AI based Location Tracking in WiFi Indoor Positioning Application

Yu, Ho Kyung; Oh, Sung Hyun; Kim, Jeong Gon

doi:10.1109/icaiic48513.2020.9065227

Cited by 12 publications

(5 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As one of the most widely used signal measures, WiFi RSS plays a pivotal role in many fingerprinting-based systems [11]- [14]. In [15], particle swarm optimisation (PSO) was applied to enhance RSS-based performance. Mahalanobis distance, rather than Euclidean distance, was utilised by [16] to make positioning estimations based on RSS fingerprinting.…”

Section: Related Workmentioning

confidence: 99%

A Wi-Fi RSS-RTT Indoor Positioning Model Based on Dynamic Model Switching Algorithm

Feng,

Nguyen,

Luo

2024

J. Ind. Sea. Pos. Nav.

View full text Add to dashboard Cite

The advances in WiFi technology have encouraged the development of numerous indoor positioning systems. However, their performance varies significantly across different indoor environments, making it challenging in identifying the most suitable system for all scenarios. To address this challenge, we propose an algorithm that dynamically selects the most optimal WiFi positioning model for each location. Our algorithm employs a Machine Learning weighted model selection algorithm, trained on raw WiFi RSS, raw WiFi RTT data, statistical RSS & RTT measures, and Access Point line-of-sight information. We tested our algorithm in four complex indoor environments, and compared its performance to traditional WiFi indoor positioning models and state-of-the-art stacking models, demonstrating an improvement of up to 1.8 meters on average.

show abstract

Section: Related Workmentioning

confidence: 99%

A Wi-Fi RSS-RTT Indoor Positioning Model Based on Dynamic Model Switching Algorithm

Feng,

Nguyen,

Luo

2024

J. Ind. Sea. Pos. Nav.

View full text Add to dashboard Cite

show abstract

“…PSO is used to find the position of the smartphone (particle) in a 2D space, for which a corresponding vector of signal strengths, obtained by a constructed path loss model, is the most like the vector of current measurement according to their objective function. Several other authors have also used PSO algorithms to improve localization accuracy and reliability [53,54].…”

Section: Nature-inspired Algorithms In Indoor Positioning Systemsmentioning

confidence: 99%

Indoor Positioning System Based on Bluetooth Low Energy Technology and a Nature-Inspired Optimization Algorithm

2022

View full text Add to dashboard Cite

Warehousing is one of the most important activities in the supply chain, enabling competitive advantage. Effective management of warehousing processes is, therefore, crucial for achieving minimal costs, maximum efficiency, and overall customer satisfaction. Warehouse Management Systems (WMS) are the first steps towards organizing these processes; however, due to the human factor involved, information on products, vehicles and workers may be missing, corrupt, or misleading. In this paper, a cost-effective Indoor Positioning System (IPS) based on Bluetooth Low Energy (BLE) technology is presented for use in Intralogistics that works automatically, and therefore minimizes the possibility of acquiring incorrect data. The proposed IPS solution is intended to be used for supervising order-picker movements, movement of packages between workstations, and tracking other mobile devices in a manually operated warehouse. Only data that are accurate, reliable and represent the actual state of the system, are useful for detailed material flow analysis and optimization in Intralogistics. Using the developed solution, IPS technology is leveraged to enhance the manually operated warehouse operational efficiency in Intralogistics. Due to the hardware independence, the developed software solution can be used with virtually any BLE supported beacons and receivers. The results of IPS testing in laboratory/office settings show that up to 98% of passings are detected successfully with time delays between approach and detection of less than 0.5 s.

show abstract

“…An indoor localization system-based Wi-Fi fingerprint using spatial multi-points matching has also been proposed to estimate the user’s position [ 54 ]. An indoor location tracking technology-based Wi-Fi fingerprint technique [ 55 ] has been proposed to improve the user’s location accuracy using mobile communication technology and location tracking technology. Additionally, for an indoor IoT application using a Bayesian network and a limited radio map, a reliable 3D indoor positioning system-based Wi-Fi RSS fingerprinting has been developed [ 56 ].…”

Section: Related Workmentioning

confidence: 99%

OHetTLAL: An Online Transfer Learning Method for Fingerprint-Based Indoor Positioning

Gidey

Guo

Zhong

et al. 2022

Sensors

View full text Add to dashboard Cite

In an indoor positioning system (IPS), transfer learning (TL) methods are commonly used to predict the location of mobile devices under the assumption that all training instances of the target domain are given in advance. However, this assumption has been criticized for its shortcomings in dealing with the problem of signal distribution variations, especially in a dynamic indoor environment. The reasons are: collecting a sufficient number of training instances is costly, the training instances may arrive online, the feature spaces of the target and source domains may be different, and negative knowledge may be transferred in the case of a redundant source domain. In this work, we proposed an online heterogeneous transfer learning (OHetTLAL) algorithm for IPS-based RSS fingerprinting to improve the positioning performance in the target domain by fusing both source and target domain knowledge. The source domain was refined based on the target domain to avoid negative knowledge transfer. The co-occurrence measure of the feature spaces (Cmip) was used to derive the homogeneous new feature spaces, and the features with higher weight values were selected for training the classifier because they could positively affect the location prediction of the target. Thus, the objective function was minimized over the new feature spaces. Extensive experiments were conducted on two real-world scenarios of datasets, and the predictive power of the different modeling techniques were evaluated for predicting the location of a mobile device. The results have revealed that the proposed algorithm outperforms the state-of-the-art methods for fingerprint-based indoor positioning and is found robust to changing environments. Moreover, the proposed algorithm is not only resilient to fluctuating environments but also mitigates the model’s overfitting problem.

show abstract

AI based Location Tracking in WiFi Indoor Positioning Application

Cited by 12 publications

References 2 publications

A Wi-Fi RSS-RTT Indoor Positioning Model Based on Dynamic Model Switching Algorithm

A Wi-Fi RSS-RTT Indoor Positioning Model Based on Dynamic Model Switching Algorithm

Indoor Positioning System Based on Bluetooth Low Energy Technology and a Nature-Inspired Optimization Algorithm

OHetTLAL: An Online Transfer Learning Method for Fingerprint-Based Indoor Positioning

Contact Info

Product

Resources

About