Sökning: "neurala nät"

Visar resultat 1 - 5 av 24 uppsatser innehållade orden neurala nät.

1. 1. Coordination of base station energy storage for renewable energy grid : Utilizing Base Station battery storage to stabilize grids with Variable Renewable Energy Sources

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

   Författare :Linus Pekkanen; [2022]
   Nyckelord :Renewable Energy; Energy Storage; Optimal Control; Model Predictive Control; Smart Grids; Machine Learning; Neural Networks; Base Stations; Telecommunications; Förnybar Energi; Energilagring; Optimal Kontroll; Modellprediktiv Reglering; Smarta Elnät; Maskininlärning; Neurala Nätverk; Basstationer; Telekommunikation;

   Sammanfattning : An increasing amount of variable renewable energy sources are being added to the world’s power grids both as an effort to reduce greenhouse gas emissions in the fight against climate change but also because some of the energy sources with the lowest levelized cost of energy are variable renewable energy sources such as wind and photovoltaics. These energy sources come with inherent difficulties since their energy production is neither constant nor entirely controllable and can cause issues for the power grids if they cause power production and consumption to become imbalanced. LÄS MER

3. 2. 3D Facial Modelling for Valence Estimation

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

   Författare :Ioannis Athanasiadis; [2022]
   Nyckelord :Computer Graphics; Machine Learning; Representation Disentanglement; Valence Estimation;

   Sammanfattning : We, as humans, purposely alter our facial expression to convey information during our daily interactions. However, our facial expressions can also unconsciously change based on external stimuli. LÄS MER

4. 3. Short-term Forecasting of EV Charging Stations Power Consumption at Distribution Scale

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

   Författare :Milan Clerc; [2022]
   Nyckelord :Electric Vehicles; Electrical grid; Ancillary services; Time series; Gradient Boosted Trees; Recurrent Neural Networks; ARIMA.; Elbilar; Elnät; Tidsserie; Återkommande neurala nätverk; Maskininlärning.;

   Sammanfattning : Due to the intermittent nature of renewable energy production, maintaining the stability of the power supply system is becoming a significant challenge of the energy transition. Besides, the penetration of Electric Vehicles (EVs) and the development of a large network of charging stations will inevitably increase the pressure on the electrical grid. LÄS MER

5. 4. Predicting average response sentiments to mass sent emails using RNN

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

   Författare :Adel Bavey; [2021]
   Nyckelord :Sentiment Analysis; Sentiment Forecasting; Natural Language Processing; Machine Learning; Recurrent Neural Nets; E-mails; Sentiment Analys; Sentiment Förutsägning; Naturlig Språkbehandling; Maskininlärning; Recurrenta Neurala nät; E-mails;

   Sammanfattning : This study is concerned with using the popular Recurrent Neural Network (RNN) model, and its variants Gated Recurrent Unit (GRU) and Long-Short Term Memory (LSTM), on the novel problem of Sentiment Forecasting (SF). The goal of SF is to predict what the sentiment of a response will be in a conversation, using only the previous utterance. LÄS MER

7. 5. Neurala nätverk försjälvkörande fordon : Utforskande av olika tillvägagångssätt

   Kandidat-uppsats, Karlstads universitet/Institutionen för matematik och datavetenskap (from 2013)

   Författare :Simon Hellner; Henrik Syvertsson; [2021]
   Nyckelord :artificial neural networks; gradient descent; genetic algorithm; backpropagation; unity; self driving; autonomous vehicles; line detection; neural network; neural net; artificiella neurala nätverk; neurala nätverk; självkörande bilar; självkörande fordon; unity; bakåtpropagering; linjedetektering; gradient descent; genetisk algoritm; neurala nät;

   Sammanfattning : Artificiella neurala nätverk (ANN) har ett brett tillämpningsområde och blir allt relevantare på flera håll, inte minst för självkörande fordon. För att träna nätverken användsmeta-algoritmer. Nätverken kan styra fordonen med hjälp av olika typer av indata. LÄS MER