No file available
To read the file of this research,
you can request a copy directly from the authors.
Deep Convolutional Auto-Encoder based Indoor Visible Light Positioning Using RSS Temporal Image
Abstract
Visible light communication is a promising candidate for achieving low-cost, high data rate and massive coverage in future wireless network. To fulfill the multimedia or broadcasting service, the prerequisite is to determine the user's position. However, traditional RSS fingerprint based positioning approach suffers the random signal fluctuation problem which significantly limits the positioning performance. To tackle this problem, this paper presents a deep learning scheme which utilize a regression DNN combined with convolutional auto-encoder (CAE) to provide robust indoor positioning. Instead of using the separate fluctuated RSS reading for positioning, the proposed method takes the RSS temporal image (RTI) composed from a set of consecutive RSS readings as input. By leveraging the spatial and temporal dependency of RTI data with stacked denoising CAE, the proposed network is expected to learn more complex and consistent features from the fluctuating RSS readings and perform better location estimation. Simulation results have shown that the proposed method is capable of providing more stable positioning result from fluctuating RSS data than traditional DNN based method.
ResearchGate has not been able to resolve any citations for this publication.
In the Internet of Things (IoT) era, indoor localization plays a vital role in academia and industry. Wi-Fi is a promising scheme for indoor localization as it is easy and free of charge, even for private networks. However, Wi-Fi has signal fluctuation problems because of dynamic changes of environments and shadowing effects. In this paper, we propose to use a deep neural network (DNN) to achieve accurate localization in Wi-Fi environments. In the localization process, we primarily construct a database having all reachable received signal strengths (RSSs), and basic service set identifiers (BSSIDs). Secondly, we fill the missed RSS values using regression, and then apply linear discriminant analysis (LDA) to reduce features. Thirdly, the 5-BSSIDs having the strongest RSS values are appended with reduced RSS vector. Finally, a DNN is applied for localizing Wi-Fi users. The proposed system is evaluated in the classification and regression schemes using the python programming language. The results show that 99.15% of the localization accuracy is correctly classified. Moreover, the coordinate-based localization provides 50%, 75%, and 93.10% accuracies for errors less than 0.50 m, 0.75 m, and 0.90 m respectively. The proposed method is compared with other algorithms, and our method provides motivated results. The simulation results also show that the proposed method can robustly localize Wi-Fi users in hierarchical and complex wireless environments.
Indoor localization of mobile nodes is receiving great interest due to the recent advances in mobile devices and the increasing number of location-based services. Fingerprinting based on Wifi received signal strength (RSS) is widely used for indoor localization due to its simplicity and low hardware requirements. However, its positioning accuracy is significantly affected by random fluctuations of RSS values caused by fading and multi-path phenomena. This paper presents a convolutional neural network (CNN) based approach for indoor localization using RSS time-series from wireless local area network (WLAN) access points. Applying CNN on a time-series of RSS readings is expected to reduce the noise and randomness present in separate RSS values and hence improve the localization accuracy. The proposed model is implemented and evaluated on a multi-building and multi-floor dataset, UJIIndoorLoc dataset. The proposed approach provides 100% accuracy for building prediction, 100% accuracy for floor prediction and the mean error in coordinates estimation is 2.77 m.
This paper introduces a new interval constraint propagation (ICP) approach dealing with the real-time vehicle localization problem. Bayesian methods like extended Kalman filter (EKF) are classically used to achieve vehicle localization. ICP is an alternative which provides guaranteed localization results rather than probabilities. Our approach assumes that all models and measurement errors are bounded within known limits without any other hypotheses on the probability distribution. The proposed algorithm uses a low-level consistency algorithm and has been validated with an outdoor vehicle equipped with a GPS receiver, a gyro, and odometers. Results have been compared to EKF and other ICP methods such as hull consistency (HC4) and 3-bound (3B) algorithms. Both consistencies of EKF and our algorithm have been experimentally studied.
Advances in Visible Light Communication (VLC) technology and the ubiquity of illumination facility have led to a growing interest in VLC-based indoor positioning. Numerous techniques have been proposed to obtain better system performance. In this paper, we survey over 100 papers ranging from pioneering papers to the state-of-the-art in the field to present the positioning technology. Not only the Light Emitting Diode (LED) technology, modulation method and types of receivers are compared, but also a novel taxonomy method is proposed. In this paper, VLC-based Indoor Positioning Systems (VLC-based-IPSs) are classified based on the methods used, (1) mathematical method, (2) sensor-assisted method, (3) optimization method. Different from other survey works, we emphasize and analyze the accuracy of VLC-based Indoor Positioning System (VLC-based-IPS) in the experiment and simulation environments. Meanwhile, the paper illustrates challenges, countermeasures and lessons learned.
Recently, indoor visible light localization has become attractive. Unfortunately, its performance is limited by diffuse reflection. The diffuse reflection is estimated by the bilinear interpolation-based method. A received signal strength-based iterative visible light positioning algorithm is proposed to reduce the influence of diffuse reflection by subtracting the estimated diffuse reflection signal from the received signal. Simulations are made to evaluate the proposed iterative positioning algorithm in a typical scenario with different parameters of the field-of-view (FOV) of the receiver and the reflectivity of the wall. Results show that the proposed algorithm can reduce the average positioning error by 12 times in a typical scenario and can reduce the positioning error greatly with various FOV of the receiver and the reflectivity of the wall. The proposed algorithm is effective and robust to reduce the degradation caused by diffuse reflection in a positioning system and will have many potential applications in indoor localization scenarios. © 2016 Society of Photo-Optical Instrumentation Engineers (SPIE).
We present a novel convolutional auto-encoder (CAE) for unsupervised feature learning. A stack of CAEs forms a convolutional
neural network (CNN). Each CAE is trained using conventional on-line gradient descent without additional regularization terms.
A max-pooling layer is essential to learn biologically plausible features consistent with those found by previous approaches.
Initializing a CNN with filters of a trained CAE stack yields superior performance on a digit (MNIST) and an object recognition
(CIFAR10) benchmark.
Because of the advanced development in computer technology, home automation system could provide a variety of convenient and novel services to people. But only providing many kinds of services is not enough; instead, upgrading the quality of services is also a very important issue. One way to upgrade the service quality is to customize the service according to the inhabitant's personal situation, and the user location is the key information for the home automation system to customize the services. Another impact of the advanced computer technology is to make the personal digital device to commonly have the capability to communicate through the wireless networks, and the popularity of wireless networks in home has increased in recent years. As a result, home automation system can bring services to personal digital devices held by people through any wireless network, and customize the services according to the location of personal digital device in home. In this paper, we present a location determination system for the home automation system to provide location aware services. This location determination system uses support vector machine to classify the location of a wireless client from its signal strength measures, and we describe its architecture and discuss its performance.
Using WiFi signals for indoor localization is the main localization modality of the existing personal indoor localization systems operating on mobile devices. WiFi fingerprinting is also used for mobile robots, as WiFi signals are usually available indoors and can provide rough initial position estimate or can be used together with other positioning systems. Currently, the best solutions rely on filtering, manual data analysis, and time-consuming parameter tuning to achieve reliable and accurate localization. In this work, we propose to use deep neural networks to significantly lower the work-force burden of the localization system design, while still achieving satisfactory results. Assuming the state-of-the-art hierarchical approach, we employ the DNN system for building/floor classification. We show that stacked autoencoders allow to efficiently reduce the feature space in order to achieve robust and precise classification. The proposed architecture is verified on the publicly available UJIIndoorLoc dataset and the results are compared with other solutions.
Visible light communication (VLC) using light-emitting-diodes (LEDs) has been
a popular research area recently. VLC can provide a practical solution for
indoor positioning. In this paper, the impact of multipath reflections on
indoor VLC positioning is investigated, considering a complex indoor
environment with walls, floor and ceiling. For the proposed positioning system,
an LED bulb is the transmitter and a photo-diode (PD) is the receiver to detect
received signal strength (RSS) information. Combined deterministic and modified
Monte Carlo (CDMMC) method is applied to compute the impulse response of the
optical channel. Since power attenuation is applied to calculate the distance
between the transmitter and receiver, the received power from each reflection
order is analyzed. Finally, the positioning errors are estimated for all the
locations over the room and compared with the previous works where no
reflections considered. Three calibration approaches are proposed to decrease
the effect of multipath reflections.
Radio Frequency Identification (RFID) technology has shown its potential in the field of indoor positioning in recent years, and has been widely used in large establishments such as the airport lobby, supermarkets, libraries, underground parking and so on. However, the complexity of the indoor environments make positioning a challenging problem in terms of accuracy, stability, reliability, and interference immunity. In this paper, we develop an algorithm of passive RFID indoor positioning based on interval Kalman filter, according to the geometric constraints of responding tags, combined with the target motion information. The interval Kalman filter is adopted to integrate target position of one preceding time point and reference tags position to estimate the current position. Advantage of this algorithm is to use passive tags to reduce hardware costs, and on the other hand the introduction of filtering algorithm improves the positioning accuracy.
A compact, dual-band, dual-port, and linearly polarized tag antenna is proposed for indoor positioning systems. It operates in both UHF and UWB bands, covering 881–913 MHz for the lower band and 2.9–5.35 GHz for the upper band. U-shaped planar inverted-F antenna for the UHF band is designed to surround the dipole for the UWB band so that both bands can share the same radiating aperture and a compact structure $(100 \times 50 \times 9 {\text{ mm}}^3)$ is realized. In order to obtain a wideband and stable radiation performance in the upper band, a novel differential feeding structure is proposed to excite the ellipse-shaped dipole that exhibits good impulse performance. Meanwhile, the isolation between both ports is greatly improved to be better than 20 dB through loaded inductors. Measurements of a prototype show stable radiation patterns at both bands. With attractive features, this antenna can be potentially useful for indoor positioning systems.
In this paper, we propose a wireless positioning method based on Deep Learning. To deal with the variant and unpredictable wireless signals, the positioning is casted in a four-layer Deep Neural Network (DNN) structure pre-trained by Stacked Denoising Autoencoder (SDA) that is capable of learning reliable features from a large set of noisy samples and avoids hand-engineering. Also, to maintain the temporal coherence, a Hidden Markov Model (HMM)-based fine localizer is introduced to smooth the initial positioning estimate obtained by the DNN-based coarse localizer. The data required for the experiments is collected from the real world in different periods to meet the actual environment. Experimental results indicate that the proposed system leads to substantial improvement on localization accuracy in coping with the turbulent wireless signals.
Indoor positioning based on visible light communication (VLC) technology
has become a very popular research topic recently. This paper provides
an overview of different VLC based indoor positioning techniques and
their performance. Three schemes of location estimation together with
their mechanisms are introduced. We then present a detailed comparison
on their performances in terms of accuracy, space dimension and
complexity. We further discuss a couple of factors that would affect the
performance of each of these positioning systems, including multipath
reflections and synchronization. Finally, conclusions and future
prospects of research are addressed.
Building upon previous work that demonstrates the effectiveness of WiFi localization information per se, in this paper we contribute a mobile robot that autonomously navigates in indoor environments using WiFi sensory data. We model the world as a WiFi signature map with geometric constraints and introduce a continuous perceptual model of the environment generated from the discrete graph-based WiFi signal strength sampling. We contribute our WiFi localization algorithm which continuously uses the perceptual model to update the robot location in conjunction with its odometry data. We then briefly introduce a navigation approach that robustly uses the WiFi location estimates. We present the results of our exhaustive tests of the WiFi localization independently and in conjunction with the navigation of our custom-built mobile robot in extensive long autonomous runs.
Localizing people in confined and underground areas is one of the topics under research in mining labs and industries. The position of personnel and equipments in areas such as mines is of high importance because it improves industrial safety and security. Due to the special nature of underground environments, signals transmitted in a mine gallery/tunnel suffer from severe multipath effects caused by reflection, refraction, diffraction and collision with humid rough surfaces. In such cases and in cases where the signals are blocked due to the non-line of sight (NLOS) regions, traditional localization techniques based on the RSS, AOA and TOA/TDOA lead to high position estimation errors. One of the proposed solutions to such challenging situations is based on extracting channel impulse response (CIR) fingerprints with reference to one wireless receiver and using an artificial neural network as a matching algorithm to localize. In this article we study this approach in a multiple access network where multiple access points are present. The diversity of the collected fingerprints will allow us to create artificial neural networks that will work separately or cooperatively using the same localization technique. The results will show that using cooperative artificial intelligence in the presence of multiple signatures from different reference points improves significantly the accuracy, precision, scalability and the overall performance of the localization system.
The effects of variable stationarity in a financial time-series on artificial neural networks
- Matthew Butler
- Dimitar Kazakov
Matthew Butler and Dimitar Kazakov. The effects of variable stationarity
in a financial time-series on artificial neural networks. In IEEE
Symposium on Computational Intelligence for Financial Engineering
and Economics (CIFEr), pages 1-8, 2011.
Ofdma-tdm position scheme for vlc indoor positioning system
- L Shi
- X Zhang
- A Vladimirescu
L. Shi, X. Zhang, and A. Vladimirescu. Ofdma-tdm position scheme
for vlc indoor positioning system. In GDR SoC-SiP Paris France, 2018.
A vlcbased 3-d indoor positioning system using fingerprinting and k-nearest neighbor
- Ming Xu
- Weiwei Xia
- Ziyan Jia
- Yaping Zhu
- Lianfeng Shen
Ming Xu, Weiwei Xia, Ziyan Jia, Yaping Zhu, and Lianfeng Shen. A vlcbased 3-d indoor positioning system using fingerprinting and k-nearest
neighbor. In Vehicular Technology Conference (VTC Spring), 2017 IEEE
85th, pages 1-5, 2017.