No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
RADAR: An in-building RF-based user location and tracking system
Abstract
The proliferation of mobile computing devices and local-area
wireless networks has fostered a growing interest in location-aware
systems and services. In this paper we present RADAR, a radio-frequency
(RF)-based system for locating and tracking users inside buildings.
RADAR operates by recording and processing signal strength information
at multiple base stations positioned to provide overlapping coverage in
the area of interest. It combines empirical measurements with signal
propagation modeling to determine user location and thereby enable
location-aware services and applications. We present experimental
results that demonstrate the ability of RADAR to estimate user location
with a high degree of accuracy
... Current radio mapping approaches struggle to balance accuracy and data efficiency, largely due to the challenges inherent in modeling signal propagation. Specifically, signal propagation modeling methods can be broadly categorized into physical models [2,22] and data-driven methods [14,53]. Physical models capture environment-signal interactions with minimal data, enabling flexible predictions for any transmitterreceiver (Tx-Rx) pairs. ...
... A team of robots equipped with Wi-Fi access nodes departs from their initial positions, collaboratively planning to execute the most parallel and cost-effective transition sequences to traverse different regions and collect signal data. environmental influences on signals, some methods model signal propagation loss and estimate parameters to capture attenuation caused by obstacles [2,38,48]. Nevertheless, these methods exhibit high errors in obstacle-rich environments due to their neglect of multipath effects and the diverse attenuation characteristics of obstacles with varying material properties. Alternatively, ray tracing approaches simulate and estimate multipath propagation, achieving realistic simulation results [17,18,35]. ...
... Fig. 2(a) shows how we compute the propagation stages. We first calculate the signal from Tx to its LOS points through distance-related attenuation [2], which are then used as weights when summing their corresponding multipath propagation signals generated at each Rx LOS point. The positions of each LOS point of Tx and Rx are paired to form network inputs for calculating the multipath propagation signal and the attenuation coefficient for each Rx LOS point when its signal is transmitted to the Rx. ...
Communication is fundamental for multi-robot collaboration, with accurate radio mapping playing a crucial role in predicting signal strength between robots. However, modeling radio signal propagation in large and occluded environments is challenging due to complex interactions between signals and obstacles. Existing methods face two key limitations: they struggle to predict signal strength for transmitter-receiver pairs not present in the training set, while also requiring extensive manual data collection for modeling, making them impractical for large, obstacle-rich scenarios. To overcome these limitations, we propose FERMI, a flexible radio mapping framework. FERMI combines physics-based modeling of direct signal paths with a neural network to capture environmental interactions with radio signals. This hybrid model learns radio signal propagation more efficiently, requiring only sparse training data. Additionally, FERMI introduces a scalable planning method for autonomous data collection using a multi-robot team. By increasing parallelism in data collection and minimizing robot travel costs between regions, overall data collection efficiency is significantly improved. Experiments in both simulation and real-world scenarios demonstrate that FERMI enables accurate signal prediction and generalizes well to unseen positions in complex environments. It also supports fully autonomous data collection and scales to different team sizes, offering a flexible solution for creating radio maps. Our code is open-sourced at https://github.com/ymLuo1214/Flexible-Radio-Mapping.
... The size of this database is often substantial to ensure adequate coverage. In the online phase, signals captured at a Test Point (TP) are matched to this database to estimate the location, using algorithms like RADAR [4] and Horus [5]. Despite its substantial practical value, fingerprint-based indoor localization faces a critical challenge: the data collection process is often labor-intensive and resource-consuming. ...
... However, existing methods [4], [6], [7] exhibit notable performance degradation in scenarios with sparse fingerprints, primarily due to their reliance on raw signal measurements without incorporating additional information, such as adjacency relationships between nearby fingerprints or environmental characteristics. The absence of such additional information limits their performance, resulting in suboptimal accuracy and reliability. ...
... To evaluate the performance of the AGML model, we selected a range of well-established and widely used state-of-the-art models, including KNN [4], WKNN [11], CNN [12], and MetaLoc [19]. The detailed configurations of each model are summarized in App. ...
Fingerprint-based indoor localization is often labor-intensive due to the need for dense grids and repeated measurements across time and space. Maintaining high localization accuracy with extremely sparse fingerprints remains a persistent challenge. Existing benchmark methods primarily rely on the measured fingerprints, while neglecting valuable spatial and environmental characteristics. In this paper, we propose a systematic integration of an Attentional Graph Neural Network (AGNN) model, capable of learning spatial adjacency relationships and aggregating information from neighboring fingerprints, and a meta-learning framework that utilizes datasets with similar environmental characteristics to enhance model training. To minimize the labor required for fingerprint collection, we introduce two novel data augmentation strategies: 1) unlabeled fingerprint augmentation using moving platforms, which enables the semi-supervised AGNN model to incorporate information from unlabeled fingerprints, and 2) synthetic labeled fingerprint augmentation through environmental digital twins, which enhances the meta-learning framework through a practical distribution alignment, which can minimize the feature discrepancy between synthetic and real-world fingerprints effectively. By integrating these novel modules, we propose the Attentional Graph Meta-Learning (AGML) model. This novel model combines the strengths of the AGNN model and the meta-learning framework to address the challenges posed by extremely sparse fingerprints. To validate our approach, we collected multiple datasets from both consumer-grade WiFi devices and professional equipment across diverse environments. Extensive experiments conducted on both synthetic and real-world datasets demonstrate that the AGML model-based localization method consistently outperforms all baseline methods using sparse fingerprints across all evaluated metrics.
... Over the past few years, fingerprint-based indoor localization has undergone a complete transformation from deterministic KNN-based methods [1,9,38] to sophisticated neural architectures, e.g., RNNs [14], CNNs [15,28,31], and more recently Transformers [23]. Although significant efforts have gone into utilizing these architectures to extract robust features for enhanced localization accuracy, knowledge transfer paradigms that could maximize the potential of these specialized networks better, as yet, only exist in embryonic form. ...
... In this category, methods aim to learn matching functions describing the relationship between RSS fingerprints and associated locations. In the early stages of development, kNNbased methods [1,9,38] driven by various distance metrics (e.g., Euclidean, Manhattan, and Cosine metrics) were widely used to determine locations from k nearest RSS fingerprints to the query fingerprint observations. After that, Gibrán et al. [7] employed DNN-based variants to enhance estimation accuracy. ...
... This dataset has a collection period spanning months and encompasses expansive campus coverage across three buildings, totaling 110,000 square meters, effectively capturing the dynamic nature of real-world environments. During the grid search process, we set specific search ranges for each hyperparameter, such as [1][2][3][4][5] for λ 1 with a step size of 0.2, and [0.1-1] for λ 2,3,4 with a step size of 0.1. Through this rigorous exploration of over 7 days, we identified that the set of values [3,0.5,0.5,0.5] ...
Despite remarkable progress in knowledge transfer across visual and textual domains, extending these achievements to indoor localization, particularly for learning transferable representations among Received Signal Strength (RSS) fingerprint datasets, remains a challenge. This is due to inherent discrepancies among these RSS datasets, largely including variations in building structure, the input number and disposition of WiFi anchors. Accordingly, specialized networks, which were deprived of the ability to discern transferable representations, readily incorporate environment-sensitive clues into the learning process, hence limiting their potential when applied to specific RSS datasets. In this work, we propose a plug-and-play (PnP) framework of knowledge transfer, facilitating the exploitation of transferable representations for specialized networks directly on target RSS datasets through two main phases. Initially, we design an Expert Training phase, which features multiple surrogate generative teachers, all serving as a global adapter that homogenizes the input disparities among independent source RSS datasets while preserving their unique characteristics. In a subsequent Expert Distilling phase, we continue introducing a triplet of underlying constraints that requires minimizing the differences in essential knowledge between the specialized network and surrogate teachers through refining its representation learning on the target dataset. This process implicitly fosters a representational alignment in such a way that is less sensitive to specific environmental dynamics. Extensive experiments conducted on three benchmark WiFi RSS fingerprint datasets underscore the effectiveness of the framework that significantly exerts the full potential of specialized networks in localization.
... In general, two main approaches are employed in WLANfingerprinting based approaches [44], [45]: deterministic methods such as RADAR [46] and probabilistic [47] such as Horus [48]. Deterministic methods rely on metrics between online and representative offline fingerprints, while probabilistic techniques exploit statistical likelihoods of online measurements at different locations, and are based on the Maximum a Posteriori (MAP) or Maximum Likelihood (ML) criteria. ...
... Pioneering deterministic approaches benefit from the k-Nearest Neighbor (kNN) criterion which utilizes the Euclidean distance between the online measurements and radio map fingerprints. The estimated location is in the convex hull of the k RPs with the least distances [44], [46], [49] and weights can also be assigned to each RP based on the similarity between the online measurement and each fingerprint Weighted KNN (WKNN) [50]. Tilejunction [51], [52], Contour-based trilateration [53], and Sectjunction [54] are also recent methods that formulate the localization problem into a convex program (with linear [51]- [53] and quadratic [54] environmental constraints such as the presence of walls, allowed area, etc.) ...
... There exists trend of indoor localization enhancement utilizing assistance data from other available sensors which are deployed in commonly used wireless devices, such as ambient lights/colors, ambient sounds [59], acoustic ranging Centaur [60], RSSI from nearby base stations [61], RFID tags [62], mostly for a proximity determination of the user so that the localization algorithm is solved in a smaller area. The EZ method [63] reduces the surveying burden and achieves better accuracy compared to other modelbased approaches, however, experiences inferior location accuracy compared to fingerprinting techniques such as RADAR [46] and Horus [48], and needs GPS fixes to remove the location ambiguities. The premise is proximity determination of the user so that the localization algorithm is solved in a smaller area [45]. ...
In this paper, we introduce two indoor Wireless Local Area Network (WLAN) positioning methods using augmented sparse recovery algorithms. These schemes render a sparse user's position vector, and in parallel, minimize the distance between the online measurement and radio map. The overall localization scheme for both methods consists of three steps: 1) coarse localization, obtained from comparing the online measurements with clustered radio map. A novel graph-based method is proposed to cluster the offline fingerprints. In the online phase, a Region Of Interest (ROI) is selected within which we search for the user's location; 2) Access Point (AP) selection; and 3) fine localization through the novel sparse recovery algorithms. Since the online measurements are subject to inordinate measurement readings, called outliers, the sparse recovery methods are modified in order to jointly estimate the outliers and user's position vector. The outlier detection procedure identifies the APs whose readings are either not available or erroneous. The proposed localization methods have been tested with Received Signal Strength (RSS) measurements in a typical office environment and the results show that they can localize the user with significantly high accuracy and resolution which is superior to the results from competing WLAN fingerprinting localization methods.
... Various techniques have been proposed for indoor positioning. From signaling perspective these approaches can be divided into two categories [12], [13]: (1) radio-based positioning such as radio frequency (RF) proximity sensors [14]- [18], also called radio-frequency identification (RFID), Ultra Wide Band (UWB) methods [19], [20], Bluetooth-based Manuscript received on Aug, 6,2016. The authors are with the Department of Electrical and Computer Engineering, The University of Texas at San Antonio. ...
... The model based approaches use the collected RSS fingerprints to train the parameters for the predefined propagation models [14], [33], [51], [52]. These techniques assume a prior path loss model for the indoor propagation which is a logarithmic decay function of the distance from the APs as [53] P L = P L 0 + 10γlog 10 d d 0 (2) where P L is the path loss measured in dB, d is the length of the path, d 0 is the reference distance, and γ is the path loss parameter. ...
... whereȓ j is the representative fingerprint value at RP j [14], [80] and d(ȓ j , y) defines a typical distance metric [92]. In case of time-average, the representative value is ψ j . ...
Wireless Local Area Network (WLAN) has become a promising choice for indoor positioning as the only existing and established infrastructure, to localize the mobile and stationary users indoors. However, since WLAN has been initially designed for wireless networking and not positioning, the localization task based on WLAN signals has several challenges. Amongst the WLAN positioning methods, WLAN fingerprinting localization has recently achieved great attention due to its promising results. WLAN fingerprinting faces several challenges and hence, in this paper, our goal is to overview these challenges and the state-of-the-art solutions. This paper consists of three main parts: 1) Conventional localization schemes; 2) State-of-the-art approaches; 3) Practical deployment challenges. Since all the proposed methods in WLAN literature have been conducted and tested in different settings, the reported results are not equally comparable. So, we compare some of the main localization schemes in a single real environment and assess their localization accuracy, positioning error statistics, and complexity. Our results depict illustrative evaluation of WLAN localization systems and guide to future improvement opportunities.
... Para cada 3-tupla (x, y, ζ), foram coletadas pelo menos 20 amostras, onde (x, y) são as coordenadas do ponto de medição e ζ é a direção para a qual o usuário estava virado. A média do RSS por AP em cada ponto/orientação foi então calculada, resultando em 70 × 4 impressões digitais de referência (BAHL, 2000). ...
... O processo foi repetido para . Os autores relataram um erro de posicionamento bidimensional (2-D) mediano de 2,94 metros(BAHL, 2000).Os autores conduziram outro experimento no mesmo local de teste, com um mapa de impressão digital (para os mesmos 70 pontos de medição) construído usando o modelo de propagação empírico dado por:O nível de luminância dos pixels é proporcional à perda adicional (em dB) devido à presença da barreira na posição do pixel. Luminância zero indica a ausência de um obstáculo na posição do pixel. ...
Resumo: Este artigo apresenta uma breve revisão da literatura sobre posicionamento de dispositivos móveis em redes WiFi, com uma análise comparativa de várias técnicas de localização para ambientes indoor de único pavimento. O foco deste trabalho está nos métodos de correlação de banco de dados (DCM), também conhecidos como métodos de correlação de assinaturas de rádio-frequência devido à sua adequação para o posicionamento em tais redes. Palavras-chave: posicionamento, dispositivos móveis, redes WiFi, ambientes indoor WIFI INDOOR POSITIONING USING RADIOFREQUENCY FINGERPRINTING Abstract: This paper presents a brief literature review on mobile device positioning in WiFi networks, with a comparative analysis of various localization techniques for single-floor indoor environments. The focus of this work is on database correlation methods (DCM), also known as radio frequency fingerprinting, due to their suitability for positioning in such networks. 1. Introdução Desde o surgimento das primeiras redes WiFi IEEE 802.11 em 1997, Redes Locais Sem Fio (WLANs-Wireless Local Area Networks) baseadas nesse padrão se espalharam enormemente. Hoje, as redes WiFi são onipresentes em ambientes domésticos, corporativos e públicos. Esse fato, aliado à disponibilidade de smartphones habilitados para WiFi, torna o posicionamento de estações móveis (MSs-Mobile Stations) em WLANs uma questão crucial. O posicionamento em WLANs WiFi não se restringe a ambientes internos, i.e., indoor. No entanto, é em tais cenários que o posicionamento WiFi se torna mais relevante, principalmente devido à (a) indisponibilidade de sinais do Sistema Global de Navegação por Satélite (GNSS-Global Navigation Satellite System) na maioria dos ambientes internos; (b) menor disponibilidade de sinais de rede de telefonia móvel celular em ambientes internos, salvo nos casos em que há micro e pico-células dedicadas implantadas especificamente para fornecer cobertura interna; e (c) alta densidade de pontos de acesso WiFi (APs-Access Points) em ambientes internos típicos. Praticamente todas as soluções de posicionamento de radiofrequência (RF) utilizam uma das seguintes técnicas básicas: (i) identidade de célula (CID-Cell Identity): assume que o MS está localizado nas coordenadas da estação de serviço; (ii) centróide: a posição do MS alvo é dada pelo centróide do polígono cujos vértices são as estações de referência; (iii) multi-lateração: fornece o posicionamento do MS com base em estimativas de distância entre o MS e as estações de referência; essas estimativas são obtidas usando medições de tempo ou de força de sinal recebido (RSS-Received Signal Strength); a multi-lateração pode ser circular ou hiperbólica; (iv) multi-angulação: usa medições de ângulo de chegada (AOA-Angle-of-Arrival) entre o MS e as estações de referência para fornecer uma estimativa de posição; (v) métodos de
... To improve real-time outdoor localization accuracy in dense urban environments where GNSS-based methods fail due to LoS issues, Yapar et al. introduced LocUNet [14], an end-to-end CNN for localization using path loss radio maps. The authors compare four different DL models: RadioUNet [133], fingerprint-based kNN [134], Adaptive KNN [135], and LocUNet, trained using path loss radio maps to improve accuracy despite signal variability and interference. For training purpose, the authors introduce two novel datasets: RadioLocSeer, which includes simulated RSS data, urban city maps, and Base Station (BS) locations; and RadioToASeer, which provides Time of Arrival (ToA) measurements across various propagation scenarios. ...
... For training purpose, the authors introduce two novel datasets: RadioLocSeer, which includes simulated RSS data, urban city maps, and Base Station (BS) locations; and RadioToASeer, which provides Time of Arrival (ToA) measurements across various propagation scenarios. LocUNet outperforms other models with an average localization error of 5 m, showing 11-and 14-m improvements over kNN-based methods [134,135]. However, the study primarily focuses on static urban scenarios without validation in dynamic urban settings. ...
Recently, with advancements in Deep Learning (DL) technology, Radio Frequency (RF) sensing has seen substantial improvements, particularly in outdoor applications. Motivated by these developments, this survey presents a comprehensive review of state-of-the-art RF sensing techniques in challenging outdoor scenarios with practical issues such as fading, interference, and environmental dynamics. We first investigate the characteristics of outdoor environments and explore potential wireless technologies. Then, we study the current trends in applying DL to RF-based systems and highlight its advantages in dealing with large-scale and dynamic outdoor environments. Furthermore, this paper provides a detailed comparison between discriminative and generative DL models in support of RF sensing, offering insights into both the theoretical underpinnings and practical applications of these technologies. Finally, we discuss the research challenges and present future directions of leveraging DL in outdoor RF sensing.
... For this purpose, an SL model is built with a labeled dataset of signal measurements and positions. Related contributions consider both deterministic (e.g., k-nearest neighbors [23], support vector machine [24], multi-layer perceptron [25] [26] [27]) and probabilistic (Bayesian regression [28], Gaussian process regression [29]) schemes. Model accuracy can be improved by preprocessing signal measurements with de-noising schemes (e.g., median/neighborhood mean filter [30], channel propagation model [23], histogrambased outlier detection [31]), clustering (e.g., k-means [32]) and feature extraction algorithms (e.g., principal component analysis [33], bag of features [34], autoencoders [25] [35]). ...
... Related contributions consider both deterministic (e.g., k-nearest neighbors [23], support vector machine [24], multi-layer perceptron [25] [26] [27]) and probabilistic (Bayesian regression [28], Gaussian process regression [29]) schemes. Model accuracy can be improved by preprocessing signal measurements with de-noising schemes (e.g., median/neighborhood mean filter [30], channel propagation model [23], histogrambased outlier detection [31]), clustering (e.g., k-means [32]) and feature extraction algorithms (e.g., principal component analysis [33], bag of features [34], autoencoders [25] [35]). Likewise, positioning accuracy can be enhanced with tracking techniques, which leverage short-term historical data with temporal convolutional networks [36], recurrent neural networks [37] or co-teaching networks [38]. ...
Radio access network optimization is a critical task in current cellular systems. For this purpose, Minimization of Drive Test (MDT) functionality provides mobile operators with georeferenced network performance statistics to tune radio propagation models in re-planning tools. However, some samples in MDT traces contain critical location errors due to the user equipment's energy-saving, thus making MDT data filtering vital to guarantee an adequate performance of MDT-driven algorithms. Supervised Learning (SL) allows to train automatic systems for detecting abnormal MDT measurements by using a labeled dataset. Unfortunately, labeling MDT data is a labor-intensive task, that can be alleviated by using Self-Supervised Learning (SSL). This work presents a novel SSL method to detect MDT measurements with abnormal position information in road scenarios. For this purpose, a dataset is first labeled by combining unlabeled MDT traces from high-mobility users and freely available land use maps, and then an SL classifier is trained. Model assessment is carried out using MDT data collected in a live Long-Term Evolution (LTE) network. Performance analysis includes the comparison of six well-known SL algorithms and 3 different sets of input features aiming to improve model accuracy, generalizability, and explainability, respectively. Results show that considering predictors regarding positioning error increases model accuracy, whereas omitting this information allows to cover a wider range of terminals. Likewise, Shapley Additive exPlanations (SHAP) analysis proves that the use of high-level predictors significantly improves model explainability.
... Too frequently, unlike at home, this requirement is not honored. Also, received signal strength (RSS) is supported by Wi-Fi (Bahl & Padmanabhan, 2000;Laoudias, Kemppi & Panayiotou, 2009;Youssef & Agrawala, 2005;Fang, Lin & Lin, 2008;Park et al., 2010). However, the channel state information (CSI) gives fresh data to calculate target positions to tackle multipath possessions (Chen et al., 2017;Wang et al., 2015). ...
... Due to its ease of use and inexpensive hardware requirements, Wi-Fi RSS measurements are used as fingerprints by several existing indoor fingerprinting systems. One such deterministic approach for position determination is Radar (Bahl & Padmanabhan, 2000), the first fingerprinting system based on RSS. Later, Youssef & Agrawala (2005) employs a probabilistic approach to indoor localization based on RSS values, which provides more precise results than radar. ...
These days, location-based services, or LBS, are used for various consumer applications, including indoor localization. Due to the ease with which Wi-Fi can be accessed in various interior settings, there has been increasing interest in Wi-Fi-based indoor localisation. Deep learning in indoor localisation systems that use channel state information (CSI) fingerprinting has seen widespread adoption. Usually, these systems comprise two primary components: a positioning network and a tracking system. The positioning network is responsible for learning the planning from high-dimensional CSI to physical positions, and the following system uses historical CSI to decrease positioning error. This work presents a novel localization method that combines high accuracy and generalizability. However, existing convolutional neural network (CNN) fingerprinting placement algorithms have a limited receptive area, limiting their effectiveness since important data in CSI has not been thoroughly explored. We offer a unique attention-augmented residual CNN to remedy this issue so that the data acquired and the global context in CSI may be utilized to their full potential. On the other hand, while considering the generalizability of a monitoring device, we uncouple the scheme from the CSI environments to make it feasible to use a single tracking system across all contexts. To be more specific, we recast the tracking issue as a denoising task and then used a deep route before solving it. The findings illuminate perspectives and realistic interpretations of the residual attention-based CNN (RACNN) in device-free Wi-Fi indoor localization using channel state information (CSI) fingerprinting. In addition, we study how the precision change of different inertial dimension units may negatively influence the tracking performance, and we implement a solution to the problem of exactness variance. The proposed RACNN model achieved a localization accuracy of 99.9%, which represents a significant improvement over traditional methods such as K-nearest neighbors (KNN) and Bayesian inference. Specifically, the RACNN model reduced the average localization error to 0.35 m, outperforming these traditional methods by approximately 14% to 15% in accuracy. This improvement demonstrates the model’s ability to handle complex indoor environments and proves its practical applicability in real-world scenarios.
... worldwide). In the fingerprinting-based methods [7], [12], [18], [19], [21], the location service providers construct a fingerprint database, transfer this database to the Mobile Station (MS), and the MS then computes its location and corresponding floor based on similar fingerprints. The fingerprint databases are typically very large since they do contain Received Signal Strengths (RSS's) coming from various Access Points (APs) and in many points or coordinates within a building. ...
... In general, fingerprint-based localization approach is a pattern matching approach [7], [18], [13], rooted in pattern recognition [10], which tries to match the pattern m MS observed by MS to the examples {m n } N f p n=1 collected in the training data set and chooses the location of the less dissimilar example (fingerprint) as the location of MS. In this regard, each element of measurements vector m n is a feature of the location c n . ...
Indoor localization in multi-floor buildings is an important research problem. Finding the correct floor, in a fast and efficient manner, in a shopping mall or an unknown university building can save the users' search time and can enable a myriad of Location Based Services in the future. One of the most widely spread techniques for floor estimation in multi-floor buildings is the fingerprinting-based localization using Received Signal Strength (RSS) measurements coming from indoor networks, such as WLAN and BLE. The clear advantage of RSS-based floor estimation is its ease of implementation on a multitude of mobile devices at the Application Programming Interface (API) level, because RSS values are directly accessible through API interface. However, the downside of a fingerprinting approach, especially for large-scale floor estimation and positioning solutions, is their need to store and transmit a huge amount of fingerprinting data. The problem becomes more severe when the localization is intended to be done on mobile devices which have limited memory, power, and computational resources. An alternative floor estimation method, which has lower complexity and is faster than the fingerprinting is the Weighted Centroid Localization (WCL) method. The trade-off is however paid in terms of a lower accuracy than the one obtained with traditional fingerprinting with Nearest Neighbour (NN) estimates. In this paper a novel K-means-based method for floor estimation via fingerprint clustering of WiFi and various other positioning sensor outputs is introduced. Our method achieves a floor estimation accuracy close to the one with NN fingerprinting, while significantly improves the complexity and the speed of the floor detection algorithm. The decrease in the database size is achieved through storing and transmitting only the cluster heads (CH's) and their corresponding floor labels.
... The output sequence of the model, P0, is represented in Eq. (18). ...
Wireless Sensor Networks (WSNs) are distributed sensor nodes that sense data from their surroundings and relay it to a central network for processing and analysis. Sensor localization is a crucial technique in WSNs, enabling precise positions of target nodes based on environmental signal perception. However, achieving high accuracy in node localization remains a challenge. This study introduces an improved DV-Hop positioning algorithm that integrates Long Short-Term Memory (OLSTM-DVHop) networks to enhance node position predictions. The algorithm processes original data through filtering, analysis, and feature extraction to improve predicted node positions. The study analyzed errors using a standard DV-Hop algorithm and designed a robust architecture for WSN positioning. Simulation experiments validated the proposed improvements, aligning with the algorithm’s accuracy requirements. The proposed error correction mechanism addresses uneven error distribution in the DV-Hop algorithm, adjusting the positions of nodes with significant deviations, reducing errors, and enhancing the positioning process’s reliability and accuracy. The effectiveness of the proposed algorithm is evaluated by comparing it with other localization algorithms across different terrain types. The improved DV-Hop algorithm significantly reduces localization errors and offers superior accuracy, outperforming other algorithms in various experimental scenarios.
... The positions are estimated using matching techniques, such as the nearest neighbor, which determines the location by identifying the closest matching signal measurements. Variants like kNN and weighted kNN improve the accuracy by considering multiple nearby reference locations and assigning weights based on similarity [16], [17]. Additionally, probabilistic methods, such as Maximum Likelihood Estimation (MLE) [18], Bayesian methods [19], [20], and Hidden Markov Models (HMM) [21], have been used to estimate the location. ...
Fingerprinting-based indoor localization methods typically require labor-intensive site surveys to collect signal measurements at known reference locations and frequent recalibration, which limits their scalability. This paper addresses these challenges by presenting a novel approach for indoor localization that utilizes crowdsourced data {\em without location labels}. We leverage the statistical information of crowdsourced data and propose a cumulative distribution function (CDF) based distance estimation method that maps received signal strength (RSS) to distances from access points. This approach overcomes the limitations of conventional distance estimation based on the empirical path loss model by efficiently capturing the impacts of shadow fading and multipath. Compared to fingerprinting, our {\em unsupervised} statistical approach eliminates the need for signal measurements at known reference locations. The estimated distances are then integrated into a three-step framework to determine the target location. The localization performance of our proposed method is evaluated using RSS data generated from ray-tracing simulations. Our results demonstrate significant improvements in localization accuracy compared to methods based on the empirical path loss model. Furthermore, our statistical approach, which relies on unlabeled data, achieves localization accuracy comparable to that of the {\em supervised} approach, the k-Nearest Neighbor (kNN) algorithm, which requires fingerprints with location labels. For reproducibility and future research, we make the ray-tracing dataset publicly available at [2].
... Dies ist immer dann der Fall, wenn eine hohe Prävalenz von Sichtverdeckungen -Non Line Of Sight (NLOS) oder starke Mehrwegausbreitungen von Signalen eine Bestimmung von Distanzen oder Richtungen zu Ankern beeinträchtigen (vgl. [BP00] und [HC16]). In Innenräumen mit vielen Einbauten ist dies besonders häufig anzutreffen, da abhängig von der Gebäudestruktur Verdeckungen oder Hinterschneidungen zu NLOS-Situationen führen. ...
Autonome, mobile Roboter benötigen für den automatischen Transport von Waren Informationen, um ihre Bewegungen zu planen, ihre Position zu bestimmen und ihre Aufgaben auszuführen. Die Automatisierung dieser Prozesse erfordert oft spezialisiertes Personal, das in der Intralogistik jedoch nicht ausreichend vorhanden ist. Deshalb wurde in dieser Arbeit eine Lösung entwickelt, die darauf abzielt, autonomen, mobilen Robotern das Lernen durch Imitation zu ermöglichen. Das Imitationslernen wird verwendet, um damit die Inbetriebnahme komplexer Robotersysteme auch für programmierferne Personengruppen zu ermöglichen. Zu diesem Zweck wird der One-Shot-Imitationslernansatz auf den Bereich der Intralogistik übertragen. Der in dieser Arbeit verfolgte Entwicklungsansatz unterscheidet dazu die Informationsgewinnung (Exploration) und die Ausnutzung der zuvor gewonnenen Informationen (Exploitation).
In der Explorationsphase wird Imitationswissen in Form von Umgebungswissen und Fähigkeitsmodellen durch Beobachtung manueller Transporte automatisch erlernt. Hierfür wird ein Planungsnetzwerk in Form einer annotierten topologischen Karte erzeugt, das auf semantischen Schlüsselstellen der Lagerumgebung basiert.
Dieses Imitationswissen wird in der Exploitationsphase mithilfe einer AI-basierten Handlungsplanung zu konkreten Missionen verknüpft, sodass die zuvor demonstrierten manuellen Transporte automatisch ausgeführt werden können. Mögliche Störungen in der Ausführung der erlernten Bewegungen werden durch einen adaptierten State-Lattice-Planner kompensiert.
Die für die Ausführung automatischer Bewegungen im Raum benötigte Lokalisation basiert auf einem Proximity-basierten Lokalisationsansatz, der für die metrisch kontinuierlichen Lokalisationsbedarfe die Verknüpfung der Knoten des Planungsnetzwerkes über die Fähigkeitsmodelle ausnutzt und damit auf einen singulären Referenzpunkt, wie einen Koordinatenursprung in metrischen Karten, verzichtet.
... As was introduced in Section 2.2 and depicted in Figure 5, the pattern-matching method maps an input set of fingerprints to a position estimate. Here, fingerprints are assumed to belong to a fingerprint domain (also referred to as the signal space in the literature [76]) and positions to a position domain. In this context, the availability of multiple sets of fingerprints associated with a position could be handled either in the fingerprint domain, before the input to the pattern-matching method, or, alternatively, in the position domain at the output of the pattern-matching method. ...
Fingerprinting-based positioning exploiting in two dimensions the spatial side information on fingerprints from adjacent positions relative to a target position is studied. The positioning is performed at the positioning device, utilizing as fingerprints the received signal strengths of downlink radio signals, collected using a two-dimensional sensor array. The motivation is to minimize the positioning error by transferring the complexity and cost from the infrastructure to the positioning device. The goal is to learn whether spatial side information on the fingerprints can minimize the positioning error. We provide a differentiation between fingerprinting in uplink and downlink, a classification of the positioning data aggregation domains, concepts, and a related literature review. We present three pattern-matching methods for estimating the position using spatial side information, two based on regression, implemented using feedforward neural networks, and one based on classification of the fractions of the positioning area, implemented using a convolutional neural network. Fingerprinting with and without spatial side information is benchmarked using the proposed pattern-matching methods in a system simulator based on Monte Carlo methods, generating synthetic fingerprints with an indoor radio channel model and calculating the positioning error. It is observed that for the given assumptions and the system considered, fingerprinting-based positioning with spatial side information substantially reduces the positioning error.
... However, the Active Bat system is susceptible to environmental interference and has a limited localization range. To tackle this issue, the Massachusetts Institute of Technology (MIT) research team developed the 'Crickets' indoor positioning system [30]. This system achieves ultra-high precision localization at the centimeter level using the TDOA algorithm. ...
Although traditional BP neural networks have shown some improvement in ultrasonic indoor localization accuracy, it has a tendency to fall into the problem of local optimal solutions, which limits the localization accuracy. To address this issue, we propose the use of the artificial rabbit optimization (ARO) algorithm as an optimization strategy. The ARO algorithm dynamically adjusts and searches for weights and thresholds during the initialization and training of BP neural networks to find the global optimal solution. This approach efficiently explores the weight space and enhances the BP neural network's performance in ultrasonic localization tasks. Experiments have confirmed that the hybrid ARO‐BP localization algorithm performs well in matching predicted trajectories with actual positions, especially in a 3D localization scenario constructed by six base stations. The algorithm produces excellent results in both line‐of‐sight (LOS) and non–line‐of‐sight (NLOS) environments, which are typical indoor settings. The ARO‐BP neural network effectively reduces the average localization error and ensures high‐precision localization under various transmission conditions and obstacle effects. In NLOS conditions, the positioning accuracy is improved by 16.05% with four tags and 10.92% with six tags, resulting in an average error reduction of 8.02 cm. The ARO‐BP algorithm enhances positioning accuracy by 13.99% with four tags and 21.76% with six tags, resulting in an average error reduction of 12.01 cm. In conclusion, ARO‐BP significantly improves the accuracy of ultrasonic localization in both LOS and NLOS indoor environments with reflections and diffractions. This advancement provides a new direction for the development of indoor positioning technology and is expected to lead to significant progress in practical applications within related fields.
... Action understanding with Wi-Fi signals has become a key technology in human sensing. The RSSI (Received Signal Strength Indicator) in Wi-Fi signals is commonly used for indoor localization [5,70]. However, its accuracy is relatively low and is susceptible to multipath effects and temporal dynamics [71,79]. ...
Human Action Recognition (HAR) plays a crucial role in applications such as health monitoring, smart home automation, and human-computer interaction. While HAR has been extensively studied, action summarization, which involves identifying and summarizing continuous actions, remains an emerging task. This paper introduces the novel XRF V2 dataset, designed for indoor daily activity Temporal Action Localization (TAL) and action summarization. XRF V2 integrates multimodal data from Wi-Fi signals, IMU sensors (smartphones, smartwatches, headphones, and smart glasses), and synchronized video recordings, offering a diverse collection of indoor activities from 16 volunteers across three distinct environments. To tackle TAL and action summarization, we propose the XRFMamba neural network, which excels at capturing long-term dependencies in untrimmed sensory sequences and outperforms state-of-the-art methods, such as ActionFormer and WiFiTAD. We envision XRF V2 as a valuable resource for advancing research in human action localization, action forecasting, pose estimation, multimodal foundation models pre-training, synthetic data generation, and more.
... The conductive properties of the human body cause it to scatter longer radio signal wavelengths and reflect or attenuate shorter wavelengths, thereby affecting radio signal propagation between a transmitter and receiver [20]. This can lead to inaccurate RSSI measurements, resulting in erroneous position estimates in RSSI fingerprinting-based localization [21]. Naghdi et al. [22] employed the fluctuations caused by human body shadowing from three different BLE sources to detect human bodies. ...
This paper examines the performance of Bluetooth Low Energy signal reception for indoor localization by analyzing the interactions between gateways, beacons, and receiver placements. The study investigates the effect of different BLE beacon placements on signal strength and localization accuracy. It evaluates ten receiver ceiling-mounted and wall-mounted configurations, as well as five beacon body positions: shoulder, front pocket, back pocket, and wrist. A dataset comprising 2700 data points was collected and localization accuracy was assessed using a Radial Basis Function-based methodology. The results demonstrate that ceiling-mounted gateways offer more stable signal strength and enhanced localization accuracy compared to wall-mounted gateways. The findings highlight the significance of optimizing both gateway positioning and body placement to improve the performance of BLE-based indoor positioning systems.
... For the k-NN algorithm, the Euclidean distance was used, alongside other similarity measures such as Mahalanobis, Minkowski, and cosine distances, as discussed in Nascimento et al. (2016). In Bahl et al. (2000), it was shown that the best performance for this classifier is achieved with k = 2-4, so we selected k = 3. These results highlight the importance of tailored algorithms for indoor positioning and offer valuable insights for future developments in this field. ...
The Indoor positioning systems have gained significant attention in recent decades, and currently remain a challenging task, given the inherent characteristics of indoor
environments. In this paper, a novel approach to resolving this problem is proposed
through the development of an extension of the method naive Bayesian classifier, known as dynamic naive Bayesian classifier. The proposed approach exhibited a better
performance than the algorithms used for comparison with an average positioning error of 0.92 m.
... Indoor activities need to handle the position detection using alternative techniques. Bahl and Padmanabhan (2000) present a framework for detecting and tracking the user's position based on radio frequency (Wi-Fi) triangulation. Other examples (Föckler, Zeidler, Brombach, Bruns, & Bimber, 2005;Ruf, Kokiopoulou, & Detyniecki, 2008) introduce frameworks that use on-device object recognition to present the appropriate information to the user. ...
Mobilogue is a tool to support educators and students in authoring and deploying learning support with location awareness and guidance to mobile devices. The application area of the framework covers informal learning settings like field trips, museum visits as well as formal classroom settings. The focus of the framework is on the simplicity and flexibility of the domain independent content authoring and content deployment. We present an authoring tool that uses a workflow-related, graph-based paradigm to model and author a path across different locations. Locations relate to physical places or artifacts through QR codes and provide supportive information. The guidance takes place by identifying the user’s location by scanning the QR codes and visualizing the appropriate information on the smartphone. Finally we describe possible scenarios for such informal learning settings and report on an evaluation of one scenario authored by students for a museum.
... The strength of the received signal is used by the Received Signal Strength Indicator (RSSI) by [2][3][4][5][6][7][8][9][10][11][12] for localization. Their placement techniques are remarkably similar to those used by Time of Arrival (TOA). ...
... It also mixes real-world measurements with some models of how signals travel to figure out where someone is, which then helps to offer services that are aware of their location. [28]. Authors [29] proposed that there's this clustering method that combines hybrid compressive sensing (CS) for sensor networks. ...
Wireless sensor network is like a setup where lots of wireless nodes are placed randomly in a certain area. The main aim is to collect data from around and then send that data to the sink node for a specific parameter. We figured out a method for transmitting the data. In WSN (Wireless Sensor Network), it has to choose a path that goes through the leader node, to the cluster head, and then from the cluster head to sink node. This path is chosen using the Ant Colony Optimization (ACO) method, which is a genetic-based way of finding the best path. This network has a mobile agent that travels along a circular route. Different performance factors like the alive nodes, dead nodes, and energy used have shown a really good boost when compared to the basic ACO technique. The mobile agent moves to each node and chooses the movement path based on the Ant Colony Optimization technique. Every horizontal line of the cluster has a mobile agent moving along it. Every agent collects data from sensor nodes and sends them to a cluster head. The moving agent gathers data from those sensor nodes and then sends the data to the base station. It performs better when it comes to alive nodes, dead nodes, and energy use compared to other methods.
... RSS, serving as an indicator of received wireless signal strength, is utilized to evaluate the quality of a link. In 2000, the system Radar, proposed by Bahl et al. [20], achieved the indoor localization function for the first time using RSS data from WiFi signals. Subsequently, RSS has been increasingly employed in human detection [8] and identification [21][22][23]. ...
WiFi-based human authentication systems are garnering substantial attention for its non-intrusiveness, privacy-preserving, and cost-effectiveness. Identity recognition in a WiFi sensing is typically achieved by analyzing the Channel State Information (CSI) that is generated as people walk. However, existing systems largely rely on models that extract an individual feature, leading to suboptimal accuracy. To address this issue, we propose a novel WiFi-based gait recognition system(NeuralWiGait), which authenticates identities by automatically learning the gait features of various users. A data preprocessing scheme is first applied, effectively reducing the signal noise and complexity of the CSI samples. In particular, a new hybrid deep learning framework (WiGaitNet) is used for automatic feature extraction for WiFi-based gait recognition. WiGaitNet integrates a specifically designed convolutional neural network (CNN) with a Bidirectional Gated Recurrent Unit(BiGRU), capable of extracting spatial and temporal features from human gait CSI samples. Subsequently, the concatenated features are fed into a softmax classifier for identification. Experimental results on public datasets (Widar 3.0 and NTU-Fi-HumanID) show that the proposed system achieves an average accuracy of 99%, demonstrating tremendous potential for application.
... By emitting radio electromagnetic waves and receiving the signals reflected from targets, radar can determine and locate the target's spatial position by analyzing these reflected signals. Even under various interference conditions such as wind, rain, fog, light, humidity, and temperature, radar can still determine the angular position, range, speed, and other identifying features of targets [3]. Common radar systems are categorized into continuous wave (CW) and pulse wave systems [4], as shown in Table 1. ...
Frequency-modulated continuous-wave (FMCW) radar is used to extract range and velocity information from the beat signal. However, the traditional joint range–velocity estimation algorithms often experience significant performances degradation under low signal-to-noise ratio (SNR) conditions. To address this issue, this paper proposes a novel approach utilizing the complementary ensemble empirical mode decomposition (CEEMD) combined with singular value decomposition (SVD) to reconstruct the beat signal prior to applying the FFT-Root-MUSIC algorithm for joint range and velocity estimation. This results in a novel joint range–velocity estimation algorithm termed as the CEEMD-SVD-FFT-Root-MUSIC (CEEMD-SVD-FRM) algorithm. First, the beat signal contaminated with additive white Gaussian noise is decomposed using CEEMD, and an appropriate autocorrelation coefficient threshold is determined to select the highly correlated intrinsic mode functions (IMFs). Then, the SVD is applied to the selected highly correlated IMFs for denoising the beat signal. Subsequently, the denoised IMFs and signal residuals are combined to reconstruct the beat signal. Finally, the FFT-Root-MUSIC algorithm is applied to the reconstructed beat signal to estimate both the range and Doppler frequencies, which are then used to calculate the range and velocity estimates of the targets. The proposed CEEMD-SVD-FRM algorithm is validated though simulations and experiments, demonstrating significant improvement in the robustness and accuracy of range and velocity estimates for the FMCW radar due to the effective denoising of the reconstructed beat signal. Moreover, it substantially outperforms the traditional methods in low SNR environments.
... The main bottlenecks of indoor localization come from its accuracy and robustness. In the past few decades, many indoor localization frameworks based on different networks were proposed, including wireless sensor networks (WSNs) [1], wireless local area network (WLAN) [21], RADAR [22], and other techniques [23]. Array signal processing has advanced tremendously and many high resolution algorithms have been studied in the past three decades, including MUSIC [24], ESPRIT [25], and their deviations [26]. ...
Most existing fingerprints-based indoor localization approaches are based on some single fingerprints, such as received signal strength (RSS), channel impulse response (CIR), and signal subspace. However, the localization accuracy obtained by the single fingerprint approach is rather susceptible to the changing environment, multi-path, and non-line-of-sight (NLOS) propagation. Furthermore, building the fingerprints is a very time consuming process. In this paper, we propose a novel localization framework by Fusing A Group Of fingerprinTs (FAGOT) via multiple antennas for the indoor environment. We first build a GrOup Of Fingerprints (GOOF), which includes five different fingerprints, namely, RSS, covariance matrix, signal subspace, fractional low order moment, and fourth-order cumulant, which are obtained by different transformations of the received signals from multiple antennas in the offline stage. Then, we design a parallel GOOF multiple classifiers based on AdaBoost (GOOF-AdaBoost) to train each of these fingerprints in parallel as five strong multiple classifiers. In the online stage, we input the corresponding transformations of the real measurements into these strong classifiers to obtain independent decisions. Finally, we propose an efficient combination fusion algorithm, namely, MUltiple Classifiers mUltiple Samples (MUCUS) fusion algorithm to improve the accuracy of localization by combining the predictions of multiple classifiers with different samples. As compared with the single fingerprint approaches, the prediction probability of our proposed approach is improved significantly. The process for building fingerprints can also be reduced drastically. We demonstrate the feasibility and performance of the proposed algorithm through extensive simulations as well as via real experimental data using a Universal Software Radio Peripheral (USRP) platform with four antennas.
... In this paper, we study another variant inspired by localization problems in wireless networks. The recent growing popularity of mobile devices (iphones, smartphones, etc.) stimulated lots of technological invention as well as theoretical research for solutions of real-life localization tasks (see [2], [10], [15]). In one of many possible approaches, a network is modeled as a graph with radio signal receivers (such as Wi-Fi access points) located at some vertices. ...
The main topic of this paper is motivated by a localization problem in cellular networks. Given a graph G we want to localize a walking agent by checking his distance to as few vertices as possible. The model we introduce is based on a pursuit graph game that resembles the famous Cops and Robbers game. It can be considered as a game theoretic variant of the \emph{metric dimension} of a graph. We provide upper bounds on the related graph invariant , defined as the least number of cops needed to localize the robber on a graph G, for several classes of graphs (trees, bipartite graphs, etc). Our main result is that, surprisingly, there exists planar graphs of treewidth 2 and unbounded . On a positive side, we prove that is bounded by the pathwidth of G. We then show that the algorithmic problem of determining is NP-hard in graphs with diameter at most 2. Finally, we show that at most one cop can approximate (arbitrary close) the location of the robber in the Euclidean plane.
... The received signal strength from a radio transmitter decreases with distance from the source, but indoor spaces present complicated propagation environments, and so simple ranging models based on free space path loss are known to produce highly-variable indoor positioning performance [6]. This was demonstrated as early as 2000 by Microsoft when they compared these two methods [2]. Fingerprinting is now the standard approach employed by indoor arXiv:1703.04150v1 ...
Location sensing is a key enabling technology for Ubicomp to support contextual interaction. However, the laboratories where calibrated testing of location technologies is done are very different to the domestic situations where `context' is a problematic social construct. This study reports measurements of Bluetooth beacons, informed by laboratory studies, but done in diverse domestic settings. The design of these surveys has been motivated by the natural environment implied in the Bluetooth beacon standards - relating the technical environment of the beacon to the function of spaces within the home. This research method can be considered as a situated, `ethnographic' technical response to the study of physical infrastructure that arises through social processes. The results offer insights for the future design of `seamful' approaches to indoor location sensing, and to the ways that context might be constructed and interpreted in a seamful manner.
IoT has revolutionized various industries with interconnected smart embedded devices featuring sensors and actuators. However, providing a sustainable power supply for these devices is a significant hurdle. The finite lifespan of traditional batteries necessitates frequent replacements, leading to increased maintenance costs, downtime, and environmental concerns associated with battery disposal. Energy harvesting offers an admirable alternative by converting ambient energy into usable electrical energy, enabling IoT devices to operate autonomously and sustainably, reducing maintenance needs, and enhancing reliability. Despite their diversity, energy harvesters face common limitations such as variable energy availability, limited power output, and high initial costs. Recognizing these limitations is essential for informed decisions regarding their use in sustainable IoT applications and their communication performance. Due to the lack of a comprehensive and inclusive study in this context, this paper gives an extensive survey on energy-harvesting technologies and their applications in IoT. By drawing insights from over 400 recent publications, this paper first introduces a taxonomy by categorizing the existing technologies based on their energy sources into five general domains, i.e., photovoltaic, vibration and kinetic, radio frequency, thermoelectric, and chemical and biological. Then it expands this categorization into 11 subdomains and delves into the working principles of every technology. Besides surveying potential IoT applications, this comprehensive study covers simulation-facilitating mathematical models, pros, cons, and Commercial-Off-The-Shelf (COTS) modules for each harvesting technology. It also includes evaluative simulations to analyze their output power behavior, focusing on their impact on wireless communication performance. Finally, by discussing the existing research trends, the survey aims to provide informed decision-making and foster the development of innovative, sustainable IoT solutions for a green future.
This paper conducts research on the algorithm to improve the location of Wireless Sensor Network (WSN) in Intelligent Transportation System (ITS). The localization algorithm introduced an improved RSSI vehicle localization algorithm based on multi-path effect and Gaussian white noise. The localization results under different values of Gaussian white noise and different density of beacon nodes are analyzes, and Kalman filtering algorithm is introduced to reduce the influence of signal noise. Finally, a simulation model of ITS is developed to test the algorithm based on mixed noise and Kalman filtering algorithm, which is used to simulate the localization of real vehicles. The simulation shows the algorithm has effect to improve location accuracy and to application
The accurate and robust unmanned aerial vehicle (UAV) localization is significant due to the requirements of safety-critical monitoring and emergency wireless communication in hostile underground environments. Existing range-based localization approaches fundamentally rely on the assumption that the environment is relatively ideal, which enables a precise range for localization. However, radio propagation in the underground environments may be dramatically influenced by various equipments, obstacles, and ambient noises. In this case, inaccurate range measurements and intermittent ranging failures inevitably occur, which leads to severe localization performance degradation. To address the challenges, a novel UAV localization scheme is proposed in this paper, which can effectively handle unreliable observations in hostile underground environments. We first propose an adaptive extended Kalman filter (EKF) based on the fusion of ultra-wideband (UWB) and inertial measurement unit (IMU) to detect and adjust the inaccurate range measurements. Aiming to deal with intermittent ranging failures, we further design the constraint condition by limiting the system state. Specifically, the auto-regressive model is proposed to implement the localization in the ranging blind areas by reconstructing the lost measurements. Finally, extensive simulations have been conducted to verify the effectiveness. We carry out field experiments in an underground garage and a coal mine based on P440 UWB sensors. Results show that the localization accuracy is improved by 16.9% compared with the recent methods in the hostile underground environments.
Location fingerprinting locates devices based on pattern matching signal observations to a pre-defined signal map. This paper introduces a technique to enable fast signal map creation given a dedicated surveyor with a smartphone and floorplan. Our technique (PFSurvey) uses accelerometer, gyroscope and magnetometer data to estimate the surveyor's trajectory post-hoc using Simultaneous Localisation and Mapping and particle filtering to incorporate a building floorplan. We demonstrate conventional methods can fail to recover the survey path robustly and determine the room unambiguously. To counter this we use a novel loop closure detection method based on magnetic field signals and propose to incorporate the magnetic loop closures and straight-line constraints into the filtering process to ensure robust trajectory recovery. We show this allows room ambiguities to be resolved. An entire building can be surveyed by the proposed system in minutes rather than days. We evaluate in a large office space and compare to state-of-the-art approaches. We achieve trajectories within 1.1 m of the ground truth 90% of the time. Output signal maps well approximate those built from conventional, laborious manual survey. We also demonstrate that the signal maps built by PFSurvey provide similar or even better positioning performance than the manual signal maps.
In order to handle spatial data efficiently, as required in computer aided design and geo-data applications, a database system needs an index mechanism that will help it retrieve data items quickly according to their spatial locations However, traditional indexing methods are not well suited to data objects of non-zero size located m multi-dimensional spaces In this paper we describe a dynamic index structure called an R-tree which meets this need, and give algorithms for searching and updating it. We present the results of a series of tests which indicate that the structure performs well, and conclude that it is useful for current database systems in spatial applications
sent out by a central facility that addresses a particular receiver unit (beeper) and produces an audible signal. In addition, it may display a number to which the called-party should phone back (some systems allow a vocal message to be conveyed about the call-back number). It is then up to the recipient to use the conventional telephone system to call-back confirming the signal and determine the required action. Although useful in practice there are still circumstances where it is not ideal. For instance, if the called party does not reply the controller has no idea if they: 1) are in an area where the signal does not penetrate 2) have been completely out of the area for some time 3) have been too busy to reply or 4) have misheard or misread the call-back number. Moreover, in the case where there are a number of people who could respond to a crisis situation, it is not known which one is the nearest to the crisis and therefore the most suitable to contact. A `tagging system' does not
Qualitative models are presented that predict the effects of
walls, office partitions, floors, and building layout on the path loss
at 914 MHz. The site-specific models have been developed based on the
number of floors, partitions, and concrete walls between the transmitter
and receiver, and provide simple prediction rules which relate signal
strength to the log of distance. The standard deviation between measured
and predicted path loss is 5.8 dB for the entire data set, and can be as
small as 4 dB for specific areas within a building. Average floor
attenuation factors, which describe the additional path loss (in
decibels) caused by floors between transmitter and receiver, are found
for as many as four floors in a typical office building. Path loss
contour plots for measured data are presented. In addition, contour
plots for the path loss prediction error indicate that the prediction
models presented are accurate to within 6 dB for a majority of locations
in a building
For an increasing number of modern database applications, efficient support of similarity search becomes an important task. Along with the complexity of the objects such as images, molecules and mechanical parts, also the complexity of the similarity models increases more and more. Whereas algorithms that are directly based on indexes work well for simple medium-dimensional similarity distance functions, they do not meet the efficiency requirements of complex high-dimensional and adaptable distance functions. The use of a multi-step query processing strategy is recommended in these cases, and our investigations substantiate that the number of candidates which are produced in the filter step and exactly evaluated in the refinement step is a fundamental efficiency parameter. After revealing the strong performance shortcomings of the state-of-the-art algorithm for k-nearest neighbor search [Korn et al. 1996], we present a novel multi-step algorithm which is guaranteed to produce the mini...
In this paper, we propose a new method for indexing large amounts of point and spatial data in highdimensional space. An analysis shows that index structures such as the R*-tree are not adequate for indexing high-dimensional data sets. The major problem of R-tree-based index structures is the overlap of the bounding boxes in the directory, which increases with growing dimension. To avoid this problem, we introduce a new organization of the directory which uses a split algorithm minimizing overlap and additionally utilizes the concept of supernodes. The basic idea of overlap-minimizing split and supernodes is to keep the directory as hierarchical as possible, and at the same time to avoid splits in the directory that would result in high overlap. Our experiments show that for high-dimensional data, the X-tree outperforms the well-known R*-tree and the TV-tree by up to two orders of magnitude. 1. Introduction In many applications, indexing of high-dimensional data has become increasingl...
This paper introduces the notion of "universal interaction," allowing a device to adapt its functionality to exploit services it discovers as it moves into a new environment. Users wish to invoke services --- such as controlling the lights, printing locally, or reconfiguring the location of DNS servers --- from their mobile devices. But a priori standardization of interfaces and methods for service invocation is infeasible. Thus, the challenge is to develop a new service architecture that supports heterogeneity in client devices and controlled objects, and which makes minimal assumptions about standard interfaces and control protocols. There are five components to a comprehensive solution to this problem: 1) allowing device mobility, 2) augmenting controllable objects to makethem network-accessible, 3) building an underlying discovery architecture, 4) mapping between exported object interfaces and client device controls, and 5) building complex behaviors from underlying composable obje...
In order to handle spatial data efficiently, as required in computer aided design and geo-data applications, a database system needs an index mechanism that will help it retrieve data items quickly according to their spatial locations However, traditional indexing methods are not well suited to data objects of non-zero size located m multi-dimensional spaces In this paper we describe a dynamic index structure called an R-tree which meets this need, and give algorithms for searching and updating it. We present the results of a series of tests which indicate that the structure performs well, and conclude that it is useful for current database systems in spatial applications
Location-aware applications are becoming increasingly attractive due to the widespread dissemination of wireless networks
and the emergence of small and cheap locating technologies. We developed a location information server that simplifies and
speeds up the development of these applications by offering a set of generic location retrieval and notification services
to the application. The data model and the access protocols of these services are based on the X.500 directory service and
the lightweight directory access protocol LDAP since these are becoming the standard attribute-value-pair retrieval mechanisms
for Internet and Intranet environments. This approach establishes a smooth migration path from conventional to location-aware
applications. The paper presents the location information server concepts, defines its directory data model and access services,
and discusses the implementation options of the location information server.
Computer Graphics: Principles and Practice is the most exhaustive overview of computer graphics techniques available. This textbook's 21 chapters cover graphics hardware, user interface software, rendering, and a host of other subjects. Assuming a solid background in computer science or a related field, Computer Graphicsgives example programs in C and provides exercises at the end of each chapter to test your knowledge of the material. The guide has over 100 beautiful, four-color photographs that illustrate important topics and algorithms, such as ray tracing and bump maps, and also inspire you to acquire the skills necessary to produce them. Encyclopedic in its coverage, the book has a good table of contents so that you can immediately turn to information on the z-Buffer algorithm or the chapter on animation.
The authors discuss concepts used in developing the CSC
(Correctional Services Canada) Duress Alarm Location System (DALS). A
block diagram and theory of operation for the system are presented. A
sample data and test results for an actual test installation are
presented and analyzed. It is concluded that the DALS is able to
acknowledge and locate a duress alarm within an indoor environment with
useful precision and reliability
Distributed systems for locating people and equipment will be at the heart of tomorrow's active offices. Computer and communications systems continue to proliferate in the office and home. Systems are varied and complex, involving wireless networks and mobile computers. However, systems are underused because the choices of control mechanisms and application interfaces are too diverse. It is therefore pertinent to consider which mechanisms might allow the user to manipulate systems in simple and ubiquitous ways, and how computers can be made more aware of the facilities in their surroundings. Knowledge of the location of people and equipment within an organization is such a mechanism. Annotating a resource database with location information allows location-based heuristics for control and interaction to be constructed. This approach is particularly attractive because location techniques can be devised that are physically unobtrusive and do not rely on explicit user action. The article describes the technology of a system for locating people and equipment, and the design of a distributed system service supporting access to that information. The application interfaces made possible by or that benefit from this facility are presented.< >
Wireless ATM networks require efficient mobility management to
cope with frequent mobile handoff and rerouting of connections. Although
much attention has been given in the literature to network architecture
design to support wide-area mobility in public ATM networks, little has
been done to the important issue of user mobility estimation and
prediction to improve the connection reliability and bandwidth
efficiency of the underlying system architecture. This paper treats the
problem by developing a hierarchical user mobility model that closely
represents the movement behavior of a mobile user, and that, when used
with appropriate pattern matching and Kalman filtering techniques,
yields an accurate location prediction algorithm, HLP, or hierarchical
location prediction, which provides necessary information for advance
resource reservation and advance optimal route establishment in wireless
ATM networks
Global positioning system (GPS) is the most important gift of the Department of Defense to the civil world, perhaps with the exception of the Internet. Civil applications unforeseen by developers of the system are thriving and many more are on the way. Commerce in GPS equipment and services continues to grow rapidly and this success has created expectations and demands that the system was not designed to meet. In order to cope with these issues and understand the technology and applications of this global resource, various aspects GPS: the satellites; receivers; positioning algorithms; and several important applications; are discussed.
In this tutorial survey the principles of radio propagation in
indoor environments are reviewed. The channel is modeled as a linear
time-varying filter at each location in the three-dimensional space, and
the properties of the filter's impulse response are described.
Theoretical distributions of the sequences of arrival times, amplitudes
and phases are presented. Other relevant concepts such as spatial and
temporal variations of the channel, large-scale path losses, mean excess
delay and RMS delay spread are explored. Propagation characteristics of
the indoor and outdoor channels are compared and their major differences
are outlined. Previous measurement and modeling efforts are surveyed,
and areas for future research are suggested
this document, but I'm also interested in hearing about inaccuracies, typos, or any other constructive criticism you might have. 2 DRAFT (8/12/93): Distribution Restricted 1 DRAFT (8/12/93): Distribution Restricted
A Distributed Location System for the Active Office00 (c) The Indoor Radio Propagation Channel
- A Harter
- A H Hopperhas
- Hashemi
A. Harter and A. Hopper, " A Distributed Location System for the Active Office, " IEEE Network, January 1994 0-7803-5880-5/00/$10.00 (c) 2000 IEEE [Has931 H. Hashemi, " The Indoor Radio Propagation Channel, " Proceedings of the IEEE, Vol. 81, No. 7, pages 943-968 July 1993 [Hod971 T. D. Hodes, R. H. Katz, E. S. Schreiber, and L. Rowe, " Composable Ad Hoc Mobile Services for Universal Interaction, " MobiCom '97 Proceedings, pp: 1 -12, September [Jai91] R. Jain, The Art of Computer Systems Performance Analysis, John Wiley, 1991
Programming Perl The Active Badge Location System
- L Wall
- T Christiansen
- R L Schwartzreilly & Associates
- Inc
- R Wan
- A Want
- V Hopper
- J Falcao
- Gibbons
L. Wall, T. Christiansen, R. L. Schwartz, " Programming Perl, " O'Reilly & Associates, Inc., 1996 [Wan921 R. Want, A. Hopper, V. Falcao, J. Gibbons., " The Active Badge Location System, " ACM Transactions on Information Systems, Vol. 40, No. 1, pp. 91-102, January 1992 JSAC, Vol. 16, NO. 6, pp. 922-936, August 1998
Tracking Requirements for Augmented Reality The X-tree: An Index Structure for High-Dimensional Data A Prison Guard Duress Alarm Location System Introduction to Algorithms
- R Azumaber
- S Berchtold
- D A Keim
- H P Kriegel
R. Azuma, " Tracking Requirements for Augmented Reality, " Communications ofthe ACM, Vol. 36, No. 7, pp: 50-5 1, July I993 [Ber96] S. Berchtold, D. A. Keim, H. P. Kriegel, " The X-tree: An Index Structure for High-Dimensional Data, ", Proc. VLDB, 1996 [CG93] T. W. Christ, P. A. Godwin, " A Prison Guard Duress Alarm Location System ", Proc. IEEE International Carnahan Conference on Security Technology, October 1993 [Cor901 T. H. Cormen, C. E. Leiserson, R. L. Rivest, " Introduction to Algorithms, " The MIT Press, 1990
Mobility Modeling, Location Tracking, and Trajectory Prediction in Wireless ATM Networks Location-Aware Mobile Applications based on Directory Services Context-Aware and Location Systems
- T Liu
- P Bahlne
- G J Nelson
T. Liu, P. Bahl, " Mobility Modeling, Location Tracking, and Trajectory Prediction in Wireless ATM Networks ", IEEE [Maa97] H. Maass, " Location-Aware Mobile Applications based on Directory Services, " MobiCom '97, pp. 23-33, September 1997 [Ne1981 G. J. Nelson, " Context-Aware and Location Systems, " Ph.D. Theses, University of Cambridge, Computer Lab., UK., Jan. 1998
Computer Graphics Principles and Practice Special Issue on GPS: The Global positioning System
- Foley
- Dam
- Feiner
- P Hughesgps
- P Enge
- Misra
Foley, van Dam, Feiner, and Hughes, Computer Graphics Principles and Practice, 2nd Edition, Addison-Wesley, 1990 [GPS99] P. Enge, and P. Misra, " Special Issue on GPS: The Global positioning System, " Proc. of the IEEE, pp. 3-172, January 1999 [Gut841 A. Guttman, " R-Trees: A Dynamic Index Structure for Spatial Searching, " ACM, 1984
Wireless Communications -Principles and Practice Digital RoamAbout 915/2400 DSPC Card and ISA Network Adapter: Installation and Configuration Optimal Multi-Step k-Nearest Neighbor Search
- Ricerap961 T S Rapportsei
- T Seidl
- H P Kriegel
Rice, " Mathematical analysis of Random Noise, " Bell Systems Technical Journal, Vol. 23 (1944), & Vol. 24 (1945) [Rap961 T. S. Rapport, Wireless Communications -Principles and Practice, IEEE Press, 1996 [Roa96] " Digital RoamAbout 915/2400 DSPC Card and ISA Network Adapter: Installation and Configuration, " DEC. April 1996 [Sei981 T. Seidl, H. P. Kriegel, " Optimal Multi-Step k-Nearest Neighbor Search, " Proc. ACM SIGMOD, 1998 [Sei921 S. Y. Seidel and T. S. Rapport, " 914 MHz path loss prediction Model for Indoor Wireless Communications in Multi-floored buildings, " IEEE Trans. on Antennas & Propagation, Feb. 1992
Wireless Communications-Principles and PracticeDigital RoamAbout 915/2400 DS/PC Card and ISA Network Adapter: Installation and Configuration
- T S Rapport
T. S. Rapport, Wireless Communications-Principles and
Practice, IEEE Press, 1996
[Roa96] "Digital RoamAbout 915/2400 DS/PC Card and ISA
Network Adapter: Installation and Configuration," DEC, April
1996