Driving intention recognition and behaviour prediction based on a double-layer hidden Markov model

We propose a model structure with a double-layer hidden Markov model (HMM) to recognise driving intention and predict driving behaviour. The upper-layer multi-dimensional discrete HMM (MDHMM) in the double-layer HMM represents driving intention in a combined working case, constructed according to the driving behaviours in certain single working cases in the lower-layer multi-dimensional Gaussian HMM (MGHMM). The driving behaviours are recognised by manoeuvring the signals of the driver and vehicle state information, and the recognised results are sent to the upper-layer HMM to recognise driving intentions. Also, driving behaviours in the near future are predicted using the likelihood-maximum method. A real-time driving simulator test on the combined working cases showed that the double-layer HMM can recognise driving intention and predict driving behaviour accurately and efficiently. As a result, the model provides the basis for pre-warning and intervention of danger and improving comfort performance.     

考虑换道意图的LSTM-AdaBoost车辆轨迹预测模型

不合理的车辆的换道行为是导致交通事故发生的主要原因之一,提前预知换道车辆的轨迹并及时做出相应调整有助于减少事故的发生。针对换道车辆轨迹预测问题,采用将深度学习和集成学习相结合的轨迹预测方法,并考虑了换道意图的影响。建立连续隐马尔可夫模型对车辆进行换道意图检测,提前判别车辆的换道状态,并输入至相应的轨迹预测模型中;将LSTM（long short term memory）作为AdaBoost算法（adaptive boosting）的基预测器,建立LSTM-AdaBoost模型,在多个基预测器同时进行轨迹预测的基础上,通过训练调整各个基预测器的权重并将结果加权集成,提升预测模型的精度和稳定性;通过NSGIM（next generation simulation）数据集对模型进行训练和测试,结果显示意图预测模型在变道前一秒的准确率在90%以上,LSTM-AdaBoost集成轨迹预测模型与单一的LSTM模型相比精度和稳定性显著提升,且预测结果中异常数据更少,具有较好的稳定性;同时预测对比结果也表明增加意图预测模块有助于提升换道轨迹预测的精度。     

一种面向加密流量的网络应用识别方法

为实现网络流量的有效管控,提出一种基于安全套接层(SSL)协议交互字段与多输入最大化单输出隐马尔可夫模型(HMM)的加密应用并行识别方法.将来自客户端或者服务器的单向数据流SSL协议交互阶段的字段作为HMM模型的观测序列,并对所有待识别的加密应用建立HMM模型形成指纹库.在此基础上,利用前向算法计算未知观测序列被识别为HMM模型的概率,选取概率最大HMM模型所对应的加密应用作为识别结果.实验结果表明,与传统应用识别方法相比,该方法对典型加密应用具有更好的识别效果及鲁棒性.     

HMM based recognition of Chinese tones in continuous speech

This paper describes a method for recognizing Chinese tones in continuous speech. The first and second order differentials of the fundamental frequency logarithmically converted are used as feature parameters. A left-to-right hidden Markov modeling with five states, each of which is modeled by a single Gaussian distribution, expresses each of Chinese tones. Non-voiced portions are coded by random values normally distributed to uniformly deal with all the time frames in an utterance. Speaker dependent tone recognition was conducted for ten speakers. The average rate of 81.8% was obtained for these speakers.     

消除溢出问题的精确Baum-Welch算法

Baum-Welch算法是在语音领域中用于HMM(hidden Markov model)模型参数训练的最基本方法之一.但它在多样本训练时存在着严重的上、下溢问题,需要不断地人工介入来调整中间参数.该文提出了一种新的能消除上、下溢问题的Baum-Welch改进算法.该算法不但摆脱了人工介入,保证了计算的精度,而且不会带来过大的计算和存储要求.实验结果表明了这种新算法的有效性.     

主机系统安全态势实时评估方法的研究

为了解决传统安全评估方法不能详细刻画安全态势变化以及安全指标确定不够科学、全面的问题,提出了基于隐马尔可夫模型(HMM)的主机系统安全态势实时评估方法,从攻击的可信度、严重度、资产值和敏感度方面分析影响攻击威胁度等因素,利用HMM模型计算主机系统处于不同安全状态的概率.通过实例表明,该方法能对IDS的报警信息进行科学响应,动态获取主机系统安全态势变化曲线,为管理员了解和防范主机系统安全风险提供指导,具有一定的科学性和实用性.     

Speeding Up HMM Decoding and Training by Exploiting Sequence Repetitions

We present a method to speed up the dynamic program algorithms used for solving the HMM decoding and training problems for discrete time-independent HMMs. We discuss the application of our method to Viterbi’s decoding and training algorithms (IEEE Trans. Inform. Theory IT-13:260–269, 1967), as well as to the forward-backward and Baum-Welch (Inequalities 3:1–8, 1972) algorithms. Our approach is based on identifying repeated substrings in the observed input sequence. Initially, we show how to exploit repetitions of all sufficiently small substrings (this is similar to the Four Russians method). Then, we describe four algorithms based alternatively on run length encoding (RLE), Lempel-Ziv (LZ78) parsing, grammar-based compression (SLP), and byte pair encoding (BPE). Compared to Viterbi’s algorithm, we achieve speedups of Θ(log n) using the Four Russians method, using RLE, using LZ78, using SLP, and Ω(r) using BPE, where k is the number of hidden states, n is the length of the observed sequence and r is its compression ratio (under each compression scheme). Our experimental results demonstrate that our new algorithms are indeed faster in practice. We also discuss a parallel implementation of our algorithms. A preliminary version of this paper appeared in Proc. 18th Annual Symposium on Combinatorial Pattern Matching (CPM), pp. 4–15, 2007. Y. Lifshits’ research was supported by the Center for the Mathematics of Information and the Lee Center for Advanced Networking. S. Mozes’ work conducted while visiting MIT.     

Automatic Segmentation of Continuous Speech on Word Level Based on Supra-segmental Features

This article presents a cross-lingual study for Hungarian and Finnish about the segmentation of continuous speech on word and phrasal level by examination of supra-segmental parameters. A word level segmentationer has been developed which can indicate the word boundaries with acceptable precision for both languages. The ultimate aim is to increase the robustness of speech recognition on the language modelling level by the detection of word and phrase boundaries, and thus we can significantly decrease the searching space during the decoding process. Searching space reduction is highly important in the case of agglutinative languages. In Hungarian and in Finnish, if stress is present, this is always on the first syllable of the word stressed. Thus if stressed syllables can be detected, these must be at the beginning of the word. We have developed different algorithms based either on a rule-based or a data-driven approach. The rule-based algorithms and HMM-based methods are compared. The best results were obtained by data-driven algorithms using the time series of fundamental frequency and energy together. Syllable length was found to be much less effective, hence was discarded. By use of supra-segmental features, word boundaries can be marked with high accuracy, even if we are unable to find all of them. The method we evaluated is easily adaptable to other fixed-stress languages. To investigate this we adapted our data-driven method to the Finnish language and obtained similar results.     

基于步行加速度信息分割的人员识别

为提高基于智能手机内置加速度传感器的人员识别率,提出了一种基于信息分割的组合分类器识别方法。根据人员步行加速度变化特点提出了基于HMM（隐马尔可夫模型）的划分方法,将人员步行加速度划分成相对动态与稳态两个部分,分别从两个区域提取标准差、均值、能量等特征;根据不同步行速率选择这些特征和峰值点连线斜率组合成新的特征集合;最后,采用组合分类器的方法获得了更加理想的识别精度。实验结果表明,在人员慢步行走的姿态下的识别率达到了98.3%,快速步行达到了97.6%。较现有人员识别方法有较大的提高。     

基于字素分割的蒙古文手写识别研究

隐马尔科夫模型(HMM)对序列数据有很强的建模能力,在语音和手写识别中都得到了广泛的应用。利用HMM研究蒙古文手写识别,首先需要解决的问题是手写文字的序列化。从蒙古文的构词和书写特点看,蒙古文由多个字素从上到下串联构成。选择字素集合和词的字素分割是手写识别的基础,也是影响识别效果的关键因素。该文根据蒙古文音节和编码知识确定了蒙古文字母集合,共包括1 171个字母。通过相关性处理、HMM排序筛选等手段得到长字素集合,共包括378个字素。对长字素经过人工分解,获得了50个短字素。最后利用两层映射给出了词转字素序列的算法。为了验证长短字素在手写识别中的效果,我们在HTK(hidden Markov model toolkit)环境下利用小规模字库实现了手写识别系统,实验结果表明短字素比长字素有更好的性能。文中给出的字素集合和词转字素序列的算法为后续基于HMM的蒙古文手写识别研究奠定了基础。