This paper addresses the problem of finding multiple near-optimal, spatially-dissimilar paths that can be considered as alternatives in the decision making process, for finding optimal corridors in which to construct a new road. We further consider combinations of techniques for reducing the costs associated with the computation and increasing the accuracy of the cost formulation. Numerical results for five algorithms to solve the dissimilar multipath problem show that a "bidirectional approach" yields the fastest running times and the most robust algorithm. Further modifications of the algorithms to reduce the running time were tested and it is shown that running time can be reduced by an average of 56% without compromising the quality of the results.
Optimization of three-dimensional road alignments is a nonlinear non-convex optimization problem. The development of models that fully optimize a three-dimensional road alignment problem is challenging due to numerous factors involved and complexities in the geometric specification of the alignment. In this study, we developed a novel bi-objective optimization approach to solve a three dimensional road alignment problem where the horizontal and vertical alignments are optimized simultaneously. Two conflicting cost objective functions, earthwork cost and the utility cost, are cast in a bi-objective optimization problem. We numerically compare several multiobjective optimization solvers, and find that it is possible to determine the Pareto front in a reasonable time.good road alignments and approximate construction costs have been developed [23]. The automation of the road design problem reduces the tedious and error-prone manual tasks, most notably drafting [27]. In addition, this procedure allows the use of optimization techniques in search of a good alignment [38]. Optimization techniques save design time and provide the decision maker with powerful tools that search for an alignment with minimum cost from a large number of alternative alignments. In fact, optimization of road alignment can yield considerable savings in construction costs when compared with unoptimized design procedures [38].The road design problem can be broken down into three interconnected stages: the horizontal alignment, the vertical alignment, and the earthwork [18]. The horizontal alignment is a bird's eye view of a road trajectory. A typical horizontal alignment is composed of a sequence of tangents, circular curves, and transition curves. Transition curves have the property that the radius of curvature changes progressively along them. The main considerations in horizontal alignment design are that it should avoid lands which are restricted or expensive to purchase, obstacles which present engineering difficulties, and ground which may involve large amount of earthwork. The cost of road construction for the horizontal alignment problem depends on the cost of acquiring land and on the output of the vertical alignment stage [18]. Optimization of the horizontal alignment seeks a low cost route while adhering to the design standards and reducing environmental impacts [1]. However, optimization of horizontal alignment should also seek a highly utile route. These two goals may often be in conflict with each other. In the literature, the following models have been developed for optimizing horizontal alignments: calculus of variation [37], network optimization [40], dynamic programming [38], and genetic algorithms [24]. Detailed discussion on the advantages and disadvantage of these methods can be found in [22].The vertical alignment is the view of the centreline of the road when seen along the longitudinal cross-section of the road. A typical vertical alignment is composed of straight sections known as vertical tangents and parabolic curves, n...
As interest in machine learning and its applications becomes more widespread, how to choose the best models and hyper-parameter settings becomes more important. This problem is known to be challenging for human experts, and consequently, a growing number of methods have been proposed for solving it, giving rise to the area of automated machine learning ( AutoML ). Many of the most popular AutoML methods are based on Bayesian optimization, which makes only weak assumptions about how modifying hyper-parameters effects the loss of a model. This is a safe assumption that yields robust methods, as the AutoML loss landscapes that relate hyper-parameter settings to loss are poorly understood. We build on recent work on the study of one-dimensional slices of algorithm configuration landscapes by introducing new methods that test n -dimensional landscapes for statistical deviations from uni-modality and convexity, and we use them to show that a diverse set of AutoML loss landscapes are highly structured. We introduce a method for assessing the significance of hyper-parameter partial derivatives, which reveals that most (but not all) AutoML loss landscapes only have a small number of hyper-parameters that interact strongly. To further assess hyper-parameter interactions, we introduce a simplistic optimization procedure that assumes each hyper-parameter can be optimized independently, a single time in sequence, and we show that it obtains configurations that are statistically tied with optimal in all of the n -dimensional AutoML loss landscapes that we studied. Our results suggest many possible new directions for substantially improving the state of the art in AutoML.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.