FSTNet: Learning spatial–temporal correlations from fingerprints for indoor positioning

Ren, Qianqian; Wang, Yan; Liu, S M; Lv, Xingfeng

doi:10.1016/j.adhoc.2023.103244

Cited by 6 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1. Observation area at an intersection measurements, its accuracy is comparable to those reported in the literature [13]- [16]. However, the reported accuracy cannot be directly compared with those reported previously because the conditions such as the performance metrics and the situations of localization differ among the publications.…”

Section: Related Worksupporting

confidence: 73%

“…Yang et al [14] proposed a deep neural network-based indoor localization system via spatial and temporal features learned from UWB RSS and distance information based on the time of arrival (ToA). Several methods that combine fingerprinting and deep learning have been proposed [15], [16]. Fingerprint-based indoor localization using a deep neural network that extracts features from the spatial and temporal representations of geomagnetic sequences has been proposed [15].…”

Section: Related Workmentioning

confidence: 99%

“…Fingerprint-based indoor localization using a deep neural network that extracts features from the spatial and temporal representations of geomagnetic sequences has been proposed [15]. Similarly, Ren et al [16] used Wi-Fi RSSI measurements [16].…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Sensor Response-Based Localization Using Spatial Correlation of Nongeotagged Data

Shiraki,

Shioda,

Matsuda

2024

IEEE Sensors J.

View full text Add to dashboard Cite

Sensor devices in future wireless communication systems such as beyond fifth generation (Beyond 5G) and sixth generation (6G) require highly accurate location information. Owing to high power consumption and cost, global navigation satellite system receivers may not be installed on sensor devices, requiring the localization of sensor devices on a wireless sensor network (WSN). In many WSN applications, a spatially dense sensor installation is required to achieve satisfactory coverage. When object detectiontype sensor devices are installed at high density, the responses of spatially proximate sensors are highly correlated. In other words, these sensor responses indirectly include location information. Based on this consideration, we proposed a sensor localization method using the spatial correlation of nongeotagged sensor response data and evaluated its performance. Our method enables location estimation from the response data obtained during environmental monitoring, even for sensors that are not equipped with range functions. The simulation experiments showed that a more accurate sensor localization is possible with an error of 1 m using a wider sensor detection range, even with rough proximity pair ratio settings. In addition, we verified that there is a trade-off between localizability and observability during environmental monitoring, such as the visualization of vehicle positions from sensor responses. Our proposed method may be applied to future urban environments with a large number of sensor devices installed for environmental monitoring.

show abstract

Section: Related Worksupporting

confidence: 73%