基于词组的语音识别模型研究

本文在简单介绍三种词组语音识别模型后,提出了采用离散隐马尔柯夫模型（DHMM）来构建语音识别系统,并在此基础上引入矢量量化（VQ）模块来保证识别率和识别速度,具有良好的实用性     

基于语义的p2p路由算法研究综述

路由算法在P2P网路中占有重要的地位,资源的定位、查找均依赖于高效的路由算法。传统的P2P网络采用分布式哈希表来进行路由,是与资源的自然语义内容无关的算法,或者说分布式哈希表破坏了自然语言的语义内容。最近10年以来,语义路由算法在P2P网络中逐渐兴起。随着语义网的提出,本体成为自然语言研究方面的热点。语义覆盖网正是基于本体的知识体系构建的。而随着社交网路的兴起,又提出了语义小世界的概念。LSI、LSH、VSM以及各中聚类算法均在P2P网络的语义路由中得到了广泛的应用。     

利用SVM与灰度共生矩阵从QuickBird影像中提取枇杷信息

以福建省莆田市东圳水库库区为例,采用QuickBird卫星影像,利用主成分分析方法对灰度共生矩阵方法提取的地物纹理特征进行筛选,选择最佳的影像纹理特征,组成新的波段组合,并应用支持向量机方法(Support Vector Machine,SVM)进行枇杷树的提取分类,最后与只依靠光谱信息来分类的SVM法分类结果进行比较,其分类总精度由原来的71.33%提高到了86.67%,Kappa系数也由原来的0.6410提高到了0.8293,分类精度明显提高,表明光谱信息加入纹理特征信息能辅助并提升高分辨率遥感枇杷树信息提取的精度。     

ISG电机在冷起动中的策略仿真

ISG电机的控制系统决定着发动机冷起动性能,是弱混合动力系统中关键部件。它必须在很短的时间内拖动发动机至点火转速,并且要求转速过渡平稳,脉动冲击小。基于永磁同步电机(PMSM)数学模型选定矢量调速策略,采用脉宽调制器(SVPWM),因具有谐波少、响应快的优势,可作为电流调制方法。采用建立S imu link上的发动机阻力矩模型制定发动机起动策略,对冷起动过程进行仿真。仿真结果表明控制策略能够满足发动机快速起动的要求,并且升速过程平稳,受阻力矩变化影响较小,具有较好的抗负载扰动性能。     

基于支持向量机的乐音识别

乐音识别的研究早在20世纪60年代就开始了,但是直到最近,识别系统的性能仍不令人满意。本文通过研究乐音的声音和物理特性,提出了利用支持向量机进行乐音识别的新思路,给出了基本的算法框架,并对钢琴的所有单音进行了识别,实验证明该算法提高了识别的快速性和准确性。     

在线旅游业务中Web页面主体块提取方法研究

Web信息提取是在线旅游业务的重要技术。页面的主体语义块集中了最主要的信息量,它的正确提取是Web信息提取的基础。本文在对现有页面分割方案总结的基础上,提出了结合机器学习方法的Web页面主体语义块节点识别算法,并基于启发式规则对正结果集进行后续的校验,以定位最佳的主体语义块节点。通过实验,本文提出的方案达到了比较理想的准确率。     

A hardware design of a massive-parallel, modular NN-based vector quantizer for real-time video coding

This report describes the design of a modular, massive-parallel, neural-network (NN)-based vector quantizer for real-time video coding. The NN is a self-organizing map (SOM) that works only in the training phase for codebook generation, only at the recall phase for real-time image coding, or in both phases for adaptive applications. The neural net can be learned using batch or adaptive training and is controlled by an inside circuit, finite-state machine-based hard controller. The SOM is described in VHDL and implemented on electrically (FPGA) and mask (standard-cell) programmable devices.     

A hybrid aggregation and compression technique for road network databases

Vector data and in particular road networks are being queried, hosted and processed in many application domains such as in mobile computing. Many client systems such as PDAs would prefer to receive the query results in unrasterized format without introducing an overhead on overall system performance and result size. While several general vector data compression schemes have been studied by different communities, we propose a novel approach in vector data compression which is easily integrated within a geospatial query processing system. It uses line aggregation to reduce the number of relevant tuples and Huffman compression to achieve a multi-resolution compressed representation of a road network database. Our experiments performed on an end-to-end prototype verify that our approach exhibits fast query processing on both client and server sides as well as high compression ratio.

Following non-stationary distributions by controlling the vector quantization accuracy of a growing neural gas network

In this paper, an original method extended from growing neural gas (GNG-T) [B. Fritzke, A growing neural gas network learns topologies, in: G. Tesauro, D.S. Touretzky, T.K. Leen (Eds.), Advances in Neural Information Processing Systems 7, MIT Press, Cambridge, MA, 1995, pp. 625–632] is presented. The method performs continuously vector quantization over a distribution that changes over time. It deals with both sudden changes and continuous ones, and is thus suited for the video tracking framework, where continuous tracking is required as well as fast adaptation to incoming and outgoing people. The central mechanism relies on the management of the quantization resolution, that copes with stopping condition problems of usual GNG inspired methods. Application to video tracking is presented.