A Tournament of Transformation Models: B-Spline-based vs. Mesh-based Multi-Objective Deformable Image Registration

The transformation model is an essential component of any deformable image registration approach. It provides a representation of physical deformations between images, thereby defining the range and realism of registrations that can be found. Two types of transformation models have emerged as popular choices: B-spline models and mesh models....

A Hybrid Approach for Considering Topography in Graph-Based Optimization of Water Distribution Networks

Water distribution networks (WDNs) are a vital component of urban water infrastructure. They transport water from production sites (sources) to spatially distributed consumers (sinks). Multiobjective optimization procedures are often used to minimize construction costs and at the same time maximize the resilience of such systems, which is...

Evolvability degeneration in multi-objective genetic programming for symbolic regression

Genetic programming (GP) is one of the best approaches today to discover symbolic regression models. To find models that trade off accuracy and complexity, the non-dominated sorting genetic algorithm II (NSGA-II) is widely used. Unfortunately, it has been shown that NSGA-II can be inefficient: in early generations, low-complexity models over...

Training for Implicit Norms in Deep Reinforcement Learning Agents through Adversarial Multi-Objective Reward Optimization

We propose a deep reinforcement learning algorithm that employs an adversarial training strategy for adhering to implicit human norms alongside optimizing for a narrow goal objective. Previous methods which incorporate human values into reinforcement learning algorithms either scale poorly or assume hand-crafted state features. Our algorithm...

Analysis of Dynamic Charging Performances of Optimized Inductive Power Transfer Couplers

This paper aims to investigate the dynamic charging performance of an 11 kW dynamic inductive power transfer (DIPT) system. First, a multi-objective optimization (MOO) method is proposed to find the Pareto front of the DD charging pad. Then, the optimal design with a 96.82% efficiency is selected as the target design for the DIPT system....

Impacts of problem scale and sampling strategy on surrogate model accuracy: An application of surrogate-based optimization in building design

Surrogate-based Optimization is a useful approach when the objective function is computationally expensive to evaluate, compared to Simulation-based Optimization. In the surrogate-based method, analytically tractable “surrogate models” (also known as “Response Surface Models — RSMs” or “metamodels”), are constructed and validated for each...

A Sound Working Environment: Optimizing the Acoustic Properties of Open Plan Workspaces Using Parametric Models

Optimizing the acoustic environment of open plan offices is a complex task due to the large number of design parameters that must be considered. In current practice, acoustic analysis – even in a simplified form – is not naturally integrated into the design process of office spaces. Applying digital acoustic simulation in architectural design...

Application of Surrogate Models for Building Envelope Design Exploration and Optimization

Building performance simulations are usually timeconsuming. They may account for the major portion of time spent in Computational Design Optimization (CDO), for instance, annual hourly daylight and energy simulations. In this case, the optimization may become less efficient or even infeasible within a limited time frame of real-world projects,...

Multi-Objective Optimization and Decision Aid for Spread Footing Design in Uncertain Environment

This paper aims to present an evaluation, optimization and comparison approach for the design of isolated spread foundations in an uncertain environment. The choice of the optimal solution is made according to the decision-maker's preferences to find the best compromise between various conflicting objectives. Furthermore, this approach takes...

Multi-objective and multidisciplinary design optimization of large sports building envelopes: A case study

Currently, in the conceptual envelope design of sports facilities, multiple engineering performance feedbacks (e.g. daylight, energy and structural performance) are expected to assist architectural design decision-making. In general, it is known as Building Performance Optimization in the conceptual architectural design phase. Essentially, it...

A Multi-Pathfinder for Developing Adaptive Robust Policies in System Dynamics

Adaptivity is essential for dynamically complex and uncertain systems. Adaptive policymaking is an approach to design policies that can be adapted over time to how the future unfolds. It is crucial for adaptive policymaking to specify under what conditions and how to adapt the policy. The performance of adaptive policy is critically depended on...

The trade-off between CO2 emissions and logistics costs based on multi-objective optimization

This paper develops a decision-support tool for estimating the balanced market shares of given freight transport systems operating in a given network, satisfying both the minimum costs and the Carbon-Dioxide (CO2) emission requirements. Since CO2 constraints in logistics markets need to be realized in the near future, a modal shift in freight...

A cognitive system based on fuzzy information processing and multi-objective evolutionary algorithm

A cognitive system is presented, which is based on coupling a multi-objective evolutionary algorithm with a fuzzy information processing system. The aim of the system is to identify optimal solutions for multiple criteria that involve linguistic concepts, and to systematically identify a most suitable solution among the alternatives. The...

Multi-objective optimization in the construction industry

Multi-objective-optimization-based positioning of houses in a residential neighborhood is described. The task is the placement of the buildings in a favorable configuration constrained by two objectives, which are garden performance and visual privacy performance requirements. The method used is evolutionary computation with the Pareto front...

Multi-objective design exploration using efficient global optimization

Multi-Objective Design Exploration (MODE) and its application are presented. MODE reveals the structure of the design space from the trade-off information and visualizes it as a panorama for Decision Maker. As an optimizer for MODE, Efficient Global Optimization (EGO) based on the Kriging model has been extended to Multi-EGO to solve multi...