An online learning fuzzy controller

A fuzzy controller with online learning capability is reported in this paper. The controller learns from a standard proportional plus derivative (PD) controller. It is implicitly assumed that the tuning parameters of the PD controller are already known. The learning is realized via Wang's table lookup scheme. The controllers are applied successfully to control an open-loop unstable system, i.e., the ball and plate system. Experimental studies have demonstrated the performance of the proposed controller.     

Partial-distortion-weighted fuzzy competitive learning algorithmfor vector quantisation

An effective competitive learning algorithm called the partial-distortion-weighted fuzzy competitive learning (PDW-FCL) algorithm is developed for vector quantisation. The PDW-FCL algorithm is able to minimise the likelihood of neuron (codevector) underuse and make good use of every neuron for optimal vector quantiser design     

Optimal learning for patterns classification in RBF networks

The proposed modifying of the structure of the radial basis function (RBF) network by introducing the weight matrix to the input layer (in contrast to the direct connection of the input to the hidden layer of a conventional RBF) so that the training space in the RBF network is adaptively separated by the resultant decision boundaries and class regions is reported. The training of this weight matrix is carried out as for a single-layer perceptron together with the clustering process. In this way the network is capable of dealing with complicated problems, which have a high degree of interference in the training data, and achieves a higher classification rate over the current classifiers using RBF     

集成学习在短文本分类中的应用研究

为了进一步提高基于深度神经网络短文本分类性能,提出将集成学习方法应用于5种不同的神经网络文本分类器,即卷积神经网络、双向长短时记忆网络、卷积循环神经网络、循环卷积神经网络、分层注意力机制神经网络,分别对两种集成学习方法(Bagging,Stacking)进行了测试。实验结果表明:将多个神经网络短文本分类器进行集成的分类性能要优于单一文本分类模型;进一步两两集成的实验验证了单个模型对短文本分类性能的贡献率。     

Evolutionary learning, reinforcement learning, and fuzzy rules forknowledge acquisition in agent-based systems

The behavior of agents in complex and dynamic environments cannot be programmed a priori, but needs to self-adapt to the specific situations. We present some approaches based on evolutionary reinforcement learning algorithms, which are able to evolve in real-time fuzzy models that control behaviors. We discuss an application where an agent learns how to adapt its behavior to the different behaviors of the other agents it is interacting with, and another application where a group of agents co-evolve cooperative behaviors by using explicit communication to propose the cooperation and to distribute reinforcement to the others     

Combined compression and classification with learning vectorquantization

Combined compression and classification problems are becoming increasingly important in many applications with large amounts of sensory data and large sets of classes. These applications range from automatic target recognition (ATR) to medical diagnosis, speech recognition, and fault detection and identification in manufacturing systems. In this paper, we develop and analyze a learning vector quantization (LVQ) based algorithm for combined compression and classification. We show convergence of the algorithm using the ODE method from stochastic approximation. We illustrate the performance of the algorithm with some examples     

Adaptive hypergraph learning and its application in image classification

Recent years have witnessed a surge of interest in graph-based transductive image classification. Existing simple graph-based transductive learning methods only model the pairwise relationship of images, however, and they are sensitive to the radius parameter used in similarity calculation. Hypergraph learning has been investigated to solve both difficulties. It models the high-order relationship of samples by using a hyperedge to link multiple samples. Nevertheless, the existing hypergraph learning methods face two problems, i.e., how to generate hyperedges and how to handle a large set of hyperedges. This paper proposes an adaptive hypergraph learning method for transductive image classification. In our method, we generate hyperedges by linking images and their nearest neighbors. By varying the size of the neighborhood, we are able to generate a set of hyperedges for each image and its visual neighbors. Our method simultaneously learns the labels of unlabeled images and the weights of hyperedges. In this way, we can automatically modulate the effects of different hyperedges. Thorough empirical studies show the effectiveness of our approach when compared with representative baselines.     

Estimation of forest parameters through fuzzy classification of TMdata

Several studies have investigated the utility of Landsat 5 TM imagery to estimate forest parameters such as stand composition and density. Regression equations have generally been used to relate these parameters to the radiance responses of the TM channels. Such a method is not feasible in highly complex landscapes, where forest mixtures and terrain irregularities may obscure the existence of simple relationships. A fuzzy approach to the problem is presented based on a multi-step procedure. First, some typical forest plots with known features are spectrally identified. A maximum likelihood fuzzy classification with nonparametric priors is then applied to the study images, so as to derive fuzzy membership grades for all pixels with respect to the typical plots. Finally, these grades are used to compute the estimates of the forest parameters by a weighted average strategy. The method was tested on a complex, rugged area in Tuscany mainly covered by deciduous and coniferous forests. Two TM scenes and accurate ground references taken in spring and summer 1991 were utilized for the testing. The first results, statistically evaluated in comparison with those of a more usual multivariate regression procedure, are quite encouraging. The possible application of the fuzzy approach to other cases of environmental monitoring is finally discussed     

A fuzzy set approach for yield learning modeling in wafermanufacturing

The yield of semiconductor manufacturing can be improved through a learning process. A learning model is usually used to describe the learning process and to predict future yields. However, in traditional learning models such as Gruber's general yield model, the uncertainty and variation inherent in the learning process are not easy to consider. Also there are many strict assumptions about parameter distributions that need to be made. These result in the unreliability and imprecision of yield prediction. To improve the reliability and precision of yield prediction, expert opinions are consulted to evaluate and modify the learning model in this study. The fuzzy set theory is applied to facilitate this consulting process. At first, fuzzy forecasts are generated to predict future yields. The necessity of specifying strict parameter distributions is thus relaxed. Fuzzy yield forecasts can be defuzzified, or their α-cuts can be considered in capacity planning. The interpretation of such a treatment is also intuitive. Then, experts are requested to evaluate the learning model and express their opinions about the parameters in suitable fuzzy numbers or linguistic terms defined in advance. Two correction functions are designed to incorporate expert opinions in the learning model. Some examples are used for demonstration. The advantages of the proposed method are then discussed     

Studying cost-sensitive learning for multi-class imbalance in Internet traffic classification

Cost-sensitive learning has been applied to resolve the multi-class imbalance problem in Internet traffic classification and it has achieved considerable results.But the classification performance on the minority classes with a few bytes is still unhopeful because the existing research only focuses on the classes with a large amount of bytes.Therefore,the class-dependent misclassification cost is studied.Firstly,the flow rate based cost matrix(FCM) is investigated.Secondly,a new cost matrix named weighted cost matrix(WCM) is proposed,which calculates a reasonable weight for each cost of FCM by regarding the data imbalance degree and classification accuracy of each class.It is able to further improve the classification performance on the difficult minority class(the class with more flows but worse classification accuracy).Experimental results on twelve real traffic datasets show that FCM and WCM obtain more than 92% flow g-mean and 80% byte g-mean on average;on the test set collected one year later,WCM outperforms FCM in terms of stability.     

Multiple kernel-based multi-instance learning algorithm for image classification

In this paper, a novel multi-instance learning (MIL) algorithm based on multiple-kernels (MK) framework has been proposed for image classification. This newly developed algorithm defines each image as a bag, and the low-level visual features extracted from its segmented regions as instances. This algorithm is started from constructing a “word-space” from instances based on a collection of “visual-words” generated by affinity propagation (AP) clustering method. After calculating the distance between a “visual-word” and the bag (image), a nonlinear mapping mechanism is introduced for registering each bag as a coordinate point in the “word-space”. In this case, the MIL problem is transformed into a standard supervised learning problem, which allows multiple-kernels support vector machine (MKSVM) classifiers to be trained for the image categorization. Compared with many popular MIL algorithms, the proposed method, named as MKSVM-MIL, shows its satisfactorily experimental results on the COREL dataset, which highlights the robustness and effectiveness for image classification applications.     

基于深度学习的心电图心律失常分类方法

近些年来因心血管疾病导致的人类死亡人数不断增加,心律失常是心血管疾病发病前的常见症状.为了提高心电图对心律失常分类的效率和准确率,使医生能对心律失常及时地作出诊断和治疗,提出一种基于二维卷积神经网络模型的心律失常分类方法.该方法使用美国麻省理工学院提供的研究心律失常的MIT-BIH数据库来生成实验数据集对网络进行训练和...     

深层次特征学习的Adaboost大规模图像分类算法

针对浅层次大规模图像分类的低精度问题,提出深层次特征学习的Adaboost图像分类算法.首先以DBN作为弱分类器对样本图像进行学习,根据每次训练得到的分类错误率以及各样本的分类准确性调整权值;然后在所有弱分类器训练好以后,使用BP算子回溯再次整体调整体样本权值;最后将所有弱分类器集成强分类器,输出最终分类结果.使用MNIST和ETH-80两种数据集进行实验仿真,并将分类结果与其他算法进行比较.结果表明所提算法的分类精度明显高于其他算法,有效实现了高精度的大规模图像分类.     

基于机器学习的多光谱模糊图像降噪方法

利用当前方法对多光谱模糊图像降噪时,未对多光谱模糊图像进行增强处理,存在图像视觉效果差、主观分数低等问题。为此,提出基于机器学习的多光谱模糊图像降噪方法。首先,利用均值滤波模板增强多光谱模糊图像色彩,同时利用高斯模板增强图像细节,将两者叠加,保证图像不受失真和光晕现象等影响,保证图像以及边界的清晰度;然后,利用核主成分分析法构建图像去噪模型,将图像坐标全部投射到特征空间中;最后,采用机器学习去噪特征空间中的近似噪点,实现多光谱模糊图像降噪。实验结果表明,所提方法的图像视觉效果较好,且主观得分较高。     

Extracting fuzzy rules from polysomnographic recordings for infant sleep classification

A neuro-fuzzy classifier (NFC) of sleep-wake states and stages has been developed for healthy infants of ages 6 mo and onward. The NFC takes five input patterns previously identified on 20-s epochs from polysomnographic recordings and assigns them to one out of five possible classes: Wakefulness, REM-Sleep, Non-REM Sleep Stage 1, Stage 2, and Stage 3-4. The definite criterion for a sleep state or stage to be established is duration of at least 1 min. The data set consisted of a total of 14 continuous recordings of naturally occurring naps (average duration: 143 +/- 39 min), corresponding to a total of 6021 epochs. They were divided in a training, a validation and a test set with 7, 2, and 5 recordings, respectively. During supervised training, the system determined the fuzzy concepts associated to the inputs and the rules required for performing the classification, extracting knowledge from the training set, and pruning nonrelevant rules. Results on an independent test set achieved 83.9 +/- 0.4% of expert agreement. The fuzzy rules obtained from the training examples without a priori information showed a high level of coincidence with the crisp rules stated by the experts, which are based on internationally accepted criteria. These results show that the NFC can be a valuable tool for implementing an automated sleep-wake classification system.     

DCT basis function learning control

In this paper, a basis function learning control is developed in away parallel to time domain learning control. Basis function approach aims to reduce the dimension and computation of learning gain matrices while maintaining minimal loss of tracking precision. Here, we transplant two learning gain matrices, the transpose and the partial isometry, from time domain learning control into basis function learning control. These two learning gain matrices have no ill-conditioned problems in matrix computation and ensure a monotonic decay of tracking error. The basis vector of discrete cosine transform (DCT) is chosen as basis function for its high energy compression ratio and energy preservation feature. Experiments on two joints of a SCARA type robot verify the effectiveness of the proposed approaches. A few DCT coefficients may meet learning control specification and tracking precision can be improved by increasing the number of the DCT coefficients.     

On using fuzzy logic to integrate learning mechanisms in an electro-hydraulic system. I. Actuator's fuzzy modeling

Drive systems are usually modeled using a mathematical characterization of their physical phenomena. However, the difficulty in establishing a relevant model representation, in particular for electro-hydraulic systems, makes important the search for other modeling mechanisms that allow the combination of previously compiled system's knowledge with acquired experimental information. This paper, divided into two parts, describes the potential and possible drawbacks of integrating fuzzy learning mechanisms into a drive system that includes an electro-hydraulic actuator. First, experimental verification of the actuator's fuzzy modeling is presented in Part I of the paper, where the variable selection problem and the performance of the learning algorithm are discussed. In Part II, extensive experimental results employing the extracted fuzzy model and associated learning algorithm are presented. The feasibility and effectiveness of integrating fuzzy learning mechanisms into the actuator's control is also discussed.     

基于判别子字典学习的图像分类优化方法

本文提出了一种基于判别子字典学习算法的图像分类优化方法.在判别字典学习算法的基础上,引入字典矩阵的正则化约束项,针对每一类图像学习其对应的特定字典,使字典中包含该类别的特定原子,规避不同子字典之间原子的相关性.同时,引入标签信息矩阵和拉普拉斯正则化矩阵,使大系数集中在某一类别的特定原子上,属于同一类别的样本彼此靠近,从而提高字典的判别能力.将该算法应用在3种不同的数据集上,实验结果证明了所提方法的有效性.