Genetic Algorithm for Evolving an Objective Function of a Program Synthesizer

Program Synthesis is a challenging problem in Artificial Intelligence. An important element of a program synthesizer is the objective function that guides the combinatorial search for a program that satisfies a given user intent. Given multiple I/O example transformations that correspond to the intended behavior of the program, this function...

OpenAP.top: Open Flight Trajectory Optimization for Air Transport and Sustainability Research

Trajectory optimization has been an active area of research for air transport studies for several decades. But almost all flight optimizers proposed in the literature remain close-sourced, which presents a major disadvantage for the advancement of scientific research. This optimization depends on aircraft performance models, emission models, and...

Flexible well pattern and NPV optimisation on large scale geothermal field development

The Netherlands has set the ambitious goal to be CO2 neutral by 2050 and signed the Paris Treaty in 2015. The contribution of geothermal energy to reaching this goal are outlined in the Masterplan in 2018 which attempts to reduce CO2 emissions. It is imperative to enhance geothermal participation in renewable energy resources, so this thesis...

An improved coherent point drift method for tls point cloud registration of complex scenes

Processing unorganized 3D point clouds is highly desirable, especially for the applications in complex scenes (such as: mountainous or vegetation areas). Registration is the precondition to obtain complete surface information of complex scenes. However, for complex environment, the automatic registration of TLS point clouds is still a...

Towards Seed-Free Music Playlist Generation: Enhancing collaborative Filtering with Playlist Title Information

In this paper, we propose a hybrid Neural Collaborative Filtering (NCF) model trained with a multi-objective function to achieve a music playlist generation system. The proposed approach focuses particularly on the cold-start problem (playlists with no seed tracks) and uses a text encoder employing a Recurrent Neural Network (RNN) to exploit...

Improving model consistency and process realism in conceptual rainfall-runoff models

Hydrological models are used for several purposes, from reservoir management to stormflow prediction. However, their predictive power is often questionable. As most rainfall-runoff models are highly dependent on calibration, models often show deteriorated performance during the validation period. This is caused by too much focus on and trust in...

Mission-driven Resource Management for Reconfigurable Sensing Systems

The spectrum of threats imposed upon modern society has drastically widened in the last decades. One of the required security means is sensor systems. There exist many types of sensors and their capabilities vary, but some of them are reconfigurable and able to provide many functions. Such sensors provide at different time instances a wide range...

Correlation and Error Localization: Analytical versus Experimental Dynamics of a Large Structural Assembly

In the high tech industry the performance of a system generally depends heavily on the system’s structural dynamic behaviour. Relatively small resonating components can alter the dynamics of the assembly significantly. Due to the presence of many small components and limited test resources it is often difficult to find the disruptor. In this...

Aerodynamic optimization of an airfoil using gradient based method

A gradient based method is presented for optimization of an airfoil configuration. The flow is governed by two dimensional, compressible Euler equations. A finite volume code based on unstructured grid is developed to solve the equations. The procedure is carried out for optimizing an airfoil with initial configuration of NACA 0012. The...