Linear Programming Boosting via Column Generation

We examine linear program (LP) approaches to boosting and demonstrate their efficient solution using LPBoost, a column generation based simplex method. We formulate the problem as if all possible weak hypotheses had already been generated. The labels produced by the weak hypotheses become the new feature space of the problem. The boosting task becomes to construct a learning function in the label space that minimizes misclassification error and maximizes the soft margin. We prove that for classification, minimizing the 1-norm soft margin error function directly optimizes a generalization error bound. The equivalent linear program can be efficiently solved using column generation techniques developed for large-scale optimization problems. The resulting LPBoost algorithm can be used to solve any LP boosting formulation by iteratively optimizing the dual misclassification costs in a restricted LP and dynamically generating weak hypotheses to make new LP columns. We provide algorithms for soft margin classification, confidence-rated, and regression boosting problems. Unlike gradient boosting algorithms, which may converge in the limit only, LPBoost converges in a finite number of iterations to a global solution satisfying mathematically well-defined optimality conditions. The optimal solutions of LPBoost are very sparse in contrast with gradient based methods. Computationally, LPBoost is competitive in quality and computational cost to AdaBoost.     

Evaluating peer learning and assessment in online collaborative learning environments

Transformation of learning and teaching in higher education now offers greater educational equality through enhanced access and collaboration within the framework of lifelong learning in the digital age. This study aims to evaluate online peer learning and assessment in the collaborative learning process in higher education practices. The study also investigates the impact of online peer learning on the development of skills within collaborative learning through the use of volunteered responses from learners concerning their experiences with and perceptions of online learning. Therefore, a quantitative approach is applied through the administration of a survey with 32 items that is distributed to 715 participants. According to the objective of the study, a set of inferential statistical analyses are performed. The theoretical framework of this study is the CHAT (cultural historical activity theory) which reconstructs the knowledge of learners through the application of the Adobe Connect program to demonstrate how learners can be collaborative and social with their peers in an online context. The results revealed that the collaborative online peer learning process in higher education encourages critical reflection and self-assessment. The study contributes to the understanding of the value of learner satisfaction in online collaborative learning environments through the experiences of learners.     

Simulation of three-dimensional fatigue crack propagation using enriched finite elements

A three-dimensional methodology for simulation of fatigue crack propagation is presented. The method is leveraged by the use of enriched crack tip elements to compute the mixed-mode stress intensity factors. The crack growth model used and the crack propagation life calculation are also described. As examples, fatigue crack propagation of a mode-I surface crack and crack advancements of mixed-mode surface cracks are simulated. The predicted results showed excellent agreement with experimental data from the literature. Thus, it is concluded that the crack propagation method developed allows efficient and accurate simulation of three-dimensional fatigue crack propagation problems.     

Performance of Template School Buildings during Earthquakes in Turkey and Peru

Most of the public school buildings in Turkey and Peru are built according to a small number of template plans. Over the years, these template plans are kept the same while the structural designs are varied with the seismic design codes in force. During recent strong earthquakes in Turkey and Peru, the design concepts and construction styles for these template school buildings have been put to test. In this paper, observed earthquake performances of template reinforced concrete school buildings with moment-frames or moment-frames and shear walls are compared. The comparison reveals choices in design that were successful as well as those that were not. The disastrous results of “captive columns” are demonstrated in illustrations from what has been observed in recent earthquakes in these seismically active countries. It is shown that since 1997 the Peruvian practice has been producing school buildings that perform well during strong earthquakes.     

Sparse Regression Ensembles in Infinite and Finite Hypothesis Spaces

We examine methods for constructing regression ensembles based on a linear program (LP). The ensemble regression function consists of linear combinations of base hypotheses generated by some boosting-type base learning algorithm. Unlike the classification case, for regression the set of possible hypotheses producible by the base learning algorithm may be infinite. We explicitly tackle the issue of how to define and solve ensemble regression when the hypothesis space is infinite. Our approach is based on a semi-infinite linear program that has an infinite number of constraints and a finite number of variables. We show that the regression problem is well posed for infinite hypothesis spaces in both the primal and dual spaces. Most importantly, we prove there exists an optimal solution to the infinite hypothesis space problem consisting of a finite number of hypothesis. We propose two algorithms for solving the infinite and finite hypothesis problems. One uses a column generation simplex-type algorithm and the other adopts an exponential barrier approach. Furthermore, we give sufficient conditions for the base learning algorithm and the hypothesis set to be used for infinite regression ensembles. Computational results show that these methods are extremely promising.     

Supporting OpenMP on Cell

The Cell processor is a heterogeneous multi-core processor with one power processing engine (PPE) core and eight synergistic processing engine (SPE) cores. There is a significant amount of ongoing research in programming models and tools that attempts to make it easy to exploit the computation power of the Cell architecture. In our work, we explore supporting OpenMP on the Cell processor. It is attractive to support OpenMP because programmers can continue using their familiar programming model, and existing code can be re-used. We base our work on IBM’s XL compiler, and developed new components in the XL compiler and a new runtime library. Three major issues are addressed: (1) synchronization support on heterogeneous cores; (2) code generation targeting the different instruction sets; (3) data transfers and implement the OpenMP memory model. We present experimental results for some SPEC OMP 2001 and NAS benchmarks to demonstrate the effectiveness of this approach. A visualization tool based on Paraver is also used to provide some insights into actual thread and synchronization behaviors.     

Solution of one-speed neutron transport equation for strongly anisotropic scattering by TN approximation: Slab criticality problem

In this study, a recently proposed version of Chebyshev polynomial approximation which was used in spectrum and criticality calculations by one-speed neutron transport equation for slabs with isotropic scattering is further developed to slab criticality problems for strongly anisotropic scattering. Backward–forward-isotropic model is employed for the scattering kernel which is a combination of linearly anisotropic and strongly backward–forward kernels. Further to that, the common approaches of using the same functional form for scattering and fission kernels or embedding fission kernel into the scattering kernel even in strongly anisotropic scattering is questioned for T_N approximation via taking an isotropic fission kernel in the transport equation. As a starting point, eigenvalue spectrum of one-speed neutron transport equation for a multiplying slab with different degrees of anisotropy in scattering and for different cross-section parameters is obtained using Chebyshev method. Later on, the spectra obtained for different degree of anisotropies and cross-section parameters are made use of in criticality problem of bare homogeneous slab with strongly anisotropic scattering. Calculated critical thicknesses by Chebysev method are almost in complete agreement with literature data except for some limiting cases. More importantly, it is observed that using a different kernel (isotropic) for fission rather than assuming it equal to the scattering kernel which is a more realistic physical approach yields in deviations in critical sizes in comparison with the values presented in literature. This separate kernel approach also eliminates the slow convergency and/or non-convergent behavior of high-order approximations arising from unphysical eigenspectrum calculations.     

Comparison of thermochemical conversion processes of biomass to hydrogen-rich gas mixtures

Hydrogen can be produced from biomass materials via thermochemical conversion processes such as pyrolysis, gasification, steam gasification, steam-reforming, and supercritical water gasification (SCWG) of biomass. In general, the total hydrogen-rich gaseous products increased with increasing pyrolysis temperature for the biomass sample. The aim of gasification is to obtain a synthesis gas (bio-syngas) including mainly H₂ and CO. Steam reforming is a method of producing hydrogen-rich gas from biomass. Hydrothermal gasification in supercritical water medium has become a promising technique to produce hydrogen from biomass with high efficiency. Hydrogen production by biomass gasification in the supercritical water (SCW) is a promising technology for utilizing wet biomass. The effect of initial moisture content of biomass on the yields of hydrogen is good.     

Sustainable rural bioenergy production for developing countries

Bioenergy is a renewable energy source made from biomass, which are organic materials such as plants and animals. Until enough biomass resources to ensure energy demand in the world is available, the bioenergy obtained from biomass, there may be used for heat, electrical and transport. Main biomass thermo-chemical conversion technologies are pyrolysis, gasification, and liquefaction. Biomass can be burned to produce heat and electricity, changed to gas-like fuels such as methane, hydrogen, and carbon monoxide, or changed to a liquid fuel. Modern biomass can be used for the generation of electricity and heat using modern conversion technologies. Technological advances have made modern biomass cogeneration plants cleaner, more efficient, and, under certain conditions, cost-effective as compared to public utility grids and fossil-fuel boilers or generators. Biomass can be converted to liquid biofuels: bioethanol and biodiesel. Two biofuels are becoming more and more attractive and competitive as complementary to or substitutions for petroleum basic products, due to their economic and environmental benefits.