No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
FSTNet: Learning spatial–temporal correlations from fingerprints for indoor positioning
... Yang et al. [14] proposed a deep neural network-based indoor localization system via spatial and temporal features learned from UWB RSS and distance information based on the time of arrival (ToA). Several methods that combine fingerprinting and deep learning have been proposed [15], [16]. Fingerprint-based indoor localization using a deep neural network that extracts features from the spatial and temporal representations of geomagnetic sequences has been proposed [15]. ...
... Fingerprint-based indoor localization using a deep neural network that extracts features from the spatial and temporal representations of geomagnetic sequences has been proposed [15]. Similarly, Ren et al. [16] used Wi-Fi RSSI measurements [16]. ...
... Fingerprint-based indoor localization using a deep neural network that extracts features from the spatial and temporal representations of geomagnetic sequences has been proposed [15]. Similarly, Ren et al. [16] used Wi-Fi RSSI measurements [16]. ...
Sensor devices in future wireless communication systems such as beyond fifth generation (Beyond 5G) and sixth generation (6G) require highly accurate location information. Owing to high power consumption and cost, global navigation satellite system receivers may not be installed on sensor devices, requiring the localization of sensor devices on a wireless sensor network (WSN). In many WSN applications, a spatially dense sensor installation is required to achieve satisfactory coverage. When object detection-type sensor devices are installed at high density, the responses of spatially proximate sensors are highly correlated. In other words, these sensor responses indirectly include location information. Based on this consideration, we proposed a sensor localization method using the spatial correlation of nongeotagged sensor response data and evaluated its performance. Our method enables location estimation from the response data obtained during environmental monitoring, even for sensors that are not equipped with range functions. The simulation experiments showed that a more accurate sensor localization is possible with an error of 1 m using a wider sensor detection range, even with rough proximity pair ratio settings. In addition, we verified that there is a trade-off between localizability and observability during environmental monitoring, such as the visualization of vehicle positions from sensor responses. Our proposed method may be applied to future urban environments with a large number of sensor devices installed for environmental monitoring.
... Furthermore, the influence of temporal variation in RSSI has been explored by researchers as a means to enhance model's performance. Qianqian Ren et al. [18] proposed a model comprised of five layers, i.e., path FP construction, positional embedding, CNN, fingerprint attention, and fully connected layers. The model was trained on a self-collected dataset of 64 RPs in a comparatively small area. ...
... After the execution of (8), the classification probabilities are predicted for each of the output nodes. Although the 2D CNN can extract spatial features and is also utilized by researchers for both the spatial and temporal feature extraction [4], [18], we observed that its efficacy is limited. This limitation stems from their inability to effectively capture temporal features. ...
Fingerprint-based indoor localization is the predominant localization approach for GPS-restricted environments due to its minimal hardware requirements. However, its performance is affected by signal fluctuations caused by shadowing, fading, and multipath effect, which necessitates models capable of capturing temporal variations. Numerous machine learning and deep learning algorithms have been introduced to surmount this limitation, within which the convolutional neural network (CNN) stands out as the most prominent. The 1D and 2D CNN models developed for indoor localization have the ability to extract spatial features but not temporal, leading to degradation in online localization accuracy. In contrast to 2D CNNs, 3D CNNs possess the ability to extract spatio-temporal information, but their computational complexity precludes real-time implementation. In this paper, a novel 3D-separable CNN for indoor localization is designed using skip connections and group shuffling. By employing depth-wise and point-wise convolutions, separable convolutions significantly reduce computational complexity, achieving a 10-fold improvement over conventional convolution, which facilitating real-time applications at the cost of reduced accuracy. Incorporating skip connections and group shuffling can help offset this accuracy decline. The 2D CNN, 2D separable CNN, and 3D CNN are used as benchmarks and evaluated on the UJILIB public dataset. Numerical results reveal that the proposed model is able to attain a positioning accuracy of 66.28% with an average positioning error of 1.04 meters in distance. Compared to the 2D separable CNN, the proposed 3D separable CNN outperforms it by achieving a 24.03% lower average positioning error.
... , [127], [30], [65] [108], [128], [129], [63], [61], [18], [130], [31], [19], [131], [111], [132], [77], [122], [44], [114], [111], [112], [93], [115], [123], [30] - [133], [134], [135] [119], [136], [137], [36] [102], [120], [121], [103], [31], [138], [139], [140], [141], [142], [78] ResNet ---- [136] [105], [138], [143], [144], [145], [146], [147], [148], [ Hybrid [106], [30], [64], [156], [157] [93], [26], [96], [23], [32], [62], [20], [34], [122], [28], [44], [61], [114], [108], [112], [111], [115], [123], [60], [116], [158], [159], [160], [95], [28] [28], [21], [98], [99] [100], [119], [136] [102], [120], [121], [105], [31], [161], [162], [138] model based approaches with learnable model for data analysis and processing. Different DL architectures have been utilized in the literature for WiFi-based human sensing including multilayer Perceptron (MLP), CNN, simple RNN (SRNN), LSTM, BiLSTM, GRU, residual network (ResNet), autoencoder, transformer, and hybrid models. ...
... However, the precision of indoor positioning is hampered by issues of uncertain and unstable fingerprints fo the WiFi isgnals. To this end, the authors in [133] introduces FSTNet which is a DL framework to enhance indoor positioning accuracy by understanding the spatial-temporal relationship in the fingerprint data. The framework introduces the concept of path fingerprints to address uncertainty and instability in the fingerprint. ...
The rapid advancements in wireless technologies have led to numerous research studies that provide evidence of the successful utilization of wireless signals, particularly, WiFi signals for human activity sensing in the indoor environment. As a promising technology, WiFi-based human sensing can be utilized for a variety of applications such as smart healthcare, smart homes, security, industry, office indoor environments etc., due to the availability of rich infrastructure. Furthermore, compared to other radio frequency (RF) based systems such as radio detection and ranging (RADAR) and radio frequency identification (RFID), WiFi is non-invasive, has low-cost, and provides ubiquitous coverage in the indoor setup. However, due to the limited accuracy and high complexity of the model-based approaches for human sensing, the systems empowered by the deep learning (DL) techniques have achieved remarkable performance gains and showed more robustness in dealing with complicated human sensing tasks. The article explores the physical layer parameters used in WiFi sensing such as received signal strength indicator (RSSI) and channel state information (CSI), the estimated parameters such as angle-of-arrival (AoA) and Doppler shift (DS) along with frequency modulated continuous wave (FMCW) RADAR technology. Moreover, the preliminary signal processing stages that are applied to the received WiFi signals in the DL assisted systems are discussed. This article provides a comprehensive literature survey on the recent advances in DL-empowered WiFi sensing focusing on human activity recognition and movement tracking followed by fall detection, single task-multi task classification, crowd monitoring and sensing, indoor localization, gaits recognition, and pose estimation. Furthermore, the paper highlight the challenges in the existing literature and discusses the possible future research directions in WiFi-based human sensing assisted by DL techniques.
... For instance, ref. [56] leveraged UWB to propose a model incorporating convolution and LSTM modules to extract spatio-temporal features of positioning errors. Ref. [57] introduced the FSTNet deep learning framework, which uses convolution and attention mechanisms to capture spatio-temporal correlations from fingerprints. Currently, the modeling capabilities of deep learning have been applied to pseudolite positioning systems. ...
Pseudolite positioning systems offer precise localization when GPS signals are unavailable, advancing the development of intelligent transportation systems. However, in confined indoor environments such as kilometer-long tunnels, where vehicles move at high speeds, traditional pseudolite algorithms struggle to establish accurate physical models linking signals to spatial domains. This study introduces a deep learning-based pseudolite positioning algorithm leveraging a spatio-temporal fusion framework to address challenges such as signal attenuation, multipath effects, and non-line-of-sight (NLOS) effects. The Enconv1d model we developed is based on the spatio-temporal characteristics of the pseudolite observation signals. The model employs the encoder module from the Transformer to capture multi-step time constraints while introducing a multi-scale one-dimensional convolutional neural network module (1D CNN) to assist the encoder module in learning spatial features and finally outputs the localization results of the Enconv1d model after the dense layer integration. Four experimental tests in a 4.6 km long real-world tunnel demonstrate that the proposed framework delivers continuous decimeter-level positioning accuracy.
... Furthermore, the consideration of signal post-processing techniques [75][76][77] can allow for further reducing the error bounds of the A-TDOA architecture, especially the highest signal-related uncertainties of asynchronous systems (i.e. path losses and multipath), which further enhances the future study of novel asynchronous localization methodologies for indoor environments. ...
... Among all available indoor localization technologies and techniques, WiFi fingerprinting with RSSI has attracted widespread interest because it does not require device synchronization or extra hardware to be deployed [27]. Owing to its rapid growth, widespread deployment, and availability of wireless infrastructure networks, WiFi has become one of the most widely utilized wireless technologies for LBSs. ...
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.
Wi-Fi Received Signal Strength (RSS) fingerprinting is a leading method for indoor positioning due to its widespread infrastructure. Traditional fingerprinting classifies location by signal distance from a reference point (RP), assuming similarity between path and radio signal distances. Recently, model-based deep learning has been used to classify location estimates by identifying patterns in the radio environment. However, this method often loses consistency between space and signals as it learns without considering the correlation between RPs, necessitating retraining on unmeasured points. To address these limitations, we propose a scalable Deep Similarity Model that can incorporate new RPs without the need for retraining. This model maintains consistency between distance and RSS by preserving the feature distribution using a center estimator to effectively learn RSS features through an embedding network. Subsequently, a Deep Similarity Network (DSN) employing Scaled Dot Product Similarity (SDPS), a novel distance-based deep architecture, estimates location by comparing RSS features with the RP. We designed the model end-to-end and optimized it using cross-entropy loss. The proposed model approximates the location coordinates as the center of mass based on the estimated probabilities of RPs. Our results demonstrate that the model not only achieves improved performance over state-of-the-art techniques but also maintains its scalability and performance consistency with the addition and deletion of RPs.
In this article, we design a new time-of-arrival (TOA) system for simultaneous user device (UD) localization and synchronization with a periodic asymmetric ranging network, namely PARN. The PARN includes one primary anchor node (PAN) transmitting and receiving signals, and many secondary ANs (SAN) only receiving signals. All the UDs can transmit and receive signals. The PAN periodically transmits sync signal and the UD transmits response signal after reception of the sync signal. Using TOA measurements from the periodic sync signal at SANs, we develop a Kalman filtering method to virtually synchronize ANs with high accuracy estimation of clock parameters. Employing the virtual synchronization, and TOA measurements from the response signal and sync signal, we then develop a maximum likelihood (ML) approach, namely ML-LAS, to simultaneously localize and synchronize a moving UD. We analyze the UD localization and synchronization error, and derive the Cramér-Rao lower bound (CRLB). Different from existing asymmetric ranging network-based TOA systems, the new PARN i) uses the periodic sync signals at the SAN to exploit the temporal correlated clock information for high accuracy virtual synchronization, and ii) compensates the UD movement and clock drift using various TOA measurements to achieve consistent and simultaneous localization and synchronization performance. Numerical results verify the theoretical analysis that the new system has high accuracy in AN clock offset estimation and simultaneous localization and synchronization for a moving UD. We implement a prototype hardware system and demonstrate the feasibility and superiority of the PARN in real-world applications by experiments.
p class="0abstract"> Indoor Positioning has come under the spotlight in the last decade due to the increasing of location-based services demands. RSS Wi-Fi based positioning using the fingerprinting technique is widely used due to its low hardware requirements and simplicity. However, multi-path and fading cause random fluctuations of collected RSS values which affects the positioning accuracy. For this purpose, we propose an indoor positioning system based on RSS and convolutional neural network. This approach aims to improve accuracy by reducing the noise and the randomness of collected RSS values from a wireless sensor network. We implemented and evaluated our system using a single floor and multi-grid dataset. Our proposed approach provides a room and grid prediction accuracies of 100% and a mean error of location estimation of 0.98 m. </p
The number of older adults with Alzheimer’s disease is increasing every year. The associated memory problems cause many difficulties for Alzheimer’s patients and their caretakers; patients may even become lost in familiar surroundings. In this paper, a proposed localization system based on a wireless sensor network (WSN) and backpropagation based artificial neural network (BP-ANN) was practically implemented to detect and determine the position of an Alzheimer’s patient in an indoor environment. The proposed system consisted of four ZigBee-based XBee S2C anchor nodes and one mobile node carried by the Alzheimer’s patient. The received signal strength indicator (RSSI) of the anchor nodes was collected by the mobile node using a laptop supported by X-CTU software. The obtained RSSI values were used as input for training, testing, and validation processes of the BP-ANN, while two-dimension (2D) locations (x and y) were used as the output of the ANN. The results showed that the obtained mean localization errors were 0.964 and 0.921m for validation and testing phases, respectively, after applying the ANN. Based on a comparison with state-of-the-art technology, we deduced that the proposed ANN method outperformed other techniques in previous studies in terms of mean localization error.
The intelligent use of deep learning (DL) techniques can assist in overcoming noise and uncertainty during fingerprinting-based localization. With the rise in the available computational power on mobile devices, it is now possible to employ DL techniques, such as convolutional neural networks (CNNs), for smartphones. In this paper, we introduce a CNN model based on received signal strength indicator (RSSI) fingerprint datasets and compare it with different CNN application models, such as AlexNet, ResNet, ZFNet, Inception v3, and MobileNet v2, for indoor localization. The experimental results show that the proposed CNN model can achieve a test accuracy of 94.45% and an average location error as low as 1.44 m. Therefore, our CNN model outperforms conventional CNN applications for RSSI-based indoor positioning.
With the ubiquitous deployment of wireless systems and pervasive availability of smart devices, indoor localization is empowering numerous location-based services. With the established radio maps, WiFi fingerprinting has become one of the most practical approaches to localize mobile users. However, most fingerprint-based localization algorithms are computation-intensive, with heavy dependence on both offline training phase and online localization phase. In this paper, we propose CNNLoc, a Convolutional Neural Network (CNN) based indoor localization system with WiFi fingerprints for multi-building and multi-floor localization. Specifically, we devise a novel classification model and a novel positioning model by combining a Stacked Auto-Encoder (SAE) with a one-dimensional CNN. The SAE is utilized to precisely extract key features from sparse Received Signal Strength (RSS) data while the CNN is trained to effectively achieve high accuracy in the positioning phase. We evaluate the proposed system on the UJIIndoorLoc dataset and Tampere dataset and compare the performance with several state-of-the-art methods. Moreover, we further propose a newly collected WiFi fingerprinting dataset UTSIndoorLoc and test the positioning model of CNNLoc on it. The results show CNNLoc outperforms the existing solutions with 100% and 95% success rates on building-level localization and floor-level localization, respectively.
Robust and accurate indoor localization has been the goal of several research efforts over the past decade. Due to the ubiquitous availability of WiFi indoors, many indoor localization systems have been proposed relying on WiFi fingerprinting. However, due to the inherent noise and instability of the wireless signals, the localization accuracy usually degrades and is not robust to dynamic changes in the environment. We present WiDeep, a deep learning-based indoor localization system that achieves a fine-grained and robust accuracy in the presence of noise. Specifically, WiDeep combines a stacked denoising autoencoders deep learning model and a probabilistic framework to handle the noise in the received WiFi signal and capture the complex relationship between the WiFi APs signals heard by the mobile phone and its location. WiDeep also introduces a number of modules to address practical challenges such as avoiding over-training and handling heterogeneous devices. We evaluate WiDeep in two testbeds of different sizes and densities of access points. The results show that it can achieve a mean localization accuracy of 2.64m and 1.21m for the larger and the smaller testbeds, respectively. This accuracy outperforms the state-of-the-art techniques in all test scenarios and is robust to heterogeneous devices.
This paper proposes a soft range limited K nearest neighbours (SRL-KNN) localization fingerprinting algorithm. The conventional KNN determines the neighbours of a user by calculating and ranking the fingerprint distance measured at the unknown user location and the reference locations in the database. Different from that method, SRL-KNN scales the fingerprint distance by a range factor related to the physical distance between the user’s previous position and the reference location in the database to reduce the spatial ambiguity in localization. Although utilizing the prior locations, SRL-KNN does not require knowledge of the exact moving speed and direction of the user. Moreover, to take into account of the temporal fluctuations of the received signal strength indicator (RSSI), RSSI histogram is incorporated into the distance calculation. Actual on-site experiments demonstrate that the new algorithm achieves an average localization error of 0:66 m with 80% of the errors under 0:89 m, which outperforms conventional KNN algorithms by 45% under the same test environment.
This research focus on the implementation of recurrent neural networks (RNN) model for indoor positioning system (IPS). Unlike global positioning system (GPS), IPS is used in closed structures such as hospitals, museums, shopping centers, office buildings, and warehouses. Positioning system is a key aspect in IPS. We propose, implemented, and evaluated an RNN model for positioning system. We used Wi-Fi-based IPS dataset from our previous research and made some comparison of RNN model performance with other methods. From the model evaluation results, we can conclude that RNN model is suitable for Wi-Fi-based IPS. It also produces generally higher accuracy compared with multi-layer perceptron model (MLP), Naïve Bayes, J48, and SVM. The RNN model training process still needs some tweaking on the parameters used in training.
In this paper, we study fingerprinting based indoor localization in commodity 5GHz WiFi networks. We first theoretically and experimentally validate three hypotheses on the CSI data of 5GHz OFDM channels. We then propose a system termed BiLoc, which uses bi-modality deep learning for localization in the indoor environment using off-the-shelf WiFi devices. We develop a deep learning based algorithm to exploit bi-modal data, i.e., estimated AOAs and average amplitudes (which are calibrated CSI data using several proposed techniques), for both the offline and online stages of indoor fingerprinting. The proposed BiLoc system is implemented using commodity WiFi devices. Its superior performance is validated with extensive experiments under three typical indoor environments and through comparison with three benchmark schemes.
The increasing demands of location-based services have spurred the rapid development of indoor positioning system and indoor localization system interchangeably (IPSs). However, the performance of IPSs suffers from noisy measurements. In this paper, two kinds of robust extreme learning machines (RELMs), corresponding to the close-to-mean constraint, and the small-residual constraint, have been proposed to address the issue of noisy measurements in IPSs. Based on whether the feature mapping in extreme learning machine is explicit, we respectively provide random-hidden-nodes and kernelized formulations of RELMs by second order cone programming. Furthermore, the computation of the covariance in feature space is discussed. Simulations and real-world indoor localization experiments are extensively carried out and the results demonstrate that the proposed algorithms can not only improve the accuracy and repeatability, but also reduce the deviation and worst case error of IPSs compared with other baseline algorithms.
Neural machine translation is a relatively new approach to statistical machine translation based purely on neural networks. The neural machine translation models often consist of an encoder and a decoder. The encoder extracts a fixed-length representation from a variable-length input sentence, and the decoder generates a correct translation from this representation. In this paper, we focus on analyzing the properties of the neural machine translation using two models; RNN Encoder--Decoder and a newly proposed gated recursive convolutional neural network. We show that the neural machine translation performs relatively well on short sentences without unknown words, but its performance degrades rapidly as the length of the sentence and the number of unknown words increase. Furthermore, we find that the proposed gated recursive convolutional network learns a grammatical structure of a sentence
automatically.
In wireless sensor networks (WSN), location estimation is important for routing efficiency and location-aware services. Traditional received signal strength based localizations using propagation-loss model are often erroneous for the low-cost WSN devices. The reason is that the wireless channel is vulnerable to so many factors that deriving the appropriate propagation-loss model for the low cost WSN devices is not possible. Hence, we propose a flexible model based on neural network and grid sensor training phase for accurate localization of sensors. Simulation results show that the location accuracy can be increased by increasing the grid sensor density and the number of access points.
Learning to store information over extended time intervals by recurrent backpropagation takes a very long time, mostly because of insufficient, decaying error backflow. We briefly review Hochreiter's (1991) analysis of this problem, then address it by introducing a novel, efficient, gradient based method called long short-term memory (LSTM). Truncating the gradient where this does not do harm, LSTM can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units. Multiplicative gate units learn to open and close access to the constant error flow. LSTM is local in space and time; its computational complexity per time step and weight is O. 1. Our experiments with artificial data involve local, distributed, real-valued, and noisy pattern representations. In comparisons with real-time recurrent learning, back propagation through time, recurrent cascade correlation, Elman nets, and neural sequence chunking, LSTM leads to many more successful runs, and learns much faster. LSTM also solves complex, artificial long-time-lag tasks that have never been solved by previous recurrent network algorithms.
Local Positioning Systems (LPS) address the limitations of Global Navigation Satellite Systems in harsh environments. LPS must attain the optimal location of their sensors in space for optimal performance, which is known as the Node Location Problem. In addition, not all the sensors under coverage present the best performance for determining the location. For this purpose, the optimal selection of the best combination of nodes requires addressing the Sensor Selection Problem. In this paper, for the first time in the literature, we present a methodology for the combined optimisation of both problems which may attain improved results than separated optimisations. Results show that the consideration of SSP based sensor selection strategies during the NLP suppose a reduction up to 10% in the localization uncertainties with respect to traditional baseline sensor selection strategies of the NLP, thus proving the effectiveness of the devised technique.
Accurate indoor location information in multi-building/floor environments is essential for establishing many indoor location-based services (LBS). Wi-Fi fingerprinting with received signal strength indicators (RSSI) has become one of the most practical techniques to localize users indoors. However, the fluctuation of wireless signals caused by fading, the multipath effect, and device heterogeneity leads to considerable variations in RSSIs, which poses a challenge to accurate localization. This paper proposes an indoor positioning method, which is constructed based on a convolutional neural network (CNN) framework. Specifically, a novel model by combining an extreme learning machine autoencoder (ELM-AE) with a two-dimensional CNN is proposed. The ELM-AE extracts critical features by reducing input dimensions, while the CNN is trained to effectively achieve significant performance in the positioning phase. To increase positioning accuracy and deal with data shortages, a data augmentation strategy by frequently adding noisy data to the original fingerprint map is devised. The statistical properties namely, the RSS values of each MAC address, are utilized to adjust input noise. The performance of the proposed system is evaluated on two Tampere and UJIIndoorLoc datasets. The experimental results show that EA-CNN achieves better performance than CNN by decreasing average positioning error up to 40.95% and 43.74% in Tampere and UJIIndoorLoc datasets, respectively. Compared to state-of-the-art deep learning-based methods, the positioning performance improves up to 68.36% in Tampere and 67.56% in the UJIIndoorLoc dataset by exploiting only 25% of the training samples.
Compared to several state-of-the-art deep learning models, EA-CNN achieves higher accuracy in both positioning and floor estimation.
Wi-Fi CSI-based indoor localization systems can realize decimeter-level localization accuracy. However, these systems require that the location and antenna array orientation of Wi-Fi Access Point (AP) are known in advance, which makes it impractical for large-scale deployment. In this paper, we present MapFi, which can realize autonomous mapping of Wi-Fi infrastructure without labor-intensive site survey. To this end, we focus on addressing three problems. First, as there will be diverse layouts of devices and antennas with respective to numerous and heterogeneous Wi-Fi APs, we propose a general method to estimate AoA and generate the Wi-Fi map. Second, while the existing systems can provide a promising median localization accuracy, tail performance is usually far worse. Consequently, we develop a revision method to reduce tail errors. Third, when deployed in large-scale indoor environment, obstacles and long-distance communication might incur failed CSI collection. Therefore, we segment Wi-Fi APs into groups and finally merge these groups to generate Wi-Fi map. We conduct experiments in different scenarios to verify proposed methods. The experimental results show that we can realize the 80% localization error within 1.15m and 0.74m in office room and open space respectively, which is as accurate as localization systems requiring known Wi-Fi map.
In order to achieve higher accuracy and lower cost of indoor localization, we propose a positioning method using multiple input and multiple output (MIMO) channel state information (CSI) as a fingerprint. The method can be divided into three stages, feature extraction, offline training and online localization. In the feature extraction, the segmented average and principal component analysis (PCA) are used to reduce the data dimension and decrease system complexity. In the offline training, the deep neural network (NN) model is trained to implement the position classification. In the online localization, the data are input into the trained NN model first, and then its output is further processed by weighted k-nearest neighbor (WKNN) technology to estimate the position. Experimental results show that the proposed method can significantly reduce the positioning error compared to other methods and the average error is 1.39m in a complex indoor environment.
Channel State Information (CSI) can provide phase and amplitude of multi-channel subcarrier to better describe signal propagation characteristics. Therefore, CSI has become one of the most commonly used features in indoor Wi-Fi localization. In addition, compared to the CSI geometric localization method, the CSI fingerprint localization method has the advantages of easy implementation and high accuracy. However, as the scale of the fingerprint database increases, the training cost and processing complexity of CSI fingerprints will also greatly increase. Based on this, this paper proposes to combine Back Propagation Neural Network (BPNN) and Adaptive Genetic Algorithm (AGA) with CSI tensor decomposition for indoor Wi-Fi fingerprint localization. Specifically, the tensor decomposition algorithm based on the Parallel Factor (PARAFAC) analysis model and the Alternate Least Squares (ALS) iterative algorithm are combined to reduce the interference of the environment. Then, we use the tensor wavelet decomposition algorithm for feature extraction and obtain the CSI fingerprint. Finally, in order to find the optimal weights and thresholds and then obtain the estimated location coordinates, we introduce an adaptive genetic algorithm to optimize BPNN. Experimental results show that the proposed algorithm has high localization accuracy, while improving the data processing ability and fitting the nonlinear relationship between CSI location fingerprints and location coordinates.
Different technologies have been proposed to provide indoor localisation: magnetic field, Bluetooth, WiFi, etc. Among them, WiFi is the one with the highest availability and highest accuracy. This fact allows for an ubiquitous accurate localisation available for almost any environment and any device. However, WiFi-based localisation is still an open problem.
In this article, we propose a new WiFi-based indoor localisation system that takes advantage of the great ability of Convolutional Neural Networks in classification problems. Three different approaches were used to achieve this goal: a custom architecture called WiFiNet, designed and trained specifically to solve this problem, and the most popular pre-trained networks using both transfer learning and feature extraction.
Results indicate that WiFiNet is as a great approach for indoor localisation in a medium-sized environment (30 positions and 113 access points) as it reduces the mean localisation error (33%) and the processing time when compared with state-of-the-art WiFi indoor localisation algorithms such as SVM.
This paper proposes a RSSI quantization and genetic algorithm based localization method. To quantize RSSI measurements from sensor nodes, we first divide sensing disks of nodes into multiple-rings and adopt genetic algorithm based on elitist preservation strategy to determine rings width. Secondly, we calculate the overlapping of rings and construct the mapping between a binary code sequence and the overlapping area. Thirdly, a density-based clustering Algorithm is presented to solve the ambiguity of the target appearing area. Based on which, a two-stage centroid localization algorithm is proposed, which is especially useful for the case of irregular appearing area of the target. Finally, we construct an experimental environment to validate the performance of our algorithm.
A framework that incorporates channel modeling, position estimation, and error analysis methods is developed for network-based indoor positioning with radio signal strength (RSS) measurements of WiFi access points (APs). To construct an accurate channel model with RSS measurements severely influenced by propagation attenuations, multipath reflections, and shadowing effects, a novel sparse Bayesian learning algorithm is developed to model the radio power map (RPM) in indoor space. Based on the proposed RPM model, a 2-stage positioning method is further developed. In the first stage for coarse positioning, the location is determined up to a room-scale indoor space. Then, in the second stage for fine positioning, the RPMs of the given indoor space are used for location estimation in the space with a Bayesian estimator. The mean squared positioning errors are verified with the Bayesian Cramer-Rao lower bound. Extensive experiments show that the average positioning error of the proposed RPM-based approach is 1.98 meters which achieve 22% improvements over the state-of-the-art RSS-based indoor positioning methods. More importantly, the proposed modeling and positioning method can effectively exploit the spatial relationship in the RSS samples to improve positioning accuracy.
This paper proposes recurrent neural networks (RNNs) for WiFi fingerprinting indoor localization. Instead of locating a mobile user’s position one at a time as in the cases of conventional algorithms, our RNN solution aims at trajectory positioning and takes into account the correlation among the received signal strength indicator (RSSI) measurements in a trajectory. To enhance the accuracy among the temporal fluctuations of RSSI, a weighted average filter is proposed for both input RSSI data and sequential output locations. The results using different types of RNN including vanilla RNN, long short-term memory (LSTM), gated recurrent unit (GRU), bidirectional RNN (BiRNN), bidirectional LSTM (BiLSTM) and bidirectional GRU (BiGRU) are presented. On-site experiments demonstrate that the proposed structure achieves an average localization error of 0.75 m with 80% of the errors under one meter, which outperforms KNN algorithms and probabilistic algorithms by approximately 30% under the same test environment.
In received signal strength (RSS)-based indoor wireless localisation system, radio pathloss model or radio map must be readily obtainable. However, the unpredictability of wireless channel makes it difficult to achieve high accuracy localisation in practice. In this study, the authors employed a multi-layer neural network (MLNN) for RSS-based indoor localisation without using the radio pathloss model or comparing the radio map. The proposed MLNN localisation system integrate the RSS signals transforming section, the raw data denoising section and the node locating section into a deep architecture. Furthermore, a boosting method is designed to promote location accuracy of the MLNN effectively. Experiment results demonstrate the feasibility and suitability of the proposed algorithm.
Indoor localization has enabled a great number of mobile and pervasive applications, attracting attentions from researchers worldwide. Most of current solutions rely on Received Signal Strength (RSS) of wireless signals as location fingerprint, to discriminate locations of interest. Fingerprint uniqueness with respect to locations is a basic requirement in these fingerprinting-based solutions. However, due to insufficient number of signal sources, temporal variations of wireless signals, and rich multipath effects, such requirement is not always met in complex indoor environments, which we refer to as fingerprint ambiguity. In this work, we explore the potential of leveraging user motion against fingerprint ambiguity. Our basic idea is that user motion patterns collected by built-in sensors of mobile phones add to the diversity built by RSS fingerprints. On this basis, we propose MoLoc, a motion-assisted localization scheme implemented on mobile phones. MoLoc can easily be integrated in existing localization systems by simply adding a motion database that is constructed automatically by crowdsourcing. We conducted experiments in a large office hall. The experiment results show that MoLoc doubles the localization accuracy achieved by the fingerprinting method, and limits the mean localization error to less than 1m.
An indoor tracking and navigation system based on measurements of received signal strength (RSS) in wireless local area network (WLAN) is proposed. In the system, the location determination problem is solved by first applying a proximity constraint to limit the distance between a coarse estimate of the current position and a previous estimate. Then, a Compressive Sensing-based (CS--based) positioning scheme, proposed in our previous work , , is applied to obtain a refined position estimate. The refined estimate is used with a map-adaptive Kalman filter, which assumes a linear motion between intersections on a map that describes the user's path, to obtain a more robust position estimate. Experimental results with the system that is implemented on a PDA with limited resources (HP iPAQ hx2750 PDA) show that the proposed tracking system outperforms the widely used traditional positioning and tracking systems. Meanwhile, the tracking system leads to 12.6 percent reduction in the mean position error compared to the CS-based stationary positioning system when three APs are used. A navigation module that is integrated with the tracking system provides users with instructions to guide them to predefined destinations. Thirty visually impaired subjects from the Canadian National Institute for the Blind (CNIB) were invited to further evaluate the performance of the navigation system. Testing results suggest that the proposed system can be used to guide visually impaired subjects to their desired destinations.
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.
This brief paper presents a novel localization algorithm, named discriminant-adaptive neural network (DANN), which takes the received signal strength (RSS) from the access points (APs) as inputs to infer the client position in the wireless local area network (LAN) environment. We extract the useful information into discriminative components (DCs) for network learning. The nonlinear relationship between RSS and the position is then accurately constructed by incrementally inserting the DCs and recursively updating the weightings in the network until no further improvement is required. Our localization system is developed in a real-world wireless LAN WLAN environment, where the realistic RSS measurement is collected. We implement the traditional approaches on the same test bed, including weighted k -nearest neighbor (WKNN), maximum likelihood (ML), and multilayer perceptron (MLP), and compare the results. The experimental results indicate that the proposed algorithm is much higher in accuracy compared with other examined techniques. The improvement can be attributed to that only the useful information is efficiently extracted for positioning while the redundant information is regarded as noise and discarded. Finally, the analysis shows that our network intelligently accomplishes learning while the inserted DCs provide sufficient information.
In this paper, techniques and algorithms developed in the framework of Statistical Learning Theory are applied to the problem of determining the location of a wireless device by measuring the signal strength values from a set of access points (location fingerprinting). Statistical Learning Theory provides a rich theoretical basis for the development of models starting from a set of examples. Signal strength measurement is part of the normal operating mode of wireless equipment, in particular Wi–Fi, so that no special-purpose hardware is required.The proposed techniques, based on the Support Vector Machine paradigm, have been implemented and compared, on the same data set, with other approaches considered in scientific literature. Tests performed in a real-world environment show that results are comparable, with the advantage of a low algorithmic complexity in the normal operating phase. Moreover, the algorithm is particularly suitable for classification, where it outperforms the other techniques.
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