A new method for improving Wi-Fi-based indoor positioning accuracy

Wi-Fi- and smartphone-based positioning technologies are playing a more and more important role in location-based service industries due to the rapid development of the smartphone market. However, the low positioning accuracy of these technologies is still an issue for indoor positioning. To address this problem, a new method for improving the indoor positioning accuracy was developed. The new method initially used the nearest neighbour (NN) algorithm of the fingerprinting method to identify the initial position estimate of the smartphone user. Then two distance correction values in two roughly perpendicular directions were calculated by the path loss model based on the two signal strength indicator values observed. The systematic error from the path loss model were eliminated by differencing two model-derived distances from the same access point. The new method was tested and the results compared and assessed against that of the commercial Ekahau RTLS system and the NN algorithm. The preliminary results showed that the positioning accuracy has been improved consistently after the new method was applied and the root mean square accuracy improved to 3.3 m from 3.8 m compared with the NN algorithm.     

一种基于位置指纹的室内WLAN定位方法

针对室内信号时变性导致定位不准的问题,提出了一种改进的3阶段位置指纹定位法。采样阶段,将采集信号的坐标、方位、接收信号强度的高斯分布及其对应的无线接入点等信息存储在数据库中生成位置指纹;在校正阶段中,利用参考点间信号强度的关联性信息,使用局部加权线性回归法,计算出一些虚拟点的信号强度;最后是线上实时定位阶段。通过与传统的加权K最邻近算法、直方图和联合聚类等3种定位方法相比较,该算法在同样的场景下可以取得更好的定位精度。     

Heuristics-based indoor positioning systems: a systematic literature review

Context: Many heuristics-based indoor positioning approaches have been developed to enhance positioning estimation. However, there is no comprehensive survey of these heuristics information and methods. Objective: The main objective of this study is to provide a holistic view and an in-depth analysis of what heuristics information and methods have been used, their general achievements and limitations. This study aims to provide a comprehensive summary to facilitate further research on indoor positioning heuristics. Method: We conducted a systematic literature review (SLR) on indoor positioning heuristics. Results: Ninety-three (93) primary studies were selected. We found two general types of heuristics information and four primary heuristics methods, which we summarised in this paper. We also found that many of these positioning heuristics are tested in experimental settings only. Some heuristics claim practical applications but are not tested for the challenging and typical indoor environments. Conclusion: Most existing heuristics information and methods rely on the assumptions that may not be true in real life environment, hence limiting the usefulness of the positioning outcomes. Based on the analysis of this SLR, we propose two research directions to enhance positioning estimation.     

Novel fingerprinting mechanisms for indoor positioning

As wireless communications and microelectronic technology rapidly develop, diverse applications and services based on smart handheld devices have drawn the attention of researchers. The popularity of Indoor Location Based services and applications has also gradually increased. Therefore, how to improve indoor positioning accuracy becomes a very important issue. Although indoor positioning has been performed using various techniques in recent years, the computational complexity of ensuring positioning accuracy and positioning is an unsolved problem. Current indoor positioning systems typically use only the receiver or the transmitter to obtain the reference point data, and only the K‐Nearest Neighbors (KNN) or Trilateration algorithm is used to perform positioning. Therefore, positioning accuracy is limited by the use of reference point data from a single source and by the positioning algorithm used. The Novel Fingerprinting Mechanisms (NFM) indoor positioning system proposed in this study, however, uses both the receiver and transmitter to obtain positioning data and employs six positioning mechanisms to improve the current positioning accuracy. The experimental results show that the average error distance is 1.18 m in the NFM indoor positioning system. That is the system outperforms both KNN and Trilateration systems, which have average error distances of 1.35 m and 2.23 m, respectively. This study proves that the positioning accuracy is actually improved. Copyright © 2015 John Wiley & Sons, Ltd.     

Building information systems based on precise indoor positioning

During the last 10 years, many modern IT-based applications have developed inside buildings. Many of those applications would benefit by the ability to locate people and/or objects inside the building (indoor positioning). However, most of today's indoor positioning systems are not able to deliver precise position information (<10?cm) along with quality parameters. Ultra wide band (UWB) is a new radio-based technology that allows the determination of distances in indoor environments with a very high spatial resolution even through building materials. At the Institute of Geodesy of TU Darmstadt, a high-resolution UWB positioning system (UWB-ILPS; ILPS, indoor local positioning systems) based on trilateration principle has been developed to estimate the position of a mobile station precisely. To benefit from knowing the position and orientation, it is necessary to select and merge data linked to the user's location for indoor location services. By this means, the visitor to a public building may benefit from the system as his position is shown on a digital floor plan generated dynamically or by retrieving location-based information inside the building. Mixed reality systems also offer advantages for a mobile building information system. For this purpose, a webcam was replaced by the digital camera in the UWB-ILPS prototype. Knowing the camera's location in space and its view direction, one is able to merge the real world taken by the webcam with the virtual world represented by a 3D CAD model of the building.     

基于改进粒子滤波的RFID室内目标定位算法

针对于LANDMARC算法的RFID室内定位精度受传输路径影响严重,直接采用粒子滤波自适应性差的问题,提出一种基于改进粒子滤波的RFID室内定位算法.该算法首先利用极限学习机(ELM)拟合阅读器接收信号强度与标签距离之间的非线性关系,构建信号传输模型,筛选邻近标签集;然后采用自适应学习因子优化粒子滤波过程,提高粒子全局...     

一种改进的无线局域网位置指纹定位法

精确、实时的室内定位技术是提供基于位置服务的关键技术之一。针对经典的基于无线局域网指纹定位法由于室内环境复杂多变、无线信号波动而不能实现精确定位的问题,提出了一种改进的指纹定位算法。该改进算法通过优化特征接入点的选取和指纹距离的计算,以及对最近邻的类聚处理,实现了对指纹匹配精确度和位置估计准确性的提高。实验表明,所提出的改进算法相比于经典的位置指纹法具有更高的定位精确度和鲁棒性。     

基于仿射传播聚类的概率分布室内定位算法

随着定位技术的快速发展,基于无线局域网的室内定位成为新的研究热点。本文提出了一种基于近邻传播聚类的概率分布无线局域网(WLAN)室内定位算法。与传统室内定位算法相比,该算法首先引入近邻传播聚类缩小参考点搜索空间,然后利用概率分布定位算法进行精确定位。仿射传播聚类可以有效减少概率分布定位算法的计算量,应用于系统后将有效降低系统复杂度。实验结果表明,本文所提算法具有更好的定位精度,可实现对WLAN室内定位目标的快速、可靠定位。     

基于WiFi的分级室内定位

在经典的K最近邻(K-Nearest Neighbors,KNN)的WiFi定位方法中,其算法复杂度随着定位区域和定位区域内的WiFi接入点(Access Point,AP)的增加而增加,无法满足实时定位的要求.为此,提出一种分级WiFi定位算法.算法分为粗定位和精定位阶段,首先通过AP的可见性利用汉明距离寻找可能的子区域,再用KNN算法在子区域内(利用信号强度欧氏距离)进行精定位.经过实测数据验证,平均单次定位时间在KNN算法下下降了约95％,在最大后验算法下下降了约96％,表明所提分级定位框架具有延迟低的优点.     

一种基于无源射频识别标签的消防员室内定位系统

消防员在地下建筑、无窗建筑、大型建筑物内,执行火情控制与人员搜救时,不可避免会遇到浓烟、黑暗、高温、陌生等情况,因此就需要精确的室内定位系统支持,已有的室内定位技术无法满足定位精度和长期部署的需求.本文提出了一种基于无源射频识别（RFID）标签的消防员室内定位系统,通过在消防员头盔内安装可变功率的RFID读写器,并将建筑物内读取的已经过精确标定的RFID标签信息回传到远程服务器进行计算处理,可实现建筑物外指挥员对室内消防员的实时精准定位和指挥功能.     

用于WLAN室内定位的PCA聚类算法

在WLAN室内定位系统中,针对接收信号强度(RSS)的时变特征降低室内定位精度的问题,提出一种基于主成分分析(PCA)白化RSS的聚类算法,该算法首先对信号强度进行PCA白化处理,去除RSS信息的相关性,提高聚类中心的可靠性和合理性,然后通过K-means聚类方式对RSS信息进行聚类,能够有效地提高聚类精度,以此来提高定位精度.实验结果表明,该算法相比于没有经过PCA的传统聚类算法,能够使定位误差在2m内的概率提高44.8％,性能更优良.     

THIP: A trajectory history-based indoor positioning algorithm using stress-free floor plan for patient monitoring

The Internet of Things (IoT) is a novel paradigm that consists of a wide network of machines and intelligent devices with the capability of communication and interaction with each other. One of the significant issues for the IoT is its healthcare applications. The positioning systems based on their environment can be classified into two main categories: Indoor and outdoor. Recently, IoT indoor positioning attracts too much attention among researchers for patient monitoring. Hence, in this paper, a stress-free floor plan indoor positioning algorithm for patient monitoring is proposed, called THIP. The history of the patient's movement is stored in a trajectory history, and this information is employed to estimate the patient's more accurate position. The proposed THIP algorithm is simulated in MATLAB software. Several experiments are conducted to evaluate the performance of the proposed algorithm. Simulation results show that the proposed THIP algorithm raises patient positioning accuracy and declines the distance error cumulative compared to LiFS by about 4.68% and 60.6 m, respectively. Moreover, it can identify the floor level of the moving user.     

5G超密集网络下的室内压缩重构指纹定位算法

为减少室内定位复杂度并进一步提高定位精度,提出了一种5G超密集网络下的室内压缩重构指纹定位算法.该算法分为离线建库阶段和在线匹配阶段两个阶段.离线建库阶段采用了矩阵填充理论进行指纹库的构建,只需采取少量的指纹点构建具有低秩特性的局部指纹库,并通过非精确增广拉格朗日乘子法(Inexact Augmented Lagrangian Multiplier Method,IALM)算法进行矩阵填充,从而恢复完整的指纹库.在线匹配阶段采用卡方距离代替传统的欧式距离来计算待定位点与参考指纹点的相似度,并用加权K近邻算法估算出待定位点坐标.经过实验仿真分析,所提算法以1.13％的误差节约了40％的工作量,在信噪比为10 dB时定位误差最小为0.2008 m,与传统K近邻指纹匹配算法相比具有更好的定位精度.     

Locus: robust and calibration-free indoor localization,tracking and navigation for multi-story buildings

A fundamental goal of indoor localisation technology is to achieve the milestone of combining minimal cost with accuracy sufficient enough for general consumer applications. To achieve this, current indoor positioning systems need either extensive calibration or expensive hardware. Moreover, very few systems built so far have addressed floor determination in multi-story buildings. In this paper, we explain a Wi-fi-based indoor localisation, tracking and navigation system for multi-story buildings called Locus. Locus determines a device’s floor as well as location on that floor using existing knowledge of infrastructure, and without requiring any calibration or proprietary hardware. It is an inexpensive solution with minimum set-up and maintenance expenses, is scalable, readily deployable and robust to environmental changes. Experimental results in three different buildings spanning multiple floors show that it can determine the floor with 95.33% accuracy and the location on the floor with an error of 6.49 m on an average in real-life practical environments. We also demonstrate its utility via two location-based applications for indoor navigation and tracking in emergency scenarios.     

基于参数拟合的室内多用户定位算法

为了提高室内环境下对目标的定位精度,提出一种室内单站精确定位技术. 该技术利用室内电波传播多径效应构成的复杂信道信息,基于机器学习,构建卷积神经网络架构,通过卷积提取不同位置目标到达接收传感器的多径时延特征信息;然后通过多层全连接层深度神经网络的模型训练,将基于复杂信道的定位问题转化为回归模型的问题,建立信道指纹与位置之间的非线性关系来完成被动定位. 训练和仿真结果表明,在室内复杂电波传播环境下,基于神经网络的室内单站精确定位技术能够实现单接收站情况下对目标的精确定位. 本文主要对3×3网格大小的金属散射体进行定位,接收站位于室内时,平均定位误差为0.621个网格（12.42 cm）;接收站位于室外时,能够分别实现信噪比20 dB、30 dB、40 dB情况下44.09 cm、21.42 cm、20.96 cm的平均定位误差. 本文方法为室内复杂环境下的目标定位提供了一种新的定位方法.     

Using Deep learning for image watermarking attack

Digital image watermarking has justified its suitability for copyright protection and copy control of digital images. In the past years, various watermarking schemes were proposed to enhance the fidelity and the robustness of watermarked images against different types of attacks such as additive noise, filtering, and geometric attacks. It is highly important to guarantee a sufficient level of robustness of watermarked images against such type of attacks. Recently, Deep learning and neural networks achieved noticeable development and improvement, especially in image processing, segmentation, and classification. Therefore, in this paper, we studied the effect of a Fully Convolutional Neural Network (FCNN), as a denoising attack, on watermarked images. This deep architecture improves the training process and denoising performance, through which the encoder–decoder remove the noise while preserving the detailed structure of the image. FCNNDA outperforms the other types of attacks because it destroys the watermarks while preserving a good quality of the attacked images. Spread Transform Dither Modulation (STDM) and Spread Spectrum (SS) are used as watermarking schemes to embed the watermarks in the images using several scenarios. This evaluation shows that such type of denoising attack preserves the image quality while breaking the robustness of all evaluated watermarked schemes. It could also be considered a deleterious attack.     

Infrastructure-free indoor navigation: a case study

In this article, we describe a low-cost indoor navigation system, based on the capabilities of modern smartphones commonly equipped with accelerometer, gyroscope, camera and Internet connection. The main claim of this paper is that, relaxing the requirement of best accuracy, with an intelligent use of inertial sensors, digital maps, and ambient tagging, it is still possible to get good results. Our mobile application helps the user in retrieving directions and finding places in large indoor environments where the global positioning system (GPS) is not available, such as airports, hospitals, museums and so on. The goal is to get a system able to work without the use of any physical ad hoc infrastructure and without relying on any wearable device. We name our infrastructure-free system Roodin, and its features are as follows: user-friendly interface, quick install and calibration tool, point-of-interest search and guidance. All the features presented in this paper are designed and implemented, and the application has been evaluated with real users. A summary of user evaluation is reported in the paper.     

A decision tree‐based NLOS detection method for the UWB indoor location tracking accuracy improvement

Among existing wireless technologies, ultra‐wideband (UWB) is the most promising solution for indoor location tracking. UWB has a great multipath fading immunity; however, great multipath resolvability alone does not eliminate the effect of non‐line‐of‐sight (NLOS) and multipath propagation. NLOS and multipath propagation in indoor environments can easily produce meters of UWB ranging error. This condition gives an enormous impact on the accuracy of indoor location tracking data. To address this problem, we propose an NLOS detection method using recursive decision tree learning. Using the UWB channel quality indicators information, we develop our model with the Gini index and altered priors splitting criteria. We then validate the constructed model using the 10‐fold cross‐validation method. Our experiment shows that the constructed model has correctly detected 90% of both line‐of‐sight (LOS) and NLOS cases on the seven different indoor environments. The result of this work can be used for the UWB indoor location tracking accuracy improvement.     

Toward intelligent wireless communications: Deep learning - based physical layer technologies

Advanced technologies are required in future mobile wireless networks to support services with highly diverse requirements in terms of high data rate and reliability, low latency, and massive access. Deep Learning (DL), one of the most exciting developments in machine learning and big data, has recently shown great potential in the study of wireless communications. In this article, we provide a literature review on the applications of DL in the physical layer. First, we analyze the limitations of existing signal processing techniques in terms of model accuracy, global optimality, and computational scalability. Next, we provide a brief review of classical DL frameworks. Subsequently, we discuss recent DL-based physical layer technologies, including both DL-based signal processing modules and end-to-end systems. Deep neural networks are used to replace a single or several conventional functional modules, whereas the objective of the latter is to replace the entire transceiver structure. Lastly, we discuss the open issues and research directions of the DL-based physical layer in terms of model complexity, data quality, data representation, and algorithm reliability.     

Deep learning for the internet of things: Potential benefits and use-cases

The massive number of sensors deployed in the Internet of Things (IoT) produce gigantic amounts of data for facilitating a wide range of applications. Deep Learning (DL) would undoubtedly play a role in generating valuable inferences from this massive volume of data and hence will assist in creating smarter IoT. In this regard, exploring the potential of DL for IoT data analytics becomes highly crucial. This paper begins with a concise discussion on the Deep Neural Network (DNN) and its different architectures. The potential benefits that DL will bring to the IoT are also discussed. Then, a detailed review of DL-driven IoT use-cases is presented. Moreover, this paper formulates a DL-based model for Human Activity Recognition (HAR). It carries out a performance comparison of the proposed model with other machine learning techniques to delineate the superiority of the DL model over other techniques. Apart from enlightening the potential of DL in IoT applications, this paper will serve as an impetus to encourage advanced research in the realm of DL-driven IoT applications.