Sökning: "henrik box"

Visar resultat 1 - 5 av 21 uppsatser innehållade orden henrik box.

  1. 1. A Comparative Study on the Effects of Removing the Most Important Feature on Random Forest and Support Vector Machine

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

    Författare :Henrik Åkesson; Hampus Fridlund; [2023]
    Nyckelord :;

    Sammanfattning : Machine learning (ML) for classification is largely regarded as a “black box”, in that it’s difficult to fully understand how the model reached a decision, and how changes to the input affects the output. Therefore, exploring the inner workings of classification models are of interest for expanding the current knowledge base, providing guidelines for choosing a more suitable classification model for a specific problem. LÄS MER

  3. 2. Physics-Enhanced Machine Learning for Energy Systems

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

    Författare :Henrik Lindström; Emil Sundström; [2022]
    Nyckelord :Technology and Engineering;

    Sammanfattning : Building operations account for a large amount of energy usage and the HVAC (Heating, Ventilation and Air Conditioning) systems are the largest consumer of energy in this sector. To reduce this demand, more energy-efficient control algorithms are implemented and a popular choice for a controller is the model predictive control. LÄS MER

  4. 3. Development and testing of a novel solar dryer design with an incorporated heat exchanger - For use in the Himalayan regions

    Master-uppsats, Lunds universitet/Institutionen för energivetenskaper

    Författare :Adam Probert; [2022]
    Nyckelord :Technology and Engineering;

    Sammanfattning : Food scarcity is a common occurrence for farmers in the rural Himalayan regions. As fruits and vegetables are a crucial part of most farmers' diet, food deficiency can become evident in between harvesting periods, when there is no fresh supply. LÄS MER

  5. 4. Evaluation of model-based fault diagnosis combining physical insights and neural networks applied to an exhaust gas treatment system case study

    Master-uppsats, Linköpings universitet/Fordonssystem

    Författare :Björn Kleman; Henrik Lindgren; [2021]
    Nyckelord :model-based; fault diagnosis; neural networks; data-driven; Hybrid; SCR; exhaust gas treatment system; recurrent neural networks; grey-box; heavy duty truck; fault isolation; fault detection; diagnosis; urea; machine learning; Scania; structural model; MSO; residual; Fault Diagnosis Toolbox;

    Sammanfattning : Fault diagnosis can be used to early detect faults in a technical system, which means that workshop service can be planned before a component is fully degraded. Fault diagnosis helps with avoiding downtime, accidents and can be used to reduce emissions for certain applications. LÄS MER

  7. 5. Migration to P4-Programmable Switches and Implementation of the Rapid Spanning Tree Protocol

    Master-uppsats, Linköpings universitet/Programvara och system

    Författare :Henrik Lindström; [2020]
    Nyckelord :P4; Switch; Hybrid; SDN; Ethernet; Migration; RSTP; STP; Rapid; Spanning; Tree; BMv2;

    Sammanfattning : P4 is a high-level language for programming the data plane of a network switch. These P4-programmable switches come with no pre-defined behavior or protocols, so it is entirely up to the loaded P4 program to define these. This allows the user to exclude any unwanted functionality and to create custom protocols. LÄS MER