Sökning: "Wavelet"

Visar resultat 1 - 5 av 122 uppsatser innehållade ordet Wavelet.

  1. 1. Predicting Patent Data using Wavelet Regression and Bayesian Machine Learning

    Master-uppsats, KTH/Matematik (Avd.)

    Författare :Mattias Martinsen; [2023]
    Nyckelord :Wavelet; Regression; Bayesian network; Prediction; Patent; Machine Learning; Wavelet; Regression; Bayesiskt nätverk; Predicering; Patent; Maskininlärning;

    Sammanfattning : Patents are a fundamental part of scientific and engineering work, ensuringprotection of inventions owned by individuals or organizations. Patents areusually made public 18 months after being filed to a patent office, whichmeans that current publicly available patent data only provides informationabout the past. LÄS MER

  3. 2. Data Assimilation for Systems with Multiple Timescales

    Kandidat-uppsats, KTH/Skolan för teknikvetenskap (SCI)

    Författare :Dan Vicente Ihanus; [2023]
    Nyckelord :Mathematics; Partial Differential Equations; Numerical analysis; Data assimilation; Numerical weather prediction; Ensemble Kalman Filter;

    Sammanfattning : This text provides an overview of problems in the field of data assimilation. We explore the possibility of recreating unknown data by continuously inserting known data into certain dynamical systems, under certain regularity assumptions. LÄS MER

  4. 3. Unsupervised Detection of Interictal Epileptiform Discharges in Routine Scalp EEG : Machine Learning Assisted Epilepsy Diagnosis

    Uppsats för yrkesexamina på avancerad nivå, Uppsala universitet/Avdelningen Vi3

    Författare :Shuai Shao; [2023]
    Nyckelord :EEG; electroencephalography; IED; interictal epileptiform discharges; spike detection; epilepsy; unsupervised; Fourier transform; STFT; short-time Fourier transform; CWT; continuous wavelet transform; DWT; discrete wavelet transform; ML; machine learning; ANN; artificial neural network; CNN; convolutional neural network; autoencoder; HMM; hidden Markov model; ECS; Euclidean distance of cumulative spectrum;

    Sammanfattning : Epilepsy affects more than 50 million people and is one of the most prevalent neurological disorders and has a high impact on the quality of life of those suffering from it. However, 70% of epilepsy patients can live seizure free with proper diagnosis and treatment. Patients are evaluated using scalp EEG recordings which is cheap and non-invasive. LÄS MER

  5. 4. Deep Learning-Driven EEG Classification in Human-Robot Collaboration

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

    Författare :Yuan Wo; [2023]
    Nyckelord :Human-robot collaboration; Electroencephalogram signal; Signal Processing Feature Extraction; Deep Learning method; Dilated Convolutional Neural Network; Människa-robot-samarbete; Elektroencefalogram-signal; Signalförädlingsfunktionsutvinning; Djupinlärningsmetod; Dilaterat konvolutionellt neuronnätverk.;

    Sammanfattning : Human-robot collaboration (HRC) occurs when people and robots work together in a shared environment. Current robots often use rigid programs unsuitable for HRC. Multimodal robot programming offers an easier way to control robots using inputs like voice and gestures. LÄS MER

  7. 5. Prediktivt underhåll av transformatorstationer genom automatisk analys av störningsdata i COMTRADE-filer

    M1-uppsats, KTH/Hälsoinformatik och logistik

    Författare :Simon Bidros; Ström Gustav; [2023]
    Nyckelord :COMTRADE; predictive maintenance; wavelet transform; substation; relay protection; COMTRADE; prediktivt underhåll; wavelettransform; transformatorstation; reläskydd;

    Sammanfattning : Arbetet beskriver möjligheten att kunna utföra prediktivt underhåll med hjälp av information frånCOMTRADE störningsfiler. En mjukvarualgoritm som hämtar tidsförlopp för händelser som uppstårvid störningar och kan ge indikationer på ifall reläer eller strömbrytare faller utanför optimalaarbetsförhållanden har utvecklats. LÄS MER