Sökning: "networks"

Visar resultat 21 - 25 av 8104 uppsatser innehållade ordet networks.

1. 21. Predicting Electricity Consumption with ARIMA and Recurrent Neural Networks

   Kandidat-uppsats, Uppsala universitet/Statistiska institutionen

   Författare :Klara Enerud; [2024]
   Nyckelord :time series forecasting; ARIMA; recurrent neural networks; LSTM; electricity forecasting; EED forecasting;

   Sammanfattning : Due to the growing share of renewable energy in countries' power systems, the need for precise forecasting of electricity consumption will increase. This paper considers two different approaches to time series forecasting, autoregressive moving average (ARMA) models and recurrent neural networks (RNNs). LÄS MER

3. 22. Är betald UGC det nya sättet att göra reklam på?

   Kandidat-uppsats, Lunds universitet/Företagsekonomiska institutionen

   Författare :Sara Melgar; Madeleine Tran; Linnea Bengtsson; [2024]
   Nyckelord :Varumärkesattityder; Brand Equity; Förtroende; UGC; FGC; Business and Economics;

   Sammanfattning : Title: Is paid UGC the new way to market? Seminar date: 2024-01-11 Authors: Linnea Bengtsson, Sara Melgar, Madeleine Tran Advisor: Clara Gustafsson Key words: Brand attitude, Brand Equity, Trust, UGC, FGC Research questions: How does paid UGC affect customers’ brand attitude in relation to brands within the makeup industry? How does paid UGC affect makeup brands Brand Equity and CBBE? Purpose: The purpose of this study is to investigate how paid UGC affects young adults’ brand attitudes towards makeup brands and how the makeup brands’ Brand Equity is affected by paid UGC. Methodology: This study was constructed through a quantitative method by a survey that was sent out to the authors’ networks and 94 responses were of use. LÄS MER

4. 23. The Role of Technology Shifts in Urban Decarbonization Modelling : Scenario creation and implementation

   Master-uppsats, KTH/Energisystem

   Författare :Batiste Fourniols; [2024]
   Nyckelord :Urban area; Decarbonization policies; Scenario modeling; District heating; Gas distribution network; Geospatial resolution; Stadsområde; utfasning av fossila bränslen; scenariomodellering; fjärrvärme; gasdistributionsnät; geospatial upplösning;

   Sammanfattning : This work includes modelling of decarbonization scenarios at the scale of an urban area, providing policy insights and a methodology focusing on introducing district heating and maintaining the existing gas distribution network in a case study. With a focus on reducing gas consumption in the residential and tertiary sectors, the research integrates scenario developments giving a methodology to develop district heating, requiring a careful balance in selecting the optimal scale for city-wide analysis. LÄS MER

5. 24. Control system and simplified timesynchronization for heterogenous IoT systems with medium time requirements

   M1-uppsats, KTH/Hälsoinformatik och logistik

   Författare :Jemma Touma; Simon Hejdenberg; [2024]
   Nyckelord :Internet of Things; time synchronization; wireless sensor networks; network time protocol; Android; Bluetooth; WiFi Direct;

   Sammanfattning : The company QTPIE conducts research on drivers and their unconscious reactions when driving. To help, they use smart devices that today must be individually handled at the start and end of a run, and have individually set timestamps, which can lead to differences between the units when data is entered and collation of the units' data after a run. LÄS MER

7. 25. A Comparative Analysis of Whisper and VoxRex on Swedish Speech Data

   Kandidat-uppsats, Uppsala universitet/Statistiska institutionen

   Författare :Max Fredriksson; Elise Ramsay Veljanovska; [2024]
   Nyckelord :ASR; Automatic Speech Recognition; Swedish Speech Recognition; Speech Recognition Models; Speech-to-Text; Whisper; VoxRex; Wav2Vec; Model Comparison; Transformer Models; Neural Networks; Machine Learning; WER; Word Error Rate; Transcription;

   Sammanfattning : With the constant development of more advanced speech recognition models, the need to determine which models are better in specific areas and for specific purposes becomes increasingly crucial. Even more so for low-resource languages such as Swedish, dependent on the progress of models for the large international languages. LÄS MER