Improved sampling of the pareto-front in multiobjective genetic optimizations by steady-state evolution: a pareto converging genetic algorithm

Previous work on multiobjective genetic algorithms has been focused on preventing genetic drift and the issue of convergence has been given little attention. In this paper, we present a simple steady-state strategy, Pareto Converging Genetic Algorithm (PCGA), which naturally samples the solution space and ensures population advancement towards the Pareto-front. PCGA eliminates the need for sharing/niching and thus minimizes heuristically chosen parameters and procedures. A systematic approach based on histograms of rank is introduced for assessing convergence to the Pareto-front, which, by definition, is unknown in most real search problems. We argue that there is always a certain inheritance of genetic material belonging to a population, and there is unlikely to be any significant gain beyond some point; a stopping criterion where terminating the computation is suggested. For further encouraging diversity and competition, a nonmigrating island model may optionally be used; this approach is particularly suited to many difficult (real-world) problems, which have a tendency to get stuck at (unknown) local minima. Results on three benchmark problems are presented and compared with those of earlier approaches. PCGA is found to produce diverse sampling of the Pareto-front without niching and with significantly less computational effort.     

Process standardization for optimal virus recovery and removal of substrate DNA and bovine serum proteins in Vero cell-derived rabies vaccine

Purification of a rabies vaccine by a single zonal centrifugation run was replaced by two runs with optimal standardization of the sucrose density gradient. As a result, significant reductions in the levels of substrate DNA and bovine serum protein in the Vero cell-derived human rabies vaccine were achieved. Following many trials, for the first run, loading of the 3.2-l capacity K-3 rotor with 1800 ml of 60% sucrose solution and 1400 ml of vaccine PBS buffer solution gave a satisfactory linear gradient. However, after the first run, the substrate DNA and bovine serum contents exceeded the required levels. After protamine sulphate and Tween-80 treatment of the concentrated inactivated material, a second run using the same procedure as in the first run was tried. However, these purification procedures resulted in low virus recovery. To achieve optimal virus recovery, and removal of substrate DNA and bovine serum protein, the peak fractions from the first run as indicated by the haemagglutination, sucrose concentration, and optical density values were pooled and the sucrose concentration of the pooled fractions was increased to 60%. A second (flotation) run was then carried out. Using this method, the virus recovery rate was more than 95% that of the first run, and the levels of cellular DNA and bovine serum protein were well within the acceptable limits of less than 100 pg/dose and one part per million, respectively. The substrate DNA was quantified by both radioactive labeling and non-radioactive biotin labeling methods. For the quantification of calf serum protein, a counter-immunoelectrophoresis method was developed and effectively applied. A potency assay was performed using the National Institutes of Health (NIH) and well-standardized in vitro single radial immuno diffusion (SRD) methods. Finally, an immunogenicity study was conducted with human volunteers and the results were confirmed by a rapid fluorescent focus inhibition test (RFFIT).     

Inducing safer oblique trees without costs

Abstract: Decision tree induction has been widely studied and applied. In safety applications, such as determining whether a chemical process is safe or whether a person has a medical condition, the cost of misclassification in one of the classes is significantly higher than in the other class. Several authors have tackled this problem by developing cost-sensitive decision tree learning algorithms or have suggested ways of changing the distribution of training examples to bias the decision tree learning process so as to take account of costs. A prerequisite for applying such algorithms is the availability of costs of misclassification. Although this may be possible for some applications, obtaining reasonable estimates of costs of misclassification is not easy in the area of safety .
This paper presents a new algorithm for applications where the cost of misclassifications cannot be quantified, although the cost of misclassification in one class is known to be significantly higher than in another class. The algorithm utilizes linear discriminant analysis to identify oblique relationships between continuous attributes and then carries out an appropriate modification to ensure that the resulting tree errs on the side of safety. The algorithm is evaluated with respect to one of the best known cost-sensitive algorithms (ICET), a well-known oblique decision tree algorithm (OC1) and an algorithm that utilizes robust linear programming.     

Load Balancing Parallel Explicit State Model Checking

This paper first identifies some of the key concerns about the techniques and algorithms developed for parallel model checking; specifically, the inherent problem with load balancing and large queue sizes resultant in a static partition algorithm. This paper then presents a load balancing algorithm to improve the run time performance in distributed model checking, reduce maximum queue size, and reduce the number of states expanded before error discovery. The load balancing algorithm is based on generalized dimension exchange (GDE). This paper presents an empirical analysis of the GDE based load balancing algorithm on three different supercomputing architectures—distributed memory clusters, Networks of Workstations (NOW) and shared memory machines. The analysis shows increased speedup, lower maximum queue sizes and fewer total states explored before error discovery on each of the architectures. Finally, this paper presents a study of the communication overhead incurred by using the load balancing algorithm, which although significant, does not offset performance gains.     

An analysis for AlGaN/GaN modulation doped field effect transistor using accurate velocity-field dependence for high power microwave frequency applications

An analytical model of Al_0.15Ga_0.85N/GaN modulation doped field effect transistor (MODFET), which uses an accurate velocity field relationship and incorporates the dominant effect of piezoelectric polarization induced charge at the AlGaN/GaN interface is presented. The effect of traps has also been taken into account. The calculated DC characteristics are in excellent agreement with the measured data. The model is extended to predict the microwave performance of the device. High current levels (>500 mA/mm), large transconductance (160.83 mS/mm) and a high cutoff frequency (9.6 GHz) have been achieved analytically and are in close agreement with the experimental data.     

A new grounded lamination gate (GLG) for diminished fringe-capacitance effects in high-/spl kappa/ gate-dielectric MOSFETs

A grounded lamination gate (GLG) structure for high-/spl kappa/ gate-dielectric MOSFETs is proposed, with grounded metal plates in the spacer oxide region. Two-dimensional device simulations performed on the new structure demonstrate a significant improvement with respect to the threshold voltage roll-off with increasing gate-dielectric constant (due to parasitic internal fringe capacitance), keeping the equivalent oxide thickness same. A simple fabrication procedure for the GLG MOSFET is also presented.     

Personal recognition using hand shape and texture.

This paper proposes a new bimodal biometric system using feature-level fusion of hand shape and palm texture. The proposed combination is of significance since both the palmprint and hand-shape images are proposed to be extracted from the single hand image acquired from a digital camera. Several new hand-shape features that can be used to represent the hand shape and improve the performance are investigated. The new approach for palmprint recognition using discrete cosine transform coefficients, which can be directly obtained from the camera hardware, is demonstrated. None of the prior work on hand-shape or palmprint recognition has given any attention on the critical issue of feature selection. Our experimental results demonstrate that while majority of palmprint or hand-shape features are useful in predicting the subjects identity, only a small subset of these features are necessary in practice for building an accurate model for identification. The comparison and combination of proposed features is evaluated on the diverse classification schemes; naive Bayes (normal, estimated, multinomial), decision trees (C4.5, LMT), k-NN, SVM, and FFN. Although more work remains to be done, our results to date indicate that the combination of selected hand-shape and palmprint features constitutes a promising addition to the biometrics-based personal recognition systems.     

Wave Interaction with a Flexible Porous Breakwater in a Two-Layer Fluid

An analysis has been carried out to study the performance of a flexible porous plate breakwater in a two-layer fluid where each fluid is assumed to be of finite depth and the breakwater is extended over the entire water depth. The problem is analyzed in two dimensions with the assumption of small amplitude wave theory and plate response. The effects of both surface and internal waves are taken into account in the present study. The associated mixed boundary value problem is reduced to a linear system of equations by utilizing a more general orthogonal relation along with least squares approximation method. The reflection and transmission coefficients for the surface and internal modes, wave load, and breakwater response are computed for various physical parameters of interest to analyze the efficiency of the flexible porous plate as a breakwater in the two-layer fluid.     

Performance-Based Optimization of Land and Water Resources within Irrigation Schemes. II: Application

The area and water allocation model which uses simulation–optimization technique for optimum allocation of land and water resources to different crops cultivated in different allocation units of the irrigation scheme was modified to include both productivity and equity in the process of developing the allocation plans for optimum productivity and/or maximum equity. This paper illustrates the potential of this approach with the help of a case study on Nazare medium irrigation scheme in India. The allocation plans were developed for optimization of different performance parameters (productivity and equity) for different management strategies based on irrigation amount and irrigation interval and cropping distribution strategies of free and fixed cropping. The results indicated that the two performance objectives productivity and equity conflict with each other and in this case, equitable water distribution may be preferred over free water distribution at the cost of a small loss in productivity. Though these results relate to one case study, they show the value of the approach of incorporating productivity and equity in the allocation process with the help of the simulation-optimization model described in the companion paper.     

Support-vector-based fuzzy neural network for pattern classification

Fuzzy neural networks (FNNs) for pattern classification usually use the backpropagation or C-cluster type learning algorithms to learn the parameters of the fuzzy rules and membership functions from the training data. However, such kinds of learning algorithms usually cannot minimize the empirical risk (training error) and expected risk (testing error) simultaneously, and thus cannot reach a good classification performance in the testing phase. To tackle this drawback, a support-vector-based fuzzy neural network (SVFNN) is proposed for pattern classification in this paper. The SVFNN combines the superior classification power of support vector machine (SVM) in high dimensional data spaces and the efficient human-like reasoning of FNN in handling uncertainty information. A learning algorithm consisting of three learning phases is developed to construct the SVFNN and train its parameters. In the first phase, the fuzzy rules and membership functions are automatically determined by the clustering principle. In the second phase, the parameters of FNN are calculated by the SVM with the proposed adaptive fuzzy kernel function. In the third phase, the relevant fuzzy rules are selected by the proposed reducing fuzzy rule method. To investigate the effectiveness of the proposed SVFNN classification, it is applied to the Iris, Vehicle, Dna, Satimage, Ijcnn1 datasets from the UCI Repository, Statlog collection and IJCNN challenge 2001, respectively. Experimental results show that the proposed SVFNN for pattern classification can achieve good classification performance with drastically reduced number of fuzzy kernel functions.