preprocessor, action detector and action recognizer. We have implemented TagController with COTS RFID devices and conducted substantial experiments in different scenarios. The results demonstrate that TagController can achieve an average recognition accuracy of 95.8% and 94.3% in the scenarios of one and two remote controllers, respectively, which promises its feasibility and robustness. CCS CONCEPTS• Human-centered computing → Ubiquitous and mobile computing systems and tools; KEYWORDS Battery-free remote controller, action recognition, COTS RFID ACM Reference format:

show abstract

TagBooth: Deep shopping data acquisition powered by RFID tags

Cited by 32 publications

References 27 publications

TMicroscope: Behavior Perception Based on the Slightest RFID Tag Motion

TMicroscope: Behavior Perception Based on the Slightest RFID Tag Motion

Mining shopping data with passive tags via velocity analysis

TagController

Contact Info

Product

Resources

About