Anna Saranti

Anna Saranti
Medical University of Graz · Institute of Medical Computer Sciences, Statistics and Documentation

Dipl.-Ing.

About

28
Publications
12,396
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
342
Citations

Publications

Publications (28)
Article
Motivation: The tremendous success of graphical neural networks (GNNs) already had a major impact on systems biology research. For example, GNNs are currently being used for drug target recognition in protein-drug interaction networks, as well as for cancer gene discovery and more. Important aspects whose practical relevance is often underestimate...
Preprint
Full-text available
Machine learning methods can detect complex relationships between variables, but usually do not exploit domain knowledge. This is a limitation because in many scientific disciplines, such as systems biology, domain knowledge is available in the form of graphs or networks, and its use can improve model performance. We need network-based algorithms t...
Preprint
Full-text available
The tremendous success of graphical neural networks (GNNs) has already had a major impact on systems biology research. For example, GNNs are currently used for drug target recognition in protein-drug interaction networks as well as cancer gene discovery and more. Important aspects whose practical relevance is often underestimated are comprehensibil...
Chapter
Explainable Artificial Intelligence (xAI) is an established field with a vibrant community that has developed a variety of very successful approaches to explain and interpret predictions of complex machine learning models such as deep neural networks. In this article, we briefly introduce a few selected methods and discuss them in a short, clear an...
Preprint
Full-text available
Last years have been characterized by an upsurge of opaque automatic decision support systems, such as Deep Neural Networks (DNNs). Although they have great generalization and prediction skills, their functioning does not allow obtaining detailed explanations of their behaviour. As opaque machine learning models are increasingly being employed to m...
Preprint
Full-text available
Machine Learning (ML) and Artificial Intelligence (AI) have shown promising results in many areas and are driven by the increasing amount of available data. However, this data is often distributed across different institutions and cannot be shared due to privacy concerns. Privacy-preserving methods, such as Federated Learning (FL), allow for traini...
Article
Full-text available
We propose a novel classification according to aggregation functions of mixed behavior by variability in ordinal sums of conjunctive and disjunctive functions. Consequently, domain experts are empowered to assign only the most important observations regarding the considered attributes. This has the advantage that the variability of the functions pr...
Preprint
Full-text available
Machine intelligence is very successful at standard recognition tasks when having high-quality training data. There is still a significant gap between machine-level pattern recognition and human-level concept learning. Humans can learn under uncertainty from only a few examples and generalize these concepts to solve new problems. The growing intere...
Chapter
The study of visual concept learning methodologies has been developed over the last years, becoming the state-of-the art research that challenges the reasoning capabilities of deep learning methods. In this paper we discuss the evolution of those methods, starting from the captioning approaches that prepared the transition to current cutting-edge v...
Article
Full-text available
AI is remarkably successful and even outperforms human experts in certain tasks, even in complex domains such as medicine. Humans on the other hand are experts at multi-modal thinking and can embed new inputs almost instantly into a conceptual knowledge space shaped by experience. In many fields the aim is to build systems capable of explaining the...
Chapter
Full-text available
Code quality is a requirement for successful and sustainable software development. The emergence of Artificial Intelligence and data driven Machine Learning in current applications makes customized solutions for both data as well as code quality a requirement. The diversity and the stochastic nature of Machine Learning algorithms require different...
Chapter
Full-text available
One-digit multiplication problems is one of the major fields in learning mathematics at the level of primary school that has been studied over and over. However, the majority of related work is focusing on descriptive statistics on data from multiple surveys. The goal of our research is to gain insights into multiplication misconceptions by applyin...
Conference Paper
One-digit multiplication errors are one of the most extensively analysed mathematical problems. Research work primarily emphasises the use of statistics whereas learning analytics can go one step further and use machine learning techniques to model simple learning misconceptions. Probabilistic programming techniques ease the development of probabil...
Conference Paper
Full-text available
Literature in the area of psychology and education provides domain knowledge to learning applications. This work detects the difficulty levels within a set of multiplication problems and analyses the dataset on different error types as described and determined in several pedagogical surveys and investigations. Our research sheds light to the impact...
Article
Full-text available
Learning Analytics (LA) is an emerging field; the analysis of a large amount of data helps us to gain deeper insights into the learning process. This contribution points out that pure analysis of data is not enough. Building on our own experiences from the field, seven features of smart learning analytics are described. From our point of view these...
Article
Full-text available
Learner profiling is a methodology that draws a parallel from user profiling. Implicit feedback is often used in recommender systems to create and adapt user profiles. In this work the implicit feedback is based on the learner's answering behaviour in the Android application UnlockYourBrain, which poses different basic mathematical questions to the...
Conference Paper
Full-text available
Literature in the area of psychology and education provides domain knowledge to learning applications. This work detects the difficulty levels within a set of multiplication problems and analyses the dataset on different error types as described and determined in several pedagogical surveys and investigations. Our research sheds light to the impact...
Conference Paper
Full-text available
Applications that try to enhance learners’ knowledge can profit by the creation and analysis of learner profiles. This work deals with the derivation of an optimal sequence of questions by comparing similar learning behaviour of users of a mathematics training application. The adaptation of the learners’ clusters to the answers of the revised optim...
Conference Paper
Full-text available
In this work we focus on a specific application named “1x1 trainer” that has been designed to assist children in primary school to learn one digit multiplications. We investigate the database of learners’ answers to the asked questions by applying Markov chain and classification algorithms. The analysis identifies different clusters of one digit mu...
Conference Paper
Full-text available
Understanding the behavior of learners within learning applications and analyzing the factors that may influence the learning process play a key role in designing and optimizing learning applications. In this work we focus on a specific application named “1x1 trainer” that has been designed for primary school children to learn one digit multiplicat...
Article
Full-text available
In this paper a way is reflected how the didactical power of podcasting is used for teaching and learning purposes at "Graz University of Technology" (TU Graz) since more than one year. The variety of different didactical scenarios that are in practice is presented and argued as well as the workflow behind. Advantages and disadvantages of software,...
Conference Paper
Full-text available
This work deals with the sonification of a quantum mechanical system and the processes that occur as a result of its quantum me- chanical nature and interactions with other systems. The quantum harmonic oscillator is not only regarded as a system with sonifi- able characteristics but also as a storage medium for quantum in- formation. By representi...
Article
Full-text available
27. Februar 2008 Zusammenfassung Ausgehend von einem tsunamiauslösenden Erdbeben der Stärke 7.8 nach Richter-Skala, das sich am 01.April 2007 in der Nähe der Solomon-Inseln ereignete, beschäftigt sich das aus vier Teilen bestehende Werk "underground sounds" mit dem Phänomen der sich ständig bewegenden und damit klingenden Erde Uber den Echtzeit-Dat...
Article
Full-text available
The composition "underground sounds" -an interdisciplinary project including a concert piece as its artistic element -deals with the phenomenon of the constantly moving, therefore resonating earth and is based on data taken from an earthquake which reached 7.8 on the Richter scale and triggered a tsunami on April 1st, 2007 close to the Solomon Isla...
Article
Full-text available
The composition "underground sounds" -an interdisciplinary project including a concert piece as its artistic element -deals with the phenomenon of the constantly moving, therefore resonating earth and is based on data taken from an earthquake which reached 7.8 on the Richter scale and triggered a tsunami on April 1st, 2007 close to the Solomon Isla...
Article
Full-text available
This paper presents the first results of the implementation of podcasting in computer supported teaching at the University of Technology of Graz. It gives an overview on the state of the art activities on this modern field of educational experience. A comparison between different didactical settings of practice on base of evaluation data is given a...

Network

Cited By

Projects

Projects (2)
Project
This project will provide important contributions to the international research community in the following ways: 1) evidence in various methods of explainability, patterns of explainability, and explainability measurements. Based on empirical studies (“How do humans explain ?”) we will develop a library of explanatory patterns and a novel grammar how these can be combined. Finally, we will define criteria/benchmarks for explainability and provide answers to the question “What is a good explanation?”. 2) Principles to measure effectiveness of explainability and explainability guidelines and 3) Mapping human understanding with machine explanations and deploying an open explanatory framework along with a set of benchmarks and open data to stimulate and inspire further research among the international AI/machine learning community. All outcomes of this project will be made openly available to the international research community.
Project
The digital revolution, in particular big data and artificial intelligence (AI), offer new opportunities to transform healthcare. However, it also harbors a constantly increasing danger to the safety of sensitive clinical data stored in critical healthcare ICT infrastructures. With FeatureCloud, we aim to minimize cyber-crime potential with a novel security-by-design concept while enabling international cross-border collaborative data mining. FeatureCloud will be implemented into a software toolkit for substantially reducing cyber risks to healthcare infrastructure. We will address this massive challenge with the first privacy-by-architecture approach that will ensure that no sensitive data is communicated through any (potentially insecure) communication channels, and not stored in one central point of attack, while still allowing the application of next-generation AI technology. To this end FeatureCloud will integrate federated machine learning (for privacy-preserving data mining) with blockchain technology (for immutability and management of patient rights - including effective revoke of previously given consent). Our FeatureCloud software platform will be based on a ground-breaking new cloud infrastructure that does not require any raw data to be sent to a central data storage – instead it only exchanges learned representations which are anonymous by default. With our consortium we cover all aspects of the value chain: assessment of cyber risks, legal considerations and international policies, development of federated AI technology coupled to blockchaining, app store and user interface design, implementation as certifiable prognostic medical devices, evaluation and translation into clinical practice, commercial exploitation, as well as dissemination and patient trust maximization. In summary, FeatureCloud has the chance to reduce the cyber-risks for AI-assisted healthcare and thereby also pave the way for big data analytics into the Medicine 4.0 age.