A5041317183- Advanced Graph Neural Networks
- Topic Modeling
- Semantic Web and Ontologies
- Natural Language Processing Techniques
- Biomedical Text Mining and Ontologies
- Data Quality and Management
- Bioinformatics and Genomic Networks
- Graph Theory and Algorithms
- Scientific Computing and Data Management
- Advanced Database Systems and Queries
- Service-Oriented Architecture and Web Services
- Speech and Audio Processing
- Algorithms and Data Compression
- Advanced Image and Video Retrieval Techniques
- Domain Adaptation and Few-Shot Learning
- Caching and Content Delivery
- Advanced Data Compression Techniques
- Speech Recognition and Synthesis
- Cloud Computing and Resource Management
- Gene expression and cancer classification
- Computational Drug Discovery Methods
- IoT and Edge/Fog Computing
- Multimodal Machine Learning Applications
- Bayesian Modeling and Causal Inference
- Smart Parking Systems Research
Vrije Universiteit Amsterdam
2019-2025
RELX Group (Netherlands)
2021-2024
University of Amsterdam
2022
Fraunhofer Institute for Applied Information Technology
2016-2021
ZB MED - Information Centre for Life Sciences
2020
University of Jyväskylä
2011-2019
RWTH Aachen University
2017-2019
In this paper <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> , we proposed an explainable deep neural networks (DNN)-based method for automatic detection of COVID-19 symptoms from chest radiography (CXR) images, which call 'DeepCOVIDExplainer'. We used 15,959 CXR images 15,854 patients, covering normal, pneumonia, and cases. are first comprehensively preprocessed augmented before classifying with a ensemble method, followed by...
Interference between pharmacological substances can cause serious medical injuries. Correctly predicting so-called drug-drug interactions (DDI) does not only reduce these cases but also result in a reduction of drug development cost. Presently, most drug-related knowledge is the clinical evaluations and post-marketing surveillance; resulting limited amount information. Existing data-driven prediction approaches for DDIs typically rely on single source information, while using information...
This book provides a comprehensive and accessible introduction to knowledge graphs, which have recently garnered notable attention from both industry academia. Knowledge graphs are founded on the
Knowledge Graphs (KG) are of vital importance for multiple applications on the web, including information retrieval, recommender systems, and metadata annotation.
Exponential growths of social media and micro-blogging sites not only provide platforms for empowering freedom expressions individual voices, but also enables people to express anti-social behavior like online harassment, cyberbul-lying, hate speech. Numerous works have been proposed utilize these data analysis, document characterization, sentiment analysis by predicting the contexts mostly highly resourced languages English. However, some are under-resources, e.g., South Asian Bengali,...
Question answering over knowledge graphs (KGQA) has evolved from simple single-fact questions to complex that require graph traversal and aggregation. We propose a novel approach for KGQA uses unsupervised message passing, which propagates confidence scores obtained by parsing an input question matching terms in the set of possible answers. First, we identify entity, relationship, class names mentioned natural language question, map these their counterparts graph. Then, mappings propagate...
Knowledge Graphs have been recognized as a valuable source for background information in many data mining, retrieval, natural language processing, and knowledge extraction tasks. However, obtaining suitable feature vector representation from RDF graphs is challenging task. In this paper, we extend the RDF2Vec approach, which leverages modeling techniques unsupervised sequences of entities. We generate by exploiting local graph substructures, harvested walks, learn latent numerical...
Amid the coronavirus disease(COVID-19) pandemic, humanity experiences a rapid increase in infection numbers across world. Challenge hospitals are faced with, fight against virus, is effective screening of incoming patients. One methodology assessment chest radiography(CXR) images, which usually requires expert radiologist's knowledge. In this paper, we propose an explainable deep neural networks(DNN)-based method for automatic detection COVID-19 symptoms from CXR call DeepCOVIDExplainer. We...
Osteoarthritis (OA) is a degenerative joint disease, which significantly affects middle-aged and elderly people. Although primarily identified via hyaline cartilage change based on medical images, technical bottlenecks like noise, artifacts, modality impose an enormous challenge high-precision, objective, efficient early quantification of OA. Owing to recent advancements, approaches neural networks (DNNs) have shown outstanding success in this application domain. However, due nested...
Understanding the impact of gene interactions on disease phenotypes is increasingly recognised as a crucial aspect genetic research. This trend reflected by growing amount clinical research oligogenic diseases, where manifestations are influenced combinations variants few specific genes. Although statistical machine-learning methods have been developed to identify relevant variant or associated with they rely abstract features and black-box models, posing challenges interpretability for...
The Sleeping Cell problem is a particular type of cell degradation in Long-Term Evolution (LTE) networks. In practice such outage leads to the lack network service and sometimes it can be revealed only after multiple user complains by an operator. this study becomes sleeping because Random Access Channel (RACH) failure, which may happen due software or hardware problems. For detection malfunctioning cells, we introduce data mining based framework. its core analysis event sequences reported...
Many commonly used data-mining techniques utilized across research fields perform poorly when for large data sets. Sequential agglomerative hierarchical non-overlapping clustering is one technique which the algorithms' scaling properties prohibit of a amount items. Besides unfavorable time complexity O(n2), these algorithms have space can be reduced to O(n) if allowed rise O(n2 log2n). In this paper, we propose use locality-sensitive hashing combined with novel structure called twister tries...
Several smart cities around the world have begun monitoring parking areas in order to estimate free spots and help drivers that are looking for parking. The current results indeed promising, however, this approach is limited by high costs of sensors need be installed throughout city achieve an accurate estimation rate. This work investigates extension estimating information from equipped with missing them. To end, similarity values between neighborhoods computed based on background data,...
Language Models (LMs) have proven to be useful in various downstream applications, such as summarisation, translation, question answering and text classification. LMs are becoming increasingly important tools Artificial Intelligence, because of the vast quantity information they can store. In this work, we present ProP (Prompting Probing), which utilizes GPT-3, a large Model originally proposed by OpenAI 2020, perform task Knowledge Base Construction (KBC). implements multi-step approach...