A5012758194- Medical Image Segmentation Techniques
- Natural Language Processing Techniques
- Text Readability and Simplification
- Computer Graphics and Visualization Techniques
- Image Retrieval and Classification Techniques
- Artificial Intelligence in Games
- Advanced Vision and Imaging
- Contact Dermatitis and Allergies
- Cerebrovascular and Carotid Artery Diseases
- Second Language Acquisition and Learning
- Industrial Vision Systems and Defect Detection
- Psoriasis: Treatment and Pathogenesis
- Translation Studies and Practices
- Tactile and Sensory Interactions
- Second Language Learning and Teaching
- Inflammatory Bowel Disease
- Visual Attention and Saliency Detection
- Mycobacterium research and diagnosis
- Educational Games and Gamification
- Hand Gesture Recognition Systems
- Cutaneous Melanoma Detection and Management
- Retinal Imaging and Analysis
- Evolutionary Algorithms and Applications
- Digital Imaging for Blood Diseases
- Sports Analytics and Performance
Lucerne University of Applied Sciences and Arts
2014-2022
University Hospital of Basel
2022
Technical University of Munich
2014
Max Planck Institute for Psycholinguistics
2010
Max Planck Society
2010
University of Nottingham
2006
Dublin City University
2003-2004
ETH Zurich
1993
Presents a novel, parameter-free technique for the segmentation and local description of line structures on multiple scales, both in 2D 3D. The algorithm is based nonlinear combination linear filters searches elongated, symmetric structures, while suppressing response to edges. filtering process creates one sharp maximum across line-feature profile scale-space. multi-scale reflects contrast independent width. filter steerable orientation scale domains, leading an efficient, implementation. A...
Assessment of psoriasis severity is strongly observer-dependent, and objective assessment tools are largely missing. The increasing number patients receiving highly expensive therapies that reimbursed only for moderate-to-severe motivates the development higher quality tools.To establish an accurate method based on segmenting images by machine learning technology.In this retrospective, non-interventional, single-centred, interdisciplinary study diagnostic accuracy, 259 standardized...
Medical image analysis has to support the clinicians ability identify, manipulate and quantify anatomical structures. On scalar 2D data, a human observer is often superior computer assisted analysis, but interpretation of vector- valued data or combined from different modalities, especially in 3D, can benefit assistance. The problem how convey complex information clinician tackled by providing colored multimodality renderings. We propose go step beyond supplying suitable modelling functional...
The main goal of the present paper is to propose use a two-reservoir solar domestic hot water system (SDHWS), reduce electric energy peak due extensive showerheads (ESH) in dwelling. proposed SDHWS designed for low-income dwelling Brazil. demand profile these houses are obtained from data collected fully monitored sample ninety houses, frame two years long experiment reported previous papers. with help software TRNSYS, by using typical meteorological year (TMY) available Brazilian capital...
The exact location of skin lesions is key in clinical dermatology. On one hand, it supports differential diagnosis (DD) since most conditions have specific predilection sites. the other matters for dermatosurgical interventions. In practice, lesion evaluation not well standardized and anatomical descriptions vary or lack altogether. Automated determination could benefit both situations.Establish an automated method to determine regions patient pictures evaluate gain DD performance a deep...
Pustular psoriasis (PP) is one of the most severe and chronic skin conditions. Its treatment difficult, measurements its severity are highly dependent on clinicians' experience. Pustules brown spots main efflorescences disease directly correlate with activity. We propose an automated deep learning model (DLM) to quantify lesions in terms count surface percentage from patient photographs.In this retrospective study, two dermatologists a student labeled 151 photographs PP patients for pustules...
Man vs. machine competitions have always been attracting much public attention and the famous defeats of human champions in chess, Jeopardy!, Go or poker undoubtedly mark important milestones history artificial intelligence. In this article we reflect on our experiences with a game-centric approach to teaching intelligence that follows historical development algorithms by popping hood these champion bots. Moreover, made available server infrastructure for playing card games perfect...
This paper looks at how Computational Linguistics (CL) and Natural Language Processing (NLP) resources can be deployed in Computer-Assisted Learning (CALL) materials for primary school learners.We draw a broad distinction between CL NLP technology briefly review the use of CL/NLP e-Learning general, it has been CALL to date specifically context.We outline used project teach Irish German children Ireland.This focuses on Finite State morphological analysis (FST) Part Speech (POS) taggers German.
Projector-depth systems (PDS) have the potential to transform any horizontal area into a touchable surface. However, robust touch detection in such is difficult achieve due measurement noise. We propose machine learning based approach for minimal hand pose estimation that relies solely on depth information. Our model enables localization of fingertips surface, which can then be used detection. This improves robustness by considerably minimizing margin noise-based errors. Compared previous...