Avancerad sökning

Visar resultat 1 - 5 av 28 uppsatser som matchar ovanstående sökkriterier.

1. 1. Automatic Detection of Common Signal Quality Issues in MRI Data using Deep Neural Networks

   Master-uppsats, Linköpings universitet/Institutionen för medicinsk teknik

   Författare :Erika Ax; Elin Djerf; [2023]
   Nyckelord :mr; magnetic resonance; machine learning; deep learning; anomaly detection; U-Net; autoencoder; 3D; classification; reconstruction; artefacts;

   Sammanfattning : Magnetic resonance imaging (MRI) is a commonly used non-invasive imaging technique that provides high resolution images of soft tissue. One problem with MRI is that it is sensitive to signal quality issues. The issues can arise for various reasons, for example by metal located either inside or outside of the body. LÄS MER

3. 2. Multi-Label Toxic Comment Classification Using Machine Learning: An In-Depth Study

   Master-uppsats, Lunds universitet/Institutionen för datavetenskap

   Författare :Matilda Froste; Mosa Hosseini; [2023]
   Nyckelord :natural language processing; machine learning; offensive speech detection; transformers; multi-label classification; Technology and Engineering;

   Sammanfattning : The classification of toxic comments is a well-researched area with many techniques available. However, effectively managing multi-label categorization still requires a considerable amount of work. LÄS MER

4. 3. Sentiment and Semantic Analysis and Urban Quality Inference using Machine Learning Algorithms

   Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknik

   Författare :Emily Ho; Michelle Schneider; [2022-10-14]
   Nyckelord :Natural Language Processing; Machine Learning; Deep Neural Networks; Transformers; BERT; NER; Text Classification; Urban Planning; Qualitative Research; Interviews;

   Sammanfattning : Qualitative interviews are conducted by researchers to gain a deeper understanding of people’s opinions and perceptions about a specific topic. The analysis of such textual data is an iterative process and often time-consuming. LÄS MER

5. 4. Methods for data and user efficient annotation for multi-label topic classification

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

   Författare :Agnieszka Miszkurka; [2022]
   Nyckelord :Natural Language Processing; Multi-label text classification; Active Learning; Zero-shot learning; Data Augmentation; Data-centric AI; Naturlig språkbehandling; Textklassificering med multipla klasser; Active Learning; Zero-shot learning; Data Augmentation; Datacentrerad AI;

   Sammanfattning : Machine Learning models trained using supervised learning can achieve great results when a sufficient amount of labeled data is used. However, the annotation process is a costly and time-consuming task. There are many methods devised to make the annotation pipeline more user and data efficient. LÄS MER

7. 5. Self-Supervised Transformer Networks for Error Classification of Tightening Traces

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

   Författare :Dennis Bogatov Wilkman; [2022]
   Nyckelord :Transformers; Self-supervised Learning; Multi-Label Error Classification; Tightening Traces; Transformatorer; Självövervakad Inlärning; Klassificering av fel med flera etiketter; Skärpnings spår;

   Sammanfattning : Transformers have shown remarkable results in the domains of Natural Language Processing and Computer Vision. This naturally raises the question whether the success could be replicated in other domains. LÄS MER