RSS Fingerprints Based Distributed Semi-Supervised Locally Linear Embedding (DSSLLE) Location Estimation System for Indoor WLAN

An important requirement for many novel location based services, is to determine the locations of people, equipment, animals, etc. The accuracy and response time of estimation are critical issues in location estimation system. Most of the location estimation system suffers with the problem of scalability and unavailability of all the access points at all the location for large site. In this paper, we have proposed a distributed semi-supervised location estimation method, which divide the location estimation system into subsystems. Our method partition the input signal space and output location space into clusters on the basis of visibility of access points at various locations of the site area. Each cluster of input signal space together with output location subspace is used to learn the association between Received Signal Strength fingerprint and their respective location in a subsystem. Previous methods for location estimation in indoor wireless networks require a large amount of labeled data for learning the radio map. However, labeled instances are often difficult, expensive, or time consuming to obtain, as they require great efforts, meanwhile unlabeled data may be relatively easy to collect. So, the use of semi-supervised learning is more feasible. On each subsystem at first, we use Locally Linear Embedding to reduce the dimensions of data, and then we use semi-supervised learning algorithm to learn the radio map. The algorithm performs nonlinear mapping between the received signal strengths from nearby access points and the user’s location. It is shown that the proposed Distributed Semi-Supervised Locally Linear Embedding scheme has the advantage of robustness, scalability, useful in large site application and is easy in training and implementation. We have compared our results with Distributed Subtract on Negative Add on Positive (DSNAP) and benchmark method RADAR. Experimental results show that our method provide better results in terms of accuracy and response time in comparison to centralized systems, in which a single system is used for large site as well as with DSNAP and benchmark method RADAR.     

一种半监督稀疏保持近邻判别嵌入算法

保持近邻嵌入（NPE）算法对局部线性嵌入（LLE）算法进行了改进,克服了新来样本问题,但在处理分类问题上表现不足。本文提出了一种半监督稀疏保持近邻判别嵌入算法,该方法首先采用小波变换对数据进行预处理,然后执行等距离映射(Isomap)算法选择合适的低维嵌入维数,最后结合稀疏表示理论、NPE和线性判别分析（LDA）的思想,重构邻域图,并在建立目标函数时使得已标签信息中同类样本点之间相互靠近,异类样本点之间相互远离,未标签信息邻域信息得以保持,这样,既得到了高维映射函数,又提高了分类正确率。通过在人脸数据库上实验,并和其他半监督算法作比较,本文提出的算法在识别率上表现较好。     

LLE-based classification algorithm for MMW radar target recognition

In this paper, a new multiclass classification algorithm is proposed based on the idea of Locally Linear Embedding (LLE), to avoid the defect of traditional manifold learning algorithms, which can not deal with new sample points. The algorithm defines an error as a criterion by computing a sample’s reconstruc-tion weight using LLE. Furthermore, the existence and characteristics of low dimensional manifold in range-profile time-frequency information are explored using manifold learning algorithm, aiming at the problem of target recognition about high range resolution MilliMeter-Wave (MMW) radar. The new algo-rithm is applied to radar target recognition. The experiment results show the algorithm is efficient. Com-pared with other classification algorithms, our method improves the recognition precision and the result is not sensitive to input parameters.     

Opportunistic channel allocation decision making in cognitive radio communications

The global spread of wireless devices with mobile Internet access and the increasing demand of multimedia‐based applications are fueling the need for wireless broadband networks. IEEE 802.16 and 802.20 are standards for a broadband wireless access with promising cognitive radio features to support mobile Internet access. However, because of the fast changing radio environment and the demand for dynamic spectrum allocation mechanisms, these standards must continuously readjust different radio parameters. The cognitive radio makes decisions based on its built‐in inference engine, which also in time can adapt itself to different situations through the process of learning from experience. In this paper we present an automated opportunistic decision making and learning process for cognitive radio based on uncertainty reasoning algorithms. This novel approach is well suited in fast changing wireless environments with vague, incomplete, and heterogeneous information. Theory and simulations prove that decision making and learning of the cognitive radio based on the proposed approach cope with the changes in the radio environment. In this work we use fuzzy logic for the learning and decision making of the cognitive radio. Simulation also show that our approach provides accurate and precise decisions on allocating spectrum to mobile Internet users even in fast varying radio conditions. Copyright © 2012 John Wiley & Sons, Ltd.     

Simulations and experiments for optimal deployment of an RFID‐based location‐aware system

The proliferation of communication and mobile computing devices and local‐area wireless networks has cultivated a growing interest in location‐aware systems and services. An essential problem in location‐aware computing is the determination of physical locations. RFID technologies are gaining much attention, as they are attractive solutions to indoor localization in many healthcare applications. In this paper, we propose a new indoor localization methodology that aims to deploying RFID technologies in achieving accurate location‐aware undertakings with real‐time computation. The proposed algorithm introduces means to improve the accuracy of the received RF signals. Optimal settings for the parameters in terms of reader and reference tag properties were investigated through simulations and experiments. The experimental results indicate that our indoor localization methodology is promising in applications that require fast installation, low cost and high accuracy. Copyright © 2009 John Wiley & Sons, Ltd.     

基于正交迭代的增量LLE算法

 LLE(Locally Linear Embedding)算法是一种较好的流形学习算法,但它只能以批处理的方式进行.只要有新的样本加入,就必须重作该算法的全部内容,而原处理结果被全部丢弃.本文提出了一种基于正交迭代的增量LLE算法,能有效地利用前面的处理结果,实现增量处理.实验表明该算法是有效的.     

一种基于WTLS的轻型移动VPN方案

各种传统的远程访问VPN方案(包括IPSec-VPN和SSL-VPN)都只是为固网环境下外出企业员工的"游牧访问"而设计的,它不适合于未来的移动无线网络场景.本文针对移动无线场景中特有的无线终端计算能力和网络带宽限制等问题,提出了一种基于WTLS安全协议的轻型移动VPN方案.该移动VPN方案支持移动节点在不同无线接入网络之间的自由切换,允许外出企业员工在任何时间、任何地点、使用最佳的无线接入网络连接到企业网络并安全地访问企业内部资源.     

Histogram Based Particle Filtering with Online Adaptation for Indoor Tracking in WLANs

Indoor localization using signal strength in Wireless Local Area Networks is becoming increasingly prevalent in today??s pervasive computing applications. In this paper, we propose an indoor tracking algorithm under the Bayesian filtering and machine learning framework. The main idea is to apply a graph-based particle filter to track a person??s location on an indoor floor map, and to utilize the machine learning method to approximate the likelihood of an observation at various locations based on the calibration data. Histograms are used to approximate the RSS distributions at the survey points, and Nadaraya?CWatson kernel regression is adopted to recover the distributions at non-survey points only from the nearby locations. In addition, we also propose a simple algorithm to continuously update the radio map with the online measurements. A series of experiments are carried out in an office environment. Results show that the proposed Histogram Based Particle Filtering (HBPF)/HBPF with Online Adaptation achieves superior performance than other existing algorithms while retaining low computational complexity.     

An adaptive location estimator using tracking algorithms for indoor WLANs

This paper presents adaptive algorithms for estimating the location of a mobile terminal (MT) based on radio propagation modeling (RPM), Kalman filtering (KF), and radio-frequency identification (RFID) assisting for indoor wireless local area networks (WLANs). The location of the MT of the extended KF positioning algorithm is extracted from the constant-speed trajectory and the radio propagation model. The observation information of the KF tracker is extracted from the empirical and RPM positioning methods. Specifically, a sensor-assisted method employs an RFID system to adapt the sequential selection cluster algorithm. As compared with the empirical method, not only can the RPM algorithm reduce the number of training data points and perform on-line calibration in the signal space, but the RPM and KF algorithms can alleviate the problem of aliasing. In addition, the KF tracker with the RFID-assisted scheme can calibrate the location estimation and improve the corner effect. Experimental results demonstrate that the proposed location-tracking algorithm using KF with the RFID-assisted scheme can achieve a high degree of location accuracy (i.e., more than 90% of the estimated positions have error distances of less than 2.1 m).     

An RSS-based regression model for user equipment location in cellular networks using machine learning

Dissemination of wireless networks and mobile devices, such as smartphones, has motivated the appearance of several types of location-based services. Consequently, the interest in low-complexity cost-effective mobile positioning techniques against the traditional method based on global positioning system has emerged. An interesting alternative is to utilize radio frequency (RF) signals to estimate the location of mobile terminals, as in multilateration and RF fingerprinting techniques. In this context, the objective of this work is to propose a new radio strength signal-based user equipment location method using a machine learning regression-based model to find directly the geographical coordinates of the mobile user in cellular networks. Numerical results show that, in most cases, the proposed method can meet the location accuracy requirements established by the Federal Communications Commission for network-based localization methods.

     

面向高光谱图像分类的半监督Laplace鉴别嵌入

为有效提取出高光谱遥感图像数据的鉴别特征,该文阐述一种融合标记样本中鉴别信息和无标记样本中局部结构信息的半监督Laplace鉴别嵌入(SSLDE)算法。该算法利用标记样本的类别信息来保持样本集的可分性,并通过构建标记样本和无标记样本的Laplace矩阵来发现样本集中局部流形结构,实现半监督的流形鉴别。在KSC 和Urban数据集上的实验结果说明:该算法具有更高的分类精度,可以有效地提取出鉴别特征信息。在总体分类精度上,该算法比半监督最大边界准则(SSMMC)算法提升了6.3%~7.4%,比半监督流形保持嵌入(SSSMPE)算法提升了1.6%~4.4%。     

Dynamic process location management in 5G

5G, as the next generation of wireless networks, promises very high throughput and low latency to mobile users that calls for a substantial innovation in computing management platforms to attend QoS metrics. Thanks to emerging technologies such as software‐defined networking (SDN)/network function virtualization (NFV), many features are available in 5G design to detect and control two types of latency caused by computation and communication. In this paper, taking features of caching mechanisms and SDN into the account, a platform is proposed to minimize latency in 5G via caching big flows intelligently and avoiding bottlenecks that may cause by virtualized computing components. First, the pioneering idea of compromising between the cloud radio access network (CRAN) and mobile edge computing (MEC)/information‐centric network (ICN) via dynamic processing location management platform is investigated. Accordingly, a mathematical optimization problem to minimize the average latency is formulated. Due to the problem complexity, a heuristic algorithm is proposed to treat the latency via dynamic orchestration of processing functionalities. Through numerical results, the performance of the proposed algorithm is analyzed, and the simulations corroborate our analytical results and illustrate the superior performance of the proposed algorithm with acceptable optimality gap.     

Robust Indoor Positioning Provided by Real-Time RSSI Values in Unmodified WLAN Networks

The positioning methods based on received signal strength (RSS) measurements, link the RSS values to the position of the mobile station(MS) to be located. Their accuracy depends on the suitability of the propagation models used for the actual propagation conditions. In indoor wireless networks, these propagation conditions are very difficult to predict due to the unwieldy and dynamic nature of the RSS. In this paper, we present a novel method which dynamically estimates the propagation models that best fit the propagation environments, by using only RSS measurements obtained in real time. This method is based on maximizing compatibility of the MS to access points (AP) distance estimates. Once the propagation models are estimated in real time, it is possible to accurately determine the distance between the MS and each AP. By means of these distance estimates, the location of the MS can be obtained by trilateration. The method proposed coupled with simulations and measurements in a real indoor environment, demonstrates its feasibility and suitability, since it outperforms conventional RSS-based indoor location methods without using any radio map information nor a calibration stage.     

Radio Network Aggregation for 5G Mobile Terminals in Heterogeneous Wireless and Mobile Networks

This paper provides a novel design concept for advanced mobile multi interface terminals with radio network aggregation capability and enhanced quality of service (QoS) provisioning for multimedia services (voice, video and data) in heterogeneous wireless and mobile networks. A new module is established which provides the best QoS and lowest cost for any given multimedia service by using simultaneously all available wireless and mobile access networks for a given traffic flow. This novel adaptive QoS module with adaptive QoS routing algorithm is called advanced QoS routing algorithm (AQoSRA), which is defined independently from any existing and future radio access technology. The performance of our proposal is evaluated using simulations and analysis with multi-interface mobile stations with AQoSRA within, carrying multimedia traffic in heterogeneous mobile and wireless environment with coexistence of multiple Radio Access Technologies, such as 3G, 4G as well as future 5G radio access networks. The analysis of the proposed framework for radio networks aggregation in advanced mobile terminals has shown overall better performances regarding the achievable throughput and multimedia access probability in heterogeneous wireless and mobile environment.     

Learning Adaptive Temporal Radio Maps for Signal-Strength-Based Location Estimation

In wireless networks, a client's locations can be estimated using the signals received from various signal transmitters. Static fingerprint-based techniques are commonly used for location estimation, in which a radio map is built by calibrating signal-strength values in the offline phase. These values, compiled into deterministic or probabilistic models, are used for online localization. However, the radio map can be outdated when the signal-strength values change with time due to environmental dynamics, and repeated data calibration is infeasible or expensive. In this paper, we present a novel algorithm, known as LEMT (Location Estimation using Model Trees), to reconstruct a radio map using real-time signal- strength readings received at the reference points. This algorithm can take into account real-time signal-strength values at each time point and make use of the dependency between the estimated locations and reference points. We show that this technique can effectively accommodate the variations of signal strength over different time periods without the need to rebuild the radio maps repeatedly. We demonstrate the effectiveness of our proposed technique on realistic data sets collected from an 802.11b wireless network and a RFID-based network.     

主动学习半监督聚类入侵检测算法

针对聚类的入侵检测算法误报率高的问题,提出一种主动学习半监督聚类入侵检测算法.在半监督聚类过程中应用主动学习策略,主动查询网络中未标记数据与标记数据的约束关系,利用少量的标记数据生成正确的样本模型来指导大量的未标记数据聚类,对聚类后仍未能标记的数据采用改进的K-近邻法进一步确定未标记数据的类型,实现对新攻击类型的检测.实验结果表明了算法的可行性及有效性.     

面向RIS-mmWave系统的机器学习辅助高效波束训练及信道估计方法

面向B5G及6G无线通信系统的高速无线信息传输,本文研究了智能超表面辅助毫米波（RIS-mmWave）系统的高效能波束训练及信道估计方法。特别地,基于RIS-mmWave波束管理及有效信道获取的内生关联性,本文创新性地提出一种机器学习辅助的RIS-mmWave系统高效波束训练及信道估计方法。具体而言,在第一阶段,设计了一种新颖的半监督学习模型,实现位置信息辅助的在线快速波束训练,并且免估计地直接获取粗略角度域信息以驱动精细化信道估计;在第二阶段中,提出半监督学习辅助的压缩感知级联信道估计算法,利用半监督学习模型直接输出的粗略角度域信息驱动块正交匹配追踪算法进行信道估计。仿真结果表明,所提波束训练及信道估计方法在系统开销和信道估计误差等方面的性能均优于代表性参考方案。     

基于动态信道预约的自适应QoS切换算法

未来无线网络将为固定和移动用户提供多媒体通信和计算业务．为移动用户提供无线多媒体业务的一个最关键的挑战是保证端到端连接的业务质量．通过重复使用无线频谱的微蜂窝或微微蜂窝结构是一个有前途的改善移动多媒体网络容量的方式．但切换次数随着蜂窝大小的降低而增加．移动多媒体网络的一个至关重要的问题是需要可以满足各种QoS需要且有更高资源利用率的有效切换方式．该文提出了一种称为基于动态信道预约的自适应QoS切换算法,并与其它切换方式进行了性能比较．     

RFID Indoor positioning based on Semi-supervised Actor-Critic Co-training

For large-scale radio frequency identification ( RFID) indoor positioning system, the positioning scale isrelatively large, with less labeled data and more unlabeled data, and it is easily affected by multipath and whitenoise. An RFID positioning algorithm based on semi-supervised actor-critic co-training (SACC) was proposed tosolve this problem. In this research, the positioning is regarded as Markov decision-making process. Firstly, theactor-critic was combined with random actions and selects the unlabeled best received signal arrival intensity(RSSI) data by co-training of the semi-supervised. Secondly, the actor and the critic were updated by employingKronecker-factored approximation calculate (K-FAC) natural gradient. Finally, the target position was obtained byco-locating with labeled RSSI data and the selected unlabeled RSSI data. The proposed method reduced the cost ofindoor positioning significantly by decreasing the number of labeled data. Meanwhile, with the increase of thepositioning targets, the actor could quickly select unlabeled RSSI data and updates the location model. Experimentshows that, compared with other RFID indoor positioning algorithms, such as twin delayed deep deterministic policygradient (TD3), deep deterministic policy gradient (DDPG), and actor-critic using Kronecker-factored trustregion ( ACKTR), the proposed method decreased the average positioning error respectively by 50.226%,41.916%, and 25.004%. Meanwhile, the positioning stability was improved by 23.430%, 28.518%, and38.631%.