Sökning: "feature selection"

Visar resultat 41 - 45 av 318 uppsatser innehållade orden feature selection.

  1. 41. Feature Selection for Sensor Failure Detection in Manufacturing Environment

    Kandidat-uppsats, Mälardalens universitet/Akademin för innovation, design och teknik

    Författare :Victor Knutmejer; Hannes Elfving; [2023]
    Nyckelord :AI; Artificiell Intelligens; Maskininlärning; Feature Selection;

    Sammanfattning : Automated manufacturing environments often benefit greatly from the ability to detect patterns that deviate from expected behavior. Anomaly Detection (AD) is vital in automated manufacturing to mitigate risks such as production delays, defects, and safety hazards, ensuring smooth operations and optimal productivity. LÄS MER

  3. 42. Probabilistic Multi-Modal Data Fusion and Precision Coordination for Autonomous Mobile Systems Navigation : A Predictive and Collaborative Approach to Visual-Inertial Odometry in Distributed Sensor Networks using Edge Nodes

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

    Författare :Isabella Luppi; [2023]
    Nyckelord :Distributed Sensor Networks; Point Cloud Processing; Bounding Box Fitting; Trajectory Tracking; Distributed Estimation; Predictive Estimation; Edge-Computing; Reti di Sensori Distribuiti; Elaborazione di Nuvole di Punti; Riquadri di Delimitazione; Tracciamento della Traiettoria; Stima Distribuita; Stima Predittiva; Calcolo Distribuito.; Distribuerade Sensornätverk; Bearbetning av Punktmoln; Anpassning av Begränsningsruta; Trajektorieuppföljning; Distribuerad Uppskattning; Prediktiv Uppskattning; Edge-datorbehandling;

    Sammanfattning : This research proposes a novel approach for improving autonomous mobile system navigation in dynamic and potentially occluded environments. The research introduces a tracking framework that combines data from stationary sensing units and on-board sensors, addressing challenges of computational efficiency, reliability, and scalability. LÄS MER

  4. 43. Compression Selection for Columnar Data using Machine-Learning and Feature Engineering

    Master-uppsats, Malmö universitet/Institutionen för datavetenskap och medieteknik (DVMT)

    Författare :Douglas Persson; Ludvig Juelsson Larsen; [2023]
    Nyckelord :Machine Learning; XGBoost; Classification; Feature Engineering; Compression Algorithms; Data Encodings; Database Management System DBMS ; Column- Oriented DBMS;

    Sammanfattning : There is a continuously growing demand for improved solutions that provide both efficient storage and efficient retrieval of big data for analytical purposes. This thesis researches the use of machine-learning together with feature engineering to recommend the most cost-effective compression algorithm and encoding combination for columns in a columnar database management system (DBMS). LÄS MER

  5. 44. Exploring Alarm Data for Improved Return Prediction in Radios : A Study on Imbalanced Data Classification

    Uppsats för yrkesexamina på avancerad nivå, Uppsala universitet/Matematiska institutionen

    Författare :Sofia Färenmark; [2023]
    Nyckelord :Imbalanced data classification; LASSO; Boruta; SVM; RFC; neural network; decision tree; AUC; AUPRC;

    Sammanfattning : The global tech company Ericsson has been tracking the return rate of their products for over 30 years, using it as a key performance indicator (KPI). These KPIs play a critical role in making sound business decisions, identifying areas for improvement, and planning. LÄS MER

  7. 45. Swedish Stock and Index Price Prediction Using Machine Learning

    Kandidat-uppsats, Mälardalens universitet/Akademin för utbildning, kultur och kommunikation

    Författare :Henrik Wik; [2023]
    Nyckelord :Stock Price Prediction; Machine Learning; Time Series Analysis; Linear Regression; K-Nearest Neighbors; Random Forest; Support Vector Machines; Neural Networks;

    Sammanfattning : Machine learning is an area of computer science that only grows as time goes on, and there are applications in areas such as finance, biology, and computer vision. Some common applications are stock price prediction, data analysis of DNA expressions, and optical character recognition. LÄS MER