用Hopfield模型求解组合优化问题的拟人策略

文章对Hopfield网络状态的更新准则，提出了一个自适应的拟人策略。数值模拟表明，引入拟人策略的Hopfield模型对求解组合优化问题非常有效。     

Scheduling flow shops in the environment of multi-functional machine tools

The concept of virtual machine tool (VMT) is introduced in this paper to specify machining resources of multi-functional machine tools. A two-level model for makespan minimization in a flow shop is developed in multi-functional machine tool environments. The model is first optimized with an Hopfield neural network to find the optimal processing sequence for components to visit all the necessary VMTs. Secondly, according to a set of shop floor control rules, the VMTs for components machining are matched with real machine tools. This procedure is driven by the events taking place in components machining, such as the arriving or the finishing of a component. Numerical experiments are conducted in a number of flow shop scheduling problems up to 8×8 and the mean relative optimizing rate is employed to assess the results of numerical experiments.     

基于CHNN聚类算法的款式部件生成模型

对智能化服装款式设计系统中的款式部件的自动获取功能进行了研究.采用基于连续Hopfield神经网络(CHNN)的聚类算法提出了一个款式部件的风格生成模型.提取表现部件造型特征的特征要素构造一个空间点集,利用CHNN网络对该点集进行聚类,分析部件类别与款式设计风格之间的关系,建立基于款式风格设计的部件搭配规则.并将该模型应用于款式的衣片部件上,实现了衣片部件的聚类.实验结果表明,该模型设计合理,分类清晰,具有可扩展性.     

Optimization with the Hopfield network based on correlated noises: Experimental approach

This paper presents two simple optimization techniques based on combining the Langevin Equation with the Hopfield Model. Proposed models – referred as stochastic model (SM) and pulsed noise model (PNM) – can be regarded as straightforward stochastic extensions of the Hopfield optimization network. Both models follow the idea of stochastic neural network (Levy and Adams, IEEE Conference on Neural Networks, vol. III, San Diego, USA, 1987, pp. 681–689) and diffusion machine (Wong, Algorithmica 6 (1991) 466–478). They differ form the referred approaches by the nature of noises and the way of their injection. Optimization with stochastic model, unlike in the previous works, in which δ-correlated Gaussian noises were considered, is based on Gaussian noises with positive autocorrelation times. This is a reasonable assumption from a hardware implementation point of view. In the other model – pulsed noise model, Gaussian noises are injected to the system only at certain time instances, as opposed to continuously maintained δ-correlated noises used in the previous related works. In both models (SM and PNM) intensities of injected noises are independent of neurons’ potentials. Moreover, instead of impractically long inverse logarithmic cooling schedules, the linear cooling is tested. With the above strong simplifications neither SM nor PNM is expected to rigorously maintain thermal equilibrium (TE). However, numerical tests based on the canonical Gibbs–Boltzmann distribution show, that differences between rigorous and estimated values of TE parameters are relatively low (within a few percent). In this sense both models are said to perform quasithermal equilibrium. Optimization performance and quasithermal equilibrium properties of both models are presented based on the travelling salesman problem (TSP).     

Noise removal using hysteretic Hopfield tunnelling network in message transmission systems

A novel approach of two-tier noise removal scheme for message transmission systems is proposed with hysteretic Hopfield tunnelling network (HHTN). The proposed system increases the security of messages and reduces the complexity of recognition of characters due to external distortion or diffusion. Though there are many error detection codes, these codes request retransmission when there is an error. If the error rate is high the number of retransmissions is high which causes a delay in data communication. Kim et al. [Y.S. Kim, Y.M. Kim, J.Y. Choi, and D.K. Baik, Information hiding system stegowaveK for improving capacity, Parallel Distributed Comput. (2003), pp. 423–426] proposed an alternate two-tier communication system with code division multiple access (CDMA) technology and a mapping table. When HHTN is added to the system, the learning ability enables the network to remember patterns and enhances the speed. But when images of larger size are stored, the network fails to recognize, which leads to further research in this area.     

Improved watershed transform for tumor segmentation: Application to mammogram image compression

In this study, an automatic image segmentation method is proposed for the tumor segmentation from mammogram images by means of improved watershed transform using prior information. The segmented results of individual regions are then applied to perform a loss and lossless compression for the storage efficiency according to the importance of region data. These are mainly performed in two procedures, including region segmentation and region compression. In the first procedure, the canny edge detector is used to detect the edge between the background and breast. An improved watershed transform based on intrinsic prior information is then adopted to extract tumor boundary. Finally, the mammograms are segmented into tumor, breast without tumor and background. In the second procedure, vector quantization (VQ) with competitive Hopfield neural network (CHNN) is applied on the three regions with different compression rates according to the importance of region data so as to simultaneously reserve important tumor features and reduce the size of mammograms for storage efficiency. Experimental results show that the proposed method gives promising results in the compression applications.     

Associative Memory Design via Path Embedding into a Graph

A graph theoretical procedure for storing a set of n-dimensional binary vectors as asymptotically stable equilibrium points of a discrete Hopfield neural network is presented. The method gives an auto-associative memory which stores an arbitrary memory set completely. Spurious memories might occur only in a small neighborhood of the original memory vectors, so cause small errors.     

用Hopfield神经网络反演横向各向同性介质参数

本文用Ｈｏｐｆｉｅｌｄ神经网络对横向各向同性介质的各向异性参数反演作了初步研究,首先简述Ｈｏｐｆｉｅｌｄ神经网络,说明该网络具有能量单调下降但并不保证收敛到能量最小的特性,然后详细推导出了运行网络的权系数和输入项公式。     

新型虚拟磁链定向的Hopfield神经网络谐波电流检测

谐波电流检测的准确性和快速性直接影响有源电力滤波器的补偿精度。相较于锁相环,虚拟磁链在电网电压波动的情况下也能准确定向,而且响应速度更快。文中采用由高通滤波器和变换坐标系组成的新型辨识算法,改善了虚拟磁链中由积分器引起的相位误差。Hopfield神经网络利用新型虚拟磁链观测到的电网电压定向角,对谐波电流进行检测。该方法引入能量函数构造反馈型神经网络,通过不断反馈收敛最后达到平衡,以实现对谐波电流的检测。仿真结果表明基于虚拟磁链的Hopfield神经网络方法能同时快速准确地检测出基波电流、总谐波电流和各次谐波电流,而且在负载突变、电压波动的情况下,与基于瞬时无功功率理论的i_p-i_q法相比响应速度更快,准确性更高,具有更好的鲁棒性。