Accurate indoor positioning system based on modify nearest point technique

Wireless fidelity (Wi-Fi) is common technology for indoor environments that use to estimate required distances, to be used for indoor localization. Due to multiple source of noise and interference with other signal, the receive signal strength (RSS) measurements unstable. The impression about targets environments should be available to estimate accurate targets location. The Wi-Fi fingerprint technique is widely implemented to build database matching with real data, but the challenges are the way of collect accurate data to be the reference and the impact of different environments on signals measurements. In this paper, optimum system proposed based on modify nearest point (MNP). To implement the proposal, 78 points measured to be the reference points recorded in each environment around the targets. Also, the case study building is separated to 7 areas, where the segmentation of environments leads to ability of dynamic parameters assignments. Moreover, database based on optimum data collected at each time using 63 samples in each point and the average will be final measurements. Then, the nearest point into specific environment has been determined by compared with at least four points. The results show that the errors of indoor localization were less than (0.102 m).

Design Space Exploration of a Multi-Model AI-Based Indoor Localization System

In this paper, we present the results of a performance evaluation and optimization process of an indoor positioning system (IPS) designed to operate on portable as well as miniaturized embedded systems. The proposed method uses the Received Signal Strength Indicator (RSSI) values from multiple Bluetooth Low-Energy (BLE) beacons scattered around interior spaces. The beacon signals were received from the user devices and processed through an RSSI filter and a group of machine learning (ML) models, in an arrangement of one model per detected node. Finally, a multilateration problem was solved using as an input the inferred distances from the advertising nodes and returning the final position approximation. In this work, we first presented the evaluation of different ML models for inferring the distance between the devices and the installed beacons by applying different optimization algorithms. Then, we presented model reduction methods to implement the optimized algorithm on the embedded system by appropriately adapting it to its constraint resources and compared the results, demonstrating the efficiency of the proposed method.

The Estimation of the Potential for Using Smart-Trackers as a Part of a Medical Indoor-Positioning System

This research aims to estimate the feasibility of using smart-bracelets as a part of a medicine indoor-positioning system, to monitor the health status and location of patients in a hospital. The smart-bracelet takes on the role of a token of the system and can measure pulse, blood pressure and saturation and provide data transmission over the BLE. The distance between token and anchor was calculated by the RSSI. The position of a token and anchor relative to each other was determined by the trilateration method. The results of the research showed that the accuracy of the developed system in a static position is 1.46 m and exceeds 3 m in a dynamic position. Results of experiments showed that measurements from the smart bracelets are transmitted to the server of the system without distortion. The study results indicated that smart-bracelets could be used to locate patients inside a hospital or estimate their current health state. Given the low accuracy of systolic pressure measurement, it is recommended to develop an algorithm that will allow smooth measuring error for higher-precision estimation of the patient`s general health state. In addition, it is planned to improve the positioning algorithm.

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

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.

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

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.

Effect of Sample Sizes in Fingerprinting Database for Wi-Fi System

Indoor positioning system has been an essential work to substitute the Global Positioning System (GPS). GPS utilizing Global Navigation Satellite Systems (GNSS) cannot provide an accurate positioning in the indoor due to the multipath effect and shadow fading. Fingerprinting method with Wi-Fi technology is a promising system to solve this issue. However, there are several problems with the fingerprinting method. The fingerprinting database collected has different sample sizes where the previous researcher does not indicate any standard for the sample size to be used. In this paper, the effect of the sample sizes in fingerprinting database for Wi-Fi technology has been discussed deeply. The statistical analyzation for different sample sizes has been analyzed. Furthermore, two methods which are K- Nearest Neighbor (KNN) and Deep Neural Network (DNN) are being used to examine the effect of the sample sizes in term of accuracy and distance error. The discussion in this paper will contribute to the better sample size selection depending on the method taken by the user. The result shows that sample sizes are an important metrics in developing the indoor positioning system as it effects the result of the location estimation.

Indoor Positioning System Based on Standardizing Waveform Tendency

Estimating the indoor position of users in commercial buildings remains a significant challenge to date. Although the WiFi-based indoor localization has been widely explored in many works by employing received signal strength (RSS) patterns as the features, they usually lead to inaccurate results as the RSS could be easily affected by the indoor environmental dynamics. Besides, existing methods are computationally intensive, which have a high time consumption that makes them unsuitable for real-life applications. In order to deal with those issues, we propose to use standardizing waveform tendency (SWT) of RSS for indoor positioning. We show that the proposed SWT is robust to the noise generated by the dynamic environment. We further develop a novel smartphone indoor positioning system by integrating SWT and kernel extreme learning machine (KELM) algorithm. Extensive real-world positioning experiments are conducted to demonstrate the superiority of our proposed model in terms of both positioning accuracy and robustness to environmental changes when comparing with state-of-the-art baselines.