基于混合微粒群算法的说话人识别

为了解决传统高斯混合模型(GMM)对初值敏感,在实际训练中极易得到局部最优参数的问题,提出了一种采用微粒群算法优化GMM参数的新方法。该方法将最大似然估计融入到微粒群算法迭代过程中,形成了新的混合算法。它利用微粒群算法的全局优化性及最大似然估计的局部寻优性求解高斯混合模型的参数,以提高参数精度。说话人辨认实验表明,与传统的方法相比,新方法可以得到更优的模型参数,使得系统的识别率进一步提高。     

结合区域颜色一致性和图割的复杂场景文本分割方法

针对复杂场景文本难以有效分割的问题, 提出一种复杂场景文本分割方法. 首先, 使用简单的线性迭代聚类(SLIC) 算法将原始图像分割为若干局部区域, 并在其区域邻接图上构建图割模型; 然后, 采用高斯混合模型(GMMs) 和支持向量机(SVM) 后验概率模型对场景文本进行建模, 并引入每个局部区域与模型之间的匹配度用于计算似然能. 为了增强GMMs的鉴别力, 在参数学习中引入模型性能描述子, 自适应地获得模型参数. 实验结果表明,所提出的算法能够较好地处理复杂场景文本分割问题, 文本的识别率得到了明显的提升.

     

一种主动学习式P2P流识别方法

P2P流的识别对于网络的维护与运营都具有重要意义,基于机器学习的流识别技术是目前研究的热点和难点内容,但目前仍然存在着建立分类模型需要大量适用的训练数据、训练数据的标记需要依赖领域专家以及因此而导致的工作量及难度过大和实用性不强等问题,而当前的研究工作很少涉及到这些问题的解决办法。针对这一问题,采用主动学习技术提取少量高质量的训练样本进行建模,并结合SVM分类算法提出了一种基于锦标赛选择的样本筛选方法。实验结果表明,其相对于已有的流识别方法,能够在仅依赖少量高质量训练样本的前提下,保证较高召回率及较低误报率,更适用于现实网络环境。     

基于遗传算法的隐马尔可夫模型在名词短语识别中的应用研究

为了进一步提高名词短语的识别精度,针对遗传算法和隐马尔可夫模型各自的特点,提出一种基于遗传算法的隐马尔可夫模型识别方法。该方法是在高准确率词性标注的基础上实现的。在训练阶段,用遗传算法获取HMM参数;识别阶段先用一种改进的Viterbi算法进行动态规划,识别同层名词短语,然后用逐层扫描算法和改进Viterbi算法相结合来识别嵌套名词短语。实验结果表明,此联合算法达到了94.78%的准确率和94.29%的召回率,充分融合了遗传算法和隐马尔可夫模型的优点,证明它较单一的隐马尔可夫模型识别法具有更好的识别效果。     

GMM与RVM融合的话者辨识方法

相关向量机(RVM)分类法使用概率输出克服了支持向量机(SVM)识别速率低的缺点,并且具有更好的稀疏性。但在与文本无关的话者辨别中,大量训练样本数据体现了RVM在模型训练时计算量与内存需求过大的缺点。针对以上特点,提出基于GMM统计特征参数与RVM融合的与文本无关的语者辨别系统,既有效地提取话者特征信息,解决大样本数据下的RVM训练问题,又结合统计模型鲁棒性高和分辨模型辨别效果好的优点。实验结果证明,该系统比基本的GMM系统具有更优的错误辨别率,比GMM/SVM系统具有更高的稀疏性。     

Faults diagnosis of a centrifugal pump using multilayer perceptron genetic algorithm back propagation and support vector machine with discrete wavelet transform‐based feature extraction

This paper presents a comparative study of two artificial intelligent systems, namely; Multilayer Perceptron (MLP) and support vector machine (SVM), to classify six fault conditions and the normal (nonfaulty) condition of a centrifugal pump. A hybrid training method for MLP is proposed for this work based on the combination of Back Propagation (BP) and Genetic Algorithm (GA). The two training algorithms are tested and compared separately as well. Features are extracted using Discrete Wavelet Transform (DWT), both approximations, details, and two mother wavelets were used to investigate their effectiveness on feature extraction. GA is also used to optimize the number of hidden layers and neurons of MLP. In this study, the feature extraction, GA‐based hidden layers, neurons selection, training algorithm, and classification performance, based on the strengths and weaknesses of each method, are discussed. From the results obtained, it is observed that the DWT with both MLP‐BP and SVM produces better classification rates and performances.     

A writer identification system for on-line whiteboard data

In this paper we address the task of writer identification of on-line handwriting captured from a whiteboard. Different sets of features are extracted from the recorded data and used to train a text and language independent on-line writer identification system. The system is based on Gaussian mixture models (GMMs) which provide a powerful yet simple means of representing the distribution of the features extracted from the handwritten text. The training data of all writers are used to train a universal background model (UBM) from which a client specific model is obtained by adaptation. Different sets of features are described and evaluated in this work. The system is tested using text from 200 different writers. A writer identification rate of 98.56% on the paragraph and of 88.96% on the text line level is achieved.     

基于SQP/GA混合优化算法的双容水箱非线性预测控制

为了计算控制序列，非线性模型预测控制可以转换为一个带约束的非线性优化过程．本文分析了三种约束处理方案，根据遗传算法的特点，将等式约束用于状态量计算，在搜索空间降维的同时消除遗传算法难以求解的等式约束．对双容水箱进行遗传算法和序列二次规划仿真试验和实际控制，结果表明遗传算法对控制量的优化效果优于序列二次规划．为克服遗传算法耗时较长、优化结果存在随机抖动的缺点，结合序列二次规划提出一种混合优化算法，仿真和实控结果表明其可行性和有效性．     

IIR system identification using cat swarm optimization

Conventional derivative based learning rule poses stability problem when used in adaptive identification of infinite impulse response (IIR) systems. In addition the performance of these methods substantially deteriorates when reduced order adaptive models are used for such identification. In this paper the IIR system identification task is formulated as an optimization problem and a recently introduced cat swarm optimization (CSO) is used to develop a new population based learning rule for the model. Both actual and reduced order identification of few benchmarked IIR plants is carried out through simulation study. The results demonstrate superior identification performance of the new method compared to that achieved by genetic algorithm (GA) and particle swarm optimization (PSO) based identification.     

Recognition of control chart patterns using fuzzy SVM with a hybrid kernel function

Accurate control chart patterns recognition (CCPR) plays an essential role in the implementation of control charts. However, it is a challenging problem since nonrandom control chart patterns (CCPs) are normally distorted by “common process variations”. In this paper, a novel method of CCPR by integrating fuzzy support vector machine (SVM) with hybrid kernel function and genetic algorithm (GA) is proposed. Firstly, two shape features and two statistical features that do not depend on the distribution parameters and number of samples are presented to explicitly describe the characteristics of CCPs. Then, a novel multiclass method based on fuzzy SVM with a hybrid kernel function is proposed. In this method, the influence of outliers on classification accuracy of SVM-based classifiers is weakened by assigning a degree of membership for every training sample. Meanwhile, a hybrid kernel function combining Gaussian kernel and polynomial kernel is adopted to further enhance the generalization ability of the classifiers. To solve the issue of features selection and parameters optimization, GA is used to simultaneously optimize the input features subsets and parameters of fuzzy SVM-based classifier. Finally, several simulation experiments and a real example are addressed to validate the feasibility and effectiveness of the proposed methodology. And the results of simulation experiments demonstrate that it can achieve excellent performance for CCPR and outperforms other approaches, such as learning vector quantization network, multi-layer perceptron network, probability neural network, fuzzy clustering and SVM, in term of recognition accuracy. The results of the practical cases manifest that the proposed method has application potential for solving the problem of control chart interpretation in real-world.     

基于混合准则的软测量建模辅助变量选择方法

软传感器在工业中被广泛应用于预测与产品质量密切相关的关键过程变量,这些变量很难在线测量。要建立一个高精度的软传感器,选择合适的辅助变量是至关重要的。针对这个问题,本文通过耦合训练集的BIC准则以及验证集的MSE准则得到一个混合整数非线性规划问题,并将该MINLP问题分成内外两层结构,外层采用遗传算法对二元整数变量进行寻优,内层在整数变量固定之后退化成了较易于求解的非线性规划问题。在此基础上经过进一步分析提出了基于混合准则的变量选择方法,然后将所得辅助变量子集代入BP神经网络进行软测量建模。最后,通过4组案例对所提出方法进行验证。结果表明,所提出方法建立的软测量模型具有较好的预测性能。     

Nonlinear system identification using optimized dynamic neural network

In this paper, both off-line architecture optimization and on-line adaptation have been developed for a dynamic neural network (DNN) in nonlinear system identification. In the off-line architecture optimization, a new effective encoding scheme—Direct Matrix Mapping Encoding (DMME) method is proposed to represent the structure of neural network by establishing connection matrices. A series of GA operations are applied to the connection matrices to find the optimal number of neurons on each hidden layer and interconnection between two neighboring layers of DNN. The hybrid training is adopted to evolve the architecture, and to tune the weights and input delays of DNN by combining GA with the modified adaptation laws. The modified adaptation laws are subsequently used to tune the input time delays, weights and linear parameters in the optimized DNN-based model in on-line nonlinear system identification. The effectiveness of the architecture optimization and adaptation is extensively tested by means of two nonlinear system identification examples.     

基于因子分析建模的电话语音说话人聚类

现有基于混合高斯模型的说话人聚类方法主要依据最大后验准则,从通用背景模型中自适应得到类别的混合高斯模型,然而自适应数据较少,模型的准确性不够。对此,文中尝试基于本征语音(EV)空间和全变化(TV)空间分析的两种因子分析建模方法,通过对差异空间的建模,减少估计类别混合高斯模型时需要估计的参数个数。结果表明,在美国国家标准技术研究所2008年说话人识别评测的电话语音数据集上,相对于基于最大后验概率准则的基线系统而言,文中所使用的基于EV和TV空间分析的建模方法都可使聚类错误率有较大幅度的下降,并且TV空间分析建模相对于EV空间分析建模能获得更低的聚类错误率。     

基于混合GA的啤酒酵母扩培系统PID控制

针对啤酒酵母扩培过程中温度较难控制的问题,提出一种基于混合遗传算法(GA)的PID控制方法。在GA中嵌入梯度下降算子,利用梯度下降法对每代中若干个精英个体以一定概率进行搜索,从而提高算法的局部搜索能力。实验结果表明,该方法的响应速度较快,且无稳态误差。     

基于GAN技术的自能源混合建模与参数辨识方法

自能源（We-energy,WE）作为能源互联网的子单元旨在实现能量间的双向传输及灵活转换.由于自能源在不同工况下运行特性存在很大差异,现有方法还不能对其参数精确地辨识.为了解决上述问题,本文根据自能源网络结构提出了一种基于GAN技术的数据——机理混合驱动方法对自能源模型参数辨识.将GAN（Generative adversarial networks）模型中训练数据与专家经验结合进行模糊分类,解决了自能源在不同运行工况下的模型切换问题.通过应用含策略梯度反馈的改进GAN技术对模型进行训练,解决了自能源中输出序列离散的问题.仿真结果表明,提出的模型具有较高的辨识精度和更好的推广性,能有效地拟合系统不同工况下各节点的状态变化.     

Monaural speech separation based on MAXVQ and CASA for robust speech recognition

Robustness is one of the most important topics for automatic speech recognition (ASR) in practical applications. Monaural speech separation based on computational auditory scene analysis (CASA) offers a solution to this problem. In this paper, a novel system is presented to separate the monaural speech of two talkers. Gaussian mixture models (GMMs) and vector quantizers (VQs) are used to learn the grouping cues on isolated clean data for each speaker. Given an utterance, speaker identification is firstly performed to identify the two speakers presented in the utterance, then the factorial-max vector quantization model (MAXVQ) is used to infer the mask signals and finally the utterance of the target speaker is resynthesized in the CASA framework. Recognition results on the 2006 speech separation challenge corpus prove that this proposed system can improve the robustness of ASR significantly.     

Uncertainty-based learning of acoustic models from noisy data

We consider the problem of acoustic modeling of noisy speech data, where the uncertainty over the data is given by a Gaussian distribution. While this uncertainty has been exploited at the decoding stage via uncertainty decoding, its usage at the training stage remains limited to static model adaptation. We introduce a new expectation maximization (EM) based technique, which we call uncertainty training, that allows us to train Gaussian mixture models (GMMs) or hidden Markov models (HMMs) directly from noisy data with dynamic uncertainty. We evaluate the potential of this technique for a GMM-based speaker recognition task on speech data corrupted by real-world domestic background noise, using a state-of-the-art signal enhancement technique and various uncertainty estimation techniques as a front-end. Compared to conventional training, the proposed training algorithm results in 3–4% absolute improvement in speaker recognition accuracy by training from either matched, unmatched or multi-condition noisy data. This algorithm is also applicable with minor modifications to maximum a posteriori (MAP) or maximum likelihood linear regression (MLLR) acoustic model adaptation from noisy data and to other data than audio.     

Fuzzy neural networks-based quality prediction system for sinteringprocess

A hybrid fuzzy neural networks and genetic algorithm (GA) system is proposed to solve the difficult and challenging problem of constructing a system model from the given input and output data to predict the quality of chemical components of the finished sintering mineral. A bidirectional fuzzy neural network (BFNN) is proposed to represent the fuzzy model and realize the fuzzy inference. The learning process of BFNN is divided into off-line and online learning. In off-line learning, the GA is used to train the BFNN and construct a system model based on the training data. During online operation, the algorithm inherited from the principle of backpropagation is used to adjust the network parameters and improve the system precision in each sampling period. The process of constructing a system model is introduced in details. The results obtained from the actual prediction demonstrate that the performance and capability of the proposed system are superior     

Change point determination for a multivariate process using a two-stage hybrid scheme

Effective identification of the change point of a multivariate process is an important research issue since it is associated with the determination of assignable causes which may seriously affect the underlying process. Most existing studies either use the maximum likelihood estimator (MLE) method or the machine learning (ML) method to estimate or identify the change point of a process. Typically, the MLE method may be criticized for its assumption that the process distribution is known, and the ML method may have the deficiency of using a large number of input variables in the modeling procedure. Diverging from existing approaches, this study proposes an integrated hybrid scheme to mitigate the difficulties of the MLE and ML methods. The proposed scheme includes four components: the logistic regression (LR) model, the multivariate adaptive regression splines (MARS) model, the support vector machine (SVM) classifier and the change point identification strategy. It performs three tasks in order to effectively identify the change point in a multivariate process. The initial task is to use the LR and MARS models to reduce and refine the whole set of input or explanatory variables. The remaining variables are then served as input variables to the SVM in the second task. The last task is to integrate use of the SVM outputs with our proposed identification strategy to determine the change point in a multivariate process. Experimental simulation results reveal that the proposed hybrid scheme is able to effectively identify the change point and outperform the typical statistical process control (SPC) chart alone and the single stage SVM methods.     

基于振动频谱的磨矿过程球磨机负荷参数集成建模方法

以磨矿过程的湿式球磨机为背景, 针对传统磨机负荷(ML)检测方法只能依靠灵敏度较低的轴承振动、筒体振声和磨机功率等信号监督判断ML状态, 难以检测磨机内部负荷参数的问题, 提出了一种基于高灵敏度的筒体振动频谱的集成建模方法. 首先, 依据磨矿过程的研磨机理, 将振动频谱采用波峰聚类方法自动划分具有不同物理意义的分频段; 然后利用核偏最小二乘(KPLS)算法分别建立各分频段的ML参数子模型; 最后, 依据子模型训练数据预测误差的信息熵获得初始权重, 加权得到最终的ML参数集成预测模型; 在线使用中则根据子模型预测误差的变化进行权值的在线自适应更新. 仿真结果证明了该方法的有效性.