Avancerad sökning

Visar resultat 1 - 5 av 20 uppsatser som matchar ovanstående sökkriterier.

  1. 1. Door closing sound quality related to door sealing stiffness

    Master-uppsats, KTH/Marcus Wallenberg Laboratoriet MWL

    Författare :Riccardo Derton; [2021]
    Nyckelord :Door Closing Sound Quality; Customer’s Perspective; Psychoacoustics; Acoustic Analysis; Wavelet Analysis; Artificial Head; Door Closing Motion; Door Seals; Door Sealing Stiffness; Stiffness Analysis; Ljudkvalitet vid dörrstängning; Kundperspektiv; Psykoakustik; Akustisk analys; Wavelet analys; Konstgjort huvud; Dörrstängningsrörelse; Dörrtätningar; Styvhet i dörrtätningar; Styvhetsanalys;

    Sammanfattning : The door closing action is a recurrent situation when using a vehicle, and its sound is therefore a common sensation, which would elicit pleasant feelings. Sensory pleasantness is an important aspect in terms of customer’s perspective, and it can be a contributing factor when deciding to buy or not a specific vehicle. LÄS MER

  3. 2. How Certain Are You of Getting a Parking Space? : A deep learning approach to parking availability prediction

    Master-uppsats, Linköpings universitet/Institutionen för datavetenskap

    Författare :Mathias Nilsson; Sophie von Corswant; [2020]
    Nyckelord :monte carlo dropout; mc dropout; long short term memory; lstm; neural network; recurrent neural network; gradient tree boosting; rnn; gradient boosting regression tree; gbrt; quantile regression; traffic congestion; parking; parking occupancy; parking availability; parking space; parking lot; machine learning;

    Sammanfattning : Traffic congestion is a severe problem in urban areas and it leads to the emission of greenhouse gases and air pollution. In general, drivers lack knowledge of the location and availability of free parking spaces in urban cities. LÄS MER

  4. 3. Domain Transfer for End-to-end Reinforcement Learning

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

    Författare :Anton Olsson; Felix Rosberg; [2020]
    Nyckelord :Reinforcement Learning; Domain Transfer; Deep Deterministic Policy Gradient; Reinforcement Learning in Real-time;

    Sammanfattning : In this master thesis project a LiDAR-based, depth image-based and semantic segmentation image-based reinforcement learning agent is investigated and compared forlearning in simulation and performing in real-time. The project utilize the Deep Deterministic Policy Gradient architecture for learning continuous actions and was designed to control a RC car. LÄS MER

  5. 4. Strategies for Road Profile in Adaptive Suspension Control

    Master-uppsats, Linköpings universitet/Fordonssystem

    Författare :Fredrik Skoglund; [2020]
    Nyckelord :;

    Sammanfattning : Semi-active suspension systems has become an increasingly popular alternative to the passive suspensions in recent time. By varying the spring stiffness and damping coefficient in the system, different characteristics can be achieved depending on driver preferability and road disturbances. LÄS MER

  7. 5. Prioritering av åtgärder för ökad säker cykling : En modell för att underlätta för Trafikverket vid val av åtgärder

    Kandidat-uppsats, Högskolan Dalarna/Samhällsbyggnadsteknik

    Författare :Karin Bransell; [2020]
    Nyckelord :Prioritization tools; cycle measure; tuning measures; Prioriteringsverktyg; cykelåtgärder; trimningsåtgärder;

    Sammanfattning : The main goal of my work was to develop a model that could facilitate Trafikverkets (the Swedish Transport Administration's) work in prioritizing different cycling measures. In order to develop a model, I first had to study the various tools available. This in order to be able to develop a model that suited my purpose. LÄS MER