A Novel Approach to Simultaneous Selection of Surrogate Models, Constitutive Kernels, and Hyper-parameter Values

2014 ◽  
Author(s):  
Ali Mehmani ◽  
Souma Chowdhury ◽  
Jie Zhang ◽  
Achille Messac
Keyword(s):  
Surrogate Models ◽  
Novel Approach ◽  
Simultaneous Selection ◽  
Parameter Values ◽  
Selection Of

Stable and Supported Semantics in Continuous Vector Spaces

2020 ◽  
Author(s):  
Yaniv Aspis ◽  
Krysia Broda ◽  
Alessandra Russo ◽  
Jorge Lobo
Keyword(s):  
Logic Program ◽  
Matrix Multiplication ◽  
Vector Spaces ◽  
Continuous Space ◽  
Continuous Vector ◽  
Novel Approach ◽  
Gradient Based ◽  
Normal Logic ◽  
Parameter Values ◽  
Normal Logic Program

We introduce a novel approach for the computation of stable and supported models of normal logic programs in continuous vector spaces by a gradient-based search method. Specifically, the application of the immediate consequence operator of a program reduct can be computed in a vector space. To do this, Herbrand interpretations of a propositional program are embedded as 0-1 vectors in $\mathbb{R}^N$ and program reducts are represented as matrices in $\mathbb{R}^{N \times N}$. Using these representations we prove that the underlying semantics of a normal logic program is captured through matrix multiplication and a differentiable operation. As supported and stable models of a normal logic program can now be seen as fixed points in a continuous space, non-monotonic deduction can be performed using an optimisation process such as Newton's method. We report the results of several experiments using synthetically generated programs that demonstrate the feasibility of the approach and highlight how different parameter values can affect the behaviour of the system.

Development of a Performance-Related Framework for Asphalt Mixture Design for the Illinois Tollway

2021 ◽  
pp. 036119812110148
Author(s):  
Behnam Jahangiri ◽  
Punyaslok Rath ◽  
Hamed Majidifard ◽  
William G. Buttlar
Keyword(s):  
Asphalt Mixture ◽  
Field Performance ◽  
Compact Tension ◽  
T Test ◽  
Novel Approach ◽  
Final Adjustment ◽  
Development And Validation ◽  
High Degree ◽  
Selection Of

Various agencies have begun to research and introduce performance-related specifications (PRS) for the design of modern asphalt paving mixtures. The focus of most recent studies has been directed toward simplified cracking test development and evaluation. In some cases, development and validation of PRS has been performed, building on these new tests, often by comparison of test values to accelerated pavement test studies and/or to limited field data. This study describes the findings of a comprehensive research project conducted at Illinois Tollway, leading to a PRS for the design of mainline and shoulder asphalt mixtures. A novel approach was developed, involving the systematic establishment of specification requirements based on: 1) selection of baseline values based on minimally acceptable field performance thresholds; 2) elevation of thresholds to account for differences between short-term lab aging and expected long-term field aging; 3) further elevation of thresholds to account for variability in lab testing, plus variability in the testing of field cores; and 4) final adjustment and rounding of thresholds based on a consensus process. After a thorough evaluation of different candidate cracking tests in the course of the project, the Disk-shaped Compact Tension—DC(T)—test was chosen to be retained in the Illinois Tollway PRS and to be presented in this study for the design of crack-resistant mixtures. The DC(T) test was selected because of its high degree of correlation with field results and its excellent repeatability. Tailored Hamburg rut depth and stripping inflection point thresholds were also established for mainline and shoulder mixes.

scholarly journals Gradient-based selection of cross sections: a novel approach for optimal frame structure design

2017 ◽  
Vol 56 (5) ◽  
pp. 959-972 ◽  
Author(s):  
Christian Krogh ◽  
Mathias H. Jungersen ◽  
Erik Lund ◽  
Esben Lindgaard
Keyword(s):  
Cross Sections ◽  
Structure Design ◽  
Frame Structure ◽  
Novel Approach ◽  
Gradient Based ◽  
Selection Of

scholarly journals A novel approach for rapid high-throughput selection of recombinant functional rat monoclonal antibodies

2018 ◽  
Vol 19 (1) ◽  
Author(s):  
Qin Chen ◽  
Shengping Qiu ◽  
Huanhuan Li ◽  
Chaolong Lin ◽  
Yong Luo ◽  
...  
Keyword(s):  
Monoclonal Antibodies ◽  
High Throughput ◽  
Novel Approach ◽  
Selection Of

scholarly journals Analysis of dengue model with fractal-fractional Caputo–Fabrizio operator

2020 ◽  
Vol 2020 (1) ◽  
Author(s):  
Fatmawati ◽  
Muhammad Altaf Khan ◽  
Cicik Alfiniyah ◽  
Ebraheem Alzahrani
Keyword(s):  
Statistical Data ◽  
Dengue Infection ◽  
Fractional Operator ◽  
Novel Approach ◽  
Reduction Number ◽  
Best Fitting ◽  
The Stability ◽  
Parameter Values ◽  
Graphical Illustration ◽  
Stability Results

AbstractIn this work, we study the dengue dynamics with fractal-factional Caputo–Fabrizio operator. We employ real statistical data of dengue infection cases of East Java, Indonesia, from 2018 and parameterize the dengue model. The estimated basic reduction number for this dataset is $\mathcal{R}_{0}\approx2.2020$ R 0 ≈ 2.2020 . We briefly show the stability results of the model for the case when the basic reproduction number is $\mathcal{R}_{0} <1$ R 0 < 1 . We apply the fractal-fractional operator in the framework of Caputo–Fabrizio to the model and present its numerical solution by using a novel approach. The parameter values estimated for the model are used to compare with fractal-fractional operator, and we suggest that the fractal-fractional operator provides the best fitting for real cases of dengue infection when varying the values of both operators’ orders. We suggest some more graphical illustration for the model variables with various orders of fractal and fractional.

scholarly journals Simultaneous Selection of Features and Metric for Optimal Nearest Neighbor Classification

2004 ◽  
Vol 33 (9) ◽  
pp. 2137-2157 ◽  
Author(s):  
David A. Johannsen ◽  
Edward J. Wegman ◽  
Jeffrey L. Solka ◽  
Carey E. Priebe
Keyword(s):  
Nearest Neighbor ◽  
Nearest Neighbor Classification ◽  
Simultaneous Selection ◽  
Neighbor Classification ◽  
Selection Of

Simultaneous selection for high yield and stability in common bean (Phaseolus vulgaris) genotypes

2002 ◽  
Vol 138 (3) ◽  
pp. 249-253 ◽  
Author(s):  
F. MEKBIB
Keyword(s):  
Common Bean ◽  
Genotype By Environment Interaction ◽  
Yield Stability ◽  
High Yield ◽  
Environment Interaction ◽  
Yield Performance ◽  
Simultaneous Selection ◽  
Selection For ◽  
Stability Statistics ◽  
Selection Of

Phenotypic yield stability is a trait of special interest for plant breeders and farmers. This value can be quantified if genotypes are evaluated in different environments. Common bean is the main cash crop and protein source of farmers in many lowland and mid-altitude areas of Ethiopia. An experiment was undertaken to evaluate common bean genotypes for yield performance at Alemaya, Bako and Nazreth in Ethiopia for 3 years. The yield performance of genotypes was subjected to stability analysis and yield-stability statistics were generated to aid the selection of genotypes that were high yielding and very stable. The significant genotype by environment interaction indicated that the relative performance of the varieties altered in the different environments. Genotype yield performance varied ranging from 1511–2216 kg/ha. Simultaneous selection for yield and yield-stability statistics using YS(i) statistics indicated that A 410, GLP x92, Mx-2500-19, G 2816, A-195, 997-CH-1173, Diacol calima, ICA 15541 and AND 635 were both high yielding and stable. Following this study, using farmers’ evaluation and other criteria, GLP x92 and G-2816 were identified as preferred genotypes and were released for further production.

Sign in / Sign up

Export Citation Format

Share Document