一种基于Bloom-filter表项压缩的TCAM业务识别算法

在三态内容寻址存储器(Ternary Content Addressable Memory, TCAM)表项宽度和存储容量约束下,该文提出一种基于匹配表项压缩的BF-TCAM算法,采用Bloom-Filter(BF)对匹配关键字进行单字节编码压缩关键字长度,解决了匹配吞吐率低和存储空间不足问题。针对BF在表项压缩过程带来的冲突率上升问题,引入向量存储空间策略,利用向量存储空间实现多个哈希函数映射,相对于比特向量策略,有利于降低匹配冲突率。测试实验表明,相对于传统的TCAM匹配算法,BF-TCAM算法不但提高了匹配吞吐率和存储空间利用率,同时可有效降低BF压缩产生的冲突率。     

一种基于协同过滤与语义分析的个性化网络广告投放方法研究

针对个性化网络广告中网页与广告匹配的问题,通过将基于关键词扩展的语义分析技术引入到协同过滤系统中,提出一种基于协同过滤与语义分析结合的个性化网络广告投放方法(CFKE)。该方法首先提取网页与广告文本的关键词,并对关键词扩展同义词;然后,计算网页扩展词与广告扩展词的相似度,并与扩展词的权重进行拟合抽取,得到网页与广告最终的相似度,将三维模型降维成二维模型;最后,再利用协同过滤方法进行匹配。仿真表明,与其他算法相比,该算法不仅具有较高的准确度,同时具有较好的系统响应能力。     

可并行识别的分组动态帧时隙ALOHA标签防碰撞算法

该文针对现有动态帧时隙ALOHA标签防碰撞算法的系统吞吐率低、算法效率低等问题,提出一种可并行识别的分组动态帧时隙ALOHA(PIGDFSA)标签防碰撞算法。该文以实验为基础,探索了待识别标签数、标签分组数、帧长对系统吞吐率与标签碰撞率的影响,研究了提升系统吞吐率与降低标签碰撞率的策略与方法。结合射频识别(RFID)的多天线系统,引入FastICA技术,从而实现碰撞时隙重新定义,并以此为基础,利用未识别标签数目自适应确定分组数与帧长。仿真结果表明：PIGDFSA算法在标签数达到2000时,算法吞吐率仍能稳定在92%以上,与FSA-256, GDFSA, BSDBG等算法相比具有更高的算法吞吐率,更少的空隙时隙,更高的算法效率。     

Web文本内容过滤方法的研究

文章研究了Web文本内容过滤的方法，分析了向量空间模型、关键词匹配算法等关键技术．并详细讨论了Web网页中文本内容过滤方法的实现过程。重点分析了该方法中的修正值选取、关键词权重函数以及过虑策略等方面的不足，提出了一个改进的Web文本内容过滤方法，能够有效降低算法的复杂性，提高性能。     

高效双Hash线速浮动字符串匹配

提出了一种在FPGA上易于实现的高效双Hash浮动字符串匹配算法,其优点是消耗FPGA资源少,处理速度快,并且模式串可以方便地在线更新.     

分组交换网络调度算法概述

为了合理利用网络资源,提高网络吞吐率,降低通信时延,需要采取有效的调度算法实现输入端和输出端的匹配.基于VOQ的输入排队交换结构是当前分组交换网络最常用的结构.本文介绍了几种基于VOQ的调度算法:用于单级crossbar的PIM、iRRM和iSLIP算法,以及适用于三级Clos网络的RD和CDDR算法.对每种算法,介绍其基本原理和性能,以及与其他算法的区别.     

一种基于浮动车数据的快速地图匹配算法

地图匹配技术被广泛用于GPS导航、城市道路交通状态分析等领域。针对目前城市交通数据量大,地图匹配算法实时性差、匹配率不高的缺点,在现有最近点算法的基础上引入网格的思想对城市路网建立索引,并对GPS定位点到路段的最短距离算法进行了改进,大大提高了匹配效率,同时在匹配过程中考虑浮动车的方向角信息,提高了匹配精度。实验结果表明,算法能够满足工程应用中浮动车地图匹配的实时性和准确性。     

适用于OFDM-UWB系统的低复杂度同步器设计

提出的同步器包括无匹配滤波器的符号同步模块,基于改进Moose算法的载波频偏纠正模块以及基于符号自相关的包检测模块.在O.13μm CMOS工艺下,实现相同的数据吞吐率528Msample/s,面积和功耗仅为传统实现方法的24%和25%.     

海量数据过滤系统中匹配算法的研究

模式匹配算法是数据过滤系统的重要组成部分,其效率直接影响到海量数据过滤系统的性能.为了应对当前不断增加的网络数据量对网络安全造成的威胁,提出了一种新的模式匹配算法——改进的AC-BM算法,并将其应用到海量数据过滤系统中.改进后的算法明显减少了匹配时间,提高了海量数据过滤系统执行效率.     

改进的Wu-Manbe算法在网闸中的实现

通过字符串匹配算法来实现文本过滤,在深入分析了现有串匹配算法的基础上,根据网闸数据从外网过渡到内网的特点,对传统的字符串匹配算法Wu-Manber进行详细分析,设计并实现了一种适合中文字符集和网闸的模式匹配算法RWM,并对改进的算法进行了实验分析。实验表明,所设计的算法在运行时间和尝试次数方面优于其他算法,满足网闸对不良信息进行查询和过滤的要求,能够解决网闸的文本过滤问题。     

An online power allocation algorithm based on deep reinforcement learning in multibeam satellite systems

Dynamic power allocation (DPA) is the key technique to improve the system throughput by matching the offered capacity with that required among distributed beams in multibeam satellite systems. Existing power allocation studies tend to adopt the metaheuristic optimization algorithms such as the genetic algorithm. The achieved DPA cannot adapt to the dynamic environments due to the varying traffic demands and the channel conditions. To solve this problem, an online algorithm named deep reinforcement learning‐based dynamic power allocation (DRL‐DPA) algorithm is proposed in this paper. The key idea of the proposed DRL‐DPA lies in the online power allocation decision making other than the offline way of the traditional metaheuristic methods. Simulation results show that the proposed DRL‐DPA algorithm can improve the system performance in terms of system throughput and power consumption in multibeam satellite systems.     

中文分词歧义识别算法的优化

中文分词系统性能的好坏直接影响到后续的工作,而歧义字段的处理更是衡量一个分词系统好坏的重要标志。解决歧义问题前首先就要找到歧义字段,本文在之前的增字最大匹配算法基础上,提出了一种结合逐字扫描算法和逆向最大匹配算法的歧义字段识别方法。实验结果表明,这里提出的算法执行效率要比增字最大匹配算法效率高,速度更快。     

Maximum size matching is unstable for any packet switch

Input-queued packet switches use a matching algorithm to configure a nonblocking switch fabric (e.g., a crossbar). Ideally, the matching algorithm will guarantee 100% throughput for a broad class of traffic, so long as the switch is not oversubscribed. An intuitive choice is the maximum size matching (MSM) algorithm, which maximizes the instantaneous throughput. It was shown (McKeown et al. (1999)) that with MSM the throughput can be less than 100% when N /spl ges/ 3, even with Terms-Instability,benign Bernoulli i.i.d. arrivals. In this letter, we extend this result to N /spl ges/ 2, and hence show it to be true for switches of any size.     

Novel distributed algorithm for coalition formation in cognitive radio networks for throughput enhancement using matching theory

In this paper, a novel algorithm is proposed for increasing the throughput in cognitive radio networks by forming coalitions among cognitive radio users in AWGN and fading channel environment. Although there have been numerous studies exploring the benefits of coalition formation in cognitive radio networks from the game theory perspective, there are several limitations in their application. To overcome the limitations of game theory, concepts from matching theory are used. Specifically, the stable marriage problem is used to formulate the interactions among the cognitive radio users as a matching game for collaborative distributed spectrum sensing under target detection probability constraint. The utility function is defined as the average probability of false alarm per cognitive radio user. The advantage of stable marriage is that it always converges to a stable matching and is Pareto optimal when the preferences of cognitive radios are strict. In the proposed model, the stable matching problem is extended to propose a novel algorithm to form coalitions of varying sizes for improving the utility of CR (false alarm and throughput). The coalitions formed using the algorithm are stable and do not deviate from the final matching. Using simulations and mathematical analysis, it is shown that the proposed algorithm leads to stable coalitions and returns significant improvement in terms of reduced probability of false alarm and improved throughput per cognitive radio user as compared to the noncooperative scenario.     

基于函数拟合的SIFT误匹配点剔除算法

针对RANSAC算法在剔除SIFT误匹配点实验中存在耗时长、误匹配等问题,提出了基于函数拟合的SIFT误匹配点剔除算法。首先采用SIFT算法进行待匹配图像与匹配图像的匹配工作,对匹配后的待匹配图像关键点采用迭代最小二乘拟合法构建函数模型,然后与匹配图像特征关键点进行拟合,最后计算两者的误差,当误差大于给定阈值时,确认该点为误匹配点,对其进行剔除。实验结果表明,采用基于函数拟合剔除误匹配点在时间上比RANSAC算法平均节省了2 s,正确匹配率提高11.75%,并且较多地保留了正确匹配点。     

Scheduling algorithm for VOQ switches

A variety of matching schemes for VOQ switches that provide high throughput for uniform traffic have been proposed. The dual round robin matching (DRRM) scheme has performance similar to iSLIP and lower implementation complexity. DRRM with exhaustive service (EDRRM) algorithm was created as modification of DRRM algorithm with goal to improve performance of DRRM algorithm for bursty and non-uniform traffic conditions. Under extremely unbalanced arrival traffic, an exhaustive service policy may lead to unfairness and starvation. This paper proposes matching scheme for VOQ switches that provides high throughput almost the same as EDRRM scheme and avoid unfairness and starvation under unbalanced traffic.     

图像匹配算法的研究进展

图像匹配是计算机视觉和图像处理中的重要研究内容.分析了图像匹配中的难点问题及其关键技术,研究了组成匹配算法的四个要素,介绍了近来出现的新思路和新方法,对匹配算法进行了分类和性能比较,提出了实际应用中有待进一步研究的内容,如算法的集成、神经网络、遗传算法和基于高层语义的应用等.     

基于布鲁姆过滤器算法和三态内容寻址存储器的高效范围匹配方法

该文基于布鲁姆过滤器算法和三态内容寻址存储器(Ternary Content Addressable Memory, TCAM)技术提出一种高效范围匹配方法,解决了目前TCAM范围匹配方案存在的存储利用率低、功耗大的问题。设计基于最长共同前缀的分段匹配算法(Segmented Match on Longest Common Prefix, SMLCP)将范围匹配拆分为前缀匹配和特征区间比对两步,TCAM空间利用率达到100%。根据SMLCP算法设计了BF-TCAM模型,使用布鲁姆过滤器对关键字过滤,屏蔽无关项参与比较,大幅降低功耗。使用流水线缩短关键路径长度,使查找操作在一个时钟周期内完成。研究结果表明,所提方法实现了零范围扩张,工作功耗较传统TCAM降低50%以上。     

A dynamic-time-warp integrated circuit for a 1000-word speech recognition system

The design of a custom MOS-LSI chip capable of performing the pattern matching portion of a 1000-word speech recognition algorithm in real time is reported. The chip implements a dynamic-time-warp algorithm. The chip is part of a single-board speech recognition system that performs spectral analysis, dictionary storage and management, and speech recognition for both isolated and connected word applications of up to 1000 words. Speech recognition algorithms are normally refined to work well on general-purpose machines without the influence of future special-purpose hardware implementation. With general-purpose machines, chip implementation issues such as bit widths and parallelism cannot be utilized so they are ignored in favor of increasing algorithmic complexity by techniques such as pruning. If developed together, the chip architecture and algorithm can be refined to fully use parallelism and increasing throughput, while retaining efficient silicon area utilization. The resulting special-purpose architecture is sufficiently general that connected speech can be recognized without a speed penalty.     

一种压缩DFA的高效FPGA实现

目前,面向网络流实时处理的正则表达式匹配技术面临两方面的挑战:一方面,复杂或大规模规则集会导致DFA存储空间爆炸的问题;另一方面,传统计算机的串行DFA匹配技术很难满足对高速主干网的线速深度包检测。本文提出了一个基于改进游程编码的DFA压缩算法,并在FPGA上高效实现了该压缩DFA的匹配引擎。测试结果表明规则集的单个DFA的吞吐率均大于800Mbps,在FPGA块内存最大利用率情况下的理论最大吞吐率达到49.5Gbps。