An Adaptive Human Activity-Aided Hand-Held Smartphone-Based Pedestrian Dead Reckoning Positioning System

Abstract

Pedestrian dead reckoning (PDR), enabled by smartphones’ embedded inertial sensors, is widely applied as a type of indoor positioning system (IPS). However, traditional PDR faces two challenges to improve its accuracy: lack of robustness for different PDR-related human activities and positioning error accumulation over elapsed time. To cope with these issues, we propose a novel adaptive human activity-aided PDR (HAA-PDR) IPS that consists of two main parts, human activity recognition (HAR) and PDR optimization. (1) For HAR, eight different locomotion-related activities are divided into two classes: steady-heading activities (ascending/descending stairs, stationary, normal walking, stationary stepping, and lateral walking) and non-steady-heading activities (door opening and turning). A hierarchical combination of a support vector machine (SVM) and decision tree (DT) is used to recognize steady-heading activities. An autoencoder-based deep neural network (DNN) and a heading range-based method to recognize door opening and turning, respectively. The overall HAR accuracy is over 98.44%. (2) For optimization methods, a process automatically sets the parameters of the PDR differently for different activities to enhance step counting and step length estimation. Furthermore, a method of trajectory optimization mitigates PDR error accumulation utilizing the non-steady-heading activities. We divided the trajectory into small segments and reconstructed it after targeted optimization of each segment. Our method does not use any a priori knowledge of the building layout, plan, or map. Finally, the mean positioning error of our HAA-PDR in a multilevel building is 1.79 m, which is a significant improvement in accuracy compared with a baseline state-of-the-art PDR system.

Wearable IMU-Based Human Activity Recognition Algorithm for Clinical Balance Assessment Using 1D-CNN and GRU Ensemble Model

“…This may allow users to wear fewer IMUs, making it easier to use IMUs in daily life. Studies on user motion recognition using an IMU in a smartphone were also performed to recognize motion for daily life [13][14][15].…”

Ensemble of RNN Classifiers for Activity Detection Using a Smartphone and Supporting Nodes

“…Accuracy of over 90% was achieved for locomotion and gesture activities. Finally, the ensembles of deep neural networks (or ensembles of classical models) show viable solutions for multiple activity recognition [ 46 ].…”

A Survey of Indoor Localization Systems in Multi-Floor Environments

“…Although less common, some systems used IMUs only for localization in multi-floor environments [158]- [162] due to their availability in the form of MEMS sensors. The common technique used with IMUs is PDR, where the initial location is required.…”

“…With the current increase in the availability of IMUs in smartphones, smartphone-based IMUs PDR systems for multistory environments appeared [158], [159]. Ye et al presented FTrack [159], where only the phone accelerometer is utilized for floor localization, without any prior knowledge regarding the building or the floor height.…”

“…This mapping can then be used to determine the floor of the user. Wu et al [158] proposed a PDR-based approach using phone IMUs for tracking in multi-floor environments. The system performs activity recognition to detect states such as ascending/descending stairs and normal walking to give an adaptive human activityaided PDR approach.…”