Neurobiology suggests the design of modular architectures for neural control

The existence of modular structures in the biological world strongly suggests that the training of this kind of structure is actually feasible. It is a key indication for the development of neural network applications, especially in the field of robotics. Indeed, a single network can only efficiently treat problems with few independent variables; the combination of several networks is necessary to address more complex tasks. We investigate learning techniques and show that using a particular form of architecture can ease the training of a modular structure: a bi-directional structure that allows combining several neural networks. The approach is illustrated with Kohonen's self-organizing maps for a robotic visual servoing task.     

THE PHASE WEB PARADIGM

We describe an information-oriented, computational physical theory based on expressing knowledge of the world via patterns of synchronization. The systems this theory describes are self-organizing, display emergent phenomena, and can be expressed in terms both of Clifford algebras and algebraic topology, and practical running programs.     

Self-organizing method for collaboration in multi-robot system on basis of balance principle

By analyzing the operation characteristics of two subtasks that have resource dependency on each other, this paper demonstrates the impact of progress relation between the two subtasks on the whole task’s progress, and then puts forward a self-organizing principle called balance principle that keeps the individual profit between robots equal. Furthermore, an algorithm is designed for adjusting subtask selection on the basis of this principle. Simulation shows the validity of the algorithm on self-organizing task allocation in a multi-robot system. __________ Translated from Chinese Journal of Scientific Instrument, 2007, 28(2): 224–228 [译自: 仪器仪表学报]     

On pattern classification of EMG signals for walking motions

We present a method to calssify electromyogram (EMG) signals which are utilized as control signals for a patient-responsive walker-supported system for paraplegics. Patterns of EMG signals for different walking motions are classified via adequate filtering, real EMG signal extraction, AR-modeling, and a modified self-organizing feature map (MSOFM). In particular, a data-reducing extraction algorithm is employed for real EMG signals. Moreover, MSOFM classifies and determines the results automatically using a fixed map. Finally, the experimental results are presented for validation.     

一种基于模糊聚类的故障诊断方法

电子设备的多个传感器实时反映了设备运行状态,对一种基于模糊聚类的电子设备故障诊断方法进行讨论,针对电子装备多个传感器状态信息采用模糊聚类的方法进行融合,进而提出了对于观测数据运用模糊聚类方法进行故障诊断,推理故障模式的方法。实例证明该模糊聚类方法成功地完成了某电子装备故障诊断的自动推理。该方法可以不依赖于被诊断系统的数学模型进行自适应诊断,实现故障诊断的智能化、自动化。     

An improved time-adaptive self-organizing map for high-speed shape modeling

In this paper, an improved active contour model based on the time-adaptive self-organizing map with a high convergence speed and low computational complexity is proposed. For this purpose, the active contour model based on the original time-adaptive self-organizing map is modified in two ways: adaptation of the speed parameter and reduction of the number of neurons. By adapting the speed parameter, the neuron motion speed is determined based on the distance of each neuron from the shape boundary which results in an increase in the speed of convergence of the contour. Using a smaller number of neurons, the computational complexity is reduced. To achieve this, the number of neurons used in the contour is determined based on the boundary curvature. The proposed model is studied and compared with the original time-adaptive self-organizing map. Both models are used in several experiments including a tracking application. Results reveal the higher speed and very good performance of the proposed model for real-time applications.     

Additive Composition of Supervised Self-Organizing Maps

The learning of complex relationships can be decomposed into several neural networks. The modular organization is determined by prior knowledge of the problem that permits to split the processing into tasks of small dimensionality. The sub-tasks can be implemented with neural networks, although the learning examples cannot be used anymore to supervise directly each of the networks. This article addresses the problem of learning in a modular context, developing in particular additive compositions. A simple rule allows defining efficient training, and combining, for example, several Supervised-SOM networks. This technique is important because it introduces interesting generalizations in many modular compositions, permitting data fusion or sequential combinations of neural networks. This revised version was published online in August 2006 with corrections to the Cover Date.     

Self-Organizing Dynamic Graphs

We propose a new self-organizing neural model that considers a dynamic topology among neurons. This leads to greater plasticity with respect to the self-organizing neural network (SOFM). Theorems are presented and proved that ensure the stability of the network and its ability to represent the input distribution. Finally, simulation results are shown to demonstrate the performance of the model, with an application to colour image compression.     

Clustering properties of hierarchical self-organizing maps

A multilayer hierarchical self-organizing map (HSOM) is discussed as an unsupervised clustering method. The HSOM is shown to form arbitrarily complex clusters, in analogy with multilayer feedforward networks. In addition, the HSOM provides a natural measure for the distance of a point from a cluster that weighs all the points belonging to the cluster appropriately. In experiments with both artificial and real data it is demonstrated that the multilayer SOM forms clusters that match better to the desired classes than do direct SOM's, classical k-means, or Isodata algorithms.     

城市元胞路网下自组织控制规则参数的整定

为解决城市信号自组织控制中,由相邻路口间各自最优通行效率冲突造成的路口群整体通行效率难以继续提升的问题,提出一种城市元胞路网下自组织控制规则参数的整定方法. 首先,利用城市路网元胞传输（CTM）模型模拟路网交通流动态状态信息;然后,基于元胞路网实时信息,以选定局域路网中各路口元胞的自组织控制规则参数为设计空间;最后,建立各路口相互协调下通行量最大化的目标函数,完成各路口自组织控制规则参数的整定. 仿真结果表明:在基于城市元胞路网实时信息条件的整定方法下,不仅解决了自组织控制中相邻路口间互相制约通行效率的问题,并且有效提高了自组织单元中所有路口的通行效率. 该方法为面向复杂城市路网的实时城市交通信号自组织控制系统提供可借鉴的智能化方法与工程化理论.