Hanreich M., Krauss O., Zwettler G.”Efficient classification of live sensor data on Low-Energy IoT devices with simple Machine Learning methods”, EUROCAST 2024.



Internet of Things (IoT) devices are ubiquitous, but often cannot be permanently connected to the power grid and therefore have to rely on batteries and other energy sources like solar power. These mobile devices should run over a long period without the need for recharging, but still be able to perform comparatively complex tasks from the realm of machine learning like a classification task on live sensor data. The state-of-the-art as far as accuracy is concerned are Neural Network models like LSTM (Long short-term memory) or CNN (Convolutional neural network). However, these models usually take up more Flash memory, more RAM of the devices and more CPU time than traditional machine learning approaches, which in turn causes a higher energy demand. Another possibility is to transfer the time series data to an external server to do the calculations there and send back the result. For a continuous classification of sensor data, this approach is often not feasible, since the constant transmission of a large quantity of data over a wireless network is required. We discuss a pipeline for efficient time series classification of live sensor data on low-energy IoT devices with on-device processing. We present our case study of detecting boats docking at an IOT-enabled buoy, which is required to be energy-self-sufficient for several months at a time.

Mühle H., Krauss O., Stöckl A.”The Human-Centered AI-DATA Model for
Digital Customer Journeys in E-Commerce”, EUROCAST 2024.



In an era characterized by rapid technological advancements and increasingly complex socio-technical systems, especially regarding Artificial Intelligence (AI) based E-Commerce Optimization, the demand for a comprehensive method to resolve problems, which could result from the lack of trust in AI-Software-Systems, has never been more significant. Systems thinking offers a robust framework for understanding the intricate relationships between various components of a system, making it particularly relevant in today’s digital and AI-based software landscape. Concurrently, the E-Commerce sector is undergoing a transformation, driven by advancements in AI and data analytics grounded in legal changes regarding the General Data Protection Regulation (GDPR) and the upcoming EU AI Act. We explore the synergies between AI-based E-Commerce and Systems Thinking by introducing the AI-DATA model, a human-centered Customer Journey Optimization approach in the context of E-Commerce marketing strategy based on Trustworthy AI. AI-DATA is a phase model consisting of Awareness, Interest, Desire, Action, Trust and Again, and is an extension of the AIDA model, which also considers the customer path to contain activities after a transaction has finished, and a cycle of repeat customers.

Sandler S., Krauss O., Stöckl A.”Using LLMs and Websearch in Order to Perform Fact Checking on Texts Generated by LLMs”, EUROCAST 2024.



This paper targets the detection of misinformation in GPT3 generated texts and the FEVER[7] dataset, using Large Language Models (LLM) and Google search. Given the uncertainty associated with LLM-produced text, a requisite arises for a fact-checking system geared towards non-human-written content under varied contexts. In general, there are two different approaches to perform fact checking: manual checking, favored by entities like politifact, and automated or semi-automated checking, like ProoFVer. Our research delvesinto fully automated checking of LLM-produced texts.

Praschl C., Dalkilic M., Bauernfeind S., Wakolbinger M., Zwettler G.”Customization and Analysis of Orthopedic Aids”, EUROCAST 2024.



In addressing congenital malformations, managing chronic diseases, and tending to musculoskeletal injuries, the provision of appropriate orthopedic aids like prostheses and orthoses stands as a pivotal measure. These aids need to be precisely tailored to the patient’s needs and anatomy, a task traditionally undertaken by skilled orthopedists or orthopedic technicians. However, this process has predominantly adhered to analog methodologies. Yet, the landscape is shifting with the emergence of adaptive manufacturing techniques, which is catalyzing the progression of orthopedic technology in the context of Industry 4.0. This transformative trajectory incorporates digital avenues such as 3D scans of the human body, 2D pedobarographic scans that aid in recommending suitable orthopedic correctives, and digitally manufactured orthopedic aids. By combining these processes – model creation through scans and patient-specific adaptions – it becomes possible in implementing a (semi-) automated approach to orthopedics. This raises the question: How can orthopedic aids be automatically customized while ensuring their structural integrity?

Praschl C., Schedl D., Stöckl A. “Modeling Wildlife Accident Risk with Gaussian
Mixture Models”, EUROCAST 2024.



Traffic accidents involving wildlife pose a widespread problem globally, harming both humans and nature. Additionally, these incidents often result in heavy vehicle damage, leading to expensive repairs and insurance claims. To mitigate these accidents, e↵orts are underway to better understand wildlife populations near high-risk roads and implement preventive measures such as visual or audible wildlife warning devices, partially utilizing artificial intelligence (AI). To prevent wildlife accidents, high-risk areas must be identified first. In this work, we propose a model that predicts dangerous areas based on animal sightings and apply it to two road segments in Austria.


Praschl, C., Krauss, O. “Extending 3D geometric file formats for geospatial applications”. Appl Geomat (2023).



This study addresses the representation and exchange of geospatial geometric 3D models, which is a common requirement in various applications like outdoor mixed reality, urban planning, and disaster risk management. Over the years, multiple file formats have been developed to cater to diverse needs, offering a wide range of supported features and target areas of application. However, classic exchange formats like the JavaScript Object Notation and the Extensible Markup Language have been predominantly favored as a basis for exchanging geospatial information, leaving out common geometric information exchange formats such as Wavefront’s OBJ, Stanford’s PLY, and OFF. To bridge this gap, our research proposes three novel extensions for the mentioned geometric file formats, with a primary focus on minimizing storage requirements while effectively representing geospatial data and also allowing to store semantic meta-information. The extensions, named GeoOBJ, GeoOFF, and GeoPLY, offer significant reductions in storage needs, ranging from 14 to 823% less compared to standard file formats, while retaining support for an adequate number of semantic features. Through extensive evaluations, we demonstrate the suitability of these proposed extensions for geospatial information representation, showcasing their efficacy in delivering low storage overheads and seamless incorporation of critical semantic features. The findings underscore the potential of GeoOBJ, GeoOFF, and GeoPLY as viable solutions for efficient geospatial data representation, empowering various applications to operate optimally with minimal storage constraints.

Praschl C., Stöckl A., Fleischer M., Schedl D. “Assessment of Wildlife Accident Risk using a Drone-based Population Monitoring System”. EU Safety 2023.


This study addresses the pressing issue of wildlife-related road accidents in Austria by developing an innovative approach using georeferenced drone data and a sophisticated statistical risk model. Despite technological advancements, accidents involving wild animals continue to pose a significant threat to road safety. Our research focuses on comprehensive data collection using camera drones equipped with visual and thermal sensors. Through extensive testing in high-risk areas of Upper and Lower Austria, we identified and counted various animals, including roe deer, rabbits, and pheasants, during different times of the day. The collected data were analyzed to create a robust statistical risk model, providing insights into possible animal effects on roads.

Praschl C., Zopf L., Kiemeyer E., Langthallner I., Ritzberger D., Slowak A., Weigl M., Blüml V., Nešić N., Stojmenović M., Kniewallner K.,Aigner L., Winkler S., Walter A. “U-Net based vessel segmentation for murine brains with small μMRI reference datasets“. Plos one (2023).

DOI: 10.1371/journal.pone.0291946


Identification and quantitative segmentation of individual blood vessels in mice visualized with preclinical imaging techniques is a tedious, manual or semiautomated task that can require weeks of reviewing hundreds of levels of individual data sets. Preclinical imaging, such as micro-magnetic resonance imaging (µMRI) can produce tomographic datasets of murine vasculature across length scales and organs, which is of outmost importance to study tumor progression, angiogenesis, or vascular risk factors for diseases such as Alzheimer’s. Training a neural network capable of accurate segmentation results requires a sufficiently large amount of labelled data, which takes a long time to compile. Recently, several reasonably automated approaches have emerged in the preclinical context but still require significant manual input and are less accurate than the deep learning approach presented in this paper – quantified by the Dice score. In this work, the implementation of a shallow, three-dimensional U-Net architecture for the segmentation of vessels in murine brains is presented, which is (1) open-source, (2) can be achieved with a small dataset (in this work only 8 μMRI imaging stacks of mouse brains were available), and (3) requires only a small subset of labelled training data. The presented model is evaluated together with two post-processing methodologies using a cross-validation, which results in an average Dice score of 61.34% in its best setup. The results show, that the methodology is able to detect blood vessels faster and more reliably compared to state-of-the-art vesselness filters with an average Dice score of 43.88% for the used dataset.

Christoph Praschl and David Schedl, “Towards an Automated Biodiversity Modelling Process for Forest Animals using Uncrewed Aerial Vehicles” in Proceedings of the 11th International Workshop on Simulation for Energy, Sustainable Development & Environment (SESDE 2023), 2023.



Climate change poses a grave threat to habitats such as forests, endangering the integrity and biodiversity of the global flora and fauna. Accurate surveying techniques are crucial to model populations, detect over and under populations, and address them accordingly. This work proposes a process for creating a biodiversity model of a forest’s fauna using uncrewed aerial vehicles equipped with RGB and thermal cameras. Real-world data, combined with computer-generated imagery and artificial intelligence models, will allow training suitable computer vision models. These models will serve as a reliable and objective data source, enabling the creation of statistical models to describe the monitored forests’ conditions and the biodiversity of its fauna. The proposed methodology is expected to have significant implications for conservation efforts. It should represent a reliable and efficient way to monitor and evaluate forest ecosystems, identifying areas of concern and prioritizing conservation efforts. By providing a comprehensive understanding of the biodiversity within a forest, it could help policymakers make informed decisions and develop effective conservation strategies. Ultimately, this work aims to contribute to the preservation of our planet’s biodiversity and the protection of its habitats.

Gerald Adam Zwettler, Martin Trixner, Clemens Schartmüller, Sophie Bauernfeind, Thomas Stockinger and Christoph Praschl, “Towards an Automated Process for Adaptive Modelling of Orthoses and Shoe Insoles in Additive Manufacturing” in Proceedings of the 12th International Workshop on Innovative Simulation for Healthcare (IWISH 2023), 2023.



Although orthopedics is becoming increasingly important as a medical domain, especially in emerging countries, the level of automation is still marginal and hardly any Industry 4.0 paradigms have been implemented. In this scientific work, solution concepts for holistic process automation in orthopedics are introduced so that prosthetic covers and orthoses for different body regions can be automated by using AI and evaluated with sensor networks. In this process, body scan models are adapted to the conditions of the anatomy or prosthesis models, so that stability as well as fitting accuracy are given in comparison with the other half of the body. Automation in the field of orthopedics leads not only to a significant reduction in costs but can also help to close the research gap regarding objectifiability of results. The first partial aspects have already been successfully implemented for leg prostheses, arm prostheses and shoe insoles with the aid of machine learning processes and physical models for elastic form fitting. As soon as the overall process has been realized, the applicability will be validated in the following year of the project by means of clinical studies and evaluated by utilizing sensor networks for pressure and temperature measurements.

Andreas Pointner, Christoph Praschl and Oliver Krauss, “Enhancing Interoperability of HL7 Resources Using Namespaces in Graph Databases” in Proceedings of the 12th International Workshop on Innovative Simulation for Healthcare (IWISH 2023), 2023.



The adoption of the FHIR (Fast Healthcare Interoperability Resources) standard has led to an exponential growth of modular healthcare data that needs to be managed efficiently. Graph databases such as Neo4j offer an effective way to store and query this data, but can become complex when dealing with FHIR resources that contain numerous extensions. We explore the use of namespaces in Neo4j graph databases to manage FHIR resources and compare it with the existing tool, CyFHIR. We demonstrate that by embedding extensions using the namespace concept, the complexity of the graph can be significantly reduced. Furthermore, we evaluate our approach on a generated dataset and show that the use of namespaces in Neo4j outperforms CyFHIR conventional methods for storing FHIR resources in graph databases. Our findings suggest that the use of namespaces can be a valuable addition to Neo4j graph databases for managing complex FHIR resources.

Clara Diesenreiter, Oliver Krauss and Barbara Traxler, “Extending International Terminology Systems to Enhance Communication Between Nursing Services” in Proceedings of the 12th International Workshop on Innovative Simulation for Healthcare (IWISH 2023), 2023.



Nursing care is a crucial part of health care, especially in our ageing society. Digitalization in this area is lacking when attempting to conduct a machine-readable, standardized, healthcare data exchange between different services. To tackle this issue two standards, International Classification for Nursing Practice (ICNP) and Systematized Nomenclature of Medicine Clinical Terms (SNOMED CT), identified as highly relevant code systems in this sector via expert interviews, were analysed. A competency catalogue of 241 terms was then mapped to both of these systems, in some case extending them with new concepts and terms. The results show that neither code system was able to translate many of the terms without extension, with ICMP covering 12,03% and SNOMED CT covering 26,14%. However, both systems can be extended, with SNOMED CT showing a better capability to support data exchange in nursing care.

Oliver Krauss, Andreas Schuler, “Identifying Energy Efficiency Patterns in Sorting Algorithms via Abstract Syntax Tree Mining” in Proceedings of the 22nd International Conference on Modelling and Applied Simulation (MAS 2023), 2023.



Energy efficiency is an important topic in the area of mobile computing. Developers are often unaware of the impact their choices ondata type use and algorithm design have on this non-functional property. Software energy consumption profiling can be utilized toidentify the energy behaviour of implemented methods, while pattern mining can be utilized to identify recurring patterns in themethods being run. We present a methodology to combine energy consumption profiling and discriminative pattern mining to identifyenergy efficiency patterns. In a study of eight sorting algorithms implemented in Java with the data types int, double and Comparable,profiled on the Android platform, we manage to identify significant patterns in the source code of these 24 implementations. Theresults show that patterns can be identified for both, the data type in use, and for the energy behaviour of efficient or inefficient sortingalgorithms, that explain the observed energy profiles.

Simone Sandler, Oliver Krauss, Elisabeth Mayrhuber, Andreas Stöckl, “Using An Event Hierarchy for İmproved Process Mining of Website User Behaviour” in Proceedings of International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME), 2023.


In the quest for improving systems, understanding user behaviour is a crucial step towards achieving optimal results. One technique that aids in comprehending user behaviour is process mining, which involves analysing event logs of a system. However, the accuracy of the process mining results can be impeded by large amounts of data or very unstructured processes, leading to confusion and difficulties in interpretation. To overcome this challenge, preprocessing techniques exist to enhance the resulting process maps. This work proposes a preprocessing method that utilizes an event hierarchy to produce a sanitized process map, that is easier to interpret. The proposed method involves analysing the event logs and creating a hierarchical structure of the events. This hierarchy allows the identification of relevant events and their corresponding dependencies, which in turn enables the extraction of useful process information. This preprocessing method has been tested on event data from an online newspaper, and it has shown promising results in improving readability of the resulting process maps. By utilizing an event hierarchy, relevant information can be extracted from large amounts of data and unstructured processes, leading to cleaner process maps that aid in understanding user behaviour.

Sebastian Pritz, Martina Zeinzinger, Christoph Praschl, Oliver Krauss, Martin Harrer, “Performance Impact of Parallel Access of Time Series in the Context of Relational, NOSQL and NEWSQL Database Management Systems” in Proceedings of International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME), 2023.


Time series data is generated in various application areas, such as IoT devices or sensors in vehicles. This type of data is often characterized by a high resource demand due to the interval at which information is measured ranges from daily down to milliseconds. Next to the frequency, the number of data sources, for example hundreds of sensors in modern airplanes generating time series concurrently, is typical for such big data scenarios. Such scenarios require the persistence of the measurements for further evaluations. In this work, we introduce an artificial data benchmark for relational, NoSQL, and NewSQL database management systems in the context of time series. We compare these databases by having multiple read and write data sources accessing the database management systems simultaneously. The evaluation shows that no tested system outperforms all other systems. While DolphinDB shows the highest read performance in single-user scenarios, CrateDB is able to show its advantages regarding when multiple users access the data simultaneously.

Christoph Praschl, Sophie Bauernfeind, Christian Leitner, Gerald Zwettler, “Domain-Driven Design as a Model Contract in Full-Stack Development” in Proceedings of International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME), 2023.


In this work, a domain-driven design process is proposed, allowing to define a contract regarding the structure of the used data within a multi-language full-stack application using a model-to-text transformation approach. This process is based on a metamodel, which allows for the implementation of language-specific transformers to generate representations of the data as domain models for arbitrary programming languages. It is evaluated in the context of a modern full-stack microservice architecture including a C\# and Python based backend with access to a database using object-relational-mapping principles and a TypeScript based frontend, connected by a GraphQL interface. The proposed methodology is intended for an agile modelling process including automatic adaptions, but also the preservation of user-defined extensions within the generated source-code artifacts.

Andreas Pointner, Martin Harrer, “A Rule Based Data Cleansing Pipeline for Automated Data Import in the Context of Social Clubs” in Proceedings of International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME), 2023.


Managing the member data of social clubs can be a tedious task. However, there are software solutions available that can help streamline this process. This although means, that existing member data, that is often in the form of text-based data formats like CSV, or semi-structured formats like XML, or Excel needs to be imported in those tools. Unfortunately, the data in these formats may contain errors, inconsistencies, and missing values, which can compromise the usability of this data. In this work, a rule-based data cleansing pipeline designed to clean, enrich, and transform social club member data into a suitable format for import into software solutions is presented. The approach is evaluated on a small data sample and shows promising results for such an application scenario.

Elisabeth Mayrhuber, Oliver Krauss, Martin Hanreich, Andreas Stöckl, “Towards an Ontology and Process Mining-Based System for Targeted E-Commerce Marketing Strategy Suggestions” in Proceedings of International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME), 2023.


This paper presents an ontology and process mining-based system that employs semantic technologies for targeted e-commerce marketing strategy suggestions. The proposed approach utilizes ontologies as a knowledge representation formalism to capture the domain knowledge, product descriptions, and website texts in the e-commerce domain. The ontology is populated with relevant attributes and corresponding values, allowing for a structured and standardized representation of users and content.

To suggest targeted marketing strategies, the system employs interest and intensity calculation techniques that utilize the concept of scroll depth and others to measure the interest in different contents and customer preferences.

Process mining techniques identify moments of truth along the customer journey and happy paths a customer usually goes through. Once the ontology is combined with the process mining results, it can be identified in which phase of the customer journey a user is, and it can be determined what marketing actions to employ to get them to enter the next phase of a marketing model.

Overall, the proposed approach is a promising approach to address the challenges of personalized e-commerce marketing strategy suggestions by utilizing ontology-based knowledge representation and intensity calculation techniques. The system has the potential to provide personalized and targeted marketing strategies for e-commerce businesses, leading to increased customer engagement, loyalty, and sales.

Sophie Bauernfeind, Christoph Praschl, Markus Wakolbinger, Gerald Zwettler, “Classification of Footprints for Correctives in Orthopedics” in Proceedings of International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME), 2023.


Foot disorders, a commonly overlooked issue, are prevalent in developed societies. These disorders can have a significant impact on a person’s quality of life and can even be debilitating, regardless of age. Non-invasive pedobarographic examinations, which evaluate the pressure fields of the plantar surface of the foot and a supporting surface, allow for analysis of a patient’s gait and posture using 2D footprints or scans. This data can then be used by orthopaedists to create customized shoes or insoles as correctives. However, the lack of standardized protocols and guidelines and the scarcity of evidence-based information can lead to a subjective evaluation and selection of correctives by the orthopaedist. This study proposes an objective and quantifiable method for the classification of footprints using computer vision paradigms, in order to create more appropriate correctives. The results show that the proposed machine learning models are able to correctly identify the required one of three correctives with an accuracy of 70% for RGB scans and 49% for blueprints. Based on the current results, future work should focus not only on the classification of suitable correctives, but also on the determination of the corrective’s position to ensure the best possible patient outcomes.

Erhard, A., Arthofer, K., & Helm, E. (2023). Extending a Data Management Maturity Model for Process Mining in Healthcare. Studies in Health Technology and Informatics301, 192-197.

DOI: 10.3233/SHTI230038


Pointner, A., Krauss, O., Erhard, A., Schuler, A., & Helm, E. (2023). Multi-Perspective Process Mining Interfaces for HL7 AuditEvent Repositories: XES and OCEL. In dHealth 2023 (pp. 168-173). IOS Press.

DOI: 10.3233/SHTI230034



A. Pointner, “Mining Attributed Input Grammars and their Applications in Fuzzing,” 2023 IEEE Conference on Software Testing, Verification and Validation (ICST), Dublin, Ireland, 2023, pp. 493-495

DOI: 10.1109/ICST57152.2023.00059


Undetected errors in software systems are a common cause of vulnerabilities and security holes. Grammar Fuzzing is an effective method for testing these systems, but it has limitations such as lack of knowledge about the semantics of the program and difficulty obtaining grammar for these systems. To address these limitations, we propose an approach to automatically mine grammars, and enhance it with semantic rules and contextual constraints to create attribute grammars. These attribute grammars can then be used for fuzzing. Our preliminary results show that this automated extraction process is feasible, as we successfully applied it to an expression parser and were able to extract an attribute grammar representing the parser’s functionality.

Schuler S., Praschl C., Pointner A. (2023). Analysing and Transforming Graph Structures: The Graph Transformation Framework. In Software 2023.



Interconnected data or, in particular, graph structures are a valuable source of information. Gaining insights and knowledge from graph structures is applied throughout a wide range of application areas, for which efficient tools are desired. In this work we present an open source Java graph transformation framework. The framework provides a simple fluent Application Programming Interface (API) to transform a provided graph structure to a desired target format and, in turn, allow further analysis. First, we provide an overview on the architecture of the framework and its core components. Second, we provide an illustrative example which shows how to use the framework’s core API for transforming and verifying graph structures. Next to that, we present an instantiation of the framework in the context of analyzing the third-party dependencies amongst open source libraries on the Android platform. The example scenario provides insights on a typical scenario in which the graph transformation framework is applied to efficiently process complex graph structures. The framework is open-source and actively developed, and we further provide information on how to obtain it from its official GitHub page.

Praschl, C. , Kaiser, R., and Zwettler, G. (2023). Generative Adversarial Network Synthesis for Improved Deep Learning Model Training of
Alpine Plants with Fuzzy Structures
. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications – VISAPP.



Deep learning approaches are highly influenced by two factors, namely the complexity of the task and the size of the training data set. In terms of both, the extraction of features of low-stature alpine plants represents a challenging domain due to their fuzzy appearance, a great structural variety in plant organs and the high effort associated with acquiring high-quality training data for such plants. For this reason, this study proposes an approach for training deep learning models in the context of alpine vegetation based on a combination of real-world and artificial data synthesised using Generative Adversarial Networks. The evaluation of this approach indicates that synthetic data can be used to increase the size of training data sets. With this at hand, the results and robustness of deep learning models are demonstrated with a U-Net segmentation model. The evaluation is carried out using a cross-validation for three alpine plants, namely Soldanella pusilla, Gnaphalium supinum, and Euphrasia minima. Improved segmentation accuracy was achieved for the latter two species. Dice Scores of 24.16% vs 26.18% were quantified for Gnaphalium with 100 real-world training images. In the case of Euphrasia, Dice Scores improved from 33.56% to 42.96% using only 20 real-world training images.


Krauss O., “Amaru: a framework for combining genetic improvement with pattern mining” in Proceedings of the Genetic and Evolutionary Computation Conference Companion. 2022.


We present Amaru, a framework for Genetic Improvement utilizing Abstract Syntax Trees directly at the interpreter and compiler level. Amaru also enables the mining of frequent, discriminative patterns from Genetic Improvement populations. These patterns in turn can be used to improve the crossover and mutation operators to increase population diversity, reduce the number of individuals failing at run-time and increasing the amount of successful individuals in the population.

Krauss, Oliver, and Konstantin Papesh. “Analysis of Threat Intelligence Information Exchange via the STIX Standard.” 2022 In International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME). IEEE, 2022.


Threat Information exchange is a highly relevant topic in today’s environment of increasing data breaches, hacks and scams. Standardized formats for exchanging such information exist, but if and how they are used by an active community is determinant for gaining information from such provided information. We provide an in depth analysis of the current state of the Structured Threat Information Expression (STIX) standard, consisting of 5 different active threat information providers. Based on an analysis of 480,867 threat information objects, we find that the STIX standard is not used to its full capabilities, and lacks usefulness due to the quality and upto-dateness of the information. We give suggestions for future improvements of standards based threat information exchange, such as more adherence to the core standard, and fostering an active community.

Mayrhuber E., Krauss O., “User Profile-Based Recommendation Engine Mitigating the Cold-Start Problem” in Proceedings of International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME), 2022.


Recommendation systems can be used in many situations in daily life. Recommending people on social media networks, products in various online shops, music, or movies are only a few use cases of these systems. The cold start problem, when no information about a new or infrequent user is available, is challenging for recommendation systems. We deal with creating restaurant and category recommendations for restaurant visitors. Recommendations are generated with different metrics and technologies based on user profiles to make recommendations as individual as possible. We use kMeans and Mean-Shift for clustering users to build a base for recommendations generated using user-based and contentbased collaborative filtering methods. These suggestions consider
the location of restaurants, the similarity between users and restaurants, and the ratings users give. We mitigate the cold-start problem by using matrix factorization and spatial information for users with few restaurant visits in the past. Recommendations are evaluated and adapted as a result of other user behavior to obtain better results. As a result, we can query recommendations
via an Application Programming Interface (API), which consist of a mixture of location and user-based recommendation to please the users’ needs by combining exploration and exploitation.

Praschl C., Pritz S., Krauss O., Harrer M., “A Comparison Of Relational, NoSQL and NewSQL Database Management Systems For The Persistence Of Time Series Data” in Proceedings of International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME), 2022.


Time series data is created in a variety of application areas such as sensors in cars, smartwatches or IoT devices. This kind of data is often characterized by high resource demand due to the frequency the information is measured, with data points once a day, hour and even down to milliseconds. While real-time processing of such data is often sufficient, there are also many use cases, where batch processing and consequently the storage and managed access of measurements is required. For this reason, this work evaluates different database management systems in the context of storing time related data using different data models such as classical relational models, non-relational models using NoSQL database systems and the recently upcoming group of NewSQL databases. The evaluation shows that a highly optimized time series databases such as InfluxDB is able to outperform the other tested systems regarding write-throughput and RAM as well as disk utilization in a single server setup.

Clara Diesenreiter, Oliver Krauss, Simone Sandler, Andreas Stöckl, “ProperBERT – Proactive Recognition of Offensive Phrasing for Effective Regulation” in Proceedings of International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME), 2022.


This work discusses and contains content that may be offensive or unsettling. Hateful communication has always been part of human interaction, even before the advent of social media. Nowadays, offensive content is spreading faster and wider through digital communication channels. To help improve regulation of hate speech, we introduce ProperBERT, a fine-tuned BERT model for hate speech and offensive language detection specific to English. To ensure the portability of our model, five data sets from literature were combined to train ProperBERT. The pooled dataset contains racist, homophobic, misogynistic and generally offensive statements. Due to the variety of statements, which differ mainly in the target the hate is aimed at and the obviousness of the hate, a sufficiently robust model was trained. ProperBERT shows stability on data sets that have not been used for training, while remaining efficiently usable due to its compact size. By performing portability tests on data sets not used for fine-tuning, it is shown that fine-tuning on large scale and varied data leads to increased model portability.

Sandler Simone, Krauss Oliver, Diesenreiter Clara, Stöckl
Andreas, “Detecting Fake News and Performing Quality Ranking of German News Papers Using Machine Learning” in Proceedings of International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME), 2022.


Nowadays, news spread quickly, and it is not always clear to the reader whether an article is real or fake. Moreover, readers use only a few sources to read the news without knowing the quality of the source. This is due to a lack of up-to-date
news or media rankings. Machine learning models can be used to automatically detect fake news. In this work, a Passive-Aggressive-Classifier, a Random-Forest, and an LSTM network are trained to distinguish between fake and non-fake (real)
news. Moreover, these models are used to classify news sources according to the amount of possible Fake News they may spread. The models are tested on English and translated German articles. The best results for Fake News detection on English articles is reached with the Passive-Aggressive-Classifier. For automatic
news ranking of translated German articles, Random-Forest provides the best result. The correlation of Random-Forest with an actual news ranking reached 0.68. This shows that automated classification can be extended to languages other than English, using this approach. In the future, other machine learning models
and translators will be used to extend the approach.

A. Veichtlbauer, C. Praschl, L. Gaisberger, G. Steinmaurer and T. I. Strasser, “Toward an Effective Community Energy Management by Using a Cluster Storage,” in IEEE Access, vol. 10, pp. 112286-112306, 2022.

DOI: 10.1109/ACCESS.2022.3216298.


The integration of renewable local energy generation in single households – turning the household into a “prosumer” – is an important way to support an ecological transition of the electric power system. However, due to the volatile and distributed nature of most renewable energy sources, the power system may face stability problems when integrating a large number of renewables. The paper at hand describes an approach to overcome these shortages in a two-fold manner: First, the effects of the installed renewables shall be limited locally to a group of households – a so-called “energy community”. To do so, all the participating households are using existing self-consumption optimization tools. However, when a household has excess energy which can not be consumed locally, this energy is shared among the other participating households by using a cluster storage device, thus enabling a community self-consumption before feeding into the low-voltage distribution grid. Second, the connected operator may request flexibility from the participating households. For that, additional loads or load sheds are triggered by the requesting grid operator, depending on the current situation in the grid. The households decide autonomously about the amount of granted flexibility, receiving respective financial incentives. This work introduces an energy management concept and a prototypical control infrastructure used for the aforementioned functionalities. In a number of simulations and field tests, the proposed approach was successfully evaluated. The article provides a comprehensive overview of the gained results and the conclusions derived from them.

Pritz S., Praschl C., Kaiser R., Zwettler, G. “Visual Change Detection in Multi-Temporal Transects of Alpine Plants”. Proceedings of the 10th International Workshop on Simulation for Energy, Sustainable Development & Environment SESDE2022, Rom, Italy (2022).


Due to the apparent effects of climate change on the Earth’s ecosystems, it is more important than ever to monitor flora and fauna in affected regions, e.g. mountain areas above the tree line. In the alpine ecosystem, and not just there, Vegetation plays a fundamental role and is the subject of this study. The work aims to develop algorithms for recognising small stature alpine plants from close range top view images. Ideally, automated assessment algorithms of the plant cover should objectively help scientists observe and interpret the state of the plant ecosystem over a long time series. Therefore, the aim in this respect was to derive visualisations that accurately describe plant growth and displacement (translocation). Additionally, recording changes in biodiversity was an intent. This work uses multi-temporal data comprising RGB images and multi-label masks to accomplish the aforementioned task. The evaluated methods involve mask comparison, optical flow estimation, detection of individual plants, and descriptive statistical analysis of image feature properties. Tests on the given data set show that all methods but the optical flow estimation have great potential. The mask comparison method captured plant growth and translocation most satisfactory. Individual plant detection and statistical analysis further helped to evaluate changes in biodiversity. When combined, the proposed methods give an immediate overview about relevant changes in the multi-temporal transects, which has not been done before for close-distance images of alpine plants.

Krauss O., Aschauer A., Stöckl A. “Modelling shifting trends over time via topic analysis of text documents”. Proceedings of the 34rd European Modeling and Simulation Symposium EMSS2022, Rom, Italy (2022).

Pointner A., Praschl C., Krauss O. “Towards Modelling Namespaces in Graph Databases”. Proceedings of the 34rd European Modeling and Simulation Symposium EMSS2022, Rom, Italy (2022).


We present a novel approach to store data with different contexts inside a property graph model. We introduce namespaces, similar to namespaces in XML, and extend nodes and relationships with labels to assign them to a specific context, i.e. namespace. Individual properties of a node or relationship can also be put in a namespace. This work is specifically targeting the utilization in graph databases, with a reference implementation provided via the Neo4j database. In addition to the theoretical approach, an object to graph mapper for the programming language Java is implemented and used to evaluate the approach. As an evaluation example, a university organization is used, which is split into two domains. The experiments show, that information of different domains can be stored within the same model using namespaces. Thus, it is possible to reuse shared information over multiple contexts, which reduces data duplication in the graph database, as otherwise multiple nodes would be required.

Zwettler, G., Ono, Y., Stradner, M., & Praschl, C. “Strategies for Semi-Automated Registration of Historic Aerial Photographs Utilizing Street and Roof Segmentations as Durable Landmarks”. Proceedings of the 34th European Modeling and Simulation Symposium EMSS2022, Rom, Italy (2022).


Historical and current aerial photographs are only of great value if the geolocation or address of the photographed areas is also available. In Western Europe, especially Austria, Germany and Czech Republic, there is a market for the sale of aerial photographs of one’s own private residential building. Automated geolocation is a feasible way to enable the sales agents to assign the addresses for the sale more quickly. In the course of this research work, a process chain is modeled that allows the assignment of aerial photographs to residential addresses using machine vision. After model-based rectifying the aerial images to compensate for perspective distortions, larger image blocks get assembled using image stitching. The assignment to a 2D reference map, such as satellite imagery via Google Maps, is done by applying a U-Net CNN after extracting durable image features such as roads or buildings. The mapping of aerial imagery to two-dimensional cartography is either automated via registration approaches or based on manually placed corresponding landmarks and homography. Test runs on imagery between the years 1969 and 2020 show that the labor-intensive process of geolocation of aerial imagery can be solved by the proposed process model in a hybrid way.

Meindl R., Sandler S., Mayrhuber E., and Krauss O. “Distributed Classification – A Scalable Approach to Semi SupervisedMachine Learning” Proceedings of the 34th European Modeling and Simulation Symposium EMSS2022, Rom, Italy (2022).


Fitting real world data into a model for classification, is a challenging task. Modern approaches to classification are often resource intensive and may become bottlenecks. A microservice architecture that allows maintaining a model of real world data, and adding new information as it becomes available is presented in this paper. Updates to the model are handled via different microservices. The architecture and connected workflows are demonstrated in a use case of classifying text data in a taxonomy represented by a directed acyclic graph (DAG). The presented architecture removes the classification bottleneck, as multiple data points can be added independent of each other, and reading access to the model is not restricted. Additional microservices also enable a manual intervention to update the model.

Praschl C., Pointner A., Krauss O., Helm E., Schuler A. “Model Verification in Graph Databases and its Application in Neo4j.” Proceedings of the 34th European Modeling and Simulation Symposium EMSS2022, Rom, Italy (2022).


This work introduces a concept for rule based model verification using a graph database on the example of Neo4j and its query language Cypher. An approach is provided that allows to define verification rules using a graph query language to detect transformation errors within a given domain model. The approach is presented based on a running example, showing its capability of detecting randomly generated errors in a transformation process. Additionally, the method’s performance is evaluated using multiple subsets of the IMDb movie data with a maximum of 17,000,000 nodes and 41,000,000 relationships. This performance evaluation is carried out in comparison to the Object Constraint Language, showing advantages in the context of highly connected datasets with a high number of nodes. Another benefit is the utilization of a well established graph database as verification tool without any need for re-implementing graph and pattern matching logic.

Kaiser R., Praschl C., Zwettler G. “Long-Term Monitoring of Alpine Plant Diversity in the National Park Hohe Tauern”. 7. Symposium for research in protected areas. Conference. Vol. 2. 2022.


The Hohe Tauern National Park has founded an interdisciplinary monitoring and research program for long-term observation of alpine ecosystems. This initiative provides – among other findings – an ongoing digital image archive in the form of strictly standardized (geo-static, colourfast), high-resolution (1 px. ≈ 0,1mm) nadir photos (view vertical to the ground) with high information content and great relevance in terms of documentation. These data, comparable to earth orthophotos, represent the basis for the project at hand. It focuses on developing a software prototype to automatically recognize plants from image data using computer vision and machine learning. The goals are threefold. First, the reliable recognition of individual plant species and their individuals, despite overlap with other plants or vegetation structures, is aimed. Secondly, the variation in nature and thus divergent appearance of a specimen is addressed. Thirdly, it should be possible to detect identical plants within a time series. In addition, this should allow the models to be updated when new data are available.

Pointner, A., Spitzer, EM., Krauss, O., Stöckl, A. (2023). Anomaly-Based Risk Detection Using Digital News Articles. In: Arai, K. (eds) Intelligent Systems and Applications. IntelliSys 2022. Lecture Notes in Networks and Systems, vol 542. Springer, Cham.



Enterprise risk management is a well established methodology used in industry. This area relies heavily on risk owners and their expert opinion. In this work, we present an approach to a semi-automated risk detection for companies using anomaly detection. We present various anomaly detection algorithms and present an approach on how to apply them on multidimensional data sources like news articles and stock data to automatically extract possible risks. To do so, NLP methods, including sentiment analysis, are used to extract numeric values from news articles, which are needed for anomaly analysis. The approach is evaluated by conducting interview questionnaires with domain experts. The results show that the presented approach is a useful tooling that helps risk owners and domain expert to find and detect potential risks for their companies.

Fernandez-Llatas, Carlos, et al. “Building Process-Oriented Data Science Solutions for Real-World Healthcare.” International Journal of Environmental Research and Public Health 19.14 (2022): 8427.



The COVID-19 pandemic has highlighted some of the opportunities, problems and barriers facing the application of Artificial Intelligence to the medical domain. It is becoming increasingly important to determine how Artificial Intelligence will help healthcare providers understand and improve the daily practice of medicine. As a part of the Artificial Intelligence research field, the Process-Oriented Data Science community has been active in the analysis of this situation and in identifying current challenges and available solutions. We have identified a need to integrate the best efforts made by the community to ensure that promised improvements to care processes can be achieved in real healthcare. In this paper, we argue that it is necessary to provide appropriate tools to support medical experts and that frequent, interactive communication between medical experts and data miners is needed to co-create solutions. Process-Oriented Data Science, and specifically concrete techniques such as Process Mining, can offer an easy to manage set of tools for developing understandable and explainable Artificial Intelligence solutions. Process Mining offers tools, methods and a data driven approach that can involve medical experts in the process of co-discovering real world evidence in an interactive way. It is time for Process-Oriented Data scientists to collaborate more closely with healthcare professionals to provide and build useful, understandable solutions that answer practical questions in daily practice. With a shared vision, we should be better prepared to meet the complex challenges that will shape the future of healthcare.

Praschl C., Thiele E., Krauss O. “Utilization of Geographic Data for the Creation of Occlusion Models in the Context of Mixed Reality Applications”. Extended Reality, 1st ed. Lecture Notes in Computer Science. Volume 13446. (2022).



Emergency responder training can benefit from outdoor use of Mixed Reality (MR) devices to make trainings more realistic and allow simulations that would otherwise not be possible due to safety risks or cost-effectiveness. But outdoor use of MR requires knowledge of the topography and objects in the area to enable accurate interaction of the real world trainees experience and the virtual elements that are placed in them. An approach utilizing elevation data and geographic information systems to create effective occlusion models is shown, that can be used in such outdoor training simulations. The initial results show that this approach enables accurate occlusion and placement of virtual objects within an urban environment. This improves immersion and spatial perception for trainees. In the future, improvements of the approach are planned with on the fly updates to outdated information in the occlusion models.

Callan, James, et al. “How do Android developers improve non-functional properties of software?.” Empirical Software Engineering 27.5 (2022): 1-42.



Nowadays there is an increased pressure on mobile app developers to take non-functional properties into account. An app that is too slow or uses much bandwidth will decrease user satisfaction, and thus can lead to users simply abandoning the app. Although automated software improvement techniques exist for traditional software, these are not as prevalent in the mobile domain. Moreover, it is yet unknown if the same software changes would be as effective. With that in mind, we mined overall 100 Android repositories to find out how developers improve execution time, memory consumption, bandwidth usage and frame rate of mobile apps. We categorised non-functional property (NFP) improving commits related to performance to see how existing automated software improvement techniques can be improved. Our results show that although NFP improving commits related to performance are rare, such improvements appear throughout the development lifecycle. We found altogether 560 NFP commits out of a total of 74,408 commits analysed. Memory consumption is sacrificed most often when improving execution time or bandwidth usage, although similar types of changes can improve multiple non-functional properties at once. Code deletion is the most frequently utilised strategy except for frame rate, where increase in concurrency is the dominant strategy. We find that automated software improvement techniques for mobile domain can benefit from addition of SQL query improvement, caching and asset manipulation. Moreover, we provide a classifier which can drastically reduce manual effort to analyse NFP improving commits.

Meindl, Rainer, et al. “A Scalable Microservice Infrastructure for Fleet Data Management.” International Conference on Database and Expert Systems Applications. Springer, Cham, 2022.



Modern Internet of Things solutions using edge devices produce large amounts of raw data. In order to utilize this data, it needs to be processed, aggregated, and categorized to enable decision making for management and end-users. This data management is a non-trivial task, as the computational load is directly proportional to the amount of data. In order to tackle this issue, we provide an extensible and scalable microservice architecture that can receive, normalize, and filter the raw data and persist it in different levels of aggregation, as well as for time series analysis.

Spitzer, Eva-Maria, Oliver Krauss, and Andreas Stöckl. “Accurately Predicting User Registration in Highly Unbalanced Real-World Datasets from Online News Portals.” International Conference on Database and Expert Systems Applications. Springer, Cham, 2022.



Getting visitors to register is a crucial factor in marketing for online news portals. Current approaches are rule-based by awarding points for specific actions [3]. Finding efficient rules can be challenging and depends on the specific task. Registration is generally rare compared to regular visitors, leading to highly imbalanced data.

We analyze different supervised learning classification algorithms under consideration of the data imbalance. As case study, we use anonymized real-world data from an Austrian newspaper outlet containing the visitor’s session behavior with around 0.1% registrations over all visits.

We identify an ensemble approach combining the Balanced Random Forest Classifier and the RUSBoost Classifier correctly identifying 76% of registrations over five independent data sets

Praschl C., Stradner M., Ono Y., Zwettler G. “Towards an Automated System for Reverse Geocoding of Aerial Photographs”. WSCG 2022: proceedings: 30. International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, p. 296-301. (2022).



Aerial photographs of buildings are often used as memorabilia sold by trading companies. Such photographs come with an issue regarding the address of the shown buildings, since the recording location of the camera may be known, but shows a spatial distance to the actual subject of the image. In addition to that, also this recording location is often not known in detail but only roughly in the form of the flight route/area. To address this problem, a methodology for reverse geocoding is proposed, allowing to identify the position of buildings that are photographed from aerial vehicles. This is done using a process for extending recording locations and a second process based on the registration of invariant features within aerial shots compared to maps.

Egelkraut, Reinhard, et al. “Open Infrastructure for Standardization of HL7® FHIR® Implementation Guides in Austria.” dHealth. 2022.



Background: HL7 Austria is a non-profit association dedicated to improving electronic data communication and interoperability in healthcare using the HL7 international standards. Objectives: We aim to provide an open infrastructure to develop, manage, and maintain HL7 FHIR implementation guides. Methods: We utilize state-of-the-art open-source tooling developed by the FHIR community to support continuous integration. Results: The implementation guides can be published as static HTML websites and maintained using GitHub. Conclusion: The solution supports all steps of a standard’s lifecycle, from drafting and reviewing to balloting, publishing, and maintenance.

Praschl C. Auserperg-Castell P., Forster-Heinlein B., Zwettler G. (2021). Segmentation and Multi-Facet Classification of Individual Logs in Wooden Piles. In Computer Aided Systems Theory Extended Abstract.



The inspection of products and assessment of quality is connected with high costs and time effort in many industrial domains. This also applies to the forestry industry. Utilizing state-of-the-art deep learning models allows automizing the analysis of wooden piles in a vision-based manner. In this work a parallel two-step approach is presented for the segmentation and multi-facet classification of individual logs, according to the wood type and quality. The present approach is based on a preliminary log localization step and like this allows determining the quality, volume and also the value of individual logs, respectively the whole wooden pile. Using a YOLOv4 model for wood species classification for douglas firs, pines and larches results in an accuracy of 74.53%, while a quality classification model for spruce logs reaches 86.58%. In addition to that, the trained U-NET segmentation model reaches an accuracy of 93%. In the future, the underlying data set and models will be further improved and integrated to a mobile application for the on site analyzation of wooden piles by foresters.

Jorge Munoz-Gama, Niels Martin, Carlos Fernandez-Llatas, Owen A. Johnson, Marcos Sepúlveda, Emmanuel Helm, Victor Galvez-Yanjari, Eric Rojas, Antonio Martinez-Millana, Davide Aloini, Ilaria Angela Amantea, Robert Andrews, Michael Arias, Iris Beerepoot, Elisabetta Benevento, Andrea Burattin, Daniel Capurro, Josep Carmona, Marco Comuzzi, Benjamin Dalmas, Rene de la Fuente, Chiara Di Francescomarino, Claudio Di Ciccio, Roberto Gatta, Chiara Ghidini, Fernanda Gonzalez-Lopez, Gema Ibanez-Sanchez, Hilda B. Klasky, Angelina Prima Kurniati, Xixi Lu, Felix Mannhardt, Ronny Mans, Mar Marcos, Renata Medeiros de Carvalho, Marco Pegoraro, Simon K. Poon, Luise Pufahl, Hajo A. Reijers, Simon Remy, Stefanie Rinderle-Ma, Lucia Sacchi, Fernando Seoane, Minseok Song, Alessandro Stefanini, Emilio Sulis, Arthur H.M. ter Hofstede, Pieter J. Toussaint, Vicente Traver, Zoe Valero-Ramon, Inge van de Weerd, Wil M.P. van der Aalst, Rob Vanwersch, Mathias Weske, Moe Thandar Wynn, Francesca Zerbato. Process Mining for Healthcare: Characteristics and Challenges, Journal of Biomedical Informatics. 2022.



Process mining techniques can be used to analyse business processes using the data logged during their execution. These techniques are leveraged in a wide range of domains, including healthcare, where it focuses mainly on the analysis of diagnostic, treatment, and organisational processes. Despite the huge amount of data generated in hospitals by staff and machinery involved in healthcare processes, there is no evidence of a systematic uptake of process mining beyond targeted case studies in a research context. When developing and using process mining in healthcare, distinguishing characteristics of healthcare processes such as their variability and patient-centred focus require targeted attention. Against this background, the Process-Oriented Data Science in Healthcare Alliance has been established to propagate the research and application of techniques targeting the data-driven improvement of healthcare processes. This paper, an initiative of the alliance, presents the distinguishing characteristics of the healthcare domain that need to be considered to successfully use process mining, as well as open challenges that need to be addressed by the community in the future. 

C. Praschl, O. Krauss. Geo-Referenced Occlusion Models for Mixed Reality Applications Using the Microsoft HoloLens. Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, Volume 3: IVAPP. 2022.



Emergency responders or task forces can benefit from outdoor Mixed Reality (MR) trainings, as they allow more realistic and affordable simulations of real-world emergencies. Utilizing MR devices for outdoor situations requires knowledge of real-world objects in the training area, enabling the realistic immersion of both, the real, as well as the virtual world, based on visual occlusions. Due to spatial limitations of state-of-the-art MR devices recognizing distant real-world items, we present an approach for sharing geo-referenced 3D geometries across multiple devices utilizing the CityJSON format for occlusion purposes in the context of geospatial MR visualization. Our results show that the presented methodology allows accurate conversion of occlusion models to geo-referenced representations based on a quantitative evaluation with an average error according to the vertices’ position from 1.30E-06 to 2.79E-04 (sub-millimeter error) using a normalized sum of squared errors metric. In the future, we plan to also incorporate 3D reconstructions from smartphones and drones to increase the number of supported devices for creating geo-referenced occlusion models.

C. Praschl, G. Zwettler. Three-Step Approach for Localization, Instance Segmentation and Multi-Facet Classification of Individual Logs in Wooden Piles. Proceedings of the 11th International Conference on Pattern Recognition Applications and Methods. 2022.



The inspection of products and the assessment of quality is connected with high costs and time effort in many industrial domains. This also applies to the forestry industry. Utilizing state-of-the-art deep learning models allows the analysis automation of wooden piles in a vision-based manner. In this work a three-step approach is presented for the localization, segmentation and multi-facet classification of individual logs based on a client/server architecture allowing to determine the quality, volume and like this the value of a wooden pile based on a smartphone application. Using multiple YOLOv4 and U-NET models leads to a client-side log localization accuracy of 82.9% with low storage requirements of 23 MB and a server-side log detection accuracy of 94.1%, together with a log type classification accuracy of 95% and 96% according to the quality assessment of spruce logs. In addition, the trained segmentation model reaches an accuracy of 89%.

Helm, Emmanuel, et al. “FHIR2BPMN: Delivering Actionable Knowledge by Transforming Between Clinical Pathways and Executable Models.” Healthcare of the Future 2022. IOS Press, 2022. 9-14.



Healthcare processes have many particularities captured and described within standards for medical information exchange such as HL7 FHIR. BPMN is a widely used standard to create readily understandable processes models. We show an approach to integrate both these standards via an automated transformation mechanism. This will allow us to use the various tools available for BPMN to visualize and automate processes in the healthcare domain. In the future we plan to extend this approach to enable mining and analyzing executed processes.


C. Praschl, A. Pointner, D. Baumgartner, G. Zwettler. Imaging framework: An interoperable and extendable connector for image-related Java frameworks. SoftwareX, Volume 16. 2021.



The number of computer vision and image processing tasks has increased during the last years. Although Python is most of the time the first choice in this area, there are situations, where the utilization of another programming language such as Java should be preferred. For this reason, multiple Java based frameworks as e.g. OpenIMAJ, ND4J or multiple OpenCV wrappers are available. Unfortunately, these frameworks are not interoperable at all. In this work, the open-source Imaging Framework is introduced to solve exactly this problem. The project features a concept for combining multiple frameworks and provides an interoperable and extendable foundation to 9 image-related projects with 10 different image representations in Java.

Helm, Emmanuel, and Oliver Krauss. “How can Interoperability Support Process Mining in Healthcare?.” PODS4H.


A discussion of the relationship between the concept of healthcare information systems interoperability and process-oriented data analysis. The goal is to show that some of the current challenges of process mining in healthcare are also interoperability problems. By participating in solving these problems we can also improve our data sources.

A. Schuler and G. Kotsis, “Mining API Interactions to Analyze Software Revisions for the Evolution of Energy Consumption,” in 2021 2021 IEEE/ACM 18th International Conference on Mining Software Repositories (MSR),, 2021 pp. 312-316.



With the widespread use and adoption of mobile platforms like Android a new software quality concern has emerged – energy consumption. However, developing energy-efficient software and applications requires knowledge and like-wise proper tooling to support mobile developers. To this aim, we present an approach to examine the energy evolution of software revisions based on their API interactions. The approach stems from the assumption that the utilization of an API has direct implications on the energy being consumed during runtime. Based on an empirical evaluation, we show initial results that API interactions serve as a flexible, lightweight, and effective way to compare software revisions regarding their energy evolution. Given our initial results we envision that in future using our approach mobile developers will be able to gain insights on the energy implications of changes in source code in the course of the software development life-cycle.

Zwettler G., Reichhard A. Stradner M., Praschl C., Helm E.(2021). In Proceedings of 33rd European Modeling & Simulation Symposium.



At a prevalence of almost 1%, potential epileptic seizures manifest a significant health risk for many juvenile patients. Thus, monitoring is essential to set early counteractive measurements to prevent from damage. The sensor-based monitoring systems mainly address epileptic seizures indicated by a change in the muscle tonus but cannot be utilized for patients that show Prévost’s-sign only. To monitor initiating Prévost’s-sign with opened-eyes as critical visual feature, the applicability of deep-learning eye detection systems on night vision images is evaluated in this paper as basis for modelling and classifying the eye state (closed, opened, not visible). A holistic research prototype is presented as proof of concept, showing the applicability of state-of-the-art face detection on night vision images as well as multi-variate feature analysis on Graph segmentation pre-fragmentation, applicable to detect the state of the eye in a robust way. Results show a single frame accuracy in face/eye detection of 73.91% and 94.44% for classification of the opened eyes as indication of a potentially initiating epileptic seizure. The monitoring system is based on a Raspberry computation unit with two ELP night vision cameras attached and a smart phone app for user-interaction and configuration besides on-demand visual monitoring. Future work will show that the single frame detection rate is sufficient for building up a rule-based monitoring state machine at user predefined sensitivity and specificity by analysing the visual content as time-series rather than single images.

Jany J., Zwettler G. (2021). In Proceedings of 33rd European Modeling & Simulation Symposium.



With recent improvements in deep-learning architectures and availability of GPU hardware, state of the art deep learning (DL) has already manifested as powerful image processing technology in the clinical routine to provide segmentation results of high accuracy. As a drawback, it’s black-box nature does not naturally feature inspection and post-processing by medical experts. We present a Graph segmentation (GS) approach that derives it’s fitness function from arbitrary DL results in a generic way. To allow for efficient and effective post-processing by the medical experts, various interaction paradigms are presented and evaluated in this paper. The trade-off of GS compared to the initial DL results is marginal (delta JI= 0.196%), yet potential DL segmentation errors can be corrected in a reliable way. The intuitive approach shows a high level of both, inter and intra user reproducibility. Change propagation of corrected slices keeps the demand for user-interaction to a minimum when successfully correction potential weaknesses in the DL segmentations. Thereby, the formerly error-prone slice mini-batches get corrected in an automated way with the JI being significantly increased.

Praschl C. Auserperg-Castell P., Forster-Heinlein B., Zwettler G. (2021). In Proceedings of 33rd European Modeling & Simulation Symposium.



In industrial domains with time and cost intensive manual or semi-automated inspection the demand for automation is high. Utilizing state of the art deep learning models for localization in vision-based domains such as wood log analysis, the precision can be increased while reducing the demand for manual inspection. In this paper a YOLO network is trained on wood log images to allow for detection of single wood piles in images with hundreds and thousands instances. Due to the high variability in scale and large amount of wood logs within the images, common YOLO architectures are not applicable. Thus, tiling is necessitated to implicitly form a multi-resolution image pyramid. Due to lack in training data, besides common data augmentation modelling of different seasonal and weather conditions is applied. The wood log detection process can be run on a client/server architecture to allow for both, preview and refined results. Evaluation on real-world data sets shows an log detection accuracy of 82,9% utilizing a tiny YOLO model and 94,1% with a fully connected YOLO model, respectively.

Helm E., Schwebach J., Pointner A., Lin A., Rothensteiner V., Keimel D. and Schuler A. (2021). In Proceedings of dHealth 2021 – Health Informatics Meets Digital Health.


There is a lack of secure official communication channels for peer review and peer feedback on medical findings. Objectives: We aimed to utilize the existing Austrian eHealth infrastructure to enable review and feedback processes. Methods: We extended the IHE XDW workflow document to enable the exchange of text messages (i.e., comments on documents or images) over an XDS infrastructure. Results: The workflow enabled the exchange of comments on specific sections of CDA documents or radiological images and was verified in an XDS test environment. Conclusion: The presented solution is a proof of concept that could lead to the specification of a new IHE workflow definition.

Helm E., Krauss O., Lin A., Pointner A., Schuler A. and Küng J. (2021). Process Mining on FHIR – An Open Standards-Based Process Analytics Approach for Healthcare. In Process Mining Workshops.


Process mining has become its own research discipline over the last years, providing ways to analyze business processes based on event logs. In healthcare, the characteristics of organizational and treatment processes, especially regarding heterogeneous data sources, make it hard to apply process mining techniques. This work presents an approach to utilize established standards for accessing the audit trails of healthcare information systems and provides automated mapping to an event log format suitable for process mining. It also presents a way to simulate healthcare processes and uses it to validate the approach.

Further information can be found here

Langdon W. and Krauss O. (2021). Genetic Improvement of Data for Maths Functions*. In Proceedings of the Genetic and Evolutionary Computation Conference Companion.


Genetic Improvement (GI) can be used to give better quality software and to create new functionality.
We show that GI can evolve the PowerPC open source GNU C runtime library square root function into cube root, binary logarithm log2 and reciprocal square root.
The GI cbrt is competitive in run-time performance and our inverted square root x**-0.5 is far more accurate than the approximation used in the Quake video game.
We use CMA-ES to adapt constants in a Newton-Raphson table, originally from glibc’s sqrt, for other double precision mathematics functions.
Such automatically customised math libraries might be used for mobile or low resource, IoT, mote, smart dust, bespoke cyber-physical systems.
Evolutionary Computing (EC) can be used to not only adapt source code but also data, such as numerical constants, and could enable a new way to conduct software data maintenance.
This is an exciting opportunity for the GECCO and optimisation communities.

Further information can be found here

Pointner A., Praschl C., Krauss O., Schuler A., Helm E., and Zwettler G. (2021). Line Clustering and Contour Extraction in the Context of 2D Building Plans. In Proceedings of 29. International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision.



For the purpose of analyzing a building according to its accessibility or structural resilience, printed 2D floor plans are not sufficient because of the missing link to semantic information.
This paper tackles this issue and introduces a concept for clustering classified lines of a floor plan and for creating semantically enriched contour elements based on different image processing,
computer vision and machine learning algorithms. Based on a general line clustering approach, we introduce type specific methods for walls, windows, doors and stairs.
The resulting clusters are in turn used for a contour creation, which uses minimal rotated rectangles. Those rectangles are transformed to polygons that are refined using post processing steps.The approach is evaluated via positive testing using a pixel-based comparison of the process’s result. For this, automatically generated as well as real world building plans are used. The final evaluation shows, that the concept reaches a confidence of >90% for door, stair and windows and only around 10% for stairs with the run-time linearly scaling with the size of the input.

Fernandez-Llatas, C., Munoz-Gama, J., Martin, N., Johnson, O., Sepulveda, M., & Helm, E. (2021). Process Mining in Healthcare. In Interactive Process Mining in Healthcare (pp. 41-52). Springer, Cham.


Since medical processes are hard to be designed by consensus of experts, the use of data available for creating medical processes is a recurrent idea in literature. Data-driven paradigms are named to be a feasible solution in this field that can support medical experts in their daily decisions. Behind this paradigm, there are frameworks specifically designed for dealing with process-oriented problems. This is the case of process mining.

Reithmeier, L.; Krauss, O. and Zwettler, G.;  (2021). Transfer Learning and Hyperparameter Optimization forInstance Segmentation with RGB-D Images in Reflective Elevator Environments. In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications – Volume 5: VISAPP, ISBN 978-989-758-488-6.



Elevators, a vital means for urban transportation, are generally lacking proper emergency call systems besides an emergency button. In the case of unconscious or otherwise incapacitated passengers this can lead to lethal situations. A camera-based surveillance system with AI-based alerts utilizing an elevator state machine can help passengers unable to initiate an emergency call. In this research work, the applicability of RGB-D images as input for instance segmentation in the highly reflective environment of an elevator cabin is evaluated. For object segmentation, a Region-based Convolution Neural Network (R-CNN) deep learning model is adapted to use depth input data besides RGB by applying transfer learning, hyperparameter optimization and re-training on a newly prepared elevator image dataset. Evaluations prove that with the chosen strategy, the accuracy of R-CNN instance segmentation is applicable on RGB-D data, thereby resolving lack of image quality in the noise affected and reflective elevator cabins. The mean average precision (mAP) of 0.753 is increased to 0.768 after the incorporation of additional depth data and with additional FuseNet-FPN backbone on RGB-D the mAP is further increased to 0.794. With the proposed instance segmentation model, reliable elevator surveillance becomes feasible as first prototypes and on-road tests proof.

Zwettler, G.; Praschl, C.; Baumgartner, D.; Zucali, T.; Turk, D.; Hanreich, M. and Schuler, A. (2021). Three-step Alignment Approach for Fitting a Normalized Mask of a Person Rotating in A-Pose or T-Pose Essential for 3D Reconstruction based on 2D Images and CGI Derived Reference Target Pose.In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications – Volume 5: VISAPP, ISBN 978-989-758-488-6, pages 281-292. DOI: 10.5220/0010194102810292


The 3D silhouette reconstruction of a human body rotating in front of a monocular camera system is a very challenging task due to elastic deformation and positional mismatch from body motion. Nevertheless, knowledge of the 3D body shape is a key information for precise determination of one’s clothing sizes, e.g. for precise shopping to reduce the number of return shipments in online retail. In this paper a novel three step alignment process is presented, utilizing As-Rigid-As-Possible (ARAP) transformations to normalize the body joint skeleton derived from OpenPose with a CGI rendered reference model in A- or T-pose. With further distance-map accelerated registration steps, positional mismatches and inaccuracies from the OpenPose joint estimation are compensated thus allowing for 3D silhouette reconstruction of a moving and elastic object without the need for sophisticated statistical shape models. Tests on both, artificial and real-world data, generally proof the practicability of th is approach with all three alignment/registration steps essential and adequate for 3D silhouette reconstruction data normalization.


Baumgartner D., Jordens I., Wilfing D., Krauss O., Zwettler G. (2020). Automatic Detection of Objects Blocking Elevator Doors using Computer Vision. In Proceedings of the 23rd International Congress on Vertical Transportation Technologies.


In this paper we present a new approach applying computer vision methods to image data acquired with depth perception cameras to map the interior of the elevator, detect the position and the state of the door and to detect objects in the door area. The depth data is used to determine the elevator cabin as safety cube, i.e. the position of the door, layout of the elevator and so on, while color data further enhances the detection of new objects. The approach can detect the state of the elevator door as either opened or closed, while no object is blocking the view to the door, as well as successfully identify objects blocking an open door. This elevator monitoring proves to be relevant for determination of the elevator state, safety as well aspects of predictive maintenance.

Int. J. Environ. Res. Public Health (Details)
Helm E., Lin M. A., Baumgartner D., Lin C. A., Küng J.

Proceedings of the 8th International Workshop on Genetic Improvement (Details)
Krauss O., Mössenböck H., Affenzeller M.

GECCO ’20: Proceedings of the Genetic and Evolutionary Computation Conference Companion (Details)
Langdon W., Krauss O.

Genetic Programming. EuroGP 2020. Lecture Notes in Computer Science, vol 12101. Springer, Cham (Details)
Krauss O., Langdon W.B.

Gerald Zwettler, David Holmes and Werner Backfrieder. “Strategies for Training Deep Learning Models in Medical Domains with Small Reference Datasets”. WSCG ’20.


With the continuous progress of Deep Learning (DL) powerful tools are now available for sophisticated segmentation tasks. Nevertheless, the generally very high demand for training data and precise reference segmentations in the medical domain often cannot be met when dealing with small and individual studies or acquisition protocols. As common strategies, reinforcement learning or transfer learning are applicable, but coherent with immense effort due to domain-specific adaptation. In this work, we evaluate the applicability of a U-grid cascade for training on a very small set of abdominal MRI datasets of the parenchyma and discuss strategies to compensate for the lack of training data. Although model accuracy is rather low when training on 13 MRI bands with achievable JI=89.41, the results are still good enough for annual post-processing using a graph-cut (GC) approach with moderate user interaction requirements. In this way, DL models are retrained as additional test data sets become available to subsequently improve classification accuracy. With only 2 additional GC post-processing datasets, the accuracy after model retraining is JI= 89.87. Furthermore, the applicability of Generative Adversarial Networks (GAN) in the medical field is evaluated, discussing to synthesize axial CT slices together with perfect ground truth reference segmentations. It is shown for abdominal CT slices of the parenchyma that in the absence of training data, synthesized slices that can be derived in arbitrary numbers can significantly improve the DL training process when only an insufficient amount of data is available. While training on 2,200 real-world images only leads to an accuracy of JI=88.75, enrichment with 2,200 additional images synthesized from a GAN trained on 5,000 datasets leads to an increase up to JI=92.02. Even when the DL model is trained exclusively on 4,400 computer-generated images, the classification accuracy on real-world data is remarkable with JI=90.81.

G. Zwettler, D. Holmes III, W. Backfrieder – Pre- and Post-processing Strategies for Generic Slice-wise Segmentation of Tomographic 3D datasets Utilizing U-Net Deep Learning Models Trained for Specific Diagnostic Domains – Proceedings of the VISAPP 2020, Valetta, Malta, 2020, pp. 66-78


An automated and generally applicable method for segmentation is still in the focus of medical image processing research. For several years, artificial intelligence methods have shown promising results, especially with widely available scalable deep learning libraries. In this work, a five-layer hybrid U-network is developed for slice-wise segmentation of liver datasets. The training data is obtained from the Medical Segmentation Decathlon database, which contains 131 fully segmented volumes. A slice-based segmentation model is implemented using Deep Learning algorithms with adjustments for variable parenchyma shape along the stacking direction and similarities between adjacent slices. Both are transformed for coronal and sagittal views. The implementation is done on a GPU rack using TensorFlow and Keras. Standardized volume and surface metrics are used for a quantitative measure of segmentation accuracy. The results DSC=97.59, JI=95.29 and NSD=99.37 show correct segmentation comparable to 3D U-meshes and other state of the art U-meshes. The development of a 2D slice oriented segmentation we justified by the advantages of short training times and lower complexity and also massively reduces memory consumption. This work manifests the high potential of AI methods for general application in medicine. Segmentation as a fully or semi-automatic tool under the supervision of the expert user.

Baumgartner,D., Praschl,C., Zucali,T., Zwettler,G.: 1. Hybrid Approach for Orientation-Estimation of Rotating Humans in Video Frames Acquired by Stationary Monocular Camera


Accurate human orientation estimation with respect to the POSE of a monocular camera system is a challenging task due to general aspects of camera calibration and the deformability of a moving human body. Therefore, novel deep learning approaches for precise object position determination in robotics are difficult to adapt for human body analysis. In this work, we present a hybrid approach for accurately estimating a human body relative to a camera system, significantly improving the results derived from poseNet by applying optical flow analysis in a frame-to-frame comparison. The human body, which rotates in the T-position in situ, is thereby center-aligned, with object tracking methods applied to compensate for translations of the body motion. After 2D skeletal extraction, optical flow is calculated for an ROI region aligned relative to the vertical skeletal junction representing the spine and compared frame by frame. To evaluate the suitability of clothing as a basis for good features, local pixel homogeneity is considered to constrain optical flow to heterogeneous regions with distinguishing features such as imprint patterns, buttons, or buckles in addition to local illumination change. Based on the mean optical flow with rough approximation of the axial body shape as an ellipse, accuracy between 0.1° and 2.0° is achieved for orientation estimation on a frame-to-frame comparison evaluated and validated on both CGI renderings and real videos of people wearing clothes with different features.

International Journal of Simulation and Process Modelling

C. Praschl, O. Krauss, G. Zwettler


This research covers generic approaches to determine the outdoor position and orientation of an augmented reality device due to the lack of outdoor suitability of depth or ambient sensing based devices currently available in the market. Orientation is primarily determined using an Attitude Heading Reference System (AHRS) for rough estimation. Based on a connected/integrated video camera, accuracy is improved for minor changes in orientation by using registration to evaluate orientation differences between two video frames, compensating for gyroscope drift errors. Position determination is performed using GPS with a real-time kinematic beacon system with rover and base station to achieve improved accuracy. The results show that based on the sensor application, AR hardware considered for indoor use can be retrofitted to work properly outdoors, at long distances, and even in moving vehicles. This will facilitate the future implementation of applications in various fields.

Daniel Dorfmeister, and Oliver Krauss. 2020. “Integrating HeuristicLab with Compilers and Interpreters for Non-Functional Code Optimization.” In Proceedings of the Genetic and Evolutionary Computation Conference Companion – GECCO ’20. Cancun, Mexico: ACM Press. (Details).

Emmanuel Helm, Anna M. Lin, David Baumgartner, Alvin C. Lin und Josef Küng. 2020. “Adopting Standard Clinical Descriptors for Process Mining Case Studies in Healthcare”.


Process mining can provide greater insight into medical treatment processes and organizational processes in healthcare. A review of case studies in the literature identified several different common aspects for comparison, which include methods, algorithms or techniques, medical domains, and healthcare specialties. However, from a medical perspective, clinical terms are not used in a consistent manner and do not follow a standardized clinical coding scheme. In addition, the characteristics of event log data are not always described. In this paper, we identified 38 clinically relevant case studies on process mining in healthcare published between 2016 and 2018 that described the tools, algorithms, and techniques used, as well as details about event log data. We then mapped the clinical aspects of the patient encounter environment, clinical specialty, and medical diagnoses using the standard SNOMED CT and ICD-10 clinical coding schemes. The possible results of adopting a standard approach for describing event log data and classifying medical terminology using standard clinical coding schemes are discussed.


IGSOFT Softw. Eng. Notes 44, 3 (July 2019) (Details)
William B. Langdon, Westley Weimer, Christopher Timperley, Oliver Krauss, Zhen Yu Ding, Yiwei Lyu, Nicolas Chausseau, Eric Schulte, Shin Hwei Tan, Kevin Leach, Yu Huang, and Gabin An

arXiv preprint arXiv:1907.03773

Process-Oriented Data Science for Healthcare (Details)
Emmanuel Helm, David Baumgartner, Anna M. Lin, Alvin Lin, Josef Küng

Proceedings of the 6th International Workshop on Genetic Improvement
Oliver Krauss, Hanspeter Mössenböck, Michael Affenzeller

ICT for Health Science Research
A. Lin, O. Krauss, E. Helm

Process Mining Conference 2019 – 1st International Conference on Process Mining, June 24-26, 2019, Aachen, Germany
Baumgartner D., Haghofer A., Limberger M., Helm E.

Information Systems and Neuroscience, p. 221 – 228, Springer Verlag
Baumgartner D., Fischer T. Riedl R., Dreiseitl S.


Proc. 9th Intl. Conf. on Society and Information Technologies (ICSIT 2018), Orlando, Vereinigte Staaten von Amerika, 2018, pp. 126-131
Mayr, H.

Proceeding ISSTA ’18 Companion Proceedings for the ISSTA/ECOOP 2018 Workshops Pages 144-149 (Details)
Schuler, A. and Anderst-Kotsis G. – MANA

International journal of environmental research and public health (Details)
Rinner C., Helm E., Dunkl R., Kittler H., Rinderle-Ma S.

GECCO ’18: Proceedings of the Genetic and Evolutionary Computation Conference Companion (Details)
Krauss, O. Mössenböck, H. Affenzeller, M. – GCE

International Conference on Business Process Management (Details)
Rinner C., Helm E., Dunkl R., Kittler H., Rinderle-Ma S.

Proceedings of the 30th European Modeling and Simulation Symposium EMSS2018, Budapest, Ungarn, 2018
A. Pointner, O. Krauss, G. Freilinger, D. Strieder, G. Zwettler – GUIDE

Proceedings of the 30th European Modeling and Simulation Symposium EMSS2018, Budapest, Ungarn, 2018
C. Praschl, O. Krauss, G. Zwettler – Drive for Knowledge

International Journal of Privacy and Health Information Management (IJPHIM)
Traxler B., Helm E., Krauss O., Schuler A., Kueng J.

European Journal of Biomedical Informatics (Details)
Lackerbauer A., Lin A., Krauss O., Hearn J., Helm E.

Studies in health technology and informatics
Helm E., Schuler A., Mayr H.


Proceedings of the International Workshop on Innovative Simulation for Health Care (IWISH), Barcelona, Spanien, 2017, pp. 26-31
W. Backfrieder, B. Kerschbaumer, G. Zwettler

Proceedings of the International Workshop on Innovative Simulation for Healthcare IWISH 2017, Barcelona, Spanien, 2017
W. Backfrieder, G. Zwettler, B. Kerschbaumer

Akkordeon InhaltaSPLASH / OOPSLA 2017 (Details)
O. Krauss

ITBAM 2017, 8th International Conference on Information Technology in Bio-and Medical Informatics, Lyon, France (Details)
González López De Murillas E., Helm E., Reijers HA., Küng J., Bursa M., Holzinger A., Elena Renda M., Khuri S.

6th International Workshop on Innovative Simulation for Health Care (IWISH 2017) (Details)
E. Helm, B. Franz, A. Schuler, O. Krauss, J. Küng

Studies in Health Technology and Informatics, 2017 – 236 (Details)
Krauss O, Holzer K, Schuler A, Egelkraut R, Franz B. – KIMBO


Information Technology in Bio- and Medical Informatics, Porto, Portugal, 2016 (Details)
E. Helm, J. Küng

IEEE Advanced Information Management,Communicates,Electronic and Automation Control Conference, Xi’an, Xi’an, China, 2016 (Details)
D. Wilfing, O. Krauss, A. Schuler – ARISE

IEEE Advanced Information Management,Communicates,Electronic and Automation Control Conference, Xi’an, Xi’an, China, 2016 (Details)
O. Krauss, D. Wilfing, A. Schuler – ARISE

Information Technology in Bio- and Medical Informatics, Porto, Portugal, 2016 (Details)
O. Krauss, M. Angermaier, E. Helm – KIMBO


International Journal of Electronics and Telecommunications, Vol. 61, No. 2, 2015, pp. 151-157
O. Krauss, B. Franz, A. Schuler

S. Porta, G. Zwettler, W. Kurschl, C. Dinu, G. Juttla, K. Pichlkastner, H. Gell, B. Kaiser, K. Kisters

International Journal of Electronics and Telecommunications, Vol. 60, No. 6, 2015, pp. 1-8
G. Zwettler, W. Backfrieder

Proceedings of the 2015 I-WISH, The International Workshop on Innovative Simulation for Healthcare , Bergeggi, Italien, 2015, pp. 6
W. Backfrieder, G. Zwettler

Proceedings of the IEEE International conference on Computing and Communications Technologies (ICCCT’15), Chennai, Indien, 2015, pp. 1-7
G. Zwettler, W. Backfrieder

eHealth2015 – Health Informatics Meets eHealth, Wien, Österreich, 2015 (Details)
E. Helm, A. Schuler, O. Krauss, B. Franz

European Journal for Biomedical Informatics, Vol. 11, No. 2, 2015 (Details)
B. Franz, A. Schuler, O. Krauss

International Journal of Electronics and Telecommunications, Vol. 61, No. 2, 2015 (Details)
A. Schuler, B. Franz, O. Krauss

MIE, Digital Healthcare Empowering Europeans, Madrid, Spanien, 2015, pp. 40-44 (Details)
F. Paster, E. Helm

International Journal of Electronics and Telecommunications, Vol. 61, No. 2, 2015, pp. 137-142 (Details)
E. Helm, F. Paster


Proceedings of the 3rd International Workshop on Innovative Simulation for Healthcare IWISH 2014, Bordeaux, Frankreich, 2014, pp. 26-35
G. Zwettler, W. Backfrieder

Proceedings of the 3rd International Workshop on Innovative Simulation for Healthcare IWISH 2014, Bordeaux, France, 2014, pp. 36-41
W. Backfrieder, G. Zwettler

California, USA, Vereinigte Staaten von Amerika, 2014, pp. 9
G. Zwettler, W. Backfrieder

Tagungsband des 8. Forschungsforum der österreichischen Fachhochschulen, Kufstein, Österreich, 2014, pp. 296-300
G. Zwettler, W. Backfrieder

Tagungsband des 8. Forschungsforum der österreichischen Fachhochschulen, Kufstein, Österreich, 2014, pp. 482-483
G. Zwettler, W. Backfrieder

Gesundheitswesen im Wandel – nationale und internationale Perspektiven (Editors: Erwin Gollner, Magdalena Thaller) – Leykam, 2014, pp. 30-35 (Details)
A. Schuler


Cross-Cultural Conference 2013, Steyr, Österreich, 2013, pp. 253-263
M. Gaisch, C. Holzmann, W. Kurschl, H. Mayr, S. Selinger

LECTURE NOTES IN COMPUTER SCIENCE, Vol. 8112, No. 1, 2013, pp. 166-173 (Details)
G. Zwettler, W. Backfrieder

Proceedings of The International Workshop on Innovative Simulation for Healthcare IWISH 2013 , Athens, Greece, Griechenland, 2013, pp. 58-64
G. Zwettler, W. Backfrieder

Proceedings of The International Workshop on Innovative Simulation for Healthcare IWISH 2013 , Athens, Greece, Griechenland, 2013, pp. 28-33
W. Backfrieder, B. Kerschbaumer, G. Zwettler

Proceedings of the 8th International Conference on Computer Vision Theory and Applications, Barcelona, Spanien, 2013, pp. 104-108
G. Zwettler, W. Backfrieder

Computer Aided Systems Theory (Eurocast 2013), Las Palmas, Spanien, 2013, pp. 118-119
G. Zwettler, W. Backfrieder

Proceedings of the 10th International Conference on Information Technology: New Generations (ITNG 2013), Las Vegas, Nevada, USA, 2013 (Details)
A. Schuler, B. Franz

6. Deutscher AAL-Kongress, Berlin, Deutschland, 2013, pp. 1-7 (Details)
B. Franz, M. Buchmayr, A. Schuler, W. Kurschl

Database and Expert Systems Applications, Prague, Tschechische Republik, 2013, pp. 466-473 (Details)
B. Franz, A. Schuler, E. Helm

eHealth2013 – Von der Wissenschaft zur Anwendung und zurück. , Wien, Österreich, 2013, pp. 207-218 (Details)
E. Helm, A. Schuler, H. Mayr


Proceedings of the 24th European Modeling and Simulation Symposium EMSS 2012, Vienna, Österreich, 2012, pp. 73-81
G. Zwettler, W. Backfrieder

Tagungsband FFH 2012, Graz, Österreich, 2012, pp. 185-189
G. Zwettler, S. Hinterholzer, P. Track, F. Waschaurek, E. Hagmann, R. Woschitz

MIE, Quality of Life through Quality of Information, Pisa, Italien, 2012 (Details)
M. Strasser, E. Helm, A. Schuler, M. Fuschlberger, B. Altendorfer

Proceedings of the 10th International Conference on Information Communication Technologies in Health, Samos, Greece, Griechenland, 2012, pp. 422-432 (Details)
M. Strasser, E. Helm, B. Franz, H. Mayr

eHealth2012 – Health Informatics meets eHealth – von der Wissenschaft zur Anwendung und zurück, Wien, Österreich, 2012, pp. 179-184 (Details)
M. Strasser, E. Helm, A. Schuler, B. Franz, H. Mayr, C. David

Proceedings IV Kongress 2012, Linz, Österreich, 2012
H. Mayr, B. Franz


eHealth 2011, Wien, Österreich, 2011, pp. 209-214
F. Pfeifer, B. Franz, E. Helm, J. Altmann, B. Aichinger

Proccedings of 23rd IEEE European Modeling & Simulation Symposium EMSS 2011, Roma, Italien, 2011, pp. 195-200
B. Franz, H. Mayr

Proceedings of the 23rd European Modeling & Simulation Symposium, Rom, Italien, 2011, pp. 111-117
G. Zwettler, W. Backfrieder, R. Pichler

Proceedings of the 23rd European Modeling & Simulation Symposium, Rom, Italien, 2011, pp. 100-104
W. Backfrieder, G. Zwettler

Tagungsband FFH 2011 (5. Forschungsforum der österreichischen Fachhochschulen), Wien (Favoriten), Österreich, 2011, pp. 38-41
G. Zwettler, W. Backfrieder, R. Pichler

Proc. of the 3rd International ICST Conference on IT Revolutions , Cordoba, Spanien, 2011, pp. 20
G. Zwettler, S. Hinterholzer, P. Track, R. Woschitz, F. Waschaurek, E. Hagmann

Proceedings of International Conference on Computer Aided Systems Theory EUROCAST 2011, Las Palmas, Spanien, 2011, pp. 233-235
G. Zwettler, S. Hinterholzer, F. Waschaurek, R. Woschitz, E. Hagmann, P. Track

Proceedings of International Conference on Computer Aided Systems Theory EUROCAST 2011, Las Palmas, Spanien, 2011, pp. 363-365
G. Zwettler, W. Backfrieder, R. Pichler

Proceedings IADIS International Conference e-Health 2011 – EH 2011, Rom, Italien, 2011, pp. 4
B. Franz, H. Mayr


ÖKZ Das österreichische Gesundheitswesen, Vol. 51, No. 7, 2010, pp. 9-11
B. Franz, M. Lehner, M. Mayr

ECOOP 2010 – 1st Workshop on Testing Object-Oriented Software Systems, Maribor, Slowenien, 2010, pp. 9-15
A. Strasser, H. Mayr, T. Naderhirn

22nd European Modeling and Simulation Symposium EMSS 2010, Fes, Marokko, 2010, pp. 49-58
G. Zwettler, S. Hinterholzer, E. Hagmann, R. Woschitz, P. Track, F. Waschaurek

Tagungsband des 4. Forschungsforum der österreichischen Fachhochschulen, Pinkafeld, Österreich, 2010, pp. 79-84
G. Zwettler, W. Backfrieder

Intelligente Objekte und Mobile Informationssysteme im Gesundheitswesen, Erlangen, Deutschland, 2010
B. Franz, H. Mayr, M. Mayr

Proceedings of 7th International Conference on Information Technology : New Generations, Las Vegas, Vereinigte Staaten von Amerika, 2010
B. Franz, H. Mayr, M. Mayr


eHealth2009, Wien, Österreich, 2009, pp. 115-121
J. Altmann, B. FRANZ, D. Mörtenschlag, F. Pfeifer, M. Strasser, B. Aichinger, R. Koller

Proceedings of 21st European Modeling and Simulation Symposium EMSS 2009, Tenerife, Spanien, 2009, pp. 3
J. Altmann, F. Pfeifer, M. Strasser, B. Franz, H. Mayr

Proceedings of 21st European Modeling and Simulation Symposium EMSS 2009, Tenerife, Spanien, 2009, pp. 161-166
G. Zwettler, W. Backfrieder, R. Swoboda, F. Pfeifer

Proceedings of 21st European Modeling and Simulation Symposium EMSS 2009, Tenerife, Spanien, 2009, pp. 154-160
R. Swoboda, G. Zwettler, J. Scharinger, C. Steinwender, F. Leisch

Tagungsband des 3. Forschungsforums der österreichischen Fachhochschulen, Fachhochschule Kärnten, Villach, Österreich, 2009, pp. 6
G. Zwettler, W. Backfrieder, R. Swoboda, F. Pfeifer

Tagungsband des 3. Forschungsforums der österreichischen Fachhochschulen, Fachhochschule Kärnten, Villach, Österreich, 2009, pp. 2
G. Zwettler, W. Backfrieder

Master/Diploma Thesis, FH OÖ Fakultät Hagenberg, Österreich, 2009, pp. 104
G. Zwettler

Proceedings of 21st European Modeling and Simulation Symposium EMSS 2009, Tenerife, Spanien, 2009, pp. 8
B. Franz, H. Mayr, M. Mayr, F. Pfeifer, J. Altmann, M. Lehner

Proceedings of the 6th International Conference on Information Technology : New Generations, Las Vegas, Vereinigte Staaten von Amerika, 2009
B. Franz, M. Lehner, H. Mayr, M. Mayr

Proceedings Med-e-Tel 2009, Global Telemedicine and eHealth Updates: Knowledge Resources Vol. 2, Luxembourg, Luxemburg, 2009, pp. 452-455
H. Mayr, B. Franz


The Insight Journal, Vol. 3, No. 2, 2008, pp. 36
R. Swoboda, W. Backfrieder, G. Zwettler, F. Pfeifer

IGRT Vienna 2008 , Wien, Österreich, 2008, pp. 14
W. Backfrieder, G. Zwettler, R. Swoboda, F. Pfeifer, H. Kratochwill, F. Fellner

Challenges in Biosciences: Image Analysis and Pattern Recognition Aspects, St. Magdalena, Linz, Austria, Österreich, 2008, pp. 91-102
G. Zwettler, W. Backfrieder, F. Pfeifer, R. Swoboda

Proceedings of FFH2008 Fachhochschul Forschungs Forum, Wels, Österreich, 2008, pp. 253-259
G. Zwettler, W. Backfrieder, F. Pfeifer, R. Swoboda, H. Kratochwill, F. Fellner

Proceedings 2009 Tagungsband Bericht 2008 Journal Tagungsband – 6 – of FFH2008 Fachhochschul Forschungs Forum, Wels, Österreich, 2008, pp. 2
F. Pfeifer, W. Backfrieder, G. Zwettler, R. Swoboda, H. Kratochwill, M. Malek, R. Hainisch

Proceedings of the 3rd International Conference on Computer Vision Theory and Applications, Funchal, Madeira – Portugal, Portugal, 2008, pp. 74-80
G. Zwettler, W. Backfrieder, F. Pfeifer, R. Swoboda

Proceedings of the 20th European Modeling and Simulation Symposium, Campora S. Giovanni, Italien, 2008
C. Novak, B. Franz, H. Mayr, M. Vesely

Proceedings of The 2008 Internationa Conference on Machine Learning; Models, Technologies and Applications, Las Vegas, Vereinigte Staaten von Amerika, 2008, pp. 787-793
M. Vesely, C. Novak, A. Reh, H. Mayr

Proc. 23. STEV-Österreich-Fachtagung IT-/Software-Qualitätsmanagement in der Praxis, Wien, Österreich, 2008, pp. 48-59
H. Mayr

Proceedings of FFH2008 Fachhochschul Forschungs Forum, Wels, Österreich, 2008, pp. 3
J. Altmann, H. Mayr, W. Steinbichl


Proceedings of International Mediterranean Modelling Multiconference I3M2007, Genoa, Italien, 2007, pp. 289-293
H. Mayr

Tagungsband des ersten Forschungsforum der österreichischen Fachhochschulen, Fachhochschule Salzburg, Campus Urstein, Österreich, 2007, pp. 244-250
H. Mayr, M. Vesely

Proc. 14th IEEE International Conference and Workshop on the Engineering of Computer Based Systems (ECBS’ 07), Tucson, Vereinigte Staaten von Amerika, 2007, pp. 397-402
H. Mayr

Proceedings of International Conference Computer Aided Systems Theory EUROCAST 2007, Las Palmas, Spanien, 2007, pp. 1097-1104
M. Vesely, H. Mayr

International Journal of Computer Assisted Radiology and Surgery, Berlin, Deutschland, 2007, pp. 460-461
W. Backfrieder, G. Zwettler, R. Swoboda, F. Pfeifer, H. Kratochwill, F. Fellner

Tagungsband des ersten Forschungsforum der österreichischen Fachhochschulen, Fachhochschule Salzburg, Campus Urstein, Österreich, 2007, pp. 425-426
G. Zwettler, W. Backfrieder, R. Swoboda, F. Pfeifer, H. Kratochwill, F. Fellner

Tagungsband des ersten Forschungsforum der österreichischen Fachhochschulen, Fachhochschule Salzburg, Campus Urstein, Österreich, 2007, pp. 401-402
F. Pfeifer, W. Backfrieder, R. Swoboda, G. Zwettler, H. Kratochwill, F. Fellner, M. Malek, R. Hainisch


Proceedings FH Science Day 2006, Hagenberg, Österreich, 2006, pp. 74-80
F. Pfeifer, W. Backfrieder, R. Swoboda, G. Zwettler

Proceedings of the International Mediterranean Modelling Multiconference (I3M 2015), Barcelona, Spanien, 2006, pp. 675-680
G. Zwettler, R. Swoboda, W. Backfrieder, C. Steinwender, F. Leisch, C. Gabriel


Proceedings of Conceptual Modeling and Simulation Conference (CMS 2005), Marseille, Frankreich, 2005, pp. 185-191
R. Swoboda, W. Backfrieder, G. Zwettler, M. Carpella, C. Steinwender, F. Leisch, C. Gabriel

Master/Diploma Thesis, FH OÖ Fakultät Hagenberg, Österreich, 2005, pp. 94
G. Zwettler