A5078285925- Bioinformatics and Genomic Networks
- Machine Learning in Bioinformatics
- Context-Aware Activity Recognition Systems
- Gene expression and cancer classification
- Cardiovascular and exercise physiology
- Physical Activity and Health
- Genetics, Bioinformatics, and Biomedical Research
- Non-Invasive Vital Sign Monitoring
- Data Mining Algorithms and Applications
- Biomedical Text Mining and Ontologies
- Opportunistic and Delay-Tolerant Networks
- Machine Learning and Data Classification
- Data-Driven Disease Surveillance
- Health Literacy and Information Accessibility
- Data Visualization and Analytics
- Time Series Analysis and Forecasting
- Complex Network Analysis Techniques
- Bayesian Modeling and Causal Inference
- Healthcare Technology and Patient Monitoring
- Healthcare Operations and Scheduling Optimization
- Personal Information Management and User Behavior
- Advanced Proteomics Techniques and Applications
- Pharmaceutical industry and healthcare
- IoT and Edge/Fog Computing
Research Studios Austria
2015-2017
University of Maribor
2009-2012
University of Manchester
2011
Tokyo University of Science
2011
Norwegian University of Science and Technology
2011
Classification is an important and widely used machine learning technique in bioinformatics. Researchers other end-users of software often prefer to work with comprehensible models where knowledge extraction explanation reasoning behind the classification model are possible.This paper presents extension existing environment a study on visual tuning decision tree classifiers. The motivation for this research comes from need build effective easily interpretable by so called one-button data...
Background: Patterns in general consumer online search logs have been used to monitor health conditions and predict health-related activities, but the multiple contexts within which consumers perform searches make significant associations difficult interpret. Physician information-seeking behavior has typically analyzed through survey-based approaches literature reviews. Activity from care professionals using medical information resources are thus a valuable yet relatively untapped resource...
Smart phones are increasingly being used to track and recognize different types of activity. However, the task using smart infer intensity sport activities has not received a lot attention yet. Therefore, we study how off-the-shelf with built-in accelerometers can be estimate recreational activities. We focus on finding most appropriate model along set high level acceleration features that could predict heart rate during activity resource constrained phone device. collect more than 300...
Predicting protein solubility has gained lots of intention in the recent years and several descriptors have been defined to describe proteins these works. Therefore, different feature selection methods used for selecting most important attributes. An empirical study, that aims explain relationship between number samples stability seven techniques datasets, is presented.
Often, the most informative genes have to be selected from different gene sets and several computer ranking algorithms been developed cope with problem. To help researchers decide which algorithm use, we analysis of (AGRA) system that offers a novel technique for comparing ranked lists genes. The important feature AGRA is no previous knowledge needed their comparison. Using text mining finding-associated concepts analysis. defines what call biomedical concept space (BCS) each list comparison...
DNA microarray is a technology that can simultaneously measure the expression levels of thousands genes in single experiment. Often, most informative have to be selected from different gene level datasets. One possible ways rank use feature selection (FS) method. There are many FS methods which used, but how do researches know one best? Several were proposed estimate "goodness" ranked lists [2–4]. However, these usually require computer experts and learning algorithms work. Therefore we...
The six sessions of the 13th International Workshop on Mobile Computing Systems and Applications (HotMobile 2012) covered mobile advertising, infrastructure tools support, health travel challenges, applications, security networking, indoor localization. HotMobile proved to be perfect venue for presenting ground-breaking out-of-the-box ideas that will help shape future community.