Cooperative, hybrid agent architecture for real-time traffic signal control

This paper presents a new hybrid, synergistic approach in applying computational intelligence concepts to implement a cooperative, hierarchical, multiagent system for real-time traffic signal control of a complex traffic network. The large-scale traffic signal control problem is divided into various subproblems, and each subproblem is handled by an intelligent agent with a fuzzy neural decision-making module. The decisions made by lower-level agents are mediated by their respective higher-level agents. Through adopting a cooperative distributed problem solving approach, coordinated control by the agents is achieved. In order for the multiagent architecture to adapt itself continuously to the dynamically changing problem domain, a multistage online learning process for each agent is implemented involving reinforcement learning, learning rate and weight adjustment as well as dynamic update of fuzzy relations using an evolutionary algorithm. The test bed used for this research is a section of the Central Business District of Singapore. The performance of the proposed multiagent architecture is evaluated against the set of signal plans used by the current real-time adaptive traffic control system. The multiagent architecture produces significant improvements in the conditions of the traffic network, reducing the total mean delay by 40% and total vehicle stoppage time by 50%.     

Global optimisation in neural network training

This paper presents a new neural network training scheme for pattern recognition applications. Our training technique is a hybrid scheme which involves, firstly, the use of the efficient BFGS optimisation method for locating minima of the total error function and, secondly, the use of genetic algorithms for finding a global minimum. This paper also describes experiments that compare the performance of our scheme with three other hybrid schemes of this kind when applied to challenging pattern recognition problems. Experiments have shown that our scheme gives better results than others.     

Robust adaptive spread-spectrum receiver with neural netpreprocessing in non-Gaussian noise

Multiuser communications channels based on code division multiple access (CDMA) technique exhibit non-Gaussian statistics due to the presence of highly structured multiple access interference (MAI) and impulsive ambient noise. Linear adaptive interference suppression techniques are attractive for mitigating MAI under Gaussian noise. However, the Gaussian noise hypothesis has been found inadequate in many wireless channels characterized by impulsive disturbance. Linear finite impulse response (FIR) filters adapted with linear algorithms are limited by their structural formulation as a simple linear combiner with a hyperplanar decision boundary, which are extremely vulnerable to impulsive interference. This raises the issues of devising robust reception algorithms accounting at the design stage the non-Gaussian behavior of the interference. We propose a multiuser receiver that involves an adaptive nonlinear preprocessing front-end based on a multilayer perceptron neural network, which acts as a mechanism to reduce the influence of impulsive noise followed by a postprocessing stage using linear adaptive filters for MAI suppression. Theoretical arguments supported by promising simulation results suggest that the proposed receiver, which combines the relative merits of both nonlinear and linear signal processing, presents an effective approach for joint suppression of MAI and non-Gaussian ambient noise.     

Reducing the complexity of an adaptive radial basis function network with a histogram algorithm

In this paper, a constructive training technique known as the dynamic decay adjustment (DDA) algorithm is combined with an information density estimation method to develop a new variant of the radial basis function (RBF) network. The RBF network trained with the DDA algorithm (i.e. RBFNDDA) is able to learn information incrementally by creating new hidden units whenever it is necessary. However, RBFNDDA exhibits a greedy insertion behaviour that absorbs both useful and non-useful information during its learning process, therefore increasing its network complexity unnecessarily. As such, we propose to integrate RBFNDDA with a histogram (HIST) algorithm to reduce the network complexity. The HIST algorithm is used to compute distribution of information in the trained RBFNDDA network. Then, hidden nodes with non-useful information are identified and pruned. The effectiveness of the proposed model, namely RBFNDDA-HIST, is evaluated using a number of benchmark data sets. A performance comparison study between RBFNDDA-HIST and other classification methods is conducted. The proposed RBFNDDA-HIST model is also applied to a real-world condition monitoring problem in a power generation plant. The results are analysed and discussed. The outcome indicates that RBFNDDA-HIST not only can reduce the number of hidden nodes significantly without requiring a long training time but also can produce promising accuracy rates.

     

Motor fault detection and diagnosis using a hybrid FMM-CART model with online learning

In this paper, a hybrid online learning model that combines the fuzzy min–max (FMM) neural network and the Classification and Regression Tree (CART) for motor fault detection and diagnosis tasks is described. The hybrid model, known as FMM-CART, incorporates the advantages of both FMM and CART for undertaking data classification (with FMM) and rule extraction (with CART) problems. In particular, the CART model is enhanced with an importance predictor-based feature selection measure. To evaluate the effectiveness of the proposed online FMM-CART model, a series of experiments using publicly available data sets containing motor bearing faults is first conducted. The results (primarily prediction accuracy and model complexity) are analyzed and compared with those reported in the literature. Then, an experimental study on detecting imbalanced voltage supply of an induction motor using a laboratory-scale test rig is performed. In addition to producing accurate results, a set of rules in the form of a decision tree is extracted from FMM-CART to provide explanations for its predictions. The results positively demonstrate the usefulness of FMM-CART with online learning capabilities in tackling real-world motor fault detection and diagnosis tasks.     

Generalized Voronoi diagrams for a ladder: II. Efficient construction of the diagram

We present a collection of algorithms, all running in timeO(n ² logn (n) ^o((n)3)) for some fixed integers(where (n) is the inverse Ackermann's function), for constructing a skeleton representation of a suitably generalized Voronoi diagram for a ladder moving in a two-dimensional space bounded by polygonal barriers consisting ofn line segments. This diagram, which is a two-dimensional subcomplex of the dimensional configuration space of the ladder, is introduced and analyzed in a companion paper by the present authors. The construction of the diagram described in this paper yields a motion-planning algorithm for the ladder which runs within the same time bound given above.Work on this paper has been supported in part by Office of Naval Research Grant N00014-82-K-0381, and by grants from the Digital Equipment Corporation, the Sloan Foundation, the System Development Foundation, the IBM corporation, and by National Science Foundation CER Grant No. DCR-8320085. Work by the second author has also been supported in part by a grant from the US-Israeli Binational Science Foundation.     

Effect of different film preparation procedures on the thermal,morphological and mechanical properties of pure and calcite‐filled HDPE films

The effect of different film preparation procedures on the thermal, morphological and mechanical properties of high density polyethylene (HDPE) films have been studied using differential scanning calorimetry (DSC), wide angle X‐ray diffraction (WAXRD), atomic force microscopy (AFM), scanning electron microscopy (SEM) and ultimate tensile testing. Film preparation procedures included variation in cooling methods, including quenching, forces (fanning) and natural cooling and techniques such as extrusion followed by melt squeezing and compression molding. The heat of fusion (from DSC), the degree of crystallinity (from WAXRD) and the crystallite size (from WAXRD and AFM) were found to be highest for naturally cooled specimens, followed by fan‐cooled and quenched ones. AFM images of surface topology exhibit stacked lamellar morphology for forcefully cooled (fan‐cooled and quenched) samples and spherulitic ‘lozenges’ for naturally cooled ones. The Young's modulus and yield stress [from the universal testing machine (UTM)] were highest for naturally cooled samples, followed by fan‐cooled and quenched ones. Among the calcite‐filled composites, the ‘base film,’ which was prepared by extrusion followed by melt squeezing and natural cooling, exhibited the lowest heat of fusion and degree of crystallinity and a similar crystallite size relative to compression‐molded films. Lower yield stress, tensile strength and Young's modulus and higher elongation at break were observed for the base film in comparison to the naturally cooled composite film. The low degree of crystallinity and crystallite size in the ‘base film’ explain all of its mechanical and morphological properties. © 2003 Wiley Periodicals, Inc. J Appl Polym Sci 91: 1427–1434, 2004     

薯蓣皂甙和甙元的研制

报道了以贵州产三种薯蓣科植物在常压下制薯蓣皂甙元的方法，提出了贵州产黄山药制薯蓣皂甙元的生产工艺路线建议。     

Continuous phenol biodegradation at high concentrations in an immobilized‐cell hollow fiber membrane bioreactor

Phenol degradation at high concentrations was investigated under continuous operation in an immobilized‐cell hollow fiber membrane bioreactor. Pseudomonas putida ATCC49451 was immobilized in asymmetric polysulfone hollow fiber membranes through entrapment within the porous regions and through attachment on the membrane surfaces. Bioreactor performance was assessed based on the startup period, the effect of feed rate (ranging from 21 to 120 mL/h), the relative contribution of the lumen and the shell sides to phenol degradation, the effect of feed phenol concentration (1000–2000 mg/L) and the long‐term operation of the bioreactor. The bioreactor startup was very short, and steady state was accomplished within 160 h. An optimum degradation capacity with respect to phenol loading rate was observed because of the tradeoff in the amount of phenol degraded against the increase in feed rate. It was also found that at higher feed rate, the shell side contributed to a larger proportion of the total phenol degraded compared with the lumen. On the basis of these results, it was found that options abound for the operating conditions of the bioreactor. These can be chosen depending on whether complete phenol degradation or high degradation capacity is desirable. Finally, long‐term sustainable continuous operation of the bioreactor was demonstrated without significant biofilm fouling on the membranes. © 2007 Wiley Periodicals, Inc. J Appl Polym Sci 2007