Sökning: "supervised classification"

Visar resultat 16 - 20 av 52 avhandlingar innehållade orden supervised classification.

1. 16. Adapting Deep Learning for Microscopy: Interaction, Application, and Validation

   Författare :Ankit Gupta; Carolina Wählby; Ida-Maria Sintorn; Ola Spjuth; Andreas Hellander; Philip Kollmannsberger; Uppsala universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Deep Learning; Microscopy; Human-in-the-Loop; Semi-Supervised Learning; Application-Specific Analysis; Image Classification; Image-to-Image Translation; Template Matching; Computerized Image Processing; Datoriserad bildbehandling;

   Sammanfattning : Microscopy is an integral technique in biology to study the fundamental components of life visually. Digital microscopy and automation have enabled biologists to conduct faster and larger-scale experiments with a sharp increase in the data generated. LÄS MER

3. 17. Machine Learning Methods for Image Analysis in Medical Applications, from Alzheimer's Disease, Brain Tumors, to Assisted Living

   Författare :Chenjie Ge; Chalmers tekniska högskola; []
   Nyckelord :MEDICIN OCH HÄLSOVETENSKAP; MEDICAL AND HEALTH SCIENCES; MEDICIN OCH HÄLSOVETENSKAP; MEDICAL AND HEALTH SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; MEDICIN OCH HÄLSOVETENSKAP; MEDICAL AND HEALTH SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; convolutional neural networks; Alzheimer s disease detection; machine learning; deep learning; fall detection; glioma subtype classification; generative adversarial networks; recurrent convolutional networks; spiking neural networks; visual prosthesis; semi-supervised learning;

   Sammanfattning : Healthcare has progressed greatly nowadays owing to technological advances, where machine learning plays an important role in processing and analyzing a large amount of medical data. This thesis investigates four healthcare-related issues (Alzheimer's disease detection, glioma classification, human fall detection, and obstacle avoidance in prosthetic vision), where the underlying methodologies are associated with machine learning and computer vision. LÄS MER

4. 18. Borgenärskollektiv : En studie av fyra borgenärskollektivs rättsliga klassificering

   Författare :Oskar Andrews; Göran Millqvist; Mikael Möller; Stockholms universitet; []
   Nyckelord :SAMHÄLLSVETENSKAP; SOCIAL SCIENCES; rättsvetenskap med inriktning mot civilrätt; Legal Science; specialisation Private Law;

   Sammanfattning : A creditor group exists when two or more creditors have claims against the same debtor and the claims of the relevant creditors are in some way interdependent. A creditor group can have come into existence as a result of an execution of a multi-creditor loan agreement of some sort. LÄS MER

5. 19. Data Driven Visual Recognition

   Författare :Omid Aghazadeh; Stefan Carlsson; Jiri Matas; KTH; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Visual Recognition; Data Driven; Supervised Learning; Mixture Models; Non-Parametric Models; Category Recognition; Novelty Detection;

   Sammanfattning : This thesis is mostly about supervised visual recognition problems. Based on a general definition of categories, the contents are divided into two parts: one which models categories and one which is not category based. We are interested in data driven solutions for both kinds of problems. LÄS MER

7. 20. Advanced Machine Learning Methods for Oncological Image Analysis

   Författare :Mehdi Astaraki; Chunliang Wang; Örjan Smedby; Iuliana Toma-Dasu; Bjoern Menze; KTH; Karolinska Institutet; Karolinska Institutet; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Medical Image Analysis; Machine Learning; Deep Learning; Survival Analysis; Early Response Assessment; Tumor Classification; Tumor Segmentation; Medicinsk teknologi; Medical Technology;

   Sammanfattning : Cancer is a major public health problem, accounting for an estimated 10 million deaths worldwide in 2020 alone. Rapid advances in the field of image acquisition and hardware development over the past three decades have resulted in the development of modern medical imaging modalities that can capture high-resolution anatomical, physiological, functional, and metabolic quantitative information from cancerous organs. LÄS MER