Optimization with regularization to create sensible vertical alignments in road design

Iannantuono, Alexander; Hare, Warren; Lucet, Yves

doi:10.1016/j.dajour.2023.100183

Cited by 4 publications

(4 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Optimization is the process of finding the best solution to a problem among a set of alternative solutions under some predefined conditions. Optimization problems arise in all branches of engineering including electrical, [65][66][67][68][69][70][71][72][73][74][75] mechanical, [76][77][78][79][80][81][82][83][84][85][86][87][88][89][90][91][92][93] and structural [94][95][96][97][98][99][100][101][102] engineering. Due to the simultaneous pursuit of several goals, often with conflicting outcomes, multi-objective optimization problems are generally more complex than single-objective problems.…”

Section: Multi-objective Optimization Methodsmentioning

confidence: 99%

A multi‐objective optimization approach to designing window and shading systems considering building energy consumption and occupant comfort

Nazari

Mohammadi

Sareh

2023

Engineering Reports

View full text Add to dashboard Cite

The energy performance of a building has a significant impact on the environment as well as the comfort of its occupants. Given that window systems and control elements such as shading devices play a critical role in a building's energy consumption and comfort, this article presents an investigation into the optimization of windows in four different orientations, along the four cardinal directions, for a typical office room in Tehran. The objective is to reduce cooling, heating, and lighting energy consumption while improving occupant comfort simultaneously, using the NSGA‐II algorithm as a multi‐objective optimization method. To this end, first, an investigation into the effects of various parameters on total building energy consumption and occupant comfort is conducted. Subsequently, each parameter is evaluated in detail concerning its impact on each façade. As the final step, for each façade, the optimal solutions and the most undesirable scenarios are determined. The results, in which the possibility of glare is also considered, can be used by architects and designers for making informed design decisions. The results show that, in all orientations, the number of slats and their distance from the wall are the most effective parameters of shading configurations. Although the eastern and western windows are larger in this study, visual discomfort can be controlled using suitable shadings to achieve acceptable levels of visual comfort. Furthermore, north façades provide the least amount of thermal comfort and consume the least amount of energy while experiencing glare for longer periods.

show abstract

Section: Multi-objective Optimization Methodsmentioning

confidence: 99%

A multi‐objective optimization approach to designing window and shading systems considering building energy consumption and occupant comfort

Nazari

Mohammadi

Sareh

2023

Engineering Reports

View full text Add to dashboard Cite

show abstract

“…Based on the 6 types of line element combinations, any point coordinate in the space along the highway center line can be determined by algebraic representation. For example, the equations of a horizontal spiral or circular curve with a vertical parabola (type SP or CP) can be expressed as formula (9). Besides, the diferent manifestations of line segments on diferent planes (xy and zy planes) are defned into four types (T, S, C, and P) to describe the changes in the curvature of a line segment.…”

Section: Parabolamentioning

confidence: 99%

“…How to comprehensively consider the coordination of horizontal and vertical alignments is challenging. Several studies have begun to contemplate and investigate combined highway alignment design [9][10][11]. To optimise highway design, Wang et al [7] and Zhou et al [12] created a method for constructing a 3D model of highway alignments using parameter programming.…”

Section: Introductionmentioning

confidence: 99%

Safety Evaluation for Highway Geometric Design Based on Spatial Path Properties

Wang

2023

Journal of Advanced Transportation

View full text Add to dashboard Cite

Safety is an important aspect of road design. In highway geometric design, road engineers use a two-stage design method due to its convenience, but the available two-dimensional design tools on the market are believed to impose limitations. Horizontal and vertical alignment parameters are considered and determined at the designer’s discretion, potentially downplaying the three-dimensional characters of spatial curves. This study focuses on the three-dimensional characteristics of highway alignments and investigates a safety evaluation method to establish the relationship between crash rate and spatial curve properties. This will necessitate an analytical investigation into the effects of higher-order properties, such as curvature and torsion, on the geometry of spatial Cartesian curves. First, these combinations of horizontal and vertical alignments were categorized into six classifications, each with its own spatial expression in mathematical form. After manipulating the curvature and torsion of the spatial curve algebraically, the correlation between geometric design variables and crash rate was ultimately established. A few cases involving geometric design data and crash facts were utilized for verification. The results revealed a considerable positive correlation between curvature or torsion variance and crashes per million vehicles kilometers, as a slight difference between curvature and torsion could also be spotted. And curvature distribution is correlated with collision frequency more closely than torsion spatial variation.

show abstract

“…Additionally, a study on optimizing regularization in DRT illustrates that lasso helps determine relevant peaks in the graphical analysis (Saccoccio et al, 2014). Lasso can also assist variation regularization, a technique effective in image diagnosis and retaining critical structural information, with results showing that a L1 and total variation Quasi-Network Flow model was promising in creating desirable road profiles and reducing the waviness of vertical road alignment in case studies on existing roads (Iannantuono et al, 2023). Additionally, (Gilbraith et al, 2021) find that a lasso model performs slightly better than a ridge and is more favorable in the elastic net model than a ridge.…”

Section: Introductionmentioning

confidence: 99%

Optimizing Linear Regression Models with Lasso and Ridge Regression: A Study on UAE Financial Behavior during COVID-19

Safi,

Alsheryani,

Alrashdi

et al. 2023

Migrat. Lett.

View full text Add to dashboard Cite

This study examines the way individuals in the United Arab Emirates handled their finances during the COVID-19 pandemic, with a focus on optimizing linear regression models utilizing Lasso and Ridge Regression methods. Using the World Bank's enormous Global Findex dataset, we navigated the obstacles of multicollinearity and missing values. Our investigation showed that specific economic indicators and demographic characteristics, including gender and educational attainment, are crucial in affecting financial choices during crises. Our study carefully analyzed the performance of Lasso and Ridge Regression in the context of the Global Findex dataset. Ridge Regression was outperformed by Lasso, which is renowned for its feature selection and complexity reduction abilities. This research provides a comprehensive knowledge of the way advanced regression approaches might improve predictive modeling in such settings, shedding light on the complex dynamics of financial activity during a worldwide crisis.

show abstract

Optimization with regularization to create sensible vertical alignments in road design

Cited by 4 publications

References 35 publications

A multi‐objective optimization approach to designing window and shading systems considering building energy consumption and occupant comfort

A multi‐objective optimization approach to designing window and shading systems considering building energy consumption and occupant comfort

Safety Evaluation for Highway Geometric Design Based on Spatial Path Properties

Optimizing Linear Regression Models with Lasso and Ridge Regression: A Study on UAE Financial Behavior during COVID-19

Contact Info

Product

Resources

About