Classification of Motor Imagery EEG Based on Time-Domain and Frequency-Domain Dual-Stream Convolutional Neural Network

Background and objectiveAn important task of the brain-computer interface (BCI) of motor imagery is to extract effective time-domain features, frequency-domain features or time-frequency domain features from the raw electroencephalogram (EEG) signals for classification of motor imagery. However, choosing an appropriate method to combine time domain and frequency domain features to improve the performance of motor imagery recognition is still a research hotspot.MethodsIn order to fully extract and utilize the time-domain and frequency-domain features of EEG in classification tasks, this paper proposed a novel dual-stream convolutional neural network (DCNN), which can use time domain signal and frequency domain signal as the inputs, and the extracted time-domain features and frequency-domain features are fused by linear weighting for classification training. Furthermore, the weight can be learned by the DCNN automatically.ResultsThe experiments based on BCI competition II dataset III and BCI competition IV dataset 2a showed that the model proposed by this study has better performance than other conventional methods. The model used time-frequency signal as the inputs had better performance than the model only used time-domain signals or frequency-domain signals. The accuracy of classification was improved for each subject compared with the models only used one signals as the inputs.ConclusionsFurther analysis shown that the fusion weight of different subject is specifically, adjusting the weight coefficient automatically is helpful to improve the classification accuracy.     

Dynamic Neural Network Models of the Premotoneuronal Circuitry Controlling Wrist Movements in Primates

Dynamic recurrent neural networks were derived to simulate neuronal populations generating bidirectional wrist movements in the monkey. The models incorporate anatomical connections of cortical and rubral neurons, muscle afferents, segmental interneurons and motoneurons; they also incorporate the response profiles of four populations of neurons observed in behaving monkeys. The networks were derived by gradient descent algorithms to generate the eight characteristic patterns of motor unit activations observed during alternating flexion-extension wrist movements. The resulting model generated the appropriate input-output transforms and developed connection strengths resembling those in physiological pathways. We found that this network could be further trained to simulate additional tasks, such as experimentally observed reflex responses to limb perturbations that stretched or shortened the active muscles, and scaling of response amplitudes in proportion to inputs. In the final comprehensive network, motor units are driven by the combined activity of cortical, rubral, spinal and afferent units during step tracking and perturbations.The model displayed many emergent properties corresponding to physiological characteristics. The resulting neural network provides a working model of premotoneuronal circuitry and elucidates the neural mechanisms controlling motoneuron activity. It also predicts several features to be experimentally tested, for example the consequences of eliminating inhibitory connections in cortex and red nucleus. It also reveals that co-contraction can be achieved by simultaneous activation of the flexor and extensor circuits without invoking features specific to co-contraction.     

A Slantlet transform based intelligent system for magnetic resonance brain image classification

The present paper proposes the development of a new approach for automated diagnosis, based on classification of magnetic resonance (MR) human brain images. Wavelet transform based methods are a well-known tool for extracting frequency space information from non-stationary signals. In this paper, the proposed method employs an improved version of orthogonal discrete wavelet transform (DWT) for feature extraction, called Slantlet transform, which can especially be useful to provide improved time localization with simultaneous achievement of shorter supports for the filters. For each two-dimensional MR image, we have computed its intensity histogram and Slantlet transform has been applied on this histogram signal. Then a feature vector, for each image, is created by considering the magnitudes of Slantlet transform outputs corresponding to six spatial positions, chosen according to a specific logic. The features hence derived are used to train a neural network based binary classifier, which can automatically infer whether the image is that of a normal brain or a pathological brain, suffering from Alzheimer's disease. An excellent classification ratio of 100% could be achieved for a set of benchmark MR brain images, which was significantly better than the results reported in a very recent research work employing wavelet transform, neural networks and support vector machines.     

Spontaneously active cells induce state transitions in a model of olfactory cortex

The existence of neurons with intrinsic oscillations does not in itself explain the synchronization of local populations of neurons, but it is likely to pace population rhythms when the neurons are suitably coupled by chemical and/or electrical synapses. In the present study, we have investigated the role of spontaneously active cells as noisy or pacemaker units in setting global oscillations in a three-layered cortical model. The presence of a small number of noisy (spontaneously active) units induce oscillations at the network level in the range of the gamma rhythm. The number of noisy units in the network and their type (excitatory or inhibitory or excitatory and inhibitory together) determines the emergence of regular oscillations or aperiodic (chaotic) behaviour. It also determines the onset of the global behaviour. On replacing a noisy unit by a pacemaker unit, similar gamma oscillations were generated. With both noisy and pacemaker units, we found that certain characteristics of the spontaneous activity determine the delay period for the onset of global activity. Preliminary studies have been carried out with spontaneously active units having a chaotic dynamics but the results are much similar to that with a noisy burst. Different functional roles have been suggested for cortical oscillations, such as determining global functional states and specifying connectivity during development. Oscillations at different frequency bands, in particular in the gamma band (around 40 Hz), have also been associated with memory and attention. The presence of spontaneously active neurons, either with noisy or oscillatory activity, could be responsible for global oscillations in the absence of external stimuli in certain cortical areas in the mature brain.     

A Study on Protein Residue Contacts Prediction by Recurrent Neural Network

1IntroductionThe three-dimensional(3D)structure of a proteinis perhaps the most important of all its features,since itdetermines completely how the protein functions andinteracts with other molecules.Most biological mech-anisms at the protein level are based on shape-complementarity,so that proteins present particularconcavities and convexities that allow them to bind toeach other and formcomplexstructures,and tendon.Forthis reason,for instance,the drug design problem con-sists primarily in th…     

Rule extraction from minimal neural networks for credit card screening

While feedforward neural networks have been widely accepted as effective tools for solving classification problems, the issue of finding the best network architecture remains unresolved, particularly so in real-world problem settings. We address this issue in the context of credit card screening, where it is important to not only find a neural network with good predictive performance but also one that facilitates a clear explanation of how it produces its predictions. We show that minimal neural networks with as few as one hidden unit provide good predictive accuracy, while having the added advantage of making it easier to generate concise and comprehensible classification rules for the user. To further reduce model size, a novel approach is suggested in which network connections from the input units to this hidden unit are removed by a very straightaway pruning procedure. In terms of predictive accuracy, both the minimized neural networks and the rule sets generated from them are shown to compare favorably with other neural network based classifiers. The rules generated from the minimized neural networks are concise and thus easier to validate in a real-life setting.     

全景绿视率自动识别和计算研究

绿视率是用于绿色空间感知的直观评价标准,传统研究的绿视率多基于平面影像进行计算,不能完全反映三维空间中人对绿量的主观感受。基于全景影像,提出全景绿视率的概念,通过全景相机获取球面全景照片,将等距圆柱投影转换为等积圆柱投影,利用基于语义分割的卷积神经网络模型,自动识别植被区域面积以实现全景绿视率自动化识别和计量。通过比较5项卷积神经网络模型对绿视率的识别效果,显示出Dilated ResNet-105神经网络模型具有最高的识别准确度。以武汉市武昌区紫阳公园为例,对各级园路和广场的全景绿视率进行计算和分析。将卷积神经网络的识别结果同人工判别结果进行对比研究,结果显示：使用Dilated ResNet-105卷积神经网络对绿植范围识别的平均交并比（mIoU）为62.53%,与人工识别的平均差异为9.17%。全景绿视率自动识别和计算可以为相关研究提供新的思路,实现客观准确、快速便捷的绿视率测量评估。     

Emergence of network structure due to spike-timing-dependent plasticity in recurrent neuronal networks. I. Input selectivity–strengthening correlated input pathways

Spike-timing-dependent plasticity (STDP) determines the evolution of the synaptic weights according to their pre- and post-synaptic activity, which in turn changes the neuronal activity. In this paper, we extend previous studies of input selectivity induced by (STDP) for single neurons to the biologically interesting case of a neuronal network with fixed recurrent connections and plastic connections from external pools of input neurons. We use a theoretical framework based on the Poisson neuron model to analytically describe the network dynamics (firing rates and spike-time correlations) and thus the evolution of the synaptic weights. This framework incorporates the time course of the post-synaptic potentials and synaptic delays. Our analysis focuses on the asymptotic states of a network stimulated by two homogeneous pools of “steady” inputs, namely Poisson spike trains which have fixed firing rates and spike-time correlations. The (STDP) model extends rate-based learning in that it can implement, at the same time, both a stabilization of the individual neuron firing rates and a slower weight specialization depending on the input spike-time correlations. When one input pathway has stronger within-pool correlations, the resulting synaptic dynamics induced by (STDP) are shown to be similar to those arising in the case of a purely feed-forward network: the weights from the more correlated inputs are potentiated at the expense of the remaining input connections.     

Growing of a Fuzzy Recurrent Artificial Neural Network (FRANN) for pattern classification

This paper describes a method for growing a recurrent neural network of fuzzy threshold units for the classification of feature vectors. Fuzzy networks seem natural for performing classification, since classification is concerned with set membership and objects generally belonging to sets of various degrees. A fuzzy unit in the architecture proposed here determines the degree to which the input vector lies in the fuzzy set associated with the fuzzy unit. This is in contrast to perceptrons that determine the correlation between input vector and a weighting vector. The resulting membership value, in the case of the fuzzy unit, is compared with a threshold, which is interpreted as a membership value. Training of a fuzzy unit is based on an algorithm for linear inequalities similar to Ho-Kashyap recording. These fuzzy threshold units are fully connected in a recurrent network. The network grows as it is trained. The advantages of the network and its training method are: (1) Allowing the network to grow to the required size which is generally much smaller than the size of the network which would be obtained otherwise, implying better generalization, smaller storage requirements and fewer calculations during classification; (2) The training time is extremely short; (3) Recurrent networks such as this one are generally readily implemented in hardware; (4) Classification accuracy obtained on several standard data sets is better than that obtained by the majority of other standard methods; and (5) The use of fuzzy logic is very intuitive since class membership is generally fuzzy.     

Feedforward neural network with adaptive reference pattern layer.

A hybrid neural network architecture is investigated for modeling purposes. The proposed hybrid is based on the multilayer perceptron (MLP) network. In addition to the usual hidden layers, the first hidden layer is selected to be an adaptive reference pattern layer. Each unit in this new layer incorporates a reference pattern that is located somewhere in the space spanned by the input variables. The outputs of these units are the component wise-squared differences between the elements of a reference pattern and the inputs. The reference pattern layer has some resemblance to the hidden layer of the radial basis function (RBF) networks. Therefore the proposed design can be regarded as a sort of hybrid of MLP and RBF networks. The presented benchmark experiments show that the proposed hybrid can provide significant advantages over standard MLPs and RBFs in terms of fast and efficient learning, and compact network structure.     

Chaotic neural network applied to two-dimensional motion control

Chaotic dynamics generated in a chaotic neural network model are applied to 2-dimensional (2-D) motion control. The change of position of a moving object in each control time step is determined by a motion function which is calculated from the firing activity of the chaotic neural network. Prototype attractors which correspond to simple motions of the object toward four directions in 2-D space are embedded in the neural network model by designing synaptic connection strengths. Chaotic dynamics introduced by changing system parameters sample intermediate points in the high-dimensional state space between the embedded attractors, resulting in motion in various directions. By means of adaptive switching of the system parameters between a chaotic regime and an attractor regime, the object is able to reach a target in a 2-D maze. In computer experiments, the success rate of this method over many trials not only shows better performance than that of stochastic random pattern generators but also shows that chaotic dynamics can be useful for realizing robust, adaptive and complex control function with simple rules.     

Functional organization within a neural network trained to update target representations across 3-D saccades

The goal of this study was to understand how neural networks solve the 3-D aspects of updating in the double-saccade task, where subjects make sequential saccades to the remembered locations of two targets. We trained a 3-layer, feed-forward neural network, using back-propagation, to calculate the 3-D motor error the second saccade. Network inputs were a 2-D topographic map of the direction of the second target in retinal coordinates, and 3-D vector representations of initial eye orientation and motor error of the first saccade in head-fixed coordinates. The network learned to account for all 3-D aspects of updating. Hidden-layer units (HLUs) showed retinal-coordinate visual receptive fields that were remapped across the first saccade. Two classes of HLUs emerged from the training, one class primarily implementing the linear aspects of updating using vector subtraction, the second class implementing the eye-orientation-dependent, non-linear aspects of updating. These mechanisms interacted at the unit level through gain-field-like input summations, and through the parallel "tweaking" of optimally-tuned HLU contributions to the output that shifted the overall population output vector to the correct second-saccade motor error. These observations may provide clues for the biological implementation of updating.     

基于优化核参数支持向量机的意识任务分类

根据支持向量机的基本原理,给出一种推广误差上界估计判据,并利用该判据进行最优核参数的自动选取。对三种不同意识任务的脑电信号进行多变量自回归模型参数估计,作为意识任务的特征向量,利用支持向量机进行训练和分类测试。分类结果表明,优化核参数的支持向量机分类器取得了最佳的分类效果,分类正确率明显高于径向基函数神经网络。     

Influence of noise on the function of a “physiological” neural network

A model neural network with stochastic elements in its millisecond dynamics is investigated. The network consists of neuronal units which are modelled in close analogy to physiological neurons. Dynamical variables of the network are the cellular potentials, axonic currents and synaptic efficacies. The dynamics of the synapses obeys a modified Hebbian rule and, as proposed by v. d. Malsburg (1981, 1985), develop on a time scale of a tenth of a second. In a previous publication (Buhmann and Schulten 1986) we have confirmed that the resulting noiseless autoassociative network is capable of the well-known computational tasks of formal associative networks (Cooper 1973; Kohonen et al. 1984, 1981; Hopfield 1982). In the present paper we demonstrate that random fluctuations of the membrane potential improve the performance of the network. In comparison to a deterministic network a noisy neural network can learn at lower input frequencies and with lower average neural firing rates. The electrical activity of a noisy network is very reminiscent of that observed by physiological recordings. We demonstrate furthermore that associative storage reduces the effective dimension of the phase space in which the electrical activity of the network develops.     

High-order behaviour in learning gate networks with lateral inhibition

In this work we present a neural network model incorporating activity-dependent presynaptic facilitation with multidimensional inputs. The processing unit used is based on a slightly simplified version of the Learning Gate Model proposed by Ciaccia et al. (1992). The network topology integrates a well-known biological neural circuit with a lateral inhibition connection subnet. By means of simulation experiments, we show that the proposed networks exhibit basic and high-order features of associative learning. In particular, overshadowing and blocking are reproduced in the presence of both noise-free and noisy inputs. The role of noise in the development of high-order learning capabilities is also discussed.This article was processed by the author using the LAT_EX style file pljour2 from Springer-Verlag.     

Molecular determination by electron microscopy of the dynein-microtubule complex structure

Dynein is a minus-end-directed microtubule (MT) motor that is responsible for the wide range of MT-based motility in eukaryotic cells. Detailed mechanism of the dynein chemomechanical conversion is still unknown, partly because the structure of dynein is not studied at high resolution. To address this problem and reconstruct the dynein-MT complex at higher resolution, we have developed new procedures based on single particle analysis. To accurately determine the orientation of the dynein-MT complex, we introduced a "dynein track model" to restrict the possible dynein positions on the images. We tested our procedures by reconstructing structures from simulated dynein-MT complex images. Starting from the simulated noisy images generated using three different models of the dynein-MT complex, we have successfully recovered the original three-dimensional (3-D) structure. We also showed that our procedure is robust against fluctuation of the dynein molecules and can determine the structure even when the dynein position fluctuates to a certain extent. Convergence of the final 3-D structure can be tested with a "two-dimensional (2-D) agreement value," which we introduced to see whether the final structure is a result of overfit from fluctuating dynein or not. When the procedures did not work well due to the fluctuation, we could recognize the failure by this 2-D agreement value. Finally, the actual structure of the dynein-MT complex was determined from actual cryoelectron micrographs of Dictyostelium cytoplasmic dynein-MT complex. This method has revealed the detailed 3-D structures of the dynein-MT complex and will shed light on the motor mechanism of the dynein molecule.     

Automatic determination of radial basis functions: an immunity-based approach

The appropriate operation of a radial basis function (RBF) neural network depends mainly upon an adequate choice of the parameters of its basis functions. The simplest approach to train an RBF network is to assume fixed radial basis functions defining the activation of the hidden units. Once the RBF parameters are fixed, the optimal set of output weights can be determined straightforwardly by using a linear least squares algorithm, which generally means reduction in the learning time as compared to the determination of all RBF network parameters using supervised learning. The main drawback of this strategy is the requirement of an efficient algorithm to determine the number, position, and dispersion of the RBFs. The approach proposed here is inspired by models derived from the vertebrate immune system, that will be shown to perform unsupervised cluster analysis. The algorithm is introduced and its performance is compared to that of the random, k-means center selection procedures and other results from the literature. By automatically defining the number of RBF centers, their positions and dispersions, the proposed method leads to parsimonious solutions. Simulation results are reported concerning regression and classification problems.     

Constructing a fuzzy rule-based system using the ILFN network and Genetic Algorithm.

In this paper, a method for automatic construction of a fuzzy rule-based system from numerical data using the Incremental Learning Fuzzy Neural (ILFN) network and the Genetic Algorithm is presented. The ILFN network was developed for pattern classification applications. The ILFN network, which employed fuzzy sets and neural network theory, equips with a fast, one-pass, on-line, and incremental learning algorithm. After trained, the ILFN network stored numerical knowledge in hidden units, which can then be directly interpreted into if then rule bases. However, the rules extracted from the ILFN network are not in an optimized fuzzy linguistic form. In this paper, a knowledge base for fuzzy expert system is extracted from the hidden units of the ILFN classifier. A genetic algorithm is then invoked, in an iterative manner, to reduce number of rules and select only discriminate features from input patterns needed to provide a fuzzy rule-based system. Three computer simulations using a simulated 2-D 3-class data, the well-known Fisher's Iris data set, and the Wisconsin breast cancer data set were performed. The fuzzy rule-based system derived from the proposed method achieved 100% and 97.33% correct classification on the 75 patterns for training set and 75 patterns for test set, respectively. For the Wisconsin breast cancer data set, using 400 patterns for training and 299 patterns for testing, the derived fuzzy rule-based system achieved 99.5% and 98.33% correct classification on the training set and the test set, respectively.     

Computation by ensemble synchronization in recurrent networks with synaptic depression

While computation by ensemble synchronization is considered to be a robust and efficient way for information processing in the cortex (C. Von der Malsburg and W. Schneider (1986) Biol. Cybern. 54: 29–40; W. Singer (1994) Inter. Rev. Neuro. 37: 153–183; J.J. Hopfield (1995) Nature 376: 33–36; E. Vaadia et al. (1995) Nature 373: 515–518), the neuronal mechanisms that might be used to achieve it are yet to be uncovered. Here we analyze a neural network model in which the computations are performed by near coincident firing of neurons in response to external inputs. This near coincident firing is enabled by activity dependent depression of inter-neuron connections. We analyze the network behavior by using a mean-field approximation, which allows predicting the network response to various inputs. We demonstrate that the network is very sensitive to temporal aspects of the inputs. In particular, periodically applied inputs of increasing frequency result in different response profiles. Moreover, applying combinations of different stimuli lead to a complex response, which cannot be easily predicted from responses to individual components. These results demonstrate that networks with synaptic depression can perform complex computations on time-dependent inputs utilizing the ability to generate temporally synchronous firing of single neurons.     

Emergence of network structure due to spike-timing-dependent plasticity in recurrent neuronal networks. II. Input selectivity—symmetry breaking

Spike-timing-dependent plasticity (STDP) is believed to structure neuronal networks by slowly changing the strengths (or weights) of the synaptic connections between neurons depending upon their spiking activity, which in turn modifies the neuronal firing dynamics. In this paper, we investigate the change in synaptic weights induced by STDP in a recurrently connected network in which the input weights are plastic but the recurrent weights are fixed. The inputs are divided into two pools with identical constant firing rates and equal within-pool spike-time correlations, but with no between-pool correlations. Our analysis uses the Poisson neuron model in order to predict the evolution of the input synaptic weights and focuses on the asymptotic weight distribution that emerges due to STDP. The learning dynamics induces a symmetry breaking for the individual neurons, namely for sufficiently strong within-pool spike-time correlation each neuron specializes to one of the input pools. We show that the presence of fixed excitatory recurrent connections between neurons induces a group symmetry-breaking effect, in which neurons tend to specialize to the same input pool. Consequently STDP generates a functional structure on the input connections of the network.