Unsupervised View-Selective Deep Learning for Practical Indoor Localization Using CSI

Radio channel state information (CSI) measured with many receivers is a good resource for localizing a transmitter device with machine learning with a discriminative model. However, CSI localization is nontrivial when the radio map is complicated, such as in building corridors. This article introduces a view-selective deep learning (VSDL) system for indoor localization using CSI of WiFi. The multiview training with CSI obtained from multiple groups of access points (APs) generates latent features on a supervised variational deep network. This information is then applied to an additional network for dominant view classification to minimize the regression loss of localization. As noninformative latent features from multiple views are rejected, we can achieve a localization accuracy of 1.28 m, which outperforms by 30% the best known accuracy in practical applications in a complex building environment. To the best of our knowledge, this is the first approach to apply variational inference and to construct a practical system for radio localization. Furthermore, our work investigates a methodology for supervised learning with multiview data where informative and noninformative views coexist.

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.

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.

Network densification through the deployment of WiFi access points (APs) is a promising solution towards achieving high connectivity rates required for emerging applications. A critical first step is to discover an AP before an active association between the client and the AP can be established. Legacy AP discovery procedures initiated by the client result in high latency in the order of a few 100 ms and waste spectrum, especially when clients need to frequently switch between multiple APs. We propose CSIscan that exploits the broadcast nature of WiFi channels by embedding discovery related information within an AP’s ongoing regular transmissions. The AP does this by intelligently distorting the transmitted OFDM frame by inducing perturbations in the preamble, and these injected ‘bits’ of information are detected via changes in the perceived channel state information (CSI). A deep learning framework allocates the optimal level of distortion on a per-subcarrier basis that keeps the resulting packet error rate to less than 1%. Existing clients perceive no changes in their ongoing communication, while potential new clients quickly obtain discovery information at the same time. We experimentally demonstrate that CSIscan reduces the overall WiFi latency from 150 ms to 10 ms and improves spectrum utilization with ~72% reduction in the probe traffic. We show that CSIscan delivers up to 40 discovery information bits in the outgoing WiFi packet in an indoor environment.

Indoor localization could benefit greatly from non-line-of-sight (NLOS) identification and mitigation, since the major challenge for WiFi indoor ranging-based localization technologies are multipath and NLOS. NLOS identification and mitigation on commodity WiFi devices, however, is challenge due to limited bandwidth and coarse multipath resolution with mere MAC layer RSSI. In this study, we explore and exploit the finer-grained PHY layer channel state information (CSI) to identify and mitigate NLOS. Key to our approach is exploiting several statistical features of CSI, which are proved to be particularly effective. Approach based on machine learning is proposed to identify NLOS and mitigate NLOS error. Experiment results in various indoor scenarios with severe interferences demonstrate that the proposed approach outperform previous threshold-based approaches and mitigate the impact of NLOS conditions perfectly.

The prevalence of WiFi infrastructures has enabled the advancement of a wide range of WiFi-based intelligent applications. Behavioral sensing, as an increasingly popular example, is attracting growing research interest in developing a device-free, accurate, and privacy-friendly interaction. Recent advances in behavioral research have shown great promise, but most of existing systems fail to capture the full scope of the relationship between WiFi signals and behaviors. In this work, we propose a behavioral sensing framework by modeling channel state information (CSI) of WiFi signals. The key insight is to harness antenna diversity and model signals reflected off the human body from multiple WiFi access points (APs) to infer daily activities. To this end, a CSI tensor is first constructed by aggregating the CSI from all WiFi APs. Next, a CANDECAMP/PARAFAC (CP) approach is leveraged for factorizing this CSI tensor into several single-rank tensors as key features. Then, a features optimization strategy is applied to the extracted features for selecting those correlated and dominant features by an embedded graph learning and constraint. Finally, a recurrent neural network (RNN) model is used to take the optimized features and capture a robust mapping between the input and output for recognizing daily activities in homes without requiring a prior calibration and any explicit involvement from the users. We design and implement a behavioral sensing prototype reusing existing WiFi and then carry out comprehensive experiments in two indoor environments. Extensive experimental results suggest that our scheme can accurately and effectively recognize the users’ behaviors and also outperforms existing ones.

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.

Next-generation Wi-Fi 8 (IEEE 802.11bn) targets ultra-high reliability (UHR) by introducing coordinated beamforming (CoBF). In dense networks with multiple access points (APs), simultaneous downlink (DL) multi-user MIMO (MU-MIMO) transmissions from multiple APs can cause severe intra-basic service set (intra-BSS) and inter-BSS interference. CoBF aided by only partial channel state information (CSI) feedback through medium access control (MAC) layer frame exchange is envisioned to support concurrent DL transmission with mitigated physical-(PHY-)layer interference. To improve the network throughput, not only the interference mitigation algorithm design requires careful design but also the selection of optimal AP CoBF clusters is crucial for dense AP deployments. This paper presents a cross-layer solution combining PHY and MAC layer design to optimize AP cluster formation for Wi-Fi 8 CoBF. At the PHY layer, we introduce two beamforming nulling strategies: full nulling, which completely cancels all intra-BSS and inter-BSS interference when sufficient spatial degrees of freedom are available, and partial nulling, which is used under limited degrees of freedom to reduce interference as much as possible. Based on this, we formulate the cross-layer problem that aims to optimize the network throughput, to which we propose an exact linear programming (LP) optimization to determine the optimal AP cluster formation. A greedy clustering algorithm is proposed as a low-complexity alternate. Simulation results demonstrate that the proposed CoBF approach significantly mitigates interference and achieves substantial throughput gains in dense AP scenarios. Furthermore, the LP-optimized AP clustering yields the higher network throughput than the greedy heuristic and mixed integer linear programming (MILP) by up to 12% and 26%, highlighting the benefits of global optimization in terms of performance and time complexity.

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.

Positioning services are increasingly used for applications such as navigation, advertising and social media. While outdoor navigation based on GPS and/or cellular systems works well, indoor navigation is a much tougher challenge. This paper proposes an indoor localization using Wi-Fi received signal strength indicator (RSSI) measurements from existing access points. Using RSSI data from multiple access points, additional access points will be added in the system thru linear regression statistical model to create virtual access points (VAPs). This paper fuses the low-cost and flexible system of fingerprint localization with VAP creation and the improvement in accuracy by adapting Kalman Filter (KF) and Particle Filter (Pf). The effectiveness of using KF with VAP has demonstrated positive results in previous research. This paper aims to integrate the use of PF in the system. To improve the performance of indoor localization, the proposed model will be an improved virtual access point localization, proposed filtering (VAP+KF+PF).

ABSTRACTUnderstanding the potential role of Smartphones and other portable wireless devices as relay nodes in message dissemination and content delivery in Delay Tolerant and Opportunistic networks depend on the knowledge about patterns and the number of encounter events among mobile nodes. One of the main challenges for extracting encounters is overlapping in the radio coverage areas of nearby access points (APs). Data about the usage of Wi-Fi networks can be used to perform an analysis of encounters among mobile devices. A realistic estimation of the number of encounters among mobile nodes is now a big challenge. In this paper, the effects of overlapping of radio coverage area among multiple APs for extracting realistic encounters among mobile devices has been discussed, and also an analytical approach has been proposed for extracting realistic encounters from overlapping in the coverage areas of multiple nearby APs. A significant difference was observed between the number of encounters by considering and ignoring overlapping. Our study finds that Wi-Fi datasets are not reliable source to estimate the number of encounters when there are overlapping in radio coverage areas of multiple APs.

Mobile edge computing (MEC) is an innovative computing paradigm to enhance the computing capacity of mobile devices (MDs) by offloading computation‐intensive tasks to MEC servers. With the widespread deployment of wireless local area networks, each MD can offload computation task to server via multiple wireless access points (WAPs). However, computation offloading can bring a higher system cost if all users select the same access points to offload their tasks. This study proposes a computation offloading strategy and resource allocation optimisation scheme in a multiple wireless access points network with MEC, which aims to minimise the system cost by providing the optimal computation offloading strategy, transmission power allocation, bandwidth assignment, and computation resource scheduling. The proposed scheme decouples the optimisation problem into subproblems of offloading strategy and resource allocation since the problem is NP‐hard. The offloading strategy involves the optimal access point selection, which is analysed by the potential game. The resource allocation is obtained using Lagrange multiplier. The authors' analysis and simulation results verify the convergence performance of the proposed scheme, and the proposed scheme outperforms the simple resource allocation scheme and the offloading strategy optimisation scheme in terms of the system cost.

A comprehensive review on detection of plant disease using machine learning and deep learning approaches

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 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.