A Novel Hybrid NN-ABPE-Based Calibration Method for Improving Accuracy of Lateration Positioning System

Positioning systems based on the lateration method utilize distance measurements and the knowledge of the location of the beacons to estimate the position of the target object. Although most of the global positioning techniques rely on beacons whose locations are known a priori, miscellaneous factors and disturbances such as obstacles, reflections, signal propagation speed, the orientation of antennas, measurement offsets of the beacons hardware, electromagnetic noise, or delays can affect the measurement accuracy. In this paper, we propose a novel hybrid calibration method based on Neural Networks (NN) and Apparent Beacon Position Estimation (ABPE) to improve the accuracy of a lateration positioning system. The main idea of the proposed method is to use a two-step position correction pipeline that first performs the ABPE step to estimate the perceived positions of the beacons that are used in the standard position estimation algorithm and then corrects these initial estimates by filtering them with a multi-layer feed-forward neural network in the second step. In order to find an optimal neural network, 16 NN architectures with 10 learning algorithms and 12 different activation functions for hidden layers were implemented and tested in the MATLAB environment. The best training outcomes for NNs were then employed in two real-world indoor scenarios: without and with obstacles. With the aim to validate the proposed methodology in a scenario where a fast set-up of the system is desired, we tested eight different uniform sampling patterns to establish the influence of the number of the training samples on the accuracy of the system. The experimental results show that the proposed hybrid NN-ABPE method can achieve a high level of accuracy even in scenarios when a small number of calibration reference points are measured.

Download Full-text

Practical And Robust Approach For A Neural Networks Based Indoor Positioning System Using Ultrawide Band

10.32920/17303813 ◽

2021 ◽

Author(s):

Ryan Murari

Keyword(s):

Neural Networks ◽

Synthetic Data ◽

Real Data ◽

Signal Propagation ◽

Indoor Positioning ◽

Sensor Technology ◽

Positioning System ◽

Distance Measurements ◽

Positioning Systems ◽

Indoor Positioning System

With the increasing widespread of sensor technology, new solutions for indoor positioning systems are continuously being developed and with them, new services requiring accurate positioning data have seen a great rise in popularity. In this thesis, a new design technique and deployment methodology for an indoor positioning system using neural networks is proposed to offer more flexibility and simplicity in the development of such a system which is currently very context-bound. The usage of battery-powered tags implies also that systems should not require excessive power consumption and the large number of targets to position requires a method that is not only accurate but also scalable. The proposed positioning system utilizes a small “swarm” of neural networks tasked to position targets based on distance measurements from Ultrawide Band sensors and requires shorter fingerprint collection campaigns and enables more flexibility in system deployment and alterations. Instead of relying solely on real data collected on the field for the training of neural networks, synthetic data is used for an initial training phase. Together, these propositions allow flexibility in terms of adding, removing or altering positions of reference nodes and simplifies offline deployment operations of an indoor positioning system. This thesis presents a system operating in a laboratory-workshop environment capable of good positioning accuracies and maintains robust performances in poor signal propagation.

Download Full-text

Practical And Robust Approach For A Neural Networks Based Indoor Positioning System Using Ultrawide Band

10.32920/17303813.v1 ◽

2021 ◽

Author(s):

Ryan Murari

Keyword(s):

Neural Networks ◽

Synthetic Data ◽

Real Data ◽

Signal Propagation ◽

Indoor Positioning ◽

Sensor Technology ◽

Positioning System ◽

Distance Measurements ◽

Positioning Systems ◽

Indoor Positioning System

Download Full-text

Localization of Distributed Wireless Sensor Networks using Two Sage SDP Optimization

International Journal of Electrical and Computer Engineering (IJECE) ◽

10.11591/ijece.v7i3.pp1255-1261 ◽

2017 ◽

Vol 7 (3) ◽

pp. 1255

Author(s):

Reza Shahbazian ◽

Seyed Ali Ghorashi

Keyword(s):

Optimization Problem ◽

Low Cost ◽

Reference Points ◽

Wireless Sensor ◽

Relaxation Techniques ◽

Problem Size ◽

Distance Measurements ◽

Localization Accuracy ◽

Positioning Systems ◽

Cost Efficient

A wireless sensor network (WSN) may comprise a large distributed set of low cost, low power sensing nodes. In many applications, the location of sensors is a necessity to evaluate the sensed data and it is not energy and cost efficient to equip all sensors with global positioning systems such as GPS. In this paper, we focus on the localization of sensors in a WSN by solving an optimization problem. In WSN localization, some sensors (called anchors) are aware of their location. Then, the distance measurements between sensors and anchors locations are used to localize the whole sensors in the network. WSN localization is a non-convex optimization problem, however, relaxation techniques such as semi-definite programming (SDP) are used to relax the optimization. To solve the optimization problem, all constraints should be considered simultaneously and the solution complexity order is O(n2) where n is the number of sensors. The complexity of SDP prevents solving large size problems. Therefore, it would be beneficial to reduce the problem size in large and distributed WSNs. In this paper, we propose a two stage optimization to reduce the solution time, while provide better accuracy compared with original SDP method. We first select some sensors that have the maximum connection with anchors and perform the SDP localization. Then, we select some of these sensors as virtual anchors. By adding the virtual anchors, we add more reference points and decrease the number of constraints. We propose an algorithm to select and add virtual anchors so that the total solution complexity and time decrease considerably, while improving the localization accuracy.

Download Full-text

Lora RTT Ranging Characterization and Indoor Positioning System

Wireless Communications and Mobile Computing ◽

10.1155/2021/5529329 ◽

2021 ◽

Vol 2021 ◽

pp. 1-10

Author(s):

Qiang Liu ◽

XiuJun Bai ◽

Xingli Gan ◽

Shan Yang

Keyword(s):

Estimation Method ◽

Ground Truth ◽

Indoor Positioning ◽

Position Estimation ◽

Cumulative Distribution ◽

Positioning System ◽

Positioning Error ◽

Positioning Systems ◽

Ground Truth Location ◽

Indoor Positioning System

In recent years, indoor positioning systems (IPS) are increasingly very important for a smart factory, and the Lora positioning system based on round-trip time (RTT) has been developed. This paper introduces the ranging characterization, RTT measurement, and position estimation method. In particular, a particle filter localization method-aided Lora pseudorange fitting correction is designed to solve the problem of indoor positioning; the cumulative distribution function (CDF) criteria are used to measure the quality of the estimated location in comparison to the ground truth location; when the positioning error on the x -axis threshold is 0.2 m and 0.6 m, the CDF with pseudorange correction is 61% and 99%, which are higher than the 32% and 85% without pseudorange correction. When the positioning error on the y -axis threshold is 0.2 m and 0.6 m, the CDF with pseudorange correction is 71% and 99.9%, which are higher than the 52% and 94.8% without pseudorange correction.

Download Full-text

Automated Calibration of RSS Fingerprinting Based Systems Using a Mobile Robot and Machine Learning

Sensors ◽

10.3390/s21186270 ◽

2021 ◽

Vol 21 (18) ◽

pp. 6270

Author(s):

Marcin Kolakowski

Keyword(s):

Neural Network ◽

Machine Learning ◽

Path Loss ◽

Gaussian Process Regression ◽

Calibration Method ◽

Positioning Systems ◽

Training Models ◽

System Environment ◽

Automated Method ◽

Median Error

This paper describes an automated method for the calibration of RSS-fingerprinting-based positioning systems. The method assumes using a robotic platform to gather fingerprints in the system environment and using them for training machine learning models. The obtained models are used for positioning purposes during the system operation. The presented calibration method covers all steps of the system calibration, from mapping the system environment using a GraphSLAM based algorithm to training models for radio map calibration. The study analyses four different models: fitting a log-distance path loss model, Gaussian Process Regression, Artificial Neural Network and Random Forest Regression. The proposed method was tested in a BLE-based indoor localisation system set up in a fully furnished apartment. The results have shown that the tested models allow for localisation with accuracy comparable to those reported in the literature. In the case of the Neural Network regression, the median error of robot positioning was 0.87 m. The median of trajectory error in a walking person localisation scenario was 0.4 m

Download Full-text

A closed-form algorithm for the least-squares trilateration problem

Robotica ◽

10.1017/s0263574710000196 ◽

2010 ◽

Vol 29 (3) ◽

pp. 375-389 ◽

Cited By ~ 12

Author(s):

Yu Zhou

Keyword(s):

Least Squares ◽

Closed Form ◽

Closed Form Solution ◽

Nonlinear Least Squares ◽

Form Solution ◽

Position Estimation ◽

Reference Points ◽

Distance Measurements ◽

Optimal Position ◽

General Number

SUMMARYTrilateration is the most adopted external reference-based localization technique for mobile robots, given the correspondence of external references. The nonlinear least-squares trilateration formulation provides an optimal position estimate from a general number (greater than or equal to the dimension of the environment) of reference points and corresponding distance measurements. This paper presents a novel closed-form solution to the nonlinear least-squares trilateration problem. The performance of the proposed algorithm in dealing with erroneous inputs of reference points and distance measurements has been analyzed through representative examples. The proposed trilateration algorithm has low computational complexity, high operational robustness, and reduced systematic error and uncertainty in position estimation. The effectiveness of the proposed algorithm has been further verified through an experimental test.

Download Full-text

Design and Implementation of Opportunity Signal Perception Unit Based on Time-Frequency Representation and Convolutional Neural Network

Sensors ◽

10.3390/s21237871 ◽

2021 ◽

Vol 21 (23) ◽

pp. 7871

Author(s):

Zhongliang Deng ◽

Hang Qi ◽

Yanxu Liu ◽

Enwen Hu

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Frequency Domain ◽

Utilization Efficiency ◽

Prototype System ◽

Positioning System ◽

Signal Recognition ◽

Positioning Systems ◽

Time Frequency ◽

Signal Perception

The traditional signal of opportunity (SOP) positioning system is equipped with dedicated receivers for each type of signal to ensure continuous signal perception. However, it causes a low equipment resources utilization and energy waste. With increasing SOP types, problems become more serious. This paper proposes a new signal perception unit for SOP positioning systems. By extracting the perception function from the positioning system and operating independently, the system can flexibly schedule resources and reduce waste based on the perception results. Through time-frequency joint representation, time-frequency image can be obtained which provides more information for signal recognition, and is difficult for traditional single time/frequency-domain analysis. We also designed a convolutional neural network (CNN) for signal recognition and a negative learning method to correct the overfitting to noisy data. Finally, a prototype system was built using USRP and LabVIEW for a 2.4 GHz frequency band test. The results show that the system can effectively identify Wi-Fi, Bluetooth, and ZigBee signals at the same time, and verified the effectiveness of the proposed signal perception architecture. It can be further promoted to realize SOP perception in almost full frequency domain, and improve the integration and resource utilization efficiency of the SOP positioning system.

Download Full-text

Calibration-Free Localizations and Applications on U-Care Cloud

International Journal of Grid and High Performance Computing ◽

10.4018/jghpc.2013070106 ◽

2013 ◽

Vol 5 (3) ◽

pp. 65-74

Author(s):

Shih-Lin Wu ◽

Yu-Liang Yeh ◽

Chia-Feng Lin

Keyword(s):

Minimum Mean Square Error ◽

Main Idea ◽

Signal Strength ◽

Location Estimation ◽

Reference Points ◽

Mobile Users ◽

Average Error ◽

Positioning System ◽

Care Project ◽

Radio Map

The key technique of the location-based service (LBS) is localization which is a kind of techniques for determining the location of mobile users (MU). One of the most common techniques for the location estimation of mobile users (MU) is the radio frequency (RF) site survey. The main idea of the technique is to build a signal strength model, called a radio map, in the off-line phase and to estimate the location of an MU by finding the best match from the radio map in the on-line phase. However, when signal strength values vary frequently due to the characteristics of environmental dynamics, the radio map will quickly become outdated, and recalibration requires considerable manual effort. A good positioning technique should be able to adapt to a dynamically changing environment. In this paper, the authors describe the design and implementation of a positioning system which can provide low-cost, but highly adaptable and precise positioning in the context of changeable radio environments. Instead of constructing a radio map, the authors use reference points (RP) installed in the localization area to continuously monitor changes in the environment. The authors then employ the minimum mean square error (MMSE) method to estimate the location of the MU. Experimental results show that the average error distance is about 3 meters. The positioning system has been implemented as a subsystem of the U-care project in the Chang Gung Health and Culture Village. From the results of questionnaire made by residents, the authors find that the most satisfaction system in the U-care project is the positioning and rescuing system because it can locate the exact position of a resident in need of emergency.

Download Full-text

An Effective Trilateration Algorithm for Mobile Robot Positioning Based on Multiple Reference Points

Volume 7: 33rd Mechanisms and Robotics Conference, Parts A and B ◽

10.1115/detc2009-87505 ◽

2009 ◽

Author(s):

Yu Zhou

Keyword(s):

Mobile Robot ◽

Nonlinear Least Squares ◽

Target Object ◽

Position Estimation ◽

Reference Points ◽

Distance Measurements ◽

Optimal Position ◽

General Number ◽

Robot Positioning ◽

Multiple Reference

This paper presents a novel trilateration algorithm which estimates the position of a target object, such as a mobile robot, in a 2D or 3D space based on the simultaneous distance measurements from multiple reference points. The proposed algorithm is derived from the nonlinear least-squares formulation of trilateration, and provides a globally optimal position estimate from a general number of reference points and corresponding distance measurements. Using standard linear algebra techniques, the proposed algorithm has relatively low computational complexity and high operational robustness. Simulations have been conducted through representative examples to analyze the performance of the proposed trilateration algorithm in dealing with erroneous inputs of reference points and distance measurements. The results show that the proposed algorithm has lower systematic error and uncertainty in position estimation comparing with representative closed-form methods.

Download Full-text

Algorithm for Dynamic Fingerprinting Radio Map Creation Using IMU Measurements

Sensors ◽

10.3390/s21072283 ◽

2021 ◽

Vol 21 (7) ◽

pp. 2283

Author(s):

Peter Brida ◽

Juraj Machaj ◽

Jan Racko ◽

Ondrej Krejcar

Keyword(s):

Dead Reckoning ◽

Indoor Positioning ◽

Position Estimation ◽

Reference Points ◽

Location Based Services ◽

Position Information ◽

Vast Number ◽

Positioning Systems ◽

Time Required ◽

Radio Map

While a vast number of location-based services appeared lately, indoor positioning solutions are developed to provide reliable position information in environments where traditionally used satellite-based positioning systems cannot provide access to accurate position estimates. Indoor positioning systems can be based on many technologies; however, radio networks and more precisely Wi-Fi networks seem to attract the attention of a majority of the research teams. The most widely used localization approach used in Wi-Fi-based systems is based on fingerprinting framework. Fingerprinting algorithms, however, require a radio map for position estimation. This paper will describe a solution for dynamic radio map creation, which is aimed to reduce the time required to build a radio map. The proposed solution is using measurements from IMUs (Inertial Measurement Units), which are processed with a particle filter dead reckoning algorithm. Reference points (RPs) generated by the implemented dead reckoning algorithm are then processed by the proposed reference point merging algorithm, in order to optimize the radio map size and merge similar RPs. The proposed solution was tested in a real-world environment and evaluated by the implementation of deterministic fingerprinting positioning algorithms, and the achieved results were compared with results achieved with a static radio map. The achieved results presented in the paper show that positioning algorithms achieved similar accuracy even with a dynamic map with a low density of reference points.

Download Full-text