FitLoc: Fine-grained and low-cost device-free localization for multiple targets over various areas

Chang, Liqiong; Liu, Chen; Wang, Yu; Fang, Dingyi; Wang, Ju; Tong, Xing; Tang, Zhanyong

doi:10.1109/infocom.2016.7524390

Cited by 23 publications

(19 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to CSI, we also apply CrossSense to RSSI-based gesture recognition and compared it with Tele-pathicPhone [60]. We compare our roaming method to Fit-Loc [13], a WiFi signal translation approach for RSSI-based localization.…”

Section: Evaluation Methodologiesmentioning

confidence: 99%

“…Wireless signal transfer has been exploited in prior work in indoor localization to translate wireless fingerprints between different areas within an environment. The transferring method employed by FitLoc [13] is the current stateof-the art. This experiment compares our roaming model against FitLoc's transferring method.…”

Section: Crosssense Versus Fitlocmentioning

confidence: 99%

“…We demonstrate the benefits of CrossSense by applying it to WiFi-based gait identification and gesture recognition, and considering CSI and RSSI based metrics. We compare to five state-of-the-art WiFi sensing methods [26,60,66,76,90] and a wireless signal translation approach [13]. We perform an extensive evaluation across three controlled sites, involving 100 users, 40 gestures, and over 1.2 million wireless activity samples.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

CrossSense

Zhang

Tang

et al. 2018

Proceedings of the 24th Annual International Conference on Mobile Computing and Networking

Self Cite

161

View full text Add to dashboard Cite

We present CrossSense, a novel system for scaling up WiFi sensing to new environments and larger problems. To reduce the cost of sensing model training data collection, CrossSense employs machine learning to train, off-line, a roaming model that generates from one set of measurements synthetic training samples for each target environment. To scale up to a larger problem size, CrossSense adopts a mixture-of-experts approach where multiple specialized sensing models, or experts, are used to capture the mapping from diverse WiFi inputs to the desired outputs. The experts are trained offline and at runtime the appropriate expert for a given input is automatically chosen. We evaluate CrossSense by applying it to two representative WiFi sensing applications, gait identification and gesture recognition, in controlled single-link environments. We show that CrossSense boosts the accuracy of state-of-the-art WiFi sensing techniques from 20% to over 80% and 90% for gait identification and gesture recognition respectively, delivering consistently good performance-particularly when the problem size is significantly greater than that current approaches can effectively handle. CCS CONCEPTS • Networks → Wireless access networks; • Human-centered computing → Ubiquitous and mobile computing systems and tools;

show abstract

Section: Evaluation Methodologiesmentioning

confidence: 99%

Section: Crosssense Versus Fitlocmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

CrossSense

Zhang

Tang

et al. 2018

Proceedings of the 24th Annual International Conference on Mobile Computing and Networking

Self Cite

161

View full text Add to dashboard Cite

show abstract

“…It must be noted that an only K * number of nodes are finally used to create an SW-WSN. In (17) and 18 N(N − 1)))∑ i ≠ j h i j (k). The optimal link π i m * , j m * is introduced in the network iteratively till the localisation error reduces below a desired threshold.…”

Section: Optimal H-node Allocation Using a Heuristic Modelmentioning

confidence: 99%

Cooperative localisation over small world WSN using optimal allocation of heterogeneous nodes

Pandey

Hegde

2018

IET wirel. sens. syst.

View full text Add to dashboard Cite

Localisation of sensor nodes in a wireless sensor network (WSN) is an important problem in various applications like cyber-physical systems, Internet of things and context aware pervasive systems. Cooperative localisation using multidimensional scaling (MDS) has been used successfully in many localisation applications. A primary requirement in MDS is the computation of accurate distance estimates between pairs of nodes in a WSN. However, the estimated distances are erroneous in MDS especially for node pairs that are connected using multiple hops. This leads to an overall increase in error of location estimates. A recent development in social networks called small world phenomena can be introduced in a WSN leading to small world WSN (SW-WSN). SW-WSN exhibits low average path length and high average clustering coefficient and yields accurate distance estimates between pairs of nodes. In this work, a novel cooperative localisation method that uses heterogeneous nodes (H-nodes) is proposed over SW-WSN. In addition, two optimal H-node allocation methods are also developed for the cooperative localisation method. The significance of the proposed method in reducing localisation error, energy consumption, and bandwidth requirement is illustrated by simulations and extensive experiments on a real WSN testbed.

show abstract

“…Therefore, alternative indoor localization techniques have to be invented and developed. Recently, there have been tremendous efforts on the research of indoor localization using various wireless medium or communications, for example, using WiFi signals [5][6][7][8][9][10], Radio Frequency Identification (RFID) [11][12][13][14], Bluetooth [15][16][17], Ultra-Wideband (UWB) [18,19], Acoustic Signals [20][21][22], Inertial Sensor/Measurement Unit (IMU) [23][24][25], or other wireless communication techniques. WiFi and Bluetooth based systems have been deployed in real applications more than the others in the last few decades.…”

Section: Introductionmentioning

confidence: 99%

Recent Advances in Indoor Localization via Visible Lights: A Survey

Rahman

Wang

2020

Sensors

Self Cite

View full text Add to dashboard Cite

Because of the limitations of the Global Positioning System (GPS) in indoor scenarios, various types of indoor positioning or localization technologies have been proposed and deployed. Wireless radio signals have been widely used for both communication and localization purposes due to their popular availability in indoor spaces. However, the accuracy of indoor localization based purely on radio signals is still not perfect. Recently, visible light communication (VLC) has made use of electromagnetic radiation from light sources for transmitting data. The potential for deploying visible light communication for indoor localization has been investigated in recent years. Visible-light-based localization enjoys low deployment cost, high throughput, and high security. In this article, the most recent advances in visible-light-based indoor localization systems have been reviewed. We strongly believe that visible-light-based localization will become a low-cost and feasible complementary solution for indoor localization and other smart building applications.

show abstract

FitLoc: Fine-grained and low-cost device-free localization for multiple targets over various areas

Cited by 23 publications

References 21 publications

CrossSense

CrossSense

Cooperative localisation over small world WSN using optimal allocation of heterogeneous nodes

Recent Advances in Indoor Localization via Visible Lights: A Survey

Contact Info

Product

Resources

About