Publications
Chosen filters:
Chosen filters:
Anticipating heat accumulation in laser oxygen cutting of thick metal plates KU Leuven
Excessive heating of the metal sheet during laser oxygen cutting can cause quality deterioration and even lead to cut loss and possible machine idle time, especially for cutting of thick plates, where the cutting speed is slower. There are at least three different strategies to handle quality deterioration by heat accumulation in flame laser cutting of thick plates: to optimize the process parameters for preheated zones, to generate tool paths ...
Introduction. Privacy, due process and the computational turn at a glance: pointers for a hurried reader Vrije Universiteit Brussel
Introduction to the volume
\"Identity in a World of Ambient Intelligence\" Vrije Universiteit Brussel
Like its ancestor "ubiquitous Computing," "ambient Intelligence" has been envisioned as a calm technology, staying in the periphery of our attention. Many ambient intelligent (AmI) devices interact with their users using a logic of anticipatory personalization to create the impression of an environment silently doing the right thing by itself. However, the machine profiling that underlies this personalized anticipation is not transparent in its ...
Improving Cluster-based Methods for Usage Anticipation by the Application of Data Transformations KU Leuven
© 2018 The Authors Published by Elsevier B.V. The wide adoption of Internet of Things (IoT) infrastructure in recent years has allowed capturing data from systems that make intensive use of electrical power or consumables typically aiming to create predictive models to anticipate a system's demand and to optimize system control, assuring the service while minimizing the overall consumption. Several methods have been presented to perform usage ...
Machine learning for crop production forecasting from time series of low resolution satellite imagery KU Leuven
Accurate forecasts of local and regional agricultural production are essential for agricultural market contractors and operators to assist prize agreements as early as possible in the crop growing season. These forecasts are also helpful for societies to anticipate to limited food availability. Satellite remote sensing is a fairly recent but already established technology for large-scale agricultural production forecasting thanks to its ability ...
Micro Electrical Discharge Machining on Ceramic Materials and Composites (Micro-vonkerosie van keramische materialen en composieten) KU Leuven
In this dissertation, the application of micro-EDM to machine ceramic composites like Si3N4-TiN, Silicon infiltrated silicon carbide (SiSiC) and sintered SiC (SSiC) is investigated. These ceramic composites are difficult to be machined at microscale by conventional processing techniques. More specifically, the influence of process parameters on machining performances such as machining speed, tool wear and surface quality is studied in detail ...
PUF Constructions with Limited Information Leakage KU Leuven
Silicon Physical Unclonable Functions (PUFs) arose from MIT research more than 15 years ago with great fanfare and promise. The idea was to use tiny electronic circuits to detect manufacturing variation on chip instead of using external test equipment, and produce a large number of challenge/response pairs (CRPs) that can be used to uniquely authenticate a silicon device. Unlike a normal mathematical function, a PUF is a physical function. When ...
A Smart Machine for Selective Laser Melting - A Controlled & Synchronized System Approach KU Leuven
The main objective of this dissertation is to improve the robustness of the Selective Laser Melting (SLM) process and eliminate machine variant quality behavior. This is realized by examining the components that are mainly responsible to form a melt-pool and thus directly influence the melt pool quality. To improve the robustness of the SLM process, the galvano scanner and laser source are dynamically improved and synchronized to form a ...
Troubleshooting an Intrusion Detection Dataset: the CICIDS2017 Case Study KU Leuven
Numerous studies have demonstrated the effectiveness of machine learning techniques in application to network intrusion detection. And yet, the adoption of machine learning for securing large-scale network environments remains challenging. The community acknowledges that network security presents unique challenges for machine learning, and the lack of training data representative of modern traffic remains one of the most intractable issues. New ...