A5037990310- AI in cancer detection
- Image Retrieval and Classification Techniques
- Advanced Image and Video Retrieval Techniques
- Radiomics and Machine Learning in Medical Imaging
- Cell Image Analysis Techniques
- Image Processing Techniques and Applications
- Human Pose and Action Recognition
- Video Surveillance and Tracking Methods
- Indoor and Outdoor Localization Technologies
- Digital Imaging for Blood Diseases
- Context-Aware Activity Recognition Systems
- Anomaly Detection Techniques and Applications
- Gait Recognition and Analysis
- Video Analysis and Summarization
- Medical Image Segmentation Techniques
- EEG and Brain-Computer Interfaces
- Image Processing and 3D Reconstruction
- Speech and Audio Processing
- Non-Invasive Vital Sign Monitoring
- Time Series Analysis and Forecasting
- Gaze Tracking and Assistive Technology
- Robotics and Sensor-Based Localization
- Advanced Vision and Imaging
- Cervical Cancer and HPV Research
- Hand Gesture Recognition Systems
University of Lübeck
2018-2025
German Research Centre for Artificial Intelligence
2024-2025
Fraunhofer Research Institution for Individualized and Cell-Based Medical Engineering
2023-2024
University of Economics in Katowice
2017-2024
Universität Trier
2023
University of Siegen
2010-2020
Universität Koblenz
2008-2010
University of Koblenz and Landau
2008-2010
Koblenz University of Applied Sciences
2009
Queen Mary University of London
2007-2008
Getting a good feature representation of data is paramount for Human Activity Recognition (HAR) using wearable sensors. An increasing number learning approaches-in particular deep-learning based-have been proposed to extract an effective by analyzing large amounts data. However, getting objective interpretation their performances faces two problems: the lack baseline evaluation setup, which makes strict comparison between them impossible, and insufficiency implementation details, can hinder...
Malaria is a disease activated by type of microscopic parasite transmitted from infected female mosquito bites to humans. fatal that endemic in many regions the world. Quick diagnosis this will be very valuable for patients, as traditional methods require tedious work its detection. Recently, some automated have been proposed exploit hand-crafted feature extraction techniques however, their accuracies are not reliable. Deep learning approaches modernize world with superior performance....
Background: Breast cancer has the highest prevalence among all cancers in women globally. The classification of histopathological images diagnosis breast is an area clinical concern. In computer-aided diagnosis, most traditional models use a single network to extract features, although this approach significant limitations. Moreover, many networks are trained and optimized on patient-level datasets, ignoring lower-level data labels. Method: This paper proposes deep ensemble model based...
In recent years, deep learning has made brilliant achievements in Environmental Microorganism (EM) image classification. However, classification of small EM datasets still not obtained good research results. Therefore, researchers need to spend a lot time searching for models with performance and suitable the current equipment working environment. To provide reliable references researchers, we conduct series comparison experiments on 21 models. The experiment includes direct classification,...
The diagnosis of cancer is typically based on histopathological sections or biopsies glass slides. Artificial intelligence (AI) approaches have greatly enhanced our ability to extract quantitative information from digital histopathology images as a rapid growth in oncology data. Gynecological cancers are major diseases affecting women's health worldwide. They characterized by high mortality and poor prognosis, underscoring the critical importance early detection, treatment, identification...
With the addition of Fine Timing Measurement (FTM) protocol in IEEE 802.11-2016, a promising sensor for smartphone-based indoor positioning systems was introduced. FTM enables Wi-Fi device to estimate distance second based on propagation time signal. Recently, has gotten more attention from scientific community as compatible devices become available. Due claimed robustness and accuracy, is often used Received Signal Strength Indication (RSSI). In this work, we evaluate 2.4 GHz band with 20...
The scarcity of labelled time-series data can hinder a proper training deep learning models. This is especially relevant for the growing field ubiquitous computing, where coming from wearable devices have to be analysed using pattern recognition techniques provide meaningful applications. To address this problem, we propose transfer method based on attributing sensor modality labels large amount collected various application fields. Using these data, our firstly trains Deep Neural Network...