Learning Sequence-Based Fingerprint for Magnetic Indoor Positioning System

Chen, Yuanyi; Zhou, Mingxuan; Zheng, Zengwei

doi:10.1109/access.2019.2952564

Cited by 20 publications

(15 citation statements)

References 36 publications

(54 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2. Assuming that the magnetic permeability is μ and the excited current is I , the magnetic moment M can be expressed as According to a previous work [16], a simplified model can be expressed as follows…”

Section: A Mb Designmentioning

confidence: 99%

“…Technologies, such as Ultra-Wide Band (UWB) [1,2], Image Recognition-Based Positioning (IRBP) [3], radio frequency identification (RFID) [4], and lasers [5]) have been investigated. The magnetic-based positioning method has attracted significant interest for indoor location and navigation [6][7][8][9][10][11][12][13][14][15][16][17] because it is less sensitive to propagation-dependent disturbances, penetration, and multipath effects compared to radio frequency (RF)-based methods. The propagation of the magnetic field is a complex process.…”

Section: Introductionmentioning

confidence: 99%

“…Furthermore, high quality magnetic sensors are required to provide effective coverage within 18 m. To address these issues, a system with a low frequency alternating current signal was considered, which provides a balance between the propagation distance, and immunity [9]. Many related works focusing on magnetic ranging [10][11][12][13][14], magnetic fingerprints positioning [15,16], and attitude estimation [17,18] have been proposed as guidance. Wu et al [14] presented a novel idea that the step-frequency signal is employed as the driving signal to track the optimal resonant frequency, which will maximize the transmission power of two resonant coils.…”

Section: Introductionmentioning

confidence: 99%

“…Tang et al [15] used WLAN RSS fingerprint and magnetic field fingerprint to improve fingerprint's spatial and time characterization and localization accuracy. Chen et al [16] proposed an indoor magnetic-based positioning model by learning sequencebased fingerprint from raw magnetic field sequences, which aimed to overcome the pattern embedded in raw magnetic field sequences that might be locally distorted or scaled. This greatly limits the positioning performance.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Magnetic-Based Positioning System for Moving Target With Feature Vector

Zheng

Wang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Underground, indoor, and harsh environments, which are complex, mutable, and hard to model, prevent high accuracy positioning and navigation. In this paper, a novel positioning system suitable to such environments is proposed. This system is based on a magnetic feature vector integrated with a miniature inertial measurement unit (MIMU). Compared with traditional magnetic-based positioning systems (MBPS), the proposed system exhibits better robustness, and applicability, which is proved by experimental results. Its non-accumulated error characteristics and outstanding penetrability enable the system to provide long-time accurate position and attitude service in underground, indoor, and harsh environments. The experiments indicate that the expected precision of the system can reach 0.055 and 0.062 m and an angle error of 2.1° and 2.8° in line of sight (LOS) and non-line of sight (NLOS) environments, respectively, in the static experiment and 0.051 m in the moving target tracking experiment.

show abstract

Section: A Mb Designmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Magnetic-Based Positioning System for Moving Target With Feature Vector

Zheng

Wang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Previous detection methods such as vision-based or laserbased techniques are time-consuming and labor intensive [1]. With the development of mobile devices and sensor technologies [2], [3], it's convenient to collect anomaly data using mobile phones, pads or other electrical devices with sensors. When the vehicle passes over the anomaly, data captured by accelerometer imply an pattern according to the type of anomaly.…”

Section: Introductionmentioning

confidence: 99%

QDetect: Time Series Querying Based Road Anomaly Detection

et al. 2020

Self Cite

View full text Add to dashboard Cite

Road anomaly detection has attracting increasing attention in recent years due to its significant role in the public transportation of modern cities. A few methods has been proposed to detect road anomaly with inertial sensors (e.g., accelerometer and gyroscope), which usually utilize classification techniques by extracting time and frequency domain features from inertial sensor data. However, existing methods are time consuming since these methods perform on the whole datasets. In addition, few of them pay attention to the self-similarity of the data when vehicle passes over the road anomalies. In this paper, we propose QDetect, a road anomaly detection system with less data-dependency via querying and re-comparing. Specifically, QDetect consists of two phases: 1) Query filter. This phase is designed to roughly extract road anomaly segments by matching existing labelled anomalies; 2) Re-comparison on suspicious anomalies to identify their anomaly types. We have conducted comprehensive experiments on two real-world data sets, and the results show that our method outperforms some existing methods in both detection performance and running time. We expect to lay the first step to some new thoughts to the field of real-time road anomalies detection in subsequent work. INDEX TERMS Time series query, road anomaly detection, acceleration data, top-k.

show abstract