Using LS-SVM Based Motion Recognition for Smartphone Indoor Wireless Positioning

Pei, Ling; Liu, Jingbin; Guinness, Robert; Chen, Yuwei; Kuusniemi, Heidi; Chen, Ruizhi

doi:10.3390/s120506155

Cited by 124 publications

(105 citation statements)

References 37 publications

Supporting

Mentioning

105

Contrasting

Order By: Relevance

“…A smartphone provides multiple types of measurements of built-in sensors and signals of opportunity (SoOP) that can be used for positioning and motion state recognition [10,37,38], as illustrated in Figure 1. Sensors include an accelerometer, gyroscope, compass, camera, barometer, acoustic sensor, proximity sensor, and even an ambient light sensor [4][5][6][7].…”

Section: Background Of Smartphone Mobility Sensingmentioning

confidence: 99%

“…The measurements of these sensors are used first to calculate informative signals and further feature values, which are used as the input of an activity classifier to resolve human motion states. In general, motion state recognition is related to a classification problem that can be managed using a number of algorithms, such as logics, K-nearest neighbor, support vector machine, artificial neural networks, decision trees and Bayesian techniques [37,38,47,48]. Most classification algorithms take a memoryless process, which does not consider motion transition.…”

Section: Background Of Smartphone Mobility Sensingmentioning

confidence: 99%

See 1 more Smart Citation

Reciprocal Estimation of Pedestrian Location and Motion State toward a Smartphone Geo-Context Computing Solution

et al. 2015

Self Cite

View full text Add to dashboard Cite

Abstract:The rapid advance in mobile communications has made information and services ubiquitously accessible. Location and context information have become essential for the effectiveness of services in the era of mobility. This paper proposes the concept of geo-context that is defined as an integral synthesis of geographical location, human motion state and mobility context. A geo-context computing solution consists of a positioning engine, a motion state recognition engine, and a context inference component. In the geo-context concept, the human motion states and mobility context are associated with the geographical location where they occur. A hybrid geo-context computing solution is implemented that runs on a smartphone, and it utilizes measurements of multiple sensors and signals of opportunity that are available within a smartphone. Pedestrian location and motion states are estimated jointly under the framework of hidden Markov models, and they are used in a reciprocal manner to improve their estimation performance of one another. It is demonstrated that pedestrian location estimation has better accuracy when its motion state is known, and in turn, the performance of motion state recognition can be improved with increasing reliability when the location is given. The geo-context inference is implemented simply with the expert system principle, and more sophisticated approaches will be developed. OPEN ACCESSMicromachines 2015, 6 700

show abstract

Section: Background Of Smartphone Mobility Sensingmentioning

confidence: 99%

Section: Background Of Smartphone Mobility Sensingmentioning

confidence: 99%

Reciprocal Estimation of Pedestrian Location and Motion State toward a Smartphone Geo-Context Computing Solution

et al. 2015

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, the deployment of diverse wireless devices operating in the 2.4 GHz unlicensed band, is met with growing concerns about signal interference and performance degradation. Pei et al, (2012b) present the preliminary results of WiFi positioning with Bluetooth interferences. In this paper, we will evaluate the performance of fingerprinting-based WiFi positioning in Bluetooth and WiFi coexistence environments.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of fingerprinting-based WiFi indoor localization coexisted with Bluetooth

Pei

Liu

Chen

et al. 2017

J. Glob. Position. Syst.

Self Cite

View full text Add to dashboard Cite

WiFi and Bluetooth are two most commonly used short range wireless communication technologies. Recent years, with increasing number of WiFi and Bluetooth mobile terminals, tags, and other devices, a demand for integration and coexistence of these two technologies including their positioning function is booming. In this paper, we firstly investigate the interferences between WiFi and Bluetooth signals from the signal and protocol perspectives. Secondly, the principle of fingerprinting approach for WiFi positioning is introduced. In order to evaluate the performance of WiFi fingerprinting coexisted with Bluetooth, both occurrence-based and Weibull-based approaches are utilized for generating the database. Field tests present the interference in the WiFi and Bluetooth coexistence environments. A WiFi mobile device with a Bluetooth device nearby obtains poor positioning results due to the interference. Weibull-based database has more robust performance than occurrence-based database in the coexistence environments.

show abstract

“…Microelectromechanical Systems (MEMS) motion sensors offer the opportunity of continuous relative navigation when the localisation infrastructure is unavailable Chen et al, 2011a;Chen et al, 2011b;Foxlin, 2005;Indoor Atlas Ltd, 2011;Mathews et al, 2011;Pei et al, 2010a;Pei et al, 2011;Pei et al, 2012;Pei et al, 2013). The low cost camera is also a potential localisation sensor (Ruotsalainen et al, 2011).…”

Section: Introduction Localisation Technologies and Location-based Amentioning

confidence: 99%

Two-stage Localisation Scheme Using a Small-scale Linear Microphone Array for Indoor Environments

Jiang

Pei

et al. 2015

J. Navigation

Self Cite

View full text Add to dashboard Cite

The small-scale linear microphone arrays that are widely found in smartphones could be used to locate a sound source for indoor environments. After the Time Differences Of Arrival (TDOAs) in microphone pairs are estimated, a TDOA-based hybrid localisation scheme is proposed for a small-scale linear microphone array. The scheme contains two stages: the initialisation stage using the Levenberg-Marquardt (LM) algorithm, and the refining solution stage using the Weighted Least-Square (WLS) algorithm or the Multi-Dimensional Scalingbased (MDS) algorithm. Simulations and field tests show that the proposed indoor localisation scheme outperforms the existing schemes, and it can achieve an average error of 0·32 metres in an 8 m by 5 m area. K E Y

show abstract

Using LS-SVM Based Motion Recognition for Smartphone Indoor Wireless Positioning

Cited by 124 publications

References 37 publications

Reciprocal Estimation of Pedestrian Location and Motion State toward a Smartphone Geo-Context Computing Solution

Reciprocal Estimation of Pedestrian Location and Motion State toward a Smartphone Geo-Context Computing Solution

Evaluation of fingerprinting-based WiFi indoor localization coexisted with Bluetooth

Two-stage Localisation Scheme Using a Small-scale Linear Microphone Array for Indoor Environments

Contact Info

Product

Resources

About