Falk Howar
YOU?
Author Swipe
View article: Improving AI-Based Canine Heart Disease Diagnosis with Expert-Consensus Auscultation Labeling
Improving AI-Based Canine Heart Disease Diagnosis with Expert-Consensus Auscultation Labeling Open
Noisy labels pose significant challenges for AI model training in veterinary medicine. This study examines expert assessment ambiguity in canine auscultation data, highlights the negative impact of label noise on classification performance…
View article: Leveraging Triggering Conditions for Efficient Scenario-Based Testing of Automated Vehicles
Leveraging Triggering Conditions for Efficient Scenario-Based Testing of Automated Vehicles Open
Scenario-based testing has become a central approach of safety verification and validation (V&V) of automated driving. The standard ISO 21448: Safety of the intended functionality (SOTIF) [1] proposes triggering conditions (e.g., an oc…
View article: Innamark: A Whitespace Replacement Information-Hiding Method
Innamark: A Whitespace Replacement Information-Hiding Method Open
Large language models (LLMs) have gained significant popularity in recent years. Differentiating between a text written by a human and one generated by an LLM has become almost impossible. Information-hiding techniques such as digital wate…
View article: Innamark: A Whitespace Replacement Information-Hiding Method
Innamark: A Whitespace Replacement Information-Hiding Method Open
123120
View article: LearnLib: 10 years later
LearnLib: 10 years later Open
In 2015, LearnLib, the open-source framework for active automata learning, received the prestigious CAV artifact award. This paper presents the advancements made since then, highlighting significant additions to LearnLib, including state-o…
View article: Language-Driven Engineering An Interdisciplinary Software Development Paradigm
Language-Driven Engineering An Interdisciplinary Software Development Paradigm Open
We illustrate how purpose-specific, graphical modeling enables application experts with different levels of expertise to collaboratively design and then produce complex applications using their individual, purpose-specific modeling languag…
View article: Scalable Tree-based Register Automata Learning
Scalable Tree-based Register Automata Learning Open
Existing active automata learning (AAL) algorithms have demonstrated their potential in capturing the behavior of complex systems (e.g., in analyzing network protocol implementations). The most widely used AAL algorithms generate finite st…
View article: Scalable Tree-based Register Automata Learning
Scalable Tree-based Register Automata Learning Open
Existing active automata learning (AAL) algorithms have demonstrated their potential in capturing the behavior of complex systems (e.g., in analyzing network protocol implementations). The most widely used AAL algorithms generate finite st…
View article: Implementing Data Sovereignty: Requirements & Challenges from Practice
Implementing Data Sovereignty: Requirements & Challenges from Practice Open
Data sovereignty, the possibility to keep control over data, is gaining increasing attention in both research and industry. Due to complex supply chains and a strong trend toward digitization, digital assets are essential to be fast and co…
View article: Tree-Based Scenario Classification: A Formal Framework for Coverage Analysis on Test Drives of Autonomous Vehicles
Tree-Based Scenario Classification: A Formal Framework for Coverage Analysis on Test Drives of Autonomous Vehicles Open
Scenario-based testing is envisioned as a key approach for the safety assurance of autonomous vehicles. In scenario-based testing, relevant (driving) scenarios are the basis of tests. Many recent works focus on specification, variation, ge…
View article: Treating the End of the Data Life Cycle as a First-Class Citizen in Data Engineering - Datasets
Treating the End of the Data Life Cycle as a First-Class Citizen in Data Engineering - Datasets Open
Additional data for paper "Treating the End of the Data Life Cycle as a First-Class Citizen in Data Engineering".
View article: Treating the End of the Data Life Cycle as a First-Class Citizen in Data Engineering - Datasets
Treating the End of the Data Life Cycle as a First-Class Citizen in Data Engineering - Datasets Open
Additional data for paper "Treating the End of the Data Life Cycle as a First-Class Citizen in Data Engineering".
View article: Structuring the End of the Data Life Cycle - Datasets
Structuring the End of the Data Life Cycle - Datasets Open
Additional data for paper "Structuring the End of the Data Life Cycle".
View article: Structuring the End of the Data Life Cycle - Datasets
Structuring the End of the Data Life Cycle - Datasets Open
Additional data for paper "Structuring the End of the Data Life Cycle".
View article: Unsupervised Automata Learning via Discrete Optimization
Unsupervised Automata Learning via Discrete Optimization Open
Automata learning is a successful tool for many application domains such as robotics and automatic verification. Typically, automata learning techniques operate in a supervised learning setting (active or passive) where they learn a finite…
View article: Thrilling AI – A novel, signal-based digital biomarker for diagnosing canine heart diseases
Thrilling AI – A novel, signal-based digital biomarker for diagnosing canine heart diseases Open
Auscultation methods enable non-invasive diagnosis of diseases, e.g. of the heart, based on heartbeat sounds. Regular, early examinations using machine learning techniques could help to detect diseases at an early stage to prevent serious …
View article: Data sovereignty for AI pipelines
Data sovereignty for AI pipelines Open
The establishment of collaborative AI pipelines, in which multiple organizations share their data and models, is often complicated by lengthy data governance processes and legal clarifications. Data sovereignty solutions, which ensure data…
View article: GWIT: A Witness Validator for Java based on GraalVM (Competition Contribution)
GWIT: A Witness Validator for Java based on GraalVM (Competition Contribution) Open
GWIT is a validator for violation witnesses produced by Java verifiers in the SV-COMP software verification competition. GWIT weaves assumptions documented in a witness into the source code of a program, effectively restricting the part of…
View article: GDart: An Ensemble of Tools for Dynamic Symbolic Execution on the Java Virtual Machine (Competition Contribution)
GDart: An Ensemble of Tools for Dynamic Symbolic Execution on the Java Virtual Machine (Competition Contribution) Open
GDart is an ensemble of tools allowing dynamic symbolic execution of JVM programs. The dynamic symbolic execution engine is decomposed into three different components: a symbolic decision engine (DSE), a concolic executor (SPouT), and a SM…
View article: Automatic Seizure Detection Using the Pulse Transit Time
Automatic Seizure Detection Using the Pulse Transit Time Open
Documentation of epileptic seizures plays an essential role in planning medical therapy. Solutions for automated epileptic seizure detection can help improve the current problem of incomplete and erroneous manual documentation of epileptic…
View article: The RERS challenge: towards controllable and scalable benchmark synthesis
The RERS challenge: towards controllable and scalable benchmark synthesis Open
This paper (1) summarizes the history of the RERS challenge for the analysis and verification of reactive systems, its profile and intentions, its relation to other competitions, and, in particular, its evolution due to the feedback of par…
View article: Utilizing Remote Evaluation for Providing Data Sovereignty in Data-sharing Ecosystems
Utilizing Remote Evaluation for Providing Data Sovereignty in Data-sharing Ecosystems Open
The maintenance of digital sovereignty is an important aspect of data-driven business models and data-sharing ecosystems. Considering this, sensitive data is often stored in proprietary systems under the data owner's control and with appro…
View article: JDart: Portfolio Solving, Breadth-First Search and SMT-Lib Strings (Competition Contribution)
JDart: Portfolio Solving, Breadth-First Search and SMT-Lib Strings (Competition Contribution) Open
JDart performs dynamic symbolic execution of Java programs: it executes programs with concrete inputs while recording symbolic constraints on executed program paths. A portfolio of constraint solvers is then used for generating new concret…