Figure 6 - available via license: CC BY
Content may be subject to copyright.
Source publication
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:...
Contexts in source publication
Context 1
... system architecture diagram of MFD system is shown as Figure 6. The system sends signals through a wireless router, and a receiver with three antennas receives signals. ...
Context 2
... total, 1500 packets are collected at each sampling point. The amplitude in Figure 6 is the average value of the 500 data packets in the middle of the 1500 packets representing the ampli- tude of the subcarrier at that point. The more obvious the change of the amplitude values between different points in the front and back, indicates that the subcar- rier is more sensitive to the change of location informa- tion. ...
Similar publications
Citations
... It allows doctors to track the position of the fetus and monitor its development during pregnancy. Ultrasound imaging is also used in musculoskeletal imaging to locate and track the movement of tendons, ligaments, and muscles [100]. In cardiac imaging, ultrasound can be used to track the movement of the heart and detect abnormalities in its function. ...
... Tao Li et al. [40] tested indoor localization. In corridor, 7×7 finger print, it is 4.2m × 4.2m with 49 sampling points. ...
Human activity recognition (HAR) plays a crucial role in human-computer interaction, smart home, health monitoring and elderly care. However, existing methods typically utilize camera, radio frequency (RF) signals or wearable devices for activity recognition. Each single-sensor modality has its inherent limitations, like camera-based methods having blind spots, Wi-Fi-based methods depending on the environment and the inconvenience of wearing Inertial Measurement Unit (IMU) devices. In this paper, we propose a HAR system that leverages three types of sensor combinations: Wi-Fi, IMU and a hybrid of Wi-Fi+IMU. We utilize the Channel State Information (CSI) provided by Wi-Fi and the accelerometer and gyroscope data from IMU devices to capture activity characteristics. Then, we employ six machine learning algorithms to recognize eight types of daily activities. These algorithms include Support Vector Machine (SVM), Multi-layer Perceptron (MLP), Decision Tree, Random Forest, Logistic Regression and k-Nearest Neighbors (kNN). Additionally, we investigate the accuracy of hand gesture recognition using different sensor combinations and analyze the calculation speed of each combination. We conduct a survey to collect user feedback on the performance of various sensor combinations in our HAR system. The results show that the combination of CSI+IMU yields the best HAR recognition accuracy, with a accuracy of 89.38%. The SVM algorithm consistently performs well across all systems, especially excelling in the CSI+IMU system supported by energy and average Fast Fourier Transform (FFT) features. However, we also find that the success of sensor fusion depends on specific algorithms and features. Fusion of CSI and IMU does not universally enhance recognition accuracy for all features and algorithms and can, in some cases, actually reduce accuracy.
... Channel state information (CSI) is a major component of the multi-level fingerprinting strategy for indoor localization proposed by Li, T. et al. in 2018 [18]. For precise localization, CSI gives comprehensive information about the wireless channel, including phase shifts, amplitude changes, and multipath effects. ...
For the establishment of future ubiquitous location-aware applications, a scalable indoor localization technique is essential technology. Numerous classification techniques for indoor localization exist, but none have proven to be as quick, secure, and dependable as what is now needed. This research proposes an effective and privacy-protective federated architecture-based framework for location classification via Wi-Fi fingerprinting. The federated indoor localization classification (f-ILC) system that was suggested had distributed client–server architecture with data privacy for any and all related edge devices or clients. To try and evaluate the proposed f-ILC framework, different data from different sources on the Internet were collected and given in a format that had already been processed. Experiments were conducted with standard learning, federated learning with a single client, and federated learning with several clients to make sure that federated deep learning models worked correctly. The success of the f-ILC framework was computed using a number of factors, such as validation of accuracy and loss. The results showed that the suggested f-ILC framework performed better than traditional distributed deep learning-based classifiers in terms of accuracy and loss while keeping data secure. Due to its innovative design and superior performance over existing classifier tools, edge devices’ data privacy makes this proposed architecture the ideal solution.
... The CSI parameter [39] calculates the distance between the receiver and the transmitter by using physical layer signal characteristics such as the amplitude and phase of each subcarrier in the frequency domain. However, only some devices support access to CSI information [40]. The RSSI parameter [41] is commonly used in the Trilateration method to determine the position of the target node. ...
Various ambient intelligent environment applications are based on location-based services. To obtain the location, many popular localization methods use the Received-Signal-Strength-Indicator (RSSI) measurement, as it can be obtained from almost any wireless communication device technology and does not require additional hardware. However, physical phenomena, such as reflection and diffraction, affect the radio signal propagation and lead to imperfections in the RSSI measurements, impacting the localization performance. In this paper, the K-Nearest Neighbors (KNN) machine learning technique is used to improve the localization accuracy of the RSSI-based geometric localization methods. First, in the training step, we proposed to model the RSSI measurement by a distance interval that accounts for the RSSI imperfections due to the signal propagation noise in the environment of interest. Then, in the online step, a Hybrid Centroid-KNN (HCK) localization method based on the defined distance intervals is proposed to calculate the position of the target node. To validate the performance of the proposed localization method, we used three datasets from three testbeds which are a residence equipped with WiFi technology, a library, and office space, both equipped with BLE technology. The obtained results show that the proposed method significantly reduces the localization error in these environments in comparison with the well-known geometric localization methods Multilateration (ML), Min–Max (MM), and Weighted Centroid Localization (WCL). In particular, the average localization errors of the HCK method are reduced compared to the ML, MM, and WCL methods in the residence by 50%, 37%, and 14%, respectively, when the inhabitant is performing daily activities and by 44%, 31%, and 14%, respectively, when the inhabitant is walking.
... UAV positioning has been widely studied at home and abroad, and has been successfully applied to the field of engineering practice. Traditionally, the positioning method of single UAV mainly includes visual positioning [10,11] and wireless positioning [12,13]. Visual positioning is to obtain the image of the environment through installing visual sensor on UAV, and then the image information is utilized to obtain the current geographical location of the UAV. ...
Unmanned Aerial Vehicle (UAV) Internet of things have been widely used in military and civilian fields such as rescue, disaster relief, urban planning. Positioning service is the core technology for UAVs to perform various tasks. However, the UAV may be attacked by external conditions, resulting in its inability to obtain self-location information during mission. For the positioning problem of UAV signal interference, this paper proposes a cooperative positioning of UAV based on optimization algorithm. In order to solve the difficulty of UAV positioning, we propose the following solutions. Firstly, we construct different numbers of beacon nodes by using the flight information of UAVs in different cycles. Secondly, the unknown number of the positioning to be solved of the UAV is reduced to improve the accuracy and speed of the subsequent optimization algorithm. Thirdly, A multi-objective optimization model is established of the UAV motion parameters under inequality constraints. And we utilize a penalty function to convert the optimization model into a minimal value solution problem under no constraints. Finally, the positioning results of each UAV are obtained by the optimization algorithm.
... The general results are demonstrated by a CDF plot comparing the systems which have the top regression performances (see Figure 16). System 1 (proposed by T. Li et al., 2018) and system 2 (proposed by X. Wang, Gao, Mao, & Pandey, 2015) are based on CSI signals while system 3 (proposed by Hoang et al., 2019) and system 4 (proposed by Xue et al., 2020) are based on WiFi RSS. As illustrated in the CDF plot, systems based on CSI could produce less than 2 m distance error more than 98% of the time. ...
One of the most popular approaches for indoor positioning is WiFi fingerprinting, which has been intrinsically tackled as a traditional machine learning problem since the beginning, to achieve a few metres of accuracy on average. In recent years, deep learning has emerged as an alternative approach, with a large number of publications reporting sub-metre positioning accuracy. Therefore, this survey presents a timely, comprehensive review of the most interesting deep learning methods being used for WiFi fingerprinting. In doing so, we aim to identify the most efficient neural networks, under a variety of positioning evaluation metrics for different readers. We will demonstrate that despite the new emerging WiFi signal measures (i.e. CSI and RTT), RSS produces competitive performances under deep learning. We will also show that simple neural networks outperform more complex ones in certain environments.
... In the following, we compare the results of our model with the measurements. For each d LOS , we calculate the difference between the model (dashed blue line) and our measurement (red dotted line) over the frequency range, exemplarily shown in Fig. 8. Inspired by [29], we chose the absolute differences between the two vectors, which is a common metric of spectral fingerprints. The absolute difference e dLOS (d model ) between a measured spectrum and each calculated spectrum is calculated with: ...
In acoustic underwater communication and sonar applications, obstacles inside and outside the line-of-sight (LOS) affect signal propagation. Both reflection and diffraction occur in underwater communication and measurement systems due to these obstacles. To the best of our knowledge, the influence of diffraction and reflection is neither described nor modeled for finite pulses yet. We propose and develop a multipath propagation model for spectral diffraction components and phase information of the received signal based on knife-edge diffraction together with reflections, transmission effects, and backscatter. This paper designs a short range underwater ultrasonic experimental system composed of an ultrasonic transceiver with wideband pulses and advanced spectral signal processing. We evaluate our proposed model with measurements made in a water tank with an obstacle moved between the transmitter and receiver. When the model includes all major propagation components and effects, it achieves an accuracy for localization of 97 % of the results in the range of twice the obstacle diameter in our test setup.
... This problem formulation is a natural fit for supervised machine learning, which is why the recent popularity of deep learning led to an increasing amount of publications that successfully apply deep learning for fingerprinting-based indoor localization [14][15][16][17][18]. RSS results from the superposition of multipath components and, as a consequence, fluctuates even at a static detection point [6], which limits the theoretically achievable localization performance. ...
... Fingerprinting is still an attractive approach for device-based-especially smartphonebased-indoor localization, since it does not require dedicated infrastructure to be installed. The advent of deep learning has resulted in increasing interest in transfering its success to indoor localization [14][15][16][17][18]. Still, the nature of the fingerprinting method limits the accuracy that can ideally be reached, such that models are required that nevertheless provide a reliable space estimation while sacrificing as little expressiveness as possible. ...
Location-based services (LBS) have gained increasing importance in our everyday lives and serve as the foundation for many smartphone applications. Whereas Global Navigation Satellite Systems (GNSS) enable reliable position estimation outdoors, there does not exist any comparable gold standard for indoor localization yet. Wireless local area network (WLAN) fingerprinting is still a promising and widely adopted approach to indoor localization, since it does not rely on preinstalled hardware but uses the existing WLAN infrastructure typically present in buildings. The accuracy of the method is, however, limited due to unstable fingerprints, etc. Deep learning has recently gained attention in the field of indoor localization and is also utilized to increase the performance of fingerprinting-based approaches. Current solutions can be grouped into models that either estimate the exact position of the user (regression) or classify the area (pre-segmented floor plan) or a reference location. We propose a model, DeepLocBox (DLB), that offers reliable area localization in multi-building/multi-floor environments without the prerequisite of a pre-segmented floor plan. Instead, the model predicts a bounding box that contains the user’s position while minimizing the required prediction space (size of the box). We compare the performance of DLB with the standard approach of neural network-based position estimation and demonstrate that DLB achieves a gain in success probability by 9.48% on a self-collected dataset at RWTH Aachen University, Germany; by 5.48% for a dataset provided by Tampere University of Technology (TUT), Finland; and by 3.71% for the UJIIndoorLoc dataset collected at Jaume I University (UJI) campus, Spain.
... Yet, which of those to use can still make a difference in implementations of ML algorithms. Most practical cellular and WiFi systems are multi-carrier signals, so that they naturally measure the Papers OFDM [61], [84], [190], [209], [211], [212], [214]- [217], [226], [228]- [239] MIMO [240] [61], [190], [205], [206], [211], [217], [226], [228], [230]- [239], [241], [242] Massive MIMO [113], [174], [208], [209], [212]- [216], [218], [243] Distributed MIMO [113], [213], [218], [219] UWB [49], [80], [83], [141], [157], [202], [222], [223], [244] CFR, or more precisely, the samples of the CFR at discrete frequencies, the subcarrier frequencies used in the multicarrier signaling. When CSI at each sub-carrier is available, CFR is usually used as feature [208], [212], [226]. ...
The last few decades have witnessed a growing interest in location-based services. Using localization systems based on Radio Frequency (RF) signals has proven its efficacy for both indoor and outdoor applications. However, challenges remain with respect to both complexity and accuracy of such systems. Machine Learning (ML) is one of the most promising methods for mitigating these problems, as ML (especially deep learning) offers powerful practical data-driven tools that can be integrated into localization systems. In this paper, we provide a comprehensive survey of ML-based localization solutions that use RF signals. The survey spans different aspects, ranging from the system architectures, to the input features, the ML methods, and the datasets. A main point of the paper is the interaction between the domain knowledge arising from the physics of localization systems, and the various ML approaches. Besides the ML methods, the utilized input features play a major role in shaping the localization solution; we present a detailed discussion of the different features and what could influence them, be it the underlying wireless technology or standards or the preprocessing techniques. A detailed discussion is dedicated to the different ML methods that have been applied to localization problems, discussing the underlying problem and the solution structure. Furthermore, we summarize the different ways the datasets were acquired, and then list the publicly available ones. Overall, the survey categorizes and partly summarizes insights from almost 400 papers in this field. This survey is self-contained, as we provide a concise review of the main ML and wireless propagation concepts, which shall help the researchers in either field navigate through the surveyed solutions, and suggested open problems.
... In the existing literatures, some investigations aim at enhancing the hardware efficiency of RSS data sampler, and the others exploit the interpolation algorithms (e.g. least square method [9], Neural Network Method [10], Inverse distance method [11]) to calculate RSS data of estimation points. However, the common problems of above-mentioned algorithms are the inaccurate RSS data of estimation points since they fail to consider that RSS values decrease rapidly in near-field region and slow in far-field region, which are separated according to the distance between observation points and AP based on the free space propagation model of wireless signal. ...
The traditional method of constructing RSS fingerprint database costs a large amount of time and human resource due to adopting the point-by-point method to sample RSS value, and consequently the positioning method based on RSS fingerprint model is difficult to be widely applied. In this paper, a RSS data generation method is proposed based on Kriging spatial interpolation algorithm. The proposed method firstly selects the model of variogram according to the properties of field, and subsequently solves the variogram by using the observation points with the restriction of unbiased estimation and minimum estimation variance, finally calculates RSS data for the estimation points. The experimental results show that the proposed method accurately acquires the RSS data of estimation points while the required reference points are much less than that of conventional point-by-point method.
