Sökning: "Unsupervised Learning"

Visar resultat 16 - 20 av 361 uppsatser innehållade orden Unsupervised Learning.

  1. 16. Unsupervised Anomaly Detection and Explainability for Ladok Logs

    Master-uppsats, Umeå universitet/Institutionen för datavetenskap

    Författare :Mimmi Edholm; [2023]
    Nyckelord :machine learing; anomaly detection; ml;

    Sammanfattning : Anomaly detection is the process of finding outliers in data. This report will explore the use of unsupervised machine learning for anomaly detection as well as the importance of explaining the decision making of the model. LÄS MER

  3. 17. Deep Learning-Based Anomaly Detection for Predictive Maintenance of Cold Isostatic Press

    Master-uppsats, Mälardalens universitet/Akademin för innovation, design och teknik

    Författare :Joakim Nylander Nordström; [2023]
    Nyckelord :Machine Learning; Deep Learning; Predictive Maintenance; High Pressure Processing;

    Sammanfattning : Predictive maintenance is an automated technique that analyses sensor data from industrial systems to enable downtime planning. Available for this study is unlabelled data from sensors placed in proximity to hydraulic system outlets of a cold isostatic press. LÄS MER

  4. 18. 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. 19. Industrial 3D Anomaly Detection and Localization Using Unsupervised Machine Learning

    Master-uppsats, Linköpings universitet/Datorseende

    Författare :Kevin Bärudde; Marcus Gandal; [2023]
    Nyckelord :Machine Learning; 3D Anomaly Detection; Feature Extraction; Manufacturing; Computer Vision; Vision Transformer; PointNet;

    Sammanfattning : Detecting defects in industrially manufactured products is crucial to ensure their safety and quality. This process can be both expensive and error-prone if done manually, making automated solutions desirable. LÄS MER

  7. 20. Anomaly Detection with Machine Learning using CLIP in a Video Surveillance Context

    Master-uppsats, Linköpings universitet/Datorseende

    Författare :Christoffer Gärdin; [2023]
    Nyckelord :Datorseende; maskininlärning; CLIP; anomalidetektion; videoövervakning;

    Sammanfattning : This thesis explores the application of Contrastive Language-Image Pre-Training (CLIP), a vision-language model, in an automated video surveillance system for anomaly detection. The ability of CLIP to perform zero-shot learning, coupled with its robustness against minor image alterations due to its lack of reliance on pixel-level image analysis, makes it a suitable candidate for this application. LÄS MER