Auflistung nach:
Auflistung Künstliche Intelligenz 38(3) - November 2024 nach Titel
1 - 10 von 16
Treffer pro Seite
Sortieroptionen
- ZeitschriftenartikelAI in Healthcare and the Public Sector(KI - Künstliche Intelligenz: Vol. 38, No. 3, 2024) Braun, Tanya; Möller, Ralf
- ZeitschriftenartikelAI in Healthcare and the Public Sector: How to Face the Challenges of High-Risk Applications and What AI Research Can Get Out of It(KI - Künstliche Intelligenz: Vol. 38, No. 3, 2024) Braun, Tanya; Möller, RalfApplication projects, may it be in healthcare and the public sector or elsewhere, have the potential to advance foundational (“genuine”) artificial intelligence (AI) research. Unfortunately, insights from specific application projects are rarely propagated back to AI research. This article argues for ways to facilitate such backpropagation and how the contributions in this special issue enable exactly this backpropagation. It also addresses the challenges that come along with high-risk application project, which frequently occur in the area of healthcare and the public sector due to the sensitivity of the subjects.
- ZeitschriftenartikelAnalyzing Semantically Enriched Trajectories(KI - Künstliche Intelligenz: Vol. 38, No. 3, 2024) Seep, JanaIn order to understand what influences the movement of an object or person it is important to consider a variety of factors. These could be the visibility of certain landmarks, the current temperature or the presence of a crowded area to be avoided. These insights then can be used to understand movement in the public sector and improve our build environment, e.g. to reduce street traffic accidents or orientation in complex buildings. The following extended abstract is a summary of a doctoral thesis submitted to the University of Münster. The thesis was successfully defended in February 2023 [ 16 ]. The dissertation focuses on the analysis of so-called semantically enriched trajectories , which are used to describe observed movement. It proposes a new model based on an extended finite state machine, which allows for the representation and consideration of the information about the context of the trajectory. With the new model, we consider two main steps in trajectory analysis: First, we aim to infer a semantically enriched representative trajectory for a given cluster of trajectories. Second, we introduce a variation of the well-known k-means algorithm to calculate clusters based on the given context of trajectories. To show semantic feasibility of our approach, we conclude this work by evaluating the possibility to provide decision support for domain experts in two different public sector related contexts.
- ZeitschriftenartikelAuditive Emotion Recognition for Empathic AI-Assistants(KI - Künstliche Intelligenz: Vol. 38, No. 3, 2024) Duwenbeck, Roswitha; Kirchner, Elsa AndreaThis paper briefly introduces the Project “AudEeKA”, whose aim is to use speech and other bio signals for emotion recognition to improve remote, but also direct, healthcare. This article takes a look at use cases, goals and challenges, of researching and implementing a possible solution. To gain additional insights, the main-goal of the project is divided into multiple sub-goals, namely speech emotion recognition, stress detection and classification and emotion detection from physiological signals. Also, similar projects are considered and project-specific requirements stemming from use-cases introduced. Possible pitfalls and difficulties are outlined, which are mostly associated with datasets. They also emerge out of the requirements, their accompanying restrictions and first analyses in the area of speech emotion recognition, which are shortly presented and discussed. At the same time, first approaches to solutions for every sub-goal, which include the use of continual learning, and finally a draft of the planned architecture for the envisioned system, is presented. This draft presents a possible solution for combining all sub-goals, while reaching the main goal of a multimodal emotion recognition system.
- ZeitschriftenartikelAutomated Computation of Therapies Using Failure Mode and Effects Analysis in the Medical Domain(KI - Künstliche Intelligenz: Vol. 38, No. 3, 2024) Luttermann, Malte; Baake, Edgar; Bouchagiar, Juljan; Gebel, Benjamin; Grüning, Philipp; Manikwadura, Dilini; Schollemann, Franziska; Teifke, Elisa; Rostalski, Philipp; Möller, RalfFailure mode and effects analysis (FMEA) is a systematic approach to identify and analyse potential failures and their effects in a system or process. The FMEA approach, however, requires domain experts to manually analyse the FMEA model to derive risk-reducing actions that should be applied. In this paper, we provide a formal framework to allow for automatic planning and acting in FMEA models. More specifically, we cast the FMEA model into a Markov decision process which can then be solved by existing solvers. We show that the FMEA approach can not only be used to support medical experts during the modelling process but also to automatically derive optimal therapies for the treatment of patients.
- ZeitschriftenartikelAutoRAG: Grounding Text and Symbols(KI - Künstliche Intelligenz: Vol. 38, No. 3, 2024) Schulz, Tim; Luttermann, Malte; Möller, RalfIn safety critical domains such as the healthcare domain, systems for natural language question answering demand special correctness guarantees. Modeling problem domains formally allows for automatic transparent reasoning, but handling comprehensive formal models may quickly demand expert knowledge. Ultimately, we need a system which is as easily accessible as large language models while the correctness of its output should be checkable using trusted knowledge. Since words are ambiguous in general but concepts of a formal model are not, we propose to expand the vocabulary of a language model by concepts of a knowledge base: Motivated by retrieval-augmented generation, we introduce AutoRAG, which does not retrieve data from external sources, rather it perceives parts of the knowledge base from special vocabulary, trained by auto-encoding text and concepts. Our AutoRAG implementation for a use case in the field of nosocomial pneumonia describes concepts it associates with the input and can naturally provide a graphical depiction from the expert-made knowledge bas to allow for feasible text sanity checks.
- ZeitschriftenartikelBuilding an AI Support Tool for Real-Time Ulcerative Colitis Diagnosis(KI - Künstliche Intelligenz: Vol. 38, No. 3, 2024) Møller, Bjørn Leth; Lo, Bobby Zhao Sheng; Burisch, Johan; Bendtsen, Flemming; Vind, Ida; Ibragimov, Bulat; Igel, ChristianUlcerative Colitis (UC) is a chronic inflammatory bowel disease decreasing life quality through symptoms such as bloody diarrhoea and abdominal pain. Endoscopy is a cornerstone of diagnosis and monitoring of UC. The Mayo endoscopic subscore (MES) index is the standard for measuring UC severity during endoscopic evaluation. However, the MES is subject to high inter-observer variability leading to misdiagnosis and suboptimal treatment. We propose using a machine-learning based MES classification system to support the endoscopic process and to mitigate the observer-variability. The system runs real-time in the clinic and augments doctors’ decision-making during the endoscopy. This project report outlines the process of designing, creating and evaluating our system. We describe our initial evaluation, which is a combination of a standard non-clinical model test and a first clinical test of the system on a real patient.
- ZeitschriftenartikelDissertation Abstract: Taming Exact Inference in Temporal Probabilistic Relational Models(KI - Künstliche Intelligenz: Vol. 38, No. 3, 2024) Gehrke, MarcelProcesses in our world are of a temporal probabilistic relational nature. An epidemic is an example of such a process. This dissertation abstract uses the scenario of an epidemic to illustrate the lifted dynamic junction tree algorithm (LDJT), which is a temporal probabilistic relational inference algorithm. More specifically, we argue that existing propositional temporal probabilistic inference algorithms are not suited to model an epidemic, i.e., without accounting for the relational part, and present how LDJT uses the relational aspect. Additionally, we illustrate how LDJT preserves groups of indistinguishable objects over time and have a look at LDJT from a theoretical side.
- ZeitschriftenartikelEpiPredict: Agent-Based Modeling of Infectious Diseases(KI - Künstliche Intelligenz: Vol. 38, No. 3, 2024) Suer, Janik; Ponge, Johannes; Hellingrath, BerndThe COVID-19 pandemic highlighted the impact of emerging infectious diseases on various aspects of public life. Decision-makers in the public-health sector faced the challenge of selecting effective countermeasures for a newly emerging disease with limited historical data and little understanding of its dynamics. To evaluate these decisions, infectious disease modeling has proven to be a valuable tool, providing insights into disease dynamics and predicting future outcomes for different scenarios. Agent-based models, which simulate populations at an individual level, are especially well-suited to capture the complex individual behaviors and the arising aggregated system evolution, making these models suitable tools to evaluate disease progression within highly heterogeneous populations. This paper focuses on the EpiPredict project, which has aimed to develop a flexible, easy-to-use simulation framework for constructing, executing, and analyzing agent-based infectious disease models. The project objective arose from the observation that epidemiologists or public-health decision-makers, i.e., people without a strong IT background, lacked simulation tools, as most available tools required extensive programming skills to create and simulate agent-based models. Within this paper, the EpiPredict project and platform will be presented, and the relation of agents to the field of artificial intelligence discussed.
- ZeitschriftenartikelHuman-Centered Explanations: Lessons Learned from Image Classification for Medical and Clinical Decision Making(KI - Künstliche Intelligenz: Vol. 38, No. 3, 2024) Finzel, BettinaTo date, there is no universal explanatory method for making decisions of an AI-based system transparent to human decision makers. This is because, depending on the application domain, data modality, and classification model, the requirements for the expressiveness of explanations vary. Explainees, whether experts or novices (e.g., in medical and clinical diagnosis) or developers, have different information needs. To address the explanation gap, we motivate human-centered explanations and demonstrate the need for combined and expressive approaches based on two image classification use cases: digital pathology and clinical pain detection using facial expressions. Various explanatory approaches that have emerged or been applied in the three-year research project “Transparent Medical Expert Companion” are shortly reviewed and categorized in expressiveness according to their modality and scope. Their suitability for different contexts of explanation is assessed with regard to the explainees’ need for information. The article highlights open challenges and suggests future directions for integrative explanation frameworks.