Semi-supervised learning via manifold regularization

This paper proposes a novel graph-based transductive learning algorithm based on manifold regularization.First,the manifold regularization was introduced to probabilistic discriminant model for semi-supervised classification task.And then a variation of the expectation maximization(EM) algorithm was derived to solve the optimization problem,which leads to an iterative algorithm.Although our method is developed in probabilistic framework,there is no need to make assumption about the specific form of data distribution.Besides,the crucial updating formula has closed form.This method was evaluated for text categorization on two standard datasets,20 news group and Reuters-21578.Experiments show that our approach outperforms the state-of-the-art graph-based transductive learning methods.     

A federated semi-supervised learning approach for network traffic classification

The classification of network traffic, which involves classifying and identifying the type of network traffic, is the most fundamental step to network service improvement and modern network management. Classic machine learning and deep learning methods have widely adopted in the field of network traffic classification. However, there are two major challenges in practice. One is the user privacy concern in cross-domain traffic data sharing for the purpose of training a global classification model, and the other is the difficulty to obtain large amount of labeled data for training. In this paper, we propose a novel approach using federated semi-supervised learning for network traffic classification, in which the federated server and clients from different domains work together to train a global classification model. Among them, unlabeled data are used on the client side, and labeled data are used on the server side. The experimental results derived from a public dataset show that the accuracy of the proposed approach can reach 97.81%, and the accuracy gap between the federated learning approach and the centralized training method is minimal.     

基于WLAN和WSN的异构网络协同定位

针对大型建筑物复杂环境室内定位的特殊性,为了克服移动终端采用WLAN或无线传感器网络单独定位精度不高的局限性,实现移动终端精确定位导航,分析了各种无线网络室内定位系统的基本算法模型,详细介绍了多个典型无线室内定位系统的实现方法,并分析其优劣点,展现了近年来国内外对室内定位的研究成果.归纳了基于WLAN和WSN的异构网络协同定位算法研究中的关键问题,指出了如何根据终端位置环境同时搜索WLAN和无线传感器网络以及改进后的网络融合定位算法,为下一步更深入的研究打下良好的基础,在此基础上,对协同定位方法的研究前景进行了展望.     

利用现有无线局域网进行室内定位算法研究

目前,多种WiFI室内定位方案被提出,但是往往需要重新部署无线AP,造成成本和复杂度上升。本文充分利用现有无线局域网的拓扑结构进行室内定位研究,提出了一种自适应网络变化的WKNN指纹算法,该算法通过实时监控无线AP的匹配数,自动根据位置适应网络变化,定位精度明显提高。在此基础上,为了减少无线信号不稳定引起的定位误差,提出了一种新的数据修正方法,该方法根据移动平均速度动态预测标准,动态调整a参数将预测坐标与实测坐标加权,从而得到最终定位坐标。最后,算法在实际环境中验证表明,利用现有无线局域网的自适应网络算法和数据修正使定位获得了33.5%的误差改善。      

室内定位现状与发展趋势研究

This paper introduces the significance of indoor positioning and analyzes the related problems. The latest research on indoor positioning is introduced. Further, the positioning accuracy and the cost of typical local and wide area indoor positioning systems are compared. The results of the comparison show that Time &; Code Divi-sion-Orthogonal Frequency Division Multi-plexing (TC-OFDM) is a system that can achieve real-time meter-accu瑀acy of indoor positioning in a wide area. Finally, in this paper, we indicate that the seamless high-accuracy indoor positioning in a wide area is the de-velopment trend of indoor positioning. The seamless Location Based Services (LBS) architecture based on a heterogeneous network, key technologies in indoor positioning for decimeter-accuracy and seam-less outdoor and indoor Geographic Infor-mation System (GIS) are elaborated as the most important research fields of future indoor positioning.     

无线局域网WLAN在高校校园网中的应用

无线局域网WLAN作为高校校园网的扩展和补充,在组网、覆盖、密度、移动、扩展和管理等方面具有显著优势,应用需求广泛。合理规划、组建和应用校园无线网络,对于促进数字化校园建设、推动高等教育信息化起到重要作用     

无线局域网安全问题研究

为了提供相当于有线局域网的数据安全,IEEE802.11定义了有线等价保密(WEP)协议。然而,最近的研究发现WEP存在严重的缺陷。介绍了无线局域网存在的安全隐患,分析了WEP的结构以及WEP协议的缺陷以及可能遭受的攻击,并探讨了改进方案。     

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.     

基于优化RBF神经网络的无线室内定位

针对径向基函数（Radial Basis Function,RBF）神经网络算法在无线网络室内定位中拓扑结构和网络参数难以确定,其定位效果不理想的问题,提出了一种用核主成分分析的模糊C均值聚类算法（Fuzzy C-Means clustering algorithm based on Kernel Principal Component Analysis,KPCA-FCM）和模拟退火自适应遗传算法（Simulated Annealing adaptive Genetic Algorithm,SAGA）优化RBF神经网络的无线室内定位算法。首先利用KPCA对原始训练数据样本进行数据预处理,再通过KPCA-FCM算法计算出最优聚类数目和聚类中心点;其次将聚类数目和聚类中心点作为隐含层神经元个数和中心值,创建RBF神经网络,并将其网络参数映射到SAGA算法中;再次由SAGA算法进行网络参数寻优,把最优的解映射回RBF神经网络;最后利用样本数据对RBF神经网络进行训练和测试,完成建立RBF神经网络算法模型。实验表明,在相同的环境中,所提算法比传统RBF神经网络定位精度提高了48.41%。     

无线局域网技术浅谈

主要介绍了无线局域网的概念、特点．以及几种无线局域网的协议标准和安全技术。     

无线通信网络中流量分析技术综述

对无线网络流量的分析和准确预测是无线网络管理与安全领域的重要研究内容之一,在网络规划、网络监控、流量趋势分析、网络优化以及入侵检测和异常检测等方面发挥着重要作用。介绍了目前典型的无线网络流量分析的模型与常用流量分析方法,综述了传统无线通信网络(如无线局域网和物联网)中的流量分析技术,指出了流量分析技术应用于无线自组网系统的可能性与面临的几点挑战,以及无线自组网系统与流量分析技术结合的发展方向。     

无线局域网室外覆盖路径损耗计算分析及规划布局建议

介绍了无线局域网(WLAN)所用IEEE 802.11x标准的技术特点和频率特性,选择修正的COST231 HATA无线信号传播模型对信号路径损耗进行计算,以图表的形式描述了WLAN所在频段(2.4 G-Hz)的空间信道衰落特征.通过计算得出结论:随着传输距离和AP/STA天线高度差的增加,WLAN无线信道路径损耗将迅...     

Improving throughput through dynamically tuning contention window size in dense wireless network

With the boom of wireless devices, the number of wireless users under wireless local area networks (WLANs) has increased dramatically. However, the standard backoff mechanism in IEEE 802.11 adopts fixed initial contention window (CW) size without considering changes of network load, which leads to a high collision probability and low channel utilization in bursty arrivals. In this paper, a novel CW dynamic adjustment scheme is proposed to achieve high throughput performance in dense user environment. In the proposed scheme, the initial CW size is dynamically adjusted to optimum according to the measured packet collision probability. Simulation results show that the proposed scheme can significantly improve the throughput performance.     

一种宽带WLAN贴片天线

文中提出了一种单馈的宽带贴片天线应用于无线局域网络通信。该天线由方形贴片、电抗性阻抗表面以及电磁带隙结构组成。文中提出同时加载电抗性阻抗表面和电磁带隙结构能够实现小型化以及宽带化。电抗性阻抗表面作为接地平面能够降低天线的谐振频率。电磁带隙结构能够提高天线的阻抗带宽。测试结果表明所提出的WLAN贴片天线的相对带宽为22.3%(S₁₁=-10 dB),覆盖4.77～5.97 GHz,可以获得6.3～7.2 dBi增益。与现有宽带小型化天线相比,该天线在保证宽带小型化的前提下仍具有较高增益,且辐射性能具有较高的一致性,十分有利于其应用。该天线能够覆盖IEEE 802.11a标准所规定的5 GHz频段,能够实现无线局域网之间的高速数传。     

3GPP LTE/WLAN无线融合技术研究进展

总结了4种在无线侧实现长期演进(LTE)系统与无线局域网(WLAN)相互融合的技术方案.在分析传统的核心网融合方案不足之处的基础上,重点介绍了无线融合在3 GPP R12和R13阶段的研究进展和标准化情况,讨论了各方案对终端、演进型节点B(eNodeB)和WLAN的影响,综合对比了每种方案的特征、优缺点及应用场景,为运营商部署LTE/WLAN融合网络提供了思路.     

CL-TAP： An Efficient Certificateless Based Trusted Access Protocol for WLAN

Based on the certificateless public key cryptography and the trusted computing technologies~ a certificateless based trusted access protocol for WLAN （Wireless local area networks） is proposed. Such proto- col realizes the mutual authentication and unicast session key agreement between STA and AP within 3 protocol rounds. In particular, the platform authentication and in- tegrity verification are achieved during the authentication procedure. The security properties of the new protocol are examined using the Extended Canetti-Krawczyk secu- rity model. The analytic comparisons show that the new protocol is very ei~icient in both computing and communi- cations.     

2.4 GHz WLAN InGaP/GaAs Power Amplifier with Temperature Compensation Technique

This letter presents a high performance 2.4 GHz two‐stage power amplifier (PA) operating in the temperature range from ?30…C to +85^oC for IEEE 802.11g, wireless local area network application. It is implemented in InGaP/GaAs hetero‐junction bipolar transistor technology and has a bias circuit employing a temperature compensation technique for error vector magnitude (EVM) performance. The technique uses a resistor made with a base layer of HBT. The design improves EVM performance in cold temperatures by increasing current. The implemented PA has a dynamic EVM of less than 4%, a gain of over 26 dB, and a current less than 130 mA below the output power of 19 dBm across the temperature range from ?30^oC to +85^oC.     

High performing multimedia transmission approach based on QoS support and admission control over IEEE 802.11e networks

Hybrid coordination function controlled channel access (HCCA) is a medium to enhance quality of service (QoS) via the IEEE 802.11e standard. The main limitation of HCAA is that it is only efficient for constant bit rate (CBR) applications. This is due to the nature of its scheduler that allocates transmission opportunities (TXOPs) based on traffic stream (TS) specifications (TSPECs) that are determined during the traffic setup time. Variable bit rate (VBR) traffics used in HCCA have nondeterministic profile, making it not optimally and efficiently supported by HCCA. The result of this inefficiency is a deterioration of the transmission performance of multimedia data as well as a drop in the number of served QoS video traffics. We propose a novel approach to deal with this issue, which is the feedback‐based admission control unit (FACU). FACU works by optimizing the usage of extra bandwidth to ensure optimal transmission performance of multimedia data. FACU achieves this by exploiting piggybacked information concerning sequential video frames in order to accurately assign the TXOP. The proposed approach is evaluated by utilizing various video sequences. It is demonstrated that FACU maximizes the overall number of video streams and optimizes the overall usage of the network without having any adverse effects on the QoS constraints determined.