Essays about: "convolutions"

Showing result 6 - 10 of 25 essays containing the word convolutions.

  1. 6. Automatic segmentation of microstructures in metals : A computer vision approach

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Oscar Larsen; [2022]
    Keywords : Image Processing; Computer Vision; Machine Learning; Deep Learning; Metallurgy; Segmentation; Bildbehandling; Datorseende; Maskininlärning; Djupinlärning; Metallurgi; Segmentering;

    Abstract : The microstructures of a metal determine the physical, electrical and chemical properties of the metal, and analysis of microstructures is therefore an important part of materials science. Modern microscopes are capable of generating a lot of high-quality micrographs in a short period of time. READ MORE

  3. 7. Classification of ultrasonic signals using machine learning to identify optimal frequency for elongation control : Threaded fastening tools

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Mazen Bahy; [2022]
    Keywords : Machine Learning; Convolutions Neural Network CNN ; Barker signals; Ultrasonic sensors; Clamp-force; Threaded fastening assembly; Maskininlärning; konvolutionellt neuralt nätverk; Barker-signaler; Ultraljudssensorer; klämkraft; Åtdragningsmontering;

    Abstract : Studying the preload in a screw joint has been the focus of today’s industry. The manufacturer reflects that demand by investigating different opportunities and techniques to develop this area. There are four different ways of controlling the tightening of bolts and joints to achieve the required clamp force that can hold for a specific preload. READ MORE

  4. 8. Convolutions on graphs for learning vehicle crash behaviour

    University essay from Göteborgs universitet/Institutionen för data- och informationsteknik

    Author : Daniel Adin; [2021-11-09]
    Keywords : Computer; science; computer science; engineering; graph; convolutions; inite element method; project; thesis;

    Abstract : Convolutional Neural Networks (CNN) have shown successful results in the recent years, especially within the area of image analysis. The idea of learning to predict the result of a crash simulation using machine learning rose from the analogy between images and Finite Element models (FE-models) used in crash simulations. READ MORE

  5. 9. Money Laundering Detection using Tree Boosting and Graph Learning Algorithms

    University essay from KTH/Matematisk statistik

    Author : Rickard Frumerie; [2021]
    Keywords : Tree boosting; XGBoost; graph convolutional networks GCN ; node and edge neural networks NENN ; exploratory data analysis EDA ; anti money laundering AML ; financial graph networks.; Trädalgoritmer; XGBoost; convolutions grafnätverk GCN ; nod och kant neurala nätverk NENN ; utforskande dataanalys; penningtvättsbekämpning AML ; finansiella grafnätverk.;

    Abstract : In this masters thesis we focused on using machine learning methods for detecting money laundering in financial transaction networks, in order to demonstrate that it can be used as a complement or instead of the more commonly used rule based systems. The graph learning method graph convolutional networks (GCN) has been a hot topic in the field since they were shown to scale well with data size back in 2018. READ MORE

  6. 10. GVT-BDNet : Convolutional Neural Network with Global Voxel Transformer Operators for Building Damage Assessment

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Leonardo Remondini; [2021]
    Keywords : Attention Operators; Convolutional Neural Networks CNNs ; Deep Learning; Building Damage Assessment; Generalizability; Global Voxel Transformer Operators GVTOs .; Attention Operators; Convolutional Neural Networks CNNs ; Deep Learning; Building Damage Assessment; Generalizability; Global Voxel Transformer Operators GVTOs .;

    Abstract : Natural disasters strike anywhere, disrupting local communication and transportation infrastructure, making the process of assessing specific local damage difficult, dangerous, and slow. The goal of Building Damage Assessment (BDA) is to quickly and accurately estimate the location, cause, and severity of the damage to maximize the efficiency of rescuers and saved lives. READ MORE