Performance-based evaluation of RFID-based indoor location sensing solutions for the built environment

Indoor location based services challenges, requirements and usability of current solutions

Smartphone positioning is an enabling technology used to create new business in the navigation and mobile location-based services (LBS) industries. This paper presents a smartphone indoor positioning engine named HIPE that can be easily integrated with mobile LBS. HIPE is a hybrid solution that fuses measurements of smartphone sensors with wireless signals. The smartphone sensors are used to measure the user’s motion dynamics information (MDI), which represent the spatial correlation of various locations. Two algorithms based on hidden Markov model (HMM) problems, the grid-based filter and the Viterbi algorithm, are used in this paper as the central processor for data fusion to resolve the position estimates, and these algorithms are applicable for different applications, e.g., real-time navigation and location tracking, respectively. HIPE is more widely applicable for various motion scenarios than solutions proposed in previous studies because it uses no deterministic motion models, which have been commonly used in previous works. The experimental results showed that HIPE can provide adequate positioning accuracy and robustness for different scenarios of MDI combinations. HIPE is a cost-efficient solution, and it can work flexibly with different smartphone platforms, which may have different types of sensors available for the measurement of MDI data. The reliability of the positioning solution was found to increase with increasing precision of the MDI data.

https://www.mdpi.com/1424-8220/12/12/17208/pdf

A Hybrid Smartphone Indoor Positioning Solution for Mobile LBS

This research focuses on sensing context, modeling human behavior and developing a new architecture for a cognitive phone platform. We combine the latest positioning technologies and phone sensors to capture human movements in natural environments and use the movements to study human behavior. Contexts in this research are abstracted as a Context Pyramid which includes six levels: Raw Sensor Data, Physical Parameter, Features/Patterns, Simple Contextual Descriptors, Activity-Level Descriptors, and Rich Context. To achieve implementation of the Context Pyramid on a cognitive phone, three key technologies are utilized: ubiquitous positioning, motion recognition, and human behavior modeling. Preliminary tests indicate that we have successfully achieved the Activity-Level Descriptors level with our LoMoCo (Location-Motion-Context) model. Location accuracy of the proposed solution is up to 1.9 meters in corridor environments and 3.5 meters in open spaces. Test results also indicate that the motion states are recognized with an accuracy rate up to 92.9% using a Least Square-Support Vector Machine (LS-SVM) classifier.

https://www.mdpi.com/1424-8220/13/2/1402/pdf

Human Behavior Cognition Using Smartphone Sensors

The paper presents an indoor navigation solution by combining physical motion recognition with wireless positioning. Twenty-seven simple features are extracted from the built-in accelerometers and magnetometers in a smartphone. Eight common motion states used during indoor navigation are detected by a Least Square-Support Vector Machines (LS-SVM) classification algorithm, e.g., static, standing with hand swinging, normal walking while holding the phone in hand, normal walking with hand swinging, fast walking, U-turning, going up stairs, and going down stairs. The results indicate that the motion states are recognized with an accuracy of up to 95.53% for the test cases employed in this study. A motion recognition assisted wireless positioning approach is applied to determine the position of a mobile user. Field tests show a 1.22 m mean error in “Static Tests” and a 3.53 m in “Stop-Go Tests”.

https://www.mdpi.com/1424-8220/12/5/6155/pdf

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

Accurate position information is nowadays very important in many applications. For instance, maintaining the situation awareness in command center in emergency operations is very crucial. Due to signal strength attenuation and multipath, Global Navigation Satellite Systems are not suitable for indoor navigation purposes. Radio network-based positioning techniques, such as wireless local area network, require local infrastructure that is often vulnerable in emergency situations. We propose here a distributed system for personal positioning based on inertial sensors. The system consists of an inertial measurement unit (IMU) connected to a radio carried by a person and the server connected to another radio. Step length and heading estimation is computed in the IMU and sent to the server. On the server side, the position is estimated using particle filter-based map matching. The benefit of the distributed architecture is that the computational capacity can be kept very low on the user side, which leads to long operation time as power consumption also remains very low.

Distributed Indoor Positioning System With Inertial Measurements and Map Matching

This paper presents a flexible approach to ubiquitous positioning technologies on smart phone. It deploys three optional indoor/outdoor locating solutions based on Multi-sensor, Satellite, and Terrestrial positioning techniques. The solutions cover six locators including Integrated GPS (Global Positioning System), Bluetooth GPS, AGPS (Assisted GPS), Network based, Multi-sensors, and Wireless LAN (WLAN). In order to merge multi positioning techniques on smart phone, a five-layer software architecture is developed on Symbian S60 platform. Moreover, the implementations of the solutions are described in the paper. Finally, we evaluate the performances of time consumption and positioning accuracy of the solutions according to the experiments on Nokia N95.

Indoor/Outdoor Seamless Positioning Technologies Integrated on Smart Phone

Commonly used Global Navigation Satellite Systems (GNSS) are inappropriate as Location Based Services (LBS) in indoor environment. Therefore research teams are developing different systems, which can be used as a suitable alternative. One of options is to use Inertial Navigation System (INS) which consists of inertial sensors and mathematic procedures. This concept has been known for a long time, but with arrival of Microelectro Mechanical System (MEMS) INS found wide use. Smartphones with inertial sensors, such as accelerometers and gyroscopes, allow us to use them as input devices for Pedestrian Dead Reckoning (PDR). In this paper we present PDR by using smartphone sensors. They can be classified as low-cost Inertial Measurement Unit (IMU), and have been compared with more precise and expensive Xsens IMU. Accuracy of inertial sensors has increased in the past few years, but they still cannot alone provide proper accuracy because of many negative effects, such as heading drift due to gyroscope bias. Particle Filter (PF) has been successfully used with map constraints to increase the accuracy of proposed location system. Presented results show that low-cost smartphone IMU combined with PF can be applicable as proper navigation system.

Pedestrian Dead Reckoning with Particle Filter for handheld smartphone

Inertial sensors are used widely for detecting different contexts. However, noise components at high frequencies can disturb the recognition. In this paper, the measurements are made with multi IMU (MIMU) which combines the results of 32 inertial sensors. Averaging of individual sensor outputs reduce the noise level significantly and enables higher resolution. As an example case, we present application for passenger detection in two environments; hallway corridor and public city bus. The results show that accuracy can be increased when MIMU is used compared to single IMU.

Pedestrian detection with high resolution inertial measurement unit

In this paper, we study the normalization of WLAN signal
strength measurements to enable the use of WLAN radio
maps generated using one device for position estimation
with signal strength measurements by another device. In
the field experiments, we used different devices: one
laptop PC and two handheld devices. The data for the
analysis was collected using these devices simultaneously
in the same locations inside an office building. The tests
demonstrated that using a simple conversion, the
measurements of two different devices can be used to
generate histogram based radio maps for positioning on a
third device. It was found that the optimal conversion is
different for different devices. The experiments also show
that the positioning with one device and radio map based
on measurements obtained with another device can be as
accurate as positioning with radio map obtained with
measurements from the device itself; the difference in
mean errors between these setups is some tens of
centimeters, the relative difference in mean errors being
less than 10%, while the mean errors are approximately 3
m.

Arto Perttula

Papers

Distributed Indoor Positioning System With Inertial Measurements and Map Matching

Indoor/Outdoor Seamless Positioning Technologies Integrated on Smart Phone

Pedestrian Dead Reckoning with Particle Filter for handheld smartphone

Pedestrian detection with high resolution inertial measurement unit

Normalization of Signal Strength Measurements for WLAN Based Indoor Positioning