Demands for indoor positioning based services (IPS) in commercial and military fields have spurred many positioning systems and techniques. Complex electromagnetic environments (CEEs) may, however, degenerate the accuracy and robustness of some existing single systems and techniques. To overcome this drawback, fusion-based positioning of multiple systems and/or techniques have been proposed to revamp the positioning performance in CEEs. In this paper, we survey the fusion-based indoor positioning techniques and systems from seminal works to elicit the state of the art within our proposed unified fusion-based positioning framework, which consists of three fusion characteristics: source, algorithm, and weight spaces. Different from other surveys, this survey summarizes and analyzes the existing fusion-based positioning systems and techniques from three characteristics. Meanwhile, discussions in terms of lessons, challenges, and countermeasures are also presented. This survey is invaluable for researchers to acquire a clear concept of indoor fusion-based positioning systems and techniques and also to gain insights from this survey to further develop other advanced fusion-based positioning systems and techniques in the future.

/pdf/a-survey-on-fusion-based-indoor-positioning-143fw93zc2.pdf

A Survey on Fusion-Based Indoor Positioning

Review Article: Power line communication technologies for smart grid applications: A review of advances and challenges

Widespread proliferation of wireless coverage has enabled culmination of number of advanced location-based services (LBS). Continuous tracking of accurate physical location is the foundation of these services, which is a challenging task especially indoors. Multitude of techniques and algorithms have been proposed for indoor positioning systems (IPS’s). However, accuracy, reliability, scalability and, adaptability to the environment still remain as challenges for widespread deployment. Especially, unpredictable radio propagation characteristics in vastly varying indoor environments plus access technology limitations contribute to these challenges. Machine learning (ML) approaches have been widely attempted recently to overcome these challenges with reasonable success. In this paper, we aim to provide a comprehensive survey of ML enabled localization techniques using most common wireless technologies. First, we provide a brief background on indoor localization techniques. Afterwards, we discuss various ML techniques (supervised and unsupervised) that could alleviate different challenges in indoor localization including Non-line-of-sight (NLOS) issue, device heterogeneity and environmental variations with reasonable complexity. The trade-offs among multitude of issues are discussed using numerous published results. We also discuss how the ML algorithms can be effectively used for fusing different technologies and algorithms to achieve a comprehensive IPS. In essence, this survey will serve as a reference material to acquire a detailed knowledge on recent development of machine learning for accurate indoor positioning.

/pdf/a-survey-of-machine-learning-for-indoor-positioning-3uqx28fbz2.pdf

A Survey of Machine Learning for Indoor Positioning

Advanced technologies are constantly emerging in automobile industry, which not only provides drivers with a comfortable driving experience, but also enhances the safety of passengers. However, there are still some security issues need to be solved in automobiles, such as automobile driver fingerprinting. At present, identification technologies, such as fingerprint recognition and iris recognition, cannot monitor the driver's identity in real-time manner. Therefore, it is of great significance to design a real-time automobile driver fingerprinting scheme to ensure the safety of people's properties and even lives. Different from previous work concerning automobile driver fingerprinting, in this article, we conduct a comprehensive study on behavioral characteristics of drivers in two vehicles, namely Luxgen U5 SUV and Buick Regal. We exploit the actual data of the controller area network to construct a driver identity comparison library by extracting and processing the feature data. Then, we construct a combined model based on convolutional neural network and support vector domain description to achieve efficient automobile driver fingerprinting. Extensive experimental results show that the proposed driver fingerprinting scheme can dynamically match the driver's identity in real time without affecting the normal driving.

Automobile Driver Fingerprinting: A New Machine Learning Based Authentication Scheme

With the wide spread of the Internet of Things (IoT), wireless localization technology has provided various location-based applications and services. Radio frequency identification (RFID) has been widely used in objects’ identification and tracking. Combining with its excellent identification ability, RFID is also a promising technique for indoor localization. This paper provides the state-of-the-art of UHF RFID localization and gives an introduction of methods and applications. The major methods of UHF RFID localization have two types: 1) range-based and 2) range-free, reported in previous literature. The range-based methods obtain the distance or angle between the antenna and tag utilizing the received signal strength indicator (RSSI), time information or signal phase and estimate tag location further combining the scheme geometrical characteristics. The methods based on fingerprinting and non-fingerprinting are mainly discussed in the range-free domain. Finally, a comparative study of these surveyed works are presented and concluded with a future trend.

Review on UHF RFID Localization Methods

Ultra-high frequency radio frequency identification (UHF RFID) localization technique has been considered increasingly promising in indoor positioning systems. However, conventional localization algorithms are vulnerable in multipath and non-line of sight (NLOS) environments. To solve this problem, this paper presents an indoor localization method based on angle of arrival and phase difference of arrival (PDOA) using virtual stations for passive UHF RFID. We use the array antenna to distinguish multipath signals and choose the two strongest paths according to the received signal strength to perform localization. The angles of the two paths are obtained through the phase difference of the received signals at different array elements, and the distances of the two paths are estimated through PDOA measurement. After obtaining the angles and distances, we establish virtual stations to convert NLOS paths into LOS paths. The possible positions of the tag are calculated through virtual stations, angle, and distance information, which are derived from the two signal paths. Then, the weighted least squares combined with residual weighted algorithm are proposed to calculate real position of the tag. Simulation results demonstrate that our method achieves decimeter level accuracy and has higher precision than traditional algorithms.

An Indoor Localization Method Based on AOA and PDOA Using Virtual Stations in Multipath and NLOS Environments for Passive UHF RFID

This letter presents a geometrical localization approach that is able to locate a mobile station in non-line-of-sight (NLOS) and multipath conditions using time-of-arrival (TOA) and direction-of-arrival (DOA) estimates. The novelty of our work resides in converting the NLOS problem into a line-of-sight problem with virtual stations, even if the signal undergoes multiple-bound scattering, which has not been resolved in previous works. We also develop a two-step weighted least squares (TSWLS) positioning estimator using the hybrid TOA and DOA values. Simulation results demonstrate the effectiveness of the proposed method.

Joint TOA and DOA Localization in Indoor Environment Using Virtual Stations

The text presented in videos contains important information for content analysis, indexing, and retrieval of videos. The key technique for extracting this information is to find, verify, and recognize video text in various languages and fonts against complex backgrounds. In this paper, we propose a novel method that combines a corner response feature map and transferred deep convolutional neural networks for detecting and recognizing video text. First, we use a corner response feature map to detect candidate text regions with a high recall. Next, we partition the candidate text regions into candidate text lines by projection analysis using two alternative methods. We then construct classification networks transferred from VGG16, ResNet50, and InceptionV3 to eliminate false positives. Finally, we develop a novel fuzzy c-means clustering-based separation algorithm to obtain a clean text layer from complex backgrounds so that the text is correctly recognized by commercial optical character recognition software. The proposed method is robust and has good performance on video text detection and recognition, which was evaluated on three publicly available test data sets and on the high-resolution test data set we constructed.

A Novel Approach for Video Text Detection and Recognition Based on a Corner Response Feature Map and Transferred Deep Convolutional Neural Network

Clock synchronization is essential for the operation of upper layer applications in Wireless Sensor Networks. When the network hops needed for clock synchronization message transmission is large, synchronization error will accumulate and synchronization accuracy may be reduced significantly. Moreover, in the existing synchronization algorithms, large number of communication resources and node energy will be expended in sending and receiving time messages. To solve the problem, this paper proposes a Bayesian estimation-based time synchronization (BETS) algorithm which uses synchronization error compensation to reduce the amount of time message interaction in clock synchronization. The key idea of BETS is to calibrate the prior information of synchronization error with a small amount of field sampling time information, which will eliminate the impact of environment on clock synchronization accuracy. In addition, the gradient descent method is used to estimate the relative clock drift rate, which provides the reference for setting algorithm execution cycle and ensures clock synchronization during network operation time. In order to evaluate the theoretical lower bound of the performance of BETS, the Bayesian Cramer-Rao bound (BCRB) is derived. Both simulation and hardware experiments show that BETS algorithm makes full use of the prior information of synchronization error, hence fewer time messages are required in synchronization and the resource constraints of WSNs are satisfied.

/pdf/clock-synchronization-in-wireless-sensor-networks-based-on-3az13bbgz4.pdf

Clock Synchronization in Wireless Sensor Networks Based on Bayesian Estimation

Power-line network is not specifically designed for high frequency signal transmission. Some tests and documents verify that power-line channel takes on many adverse characteristics that are not conducive to high frequency signal transmission, and noise characteristics are important parameters to describe the nature of power-line communication channel interference. The paper studied noise classification of the power-line communication channel, and specially analyzed the colored background noise characteristic and its mathematical model. Based on artificial neural network, optimization model is studied for the colored background noise of power-line communication channel. The paper educed the neural network algorithm used for modeling colored background noise. Through simulation, amplitude-frequency response curve is derived for neural network filter. And also time domain waveform and power spectrum density of colored noise are achieved from the neural model. The results indicate that artificial neural network modeling method is effective for modeling the colored background noise of power-line communication channel. It is helpful to construct the basis for simulation actual power-line channel.

Jiexiao Yu

Papers

An Indoor Localization Method Based on AOA and PDOA Using Virtual Stations in Multipath and NLOS Environments for Passive UHF RFID

Joint TOA and DOA Localization in Indoor Environment Using Virtual Stations

A Novel Approach for Video Text Detection and Recognition Based on a Corner Response Feature Map and Transferred Deep Convolutional Neural Network

Clock Synchronization in Wireless Sensor Networks Based on Bayesian Estimation

Modeling the colored background noise of power line communication channel based on artificial neural network