Sökning: "Graph neighbors"

Visar resultat 1 - 5 av 13 uppsatser innehållade orden Graph neighbors.

  1. 1. Anomaly Detection in the EtherCAT Network of a Power Station : Improving a Graph Convolutional Neural Network Framework

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Niklas Barth; [2023]
    Nyckelord :Unsupervised Learning; Multivariate Time Series; Graph Convolutional Neural Networks; Anomaly Detection; Industrial Control System; EtherCAT; Power Station; Electricity Grid;

    Sammanfattning : In this thesis, an anomaly detection framework is assessed and fine-tuned to detect and explain anomalies in a power station, where EtherCAT, an Industrial Control System, is employed for monitoring. The chosen framework is based on a previously published Graph Neural Network (GNN) model, utilizing attention mechanisms to capture complex relationships between diverse measurements within the EtherCAT system. LÄS MER

  3. 2. RNN-based Graph Neural Network for Credit Load Application leveraging Rejected Customer Cases

    Uppsats för yrkesexamina på avancerad nivå, Högskolan i Halmstad/Akademin för informationsteknologi

    Författare :Oskar Nilsson; Benjamin Lilje; [2023]
    Nyckelord :Machine Learning; Deep Learning; Reject Inference; GNN; GCN; Graph Neural Networks; RNN; Recursive Neural Network; LSTM; Semi-Supervised Learning; Encoding; Decoding; Feature Elimination;

    Sammanfattning : Machine learning plays a vital role in preventing financial losses within the banking industry, and still, a lot of state of the art and industry-standard approaches within the field neglect rejected customer information and the potential information that they hold to detect similar risk behavior.This thesis explores the possibility of including this information during training and utilizing transactional history through an LSTM to improve the detection of defaults. LÄS MER

  4. 3. Semi-supervised Sentiment Analysis for Sentence Classification

    Master-uppsats, Uppsala universitet/Institutionen för lingvistik och filologi

    Författare :Eirini Tsakiri; [2022]
    Nyckelord :sentiment analysis; text classification; semi-supervised learning; machine learning;

    Sammanfattning : In our work, we deploy semi-supervised learning methods to perform Sentiment Analysis on a corpus of sentences, meant to be labeled as either happy, neutral, sad, or angry. Sentence-BERT is used to obtain high-dimensional embeddings for the sentences in the training and testing sets, on which three classification methods are applied: the K-Nearest Neighbors classifier (KNN), Label Propagation, and Label Spreading. LÄS MER

  5. 4. Data Analysis for Hearability and Synchronization in Telecom Systems

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Sun Xin; [2022]
    Nyckelord :5G; Time Synchronization; Machine Learning; Deep Learning; 5G; Tidssynkronisering; Maskininlärning; Djupinlärning;

    Sammanfattning : In a wireless communication system, synchronization is one of the most critical functions. Good timing and synchronization can prevent messages of the communication system from interfering with each other and enable a smooth message transfer. LÄS MER

  7. 5. Reducing Polarization in Opinion Networks in the Presence of Stubborn Leaders

    Uppsats för yrkesexamina på avancerad nivå, Lunds universitet/Institutionen för reglerteknik

    Författare :Samuel Selleck; [2022]
    Nyckelord :Technology and Engineering;

    Sammanfattning : We study the problem of reducing polarization (variance) of opinions at stationarity in a directed weighted graph with node set divided into two groups: stubborn, initialized with a fixed opinion and regular who repeatedly update their opinion to the average of their out-neighbors, known as the DeGroot model with stubborn nodes. We show how the polarization can be minimized for a number of simple constraints, but that the problem in general is not convex. LÄS MER