Neural Computing and Applications

Chen, Min-Rong; Lu, Yong-Zai; Yang, Genke

doi: 10.1007/s00521-007-0118-6pmid: N/A

In recent years, a general-purpose local-search heuristic method called Extremal Optimization (EO) has been successfully applied in some NP-hard combinatorial optimization problems. In this paper, we present a novel Pareto-based algorithm, which can be regarded as an extension of EO, to solve multiobjective optimization problems. The proposed method, called Multiobjective Population-based Extremal Optimization (MOPEO), is validated by using five benchmark functions and metrics taken from the standard literature on multiobjective evolutionary optimization. The experimental results demonstrate that MOPEO is competitive with the state-of-the-art multiobjective evolutionary algorithms. Thus MOPEO can be considered as a viable alternative to solve multiobjective optimization problems.

Li, Ning; Lu, Huaxiang

doi: 10.1007/s00521-007-0098-6pmid: N/A

In this paper, a cellular neural network with depressing synapses for contrast-invariant pattern classification and synchrony detection is presented, starting from the impulse model of the single-electron tunneling junction. The results of the impulse model and the network are simulated using simulation program with integrated circuit emphasis (SPICE). It is demonstrated that depressing synapses should be an important candidate of robust systems since they exhibit a rapid depression of excitatory postsynaptic potentials for successive presynaptic spikes.

Ping, Ling; Chun-Guang, Zhou

doi: 10.1007/s00521-007-0097-7pmid: N/A

A novel learning schema SVCMR based on support vector is proposed in this paper to address M-class classification issue. It creates a tree-shaped decision frame where M/2 nodes are constructed with the three-separation model as the basic classifier. A class selection rule is defined to ensure basic classifiers be trained in turn on pair of classes with maximum feature distance. Class contours are extracted as data representatives to reduce training set size. Another point is that parameters involved in SVCMR are learned from data neighborhood, which brings adaptation to various datasets and avoids pricy cost spent on searching parameter spaces. Experiments on real datasets demonstrate the performance of SVCMR can be competitive to those state-of-the-art classifiers but with the higher effectiveness than them.

Shi, Ke; Dong, Yan

doi: 10.1007/s00521-007-0122-xpmid: N/A

Self-organizing overlay networks are emerging as next generation networks capable of adapting to the needs of applications at runtime. Applications performance significantly depends on the structure and behaviors of the underlying self-organizing overlay networks. To achieve desired performance, not only the logical overlay topology but also the behaviors of nodes in this overlay network need to be optimized. Moreover, self-organizing overlay networks are extremely dynamic, unreliable and often large-scale. It is therefore important to design new optimizing approaches to meet these challenges. In this paper, we present an evolutionary optimization methodology for self-organizing overlay network. The optimizations of self-organizing overlay networks are modeled as dynamically evolutionary process, in which the nodes interact with each other, change their internal structures and alter their external links to improve the collective performance. To design appropriate fitness functions and rules that guides the direction of the evolution, overlay network can reach a stable state with desired global application performance eventually. Such a methodology leads to our distributed algorithms for proximity-based overlay topology maintenance and Peer-to-Peer living media streaming, in which every node in the overlay network rewires their behaviors and connectivity according to local available information and embedded rules. These algorithms are shown to perform well using simulations.

Pengjun, Wang; Jingang, Lu; Jian, Xu

doi: 10.1007/s00521-007-0082-1pmid: N/A

A novel Neuron MOS transistor has come into being recently due to the characteristic of controlling the weighted sum of multiple-input gate and capacitance coupling effect in floating gate, as well as the function of saving the data in the floating gate. The Neuron MOS transistor can be used to replace complex operation on threshold in multiple-valued logic. Based on these characteristics, this paper proposes a new method for designing the multiple-valued D/A and A/D converter. The PSPICE simulation suggests that the designed circuit has correctly operational logic function and is characterized in low power consumption.

Zhang, Zhai; Wang, Youren; Yang, Shanshan; Yao, Rui; Cui, Jiang

doi: 10.1007/s00521-007-0095-9pmid: N/A

The properties of self-testing and self-repairing on chip are the ultimate objectives of digital circuit design. Inspiring from the reconfiguration characteristics similar to those found in biological cellular organisms, this paper presents a new digital circuit based on embryonic cellular array, which is capable of implementing self-repairing. The inner architecture and the self-repairing mechanism of this new circuit are expounded, and a design of cells in the array by LUT (look-up table) is particularized in detailed. Lastly, a parallel multiplication circuit is proposed as an example to show the effectiveness and the application of this design in terms of functionality and fault-tolerance.

chunjie, Zhou; chunjie, Xiang; hui, Chen; huajing, Fang

doi: 10.1007/s00521-007-0096-8pmid: N/A

This paper represents a genetic algorithm (GA) based dynamic reconfiguration for networked control systems (NCS) with the objective of minimizing network time-delay. With the development of NCS, it is become more and more important for them to have the minimum time-delay and the ability of dynamic reconfiguration, which can accommodate the changes rapidly, smartly and flexibly. And it is important to find a routing algorithm, which is quicker to reduce the time to update the router and decrease the reconfiguration time as much as possible. In this paper, based on NCS, we discuss the process of GA with specialized encoding, initialization, selection, crossover and mutation. A specialized repair function is used to improve performance. In addition, experiment results are given to illuminate that GA can improve the performance of the NCS.

Han, Seong-Joo; Oh, Se-Young

doi: 10.1007/s00521-006-0079-1pmid: N/A

A new approach to the design of a neural network (NN) based navigator is proposed in which the mobile robot travels to a pre-defined goal position safely and efficiently without any prior map of the environment. This navigator can be optimized for any user-defined objective function through the use of an evolutionary algorithm. The motivation of this research is to develop an efficient methodology for general goal-directed navigation in generic indoor environments as opposed to learning specialized primitive behaviors in a limited environment. To this end, a modular NN has been employed to achieve the necessary generalization capability across a variety of indoor environments. Herein, each NN module takes charge of navigating in a specialized local environment, which is the result of decomposing the whole path into a sequence of local paths through clustering of all the possible environments. We verify the efficacy of the proposed algorithm over a variety of both simulated and real unstructured indoor environments using our autonomous mobile robot platform.

Menke, Joshua; Martinez, Tony

doi: 10.1007/s00521-006-0080-8pmid: N/A

A common statistical model for paired comparisons is the Bradley–Terry model. This research re-parameterizes the Bradley–Terry model as a single-layer artificial neural network (ANN) and shows how it can be fitted using the delta rule. The ANN model is appealing because it makes using and extending the Bradley–Terry model accessible to a broader community. It also leads to natural incremental and iterative updating methods. Several extensions are presented that allow the ANN model to learn to predict the outcome of complex, uneven two-team group competitions by rating individuals—no other published model currently does this. An incremental-learning Bradley–Terry ANN yields a probability estimate within less than 5% of the actual value training over 3,379 multi-player online matches of a popular team- and objective-based first-person shooter.

Chakraverty, Snehashish; Gupta, Pallavi

doi: 10.1007/s00521-007-0093-ypmid: N/A

The accurate long-range forecast of southwest rainfall can have manifold benefits for the country, from disaster mitigation and town planning to crop planning and power generation. In this paper, the rainfall has been modeled using artificial neural network (ANN) with different network configurations. Performance of these networks are compared with some results found in the literature. The networks have also been tested for the data outside the range of the trained data and compared with known results. The present network is found to be better in term of predictions than the previous results by others. Southwest monsoon rainfall over India for 6 years in advance has been predicted.