Multiview Variational Deep Learning With Application to Practical Indoor Localization

Due to its high-dimensional data characteristics, the channel state information (CSI) of Wi-Fi signals has become a strong candidate for use in indoor localization. In addition, machine learning techniques can improve the accuracy of indoor localization systems using multiview CSI data received at multiple access points (APs). However, in complex environments, most CSI views collected at APs in non-line-of-sight (NLoS) configurations relative to a transmitter may lose so much useful data information as to become nonsalient. In this paper, we propose a practical machine learning approach named unsupervised view-selective deep learning (UVSDL), in which only the most salient CSI view is selected in an unsupervised manner to be applied in regression for localization. In an experiment in a complex building, our variational deep learning (VDL)-based regression method with the most salient CSI view achieves a localization accuracy of 1.36 m, significantly outperforming the best-known system BiLoc by 25 %.

Various machine learning techniques on indoor localization using radio signals are being rapidly developed to achieve a sub-meter accuracy under noisy and complex environments. A fingerprint database using channel state information (CSI) extracted from a radio packet based on an orthogonal frequency diversity multiplexing (OFDM) channel can provide enough information to localize a transmitter device with a neural network (NN) based machine learning technique. In this article, we concern about the more practical use of the localization system using machine learning. We introduce a novel design of a signal preprocessing method for NN fingerprinting. To deal with the real building environment with corridors where certain signals cannot arrive at the receiver, our preprocessing with nonnegative matrix factorization (NMF) recovers multiview CSI of the original signal and complete the sparse CSI matrix, which enables robust and practical localization. The recovered CSI is then applied to variational inference-based machine learning that finds informative corridor views among multiview CSI. Our proposed system significantly outperforms other existing machine learning-based systems and shows a localization accuracy of 89 cm, while it still maintains the reliable accuracy even with 30% sparse network. It is the first time to consider how to design a practical localization system in an empirical building environment.

In this paper, a novel indoor localization system with channel state information (CSI) fingerprints is proposed, which learns the spatial and frequency features of CSI in the fifth-generation (5G) cellular network by a Siamese convolution neural network. In particular, considering that the CSI continuously collected by a moving target possesses the implicit spatial association, we locate the target by the successive CSI data gathered within a time interval which can be regarded as an information subspace of the fingerprint database. Therefore, the fingerprint localization can be modeled as a subspace matching problem and solved by the Siamese network-based similarity learning. In the proposed system, we design a structure of CSI fingerprint which includes the information from multiple base stations in spatial and frequency domains. Then, the proposed Siamese architecture extracts the CSI feature and estimates the location of the target by feature similarity comparison. Compared with the existing algorithms, it can increase the positioning accuracy significantly by the feature relevance among the CSI data collected at different positions. The field tests indicate that compared to other CSI fingerprint-based positioning methods, our proposed algorithm can effectively reduce the localization error.

The indoor positioning system (IPS) is becoming increasing important in accurately determining the locations of objects by the utilization of micro-electro-mechanical-systems (MEMS) involving smartphone sensors, embedded sources, mapping localizations, and wireless communication networks. Generally, a global positioning system (GPS) may not be effective in servicing the reality of a complex indoor environment, due to the limitations of the line-of-sight (LoS) path from the satellite. Different techniques have been used in indoor localization services (ILSs) in order to solve particular issues, such as multipath environments, the energy inefficiency of long-term battery usage, intensive labour and the resources of offline information collection and the estimation of accumulated positioning errors. Moreover, advanced algorithms, machine learning, and valuable algorithms have given rise to effective ways in determining indoor locations. This paper presents a comprehensive review on the positioning algorithms for indoors, based on advances reported in radio wave, infrared, visible light, sound, and magnetic field technologies. The traditional ranging parameters in addition to advanced parameters such as channel state information (CSI), reference signal received power (RSRP), and reference signal received quality (RSRQ) are also presented for distance estimation in localization systems. In summary, the recent advanced algorithms can offer precise positioning behaviour for an unknown environment in indoor locations.

Cell-free massive MIMO (CF-mMIMO) systems promise enhanced spectral efficiency and uniform service by deploying numerous distributed access points (APs) that jointly serve users. However, centralized precoding, which offers optimal performance by leveraging global channel state information (CSI), imposes significant fronthaul overhead due to the extensive CSI exchange between APs and the central processing unit (CPU). In contrast, distributed precoding reduces fronthaul demands, but undergoes performance degradation due to the lack of coordination between APs. This paper introduces a novel framework that strikes a balance between these two scenarios by employing channel charting (CC) as a lightweight CSI compression mechanism at each AP. CC maps high-dimensional CSI into a low-dimensional pseudo-location space, capturing essential channel characteristics. These pseudo-locations are transmitted to the CPU with minimal overhead, where advanced machine learning models are employed to infer effective downlink precoding vectors, thereby approximating centralized performance while reducing fronthaul signaling. Extensive simulations on realistic synthetic datasets demonstrate that our approach achieves very promising results. This work highlights the potential of integrating CC and machine learning to enhance scalability and efficiency in CF-mMIMO networks.

Channel state information (CSI)-based fingerprinting via neural networks (NNs) is a promising approach to enable accurate indoor and outdoor positioning of user equipment (UE), even under challenging propagation conditions. In this paper, we propose a positioning pipeline for wireless LAN MIMO-OFDM systems which uses uplink CSI measurements obtained from one or more unsynchronized access points (APs). For each AP receiver, novel features are first extracted from the CSI that are robust to system impairments arising in real-world transceivers. These features are the inputs to a NN that extracts a probability map indicating the likelihood of a UE being at a given grid point. The NN output is then fused across multiple APs to provide a final position estimate. We provide experimental results with real-world indoor measurements under line-of-sight (LoS) and non-LoS propagation conditions for an 80MHz bandwidth IEEE 802.11ac system using a two-antenna transmit UE and two AP receivers each with four antennas. Our approach is shown to achieve centimeter-level median distance error, an order of magnitude improvement over a conventional baseline.

Wi-Fi based indoor localization has attracted great interest due to its ubiquitous access in many indoor environments. In this paper, we propose ResLoc, a deep residual sharing learning based system for indoor localization with channel state information (CSI) tensor data. We first introduce CSI data in wireless systems and show how to build CSI tensors for indoor localization. Then, we present the design of ResLoc, which employs dual-channel, bi-modal CSI tensor data to train the deep network using the proposed deep residual sharing learning in the offline phase. In the online test phase, we use newly received CSI tensor data to estimate the location of the mobile device based on an enhanced probabilistic method. The experimental results show that the proposed ResLoc system can obtain submeter level accuracy with a single access point.

The feasibility of implementing non-orthogonal multiple access (NOMA) in massive multiple-input multiple-output (MIMO) downlink with distributed antenna arrays is investigated. The achievable downlink rates are derived for two channel state information (CSI) cases, namely (i) estimated uplink CSI at the access points (APs) via user uplink pilots and statistical CSI at the users, and (ii) estimated uplink CSI at the APs via uplink user pilots and estimated downlink CSI at the users via downlink pilots beamformed by the APs. The trade-off between the number of served user nodes and their achievable rates is investigated. The adverse effects of imperfect successive interference cancellation (SIC) and detection uncertainty on the achievable downlink rates are quantified. We show that the achievable downlink rate of NOMA can be inferior to that of the orthogonal multiple-access (OMA) counterpart in the low-user regime. This is a direct consequence of residual interference caused by intra-cluster pilot contamination and error propagation from imperfect SIC. However, the proposed massive MIMO NOMA downlink outperforms the OMA counterpart in the highuser regime in terms of the achievable downlink rate. Moreover, the impact of downlink pilots on the sum rate is also investigated.

Acquiring accurate channel state information (CSI) is essential for enabling reliable and efficient wireless transmission and reception. However, CSI is inherently stochastic, high-dimensional, and time-varying, which makes its acquisition particularly challenging. Motivated by the success of deep learning (DL) across many data modalities, this thesis explores DL-based solutions for CSI estimation, compression, and prediction.First, we study CSI estimation in full-duplex (FD) multiple-input multiple-output (MIMO) systems, where strong self-interference (SI) complicates channel acquisition. To reduce the pilot and computational burden of estimating both SI and user channels, we propose a pilot-sharing strategy together with a convolutional neural network that jointly estimates these channels.We further introduce a neural mapping that enables CSI acquisition at the transmit chain.Second, we investigate DL–based CSI compression and its limited robustness under distribution shifts. To address this issue, we adopt a full-model fine-tuning while explicitly accounting for model update signaling overhead. Specifically, we employ a spike-and-slab prior to promote sparsity in the model updates and fine-tune the pretrained network using a rate–distortion objective regularized by the update bit rate.Third, we tackle CSI prediction using a diffusion-based generative framework. The method consists of a temporal encoder that extracts latent features from past CSI and a diffusion generator that synthesizes future CSI. We also study a simplified encoder-free design to reduce latency, compare autoregressive and sequence-to-sequence inference, and explore multiple architectures for both temporal encoding and diffusion generation.

The past few decades have seen significant advancements in WiFi indoor localization leveraging fine-grained Channel State Information (CSI). However, existing methods often require multiple access points (APs) or the target device to share sensing data. This cooperative localization complicates the deployment of practical localization systems. In this paper, we present SniFi, a non-cooperative localization method that seamlessly integrates with existing WiFi infrastructure. Unlike prior methods, SniFi does not require multiple CSI-capable APs or additional user actions. We use a single network interface card (NIC) to sniff WiFi traffic and obtain the angle information needed for localization. For APs that do not support CSI acquisition, we first utilize Beamforming Feedback Information (BFI) to estimate the Angle of Departure (AoD). Then, by analyzing the sniffed packets, we can obtain the CSI and the corresponding Angle of Arrival (AoA) from the target device to the sniffer. During experiments, we also address the challenge of angle ambiguity of the latest Intel AX210 NIC by integrating map constraints and temporal continuity. These techniques together enable us to achieve accurate localization without making changes to existing AP networks. Extensive evaluations across various environments and APs demonstrate that SniFi achieves decimeter-level accuracy in median error.

With the rapid growth of indoor positioning requirements without equipment and the convenience of channel state information acquisition, the research on indoor fingerprint positioning based on channel state information is increasingly valued. In this article, a multi-level fingerprinting approach is proposed, which is composed of two-level methods: the first layer is achieved by deep learning and the second layer is implemented by the optimal subcarriers filtering method. This method using channel state information is termed multi-level fingerprinting with deep learning. Deep neural networks are applied in the deep learning of the first layer of multi-level fingerprinting with deep learning, which includes two phases: an offline training phase and an online localization phase. In the offline training phase, deep neural networks are used to train the optimal weights. In the online localization phase, the top five closest positions to the location position are obtained through forward propagation. The second layer optimizes the results of the first layer through the optimal subcarriers filtering method. Under the accuracy of 0.6 m, the positioning accuracy of two common environments has reached, respectively, 96% and 93.9%. The evaluation results show that the positioning accuracy of this method is better than the method based on received signal strength, and it is better than the support vector machine method, which is also slightly improved compared with the deep learning method.

Received signal strength (RSS)/channel state information (CSI) fingerprinting techniques have been widely adopted for wireless local area network (WLAN)-based indoor localization. However, in most of the RSS/CSI fingerprinting techniques, an application/software has to be installed on the target for uploading RSS/CSI information to the localization system. As a result, RSS/CSI fingerprinting cannot achieve passive localization (application-free), which is an essential requirement in many existing localization systems, especially for commercial and military purposes. In this paper, we propose data rate (DR) fingerprinting to achieve passive localization. DR fingerprinting is compatible with most off-the-shelf wireless fidelity (Wi-Fi) devices and can be directly implemented in the existing WLAN-based localization system without any extra hardware. In DR fingerprinting, DRs are used to replace the RSS/CSI to form fingerprints, since DR information can be directly obtained by access points (APs). However, the inherent features of DR, including low-resolution and serious fluctuation, significantly impair the performance of DR fingerprinting. For implementing DR fingerprinting, we leverage multiple transmission power levels, propose a time-window mechanism with different fingerprint formulations, design a AP switching strategy, and design a new matching algorithm named dynamic nearest neighbors (DNNs). We conducted extensive experiments in a real-world testbed to study the performance of DR fingerprinting. Specifically, we compared DR fingerprinting with the state-of-the-art RSS/CSI fingerprinting techniques. The experimental results illustrate that DR fingerprinting can achieve the localization accuracy that is comparable to that of the RSS/CSI fingerprinting with the additional benefit of achieving passive localization.

Radio frequency (RF) fingerprinting techniques provide a promising supplement to cryptography-based approaches but rely on dedicated equipment to capture in-phase and quadrature (IQ) samples, hindering their wide adoption. Recent advances advocate easily obtainable channel state information (CSI) by commercial WiFi devices for lightweight RF fingerprinting, while falling short in addressing the challenges of coarse granularity of CSI measurements in an open-world setting. In this paper, we propose CSI<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>Q, a novel CSI fingerprinting system that achieves comparable performance to IQ-based approaches. Instead of extracting fingerprints directly from raw CSI measurements, CSI<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>Q first transforms frequency-domain CSI measurements into time-domain signals that share the same feature space with IQ samples. Then, we employ a deep auxiliary learning strategy to transfer useful knowledge from an IQ fingerprinting model to the CSI counterpart. Finally, the trained CSI model is combined with an OpenMax function to estimate the likelihood of unknown ones. We evaluate CSI<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>Q on one synthetic CSI dataset involving 85 devices and two real CSI datasets, including 10 and 25 WiFi routers, respectively. Our system achieves accuracy increases of at least 16% on the synthetic CSI dataset, 20% on the in-lab CSI dataset, and 17% on the in-the-wild CSI dataset.

Existing fingerprint-based indoor localization uses either fine-grained channel state information (CSI) from the physical layer or coarse-grained received signal strength indicator (RSSI) measurements. In this paper, we propose to use a mid-grained intermediate-level channel measurement - spatial beam signal-to-noise ratios (SNRs) that are inherently available and defined in the IEEE 802.11ad/ay standards - to construct the fingerprinting database. These intermediate channel measurements are further utilized by a deep learning approach for multiple purposes: 1) location-only classification; 2) simultaneous location-and-orientation classification; and 3) direct coordinate estimation. Furthermore, the effectiveness of the framework is thoroughly validated by an in-house experimental platform consisting of 3 access points using commercial-off-the-shelf millimeter-wave WiFi routers. The results show a 100% accuracy if the location is only interested, about 99% for simultaneous location-and-orientations classification, and an averaged root mean-square error (RMSE) of 11.1 cm and an average median error of 9.5 cm for direct coordinate estimate, greater than 2-fold improvements over the RMSE of 28.7 cm and median error of 23.6 cm for RSSI-like single SNR-based localization.

At present, there has been a booming interest in utilizing Channel State Information (CSI) extracted from MIMO-OFDM PHY layer to achieve precise indoor localization. Compared with Received Signal Strength Indicator (RSSI), CSI as a fine-grained feature has a better performance on expressing the spatial and temporal features of wireless signal. As a result, CSI is more sensitive to the noise interference and multi-path. In this paper, we present a direct-path based fingerprint extraction algorithm for indoor localization in noisy and multi-path indoor environment. Our proposed algorithm firstly extracts the amplitude and phase measurements of direct-path from the raw CSI, and then calculates the unique fingerprint feature according to the filtered CSI. The experimental results show that our proposed algorithm improves the positioning accuracy up to 23.5% in complex indoor multipath environment.