A Federated Learning Framework for Fingerprinting-Based Indoor Localization in Multibuilding and Multifloor Environments

Gao, Bo; Yang, Fan; Cui, Nan; Xiong, Ke; Lu, Yang; Wang, Yuwei

doi:10.1109/jiot.2022.3214211

Cited by 22 publications

(15 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RSSI data preprocessing have been shown in related studies to have a substantial influence on performance of indoor localization models [14,15,19,28,46,47]. To ensure optimal performance, our proposed DL framework entail detailed preparation, involving a series of steps that were executed in multiple folds.…”

Section: Data Preprocessing and Model Pretrainingmentioning

confidence: 99%

“…As a result, researchers and industrial communities must devise alternative means of localizing targets in these scenarios. These alternative means include techniques such as triangulation [10], trilateration [11,12] and fingerprinting [13][14][15][16][17] and as well as wireless technologies such as WiFi [1,6,[18][19][20], Bluetooth Low Energy (BLE) [10,11], Ultra-wideband (UWB) [21], Radio Frequency Identification (RFID) [22], Zigbee [23], and Long Range (LoRa) [24,25]. Indoor localization based on WiFi technology can be divided further into two main categories: Channel State Information (CSI) and Received Signal Strength Indicator (RSSI).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

SALLoc: An Accurate Target Localization in WiFi-Enabled Indoor Environments via SAE-ALSTM

Ayinla,

Aziz,

Drieberg

2024

IEEE Access

View full text Add to dashboard Cite

Developing a reliable and accurate indoor localization system is a crucial step for creating a seamless and interactive user-device experience in nearly all intelligent internet of things (IIoTs) and smart applications. Indoor localization systems based on WiFi fingerprinting have been considered as a promising alternative to model-based approaches owing to their accuracy, low cost, availability, and ease of configuration. However, recent studies have revealed that in complex environments, WiFi fingerprinting techniques are faced with a lot of challenges as the coverage area increases. These challenges include fingerprint spatial uncertainty, instability in the received signal strength indicator (RSSI) and discrepancy in fingerprint distribution. Furthermore, there is frequent need for database upgrades or even recreation whenever there is a change in the architecture of the location. These challenges have questioned the robustness and efficiency of most of the existing schemes. In this paper, we present an indoor localization architecture for complex multi-building multi-floor location prediction and subsequently propose SALLoc (SAE-ALSTM Localization), a WiFi fingerprinting indoor localization scheme based on Stacked Autoencoder (SAE) and Attention-based Long Short-Time Memory (ALSTM) framework. Firstly, stratified sampling technique is used to separate validation set from the entire uneven RSSI training set which ensures that the same proportion of RSSI samples are present in both sets. Secondly, SAE is utilized to select core features and decrease the dimensions of the RSSI samples. Finally, ALSTM is trained to focus on these features to achieve robust location prediction. Extensive investigations were conducted using UJIIndoorLoc, Tampere and UTSIndoorLoc datasets, and the results obtained demonstrated the superiority of the proposed scheme in terms of prediction accuracy, robustness, and generalizations when compared to state-of-the-art methods. The mean localization error (MLE) on UJIIndoorLoc, Tampere and UTSIndoorLoc datasets are 8.28 m, 9.52 m, and 6.48 m respectively. Consequently, it can be concluded that the proposed scheme is accurate and well-suited for large-scale indoor environment location prediction.

show abstract

Section: Data Preprocessing and Model Pretrainingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

SALLoc: An Accurate Target Localization in WiFi-Enabled Indoor Environments via SAE-ALSTM

Ayinla,

Aziz,

Drieberg

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…2023 [24] Proposes a FL framework called FedLoc3D to address the challenges of classifying building-floor classification and Latitude-Longitude Regression (LLR) in fingerprinting-based indoor localization, using a Convolutional Neural Network (CNN) with depth-wise separable convolutions for classification of the building floors and a Deep Neural Network (DNN) with autoencoder and data augmentation for LLR. The framework enables collaborative learning on data that are decentralized and heterogeneous and are operating over an imperfect network in a wide 3-D space.…”

Section: Pseudo Label-driven Federated Learningmentioning

confidence: 99%

6G-Enabled Mobile Access Point Placement via Dynamic Federated Learning Strategies

Mirdita

Bello

Refaey

et al. 2023

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

Advanced Indoor Positioning Systems (IPS) based on Received Signal Strength (RSS) fingerprints have been paramount in 6G network research and commercial exploitation due to their costeffectiveness and simplicity. Despite their popularity, the advent of 6G has prompted a shift towards exploring Deep Learning algorithms to further enhance their performance and precision. Deep Learning research typically demands large datasets, leading to reliance on data augmentation and crowdsourcing techniques for data collection. However, the traditional centralization of data in crowdsourcing poses privacy risks, and here is where Federated Learning (FL) comes into play. In light of this, our study introduces FL to bridge this divide in a decentralized way, eliminating the need for servers to acquire labeled data directly from users. This approach aims to minimize localization error in RSS fingerprints, preserve user privacy, and reduce system latency, all key goals for 6G networks. Moreover, we explore the use of power transmission techniques to further decrease the latency in the FL system. Our simulation outcomes confirm the superiority of FL over traditional Stochastic Gradient Descent (SGD) methods considering critical evaluation metrics like localization error and global loss, paving the way for efficient 6G implementation.

show abstract

“…Indoor positioning, often based on WiFi fingerprints, although useful, still faces notable limitations that require more advanced and accurate solutions due to the lack of precision and generalization in indoor positioning systems that make use of WiFi fingerprints [3]. When localization is needed indoors and in multi-building and multi-story environments, building and story classification (BFC) functionality can be added along with latitude and longitude regression (LLR) in a wide three-dimensional space [4].…”

mentioning

confidence: 99%

“…[3]. When there is a need for localization in indoor environments with multiple buildings and floors, federated learning (FL) can be used, addressing the challenges of a three-dimensional space [4]. On the other hand, other papers address challenges related to the accuracy and reliability of location in different technological contexts.…”

mentioning

confidence: 99%

Evaluation of an Indoor Location System Using Edge Computing and Machine Learning Algorithms

Yauri,

Espino,

Castro

2024

Int. J. Onl. Eng.

View full text Add to dashboard Cite

The paper aims to evaluate precise location techniques with indoor devices using edge computing technologies, which are important for services such as smart homes and health. Despite their growing importance, indoor locations lack precise and standard methods, especially in complex environments. Solving this is being attempted through technologies such as reconfigurable surfaces and deep learning models, with attention to overcoming the challenges of indoor placement. The main objective of the study is to design a low-cost indoor location system using the ESP32 module and RSSI signals, integrated with embedded machine learning algorithms. The system to be developed will allow determining the location of objects or people with a location device through SSID signals from access points. The main objective is to evaluate the performance of three machine learning algorithms—random forest (RF), decision tree (DT) and support vector machine (SVM)—in the detection of four different locations (bathroom, kitchen, bedroom, and living room), involving the definition of system characteristics, data acquisition, the development of classifiers, and their integration in the ESP32 module to transmit location data wirelessly through the MQTT protocol. As a result of the evaluation, the DT model stands out for its efficiency under limited resource conditions during real-time implementation, but it may face challenges related to overfitting and resources at the implementation stage.

show abstract

A Federated Learning Framework for Fingerprinting-Based Indoor Localization in Multibuilding and Multifloor Environments

Cited by 22 publications

References 42 publications

SALLoc: An Accurate Target Localization in WiFi-Enabled Indoor Environments via SAE-ALSTM

SALLoc: An Accurate Target Localization in WiFi-Enabled Indoor Environments via SAE-ALSTM

6G-Enabled Mobile Access Point Placement via Dynamic Federated Learning Strategies

Evaluation of an Indoor Location System Using Edge Computing and Machine Learning Algorithms

Contact Info

Product

Resources

About