Sökning: "prediction error method"

Visar resultat 21 - 25 av 155 uppsatser innehållade orden prediction error method.

  1. 21. Voltage-Based Multi-step Prediction : Data Labeling, Software Evaluation, and Contrasting DRL with Traditional Prediction Methods

    Uppsats för yrkesexamina på grundnivå, Högskolan i Halmstad/Akademin för informationsteknologi

    Författare :Joakim Svensson; [2023]
    Nyckelord :Deep Reinforcement Learning; Multi-step Prediction; Time Series Forecasting; Djup Förstärkningsinlärning; Flerstegsprognos; Tidsserieprognos;

    Sammanfattning : In this project, three primary problems were addressed to improve battery data management and software performance evaluation. All solutions used voltage values in time together with various device characteristics. Battery replacement labeling was performed using Hidden Markov Models. LÄS MER

  3. 22. Radio Environment Classification

    Uppsats för yrkesexamina på avancerad nivå, Umeå universitet/Institutionen för fysik

    Författare :Daniel Hagström; [2023]
    Nyckelord :;

    Sammanfattning : This thesis has looked into the possibility of classifying radio environment scenarios based on data received in base stations. It was done in order to improve forecasting of electrical output in these base stations. LÄS MER

  4. 23. GPS-Free UAV Geo-Localization Using a Reference 3D Database

    Master-uppsats, Linköpings universitet/Institutionen för systemteknik

    Författare :Justus Karlsson; [2022]
    Nyckelord :Deep Learning; Machine Learning; ML; AI; UAV; GPS-Free; CNN; 3D CNN; GCNN; 3D Database; geolocalization; geo-localization; georegistration; Hidden Markov Model; HMM; satellite; satellite database; Batch-Hard; triplet loss; PyTorch Geometric;

    Sammanfattning : The goal of this thesis has been global geolocalization using only visual input and a 3D database for reference. In recent years Convolutional Neural Networks (CNNs) have seen huge success in the task of classifying images. The flattened tensors at the final layers of a CNN can be viewed as vectors describing different input image features. LÄS MER

  5. 24. Predicting eigenvalues and eigenmodes in non-rectangular rooms with machine learning techniques

    Master-uppsats, KTH/Teknisk akustik

    Författare :Oscar Lundin; [2022]
    Nyckelord :Machine learning; Finite elements; Plane wave decomposition; ResNet; Room acoustics; Tensorflow; Keras; Eigenfrequency prediction; Maskininlärning; Finita elementmetoden; Planvåguppdelning decomposition; Rumsakustik; ResNet; Tensorflow; Keras; Prediktering av egenvärden; Egenfrekvenser; Egenmoder.;

    Sammanfattning : Knowing the eigenfrequencies and eigenmodes is of great importance to interior design and a common acoustic engineering problem. Challenges in noise control makes knowing the lower eigenfrequencies particularly important. LÄS MER

  7. 25. Combining Continuous and Event-based Hydrological Modeling in Kävlinge River Basin with HEC-HMS

    Master-uppsats, Lunds universitet/Avdelningen för Teknisk vattenresurslära

    Författare :Wenli Hu; [2022]
    Nyckelord :HEC-HMS; SCS-CN; Climate Change; GIS; Flood; Technology and Engineering;

    Sammanfattning : Prediction of flood and evaluation of the impact of climate change in a catchment needs to be correctly estimated, which can be accomplished by hydrological modelling in HEC-HMS. In this paper, the objectives were to gain an understanding of the rainfall-runoff process and estimate the flood frequency curve in the Kävlinge River Basin. LÄS MER