Andreas Holzinger
YOU?
Author Swipe
View article: Assessing the carbon footprint of language models: Towards sustainability in AI
Assessing the carbon footprint of language models: Towards sustainability in AI Open
View article: Ethical AI for sustainable development: User perceptions across the United Nations Sustainable Development Goals
Ethical AI for sustainable development: User perceptions across the United Nations Sustainable Development Goals Open
View article: What can artificial intelligence do for soil health in agriculture?
What can artificial intelligence do for soil health in agriculture? Open
View article: ForestGPT and Beyond: A Trustworthy Domain-Specific Large Language Model Paving the Way to Forestry 5.0
ForestGPT and Beyond: A Trustworthy Domain-Specific Large Language Model Paving the Way to Forestry 5.0 Open
Large language models (LLMs) such as Chat Generative Pre-Trained Transformer (ChatGPT) are increasingly used across domains, yet their generic training data and propensity for hallucination limit reliability in safety-critical fields like …
View article: Standardized Multi-Layer Tissue Maps for Enhanced Artificial Intelligence Integration and Search in Large-Scale Whole Slide Image Archives
Standardized Multi-Layer Tissue Maps for Enhanced Artificial Intelligence Integration and Search in Large-Scale Whole Slide Image Archives Open
A Whole Slide Image (WSI) is a high-resolution digital image created by scanning an entire glass slide containing a biological specimen, such as tissue sections or cell samples, at multiple magnifications. These images can be viewed, analy…
View article: Explaining and visualizing black-box models through counterfactual paths
Explaining and visualizing black-box models through counterfactual paths Open
Explainable AI (XAI) is an increasingly important area of machine learning research, which aims to make black-box models transparent and interpretable. In this paper, we propose a novel approach to XAI that uses the so-called counterfactua…
View article: Developing a User-Friendly Interface for Interactive Cable Corridor Planning
Developing a User-Friendly Interface for Interactive Cable Corridor Planning Open
Traditional methods of determining cable corridor layouts often rely on less accurate tree maps based on forest density estimates and satellite imagery, which can lead to designs that rely on infeasible corridors, undermining their reliabi…
View article: Robot usability in the wild: bridging accessibility gaps for diverse user groups in complex forestry operations
Robot usability in the wild: bridging accessibility gaps for diverse user groups in complex forestry operations Open
This study evaluated the usability and effectiveness of robotic platforms working together with foresters in the wild on forest inventory tasks using LiDAR scanning. Emphasis was on the Universal Access principle, ensuring that robotic sol…
View article: World Models in Artificial Intelligence: Sensing, Learning, and Reasoning Like a Child
World Models in Artificial Intelligence: Sensing, Learning, and Reasoning Like a Child Open
World Models help Artificial Intelligence (AI) predict outcomes, reason about its environment, and guide decision-making. While widely used in reinforcement learning, they lack the structured, adaptive representations that even young child…
View article: On the disagreement problem in Human-in-the-Loop federated machine learning
On the disagreement problem in Human-in-the-Loop federated machine learning Open
View article: Grand Challenges of Smart Technology for Older Adults
Grand Challenges of Smart Technology for Older Adults Open
View article: Enhancing trust in automated 3D point cloud data interpretation through explainable counterfactuals
Enhancing trust in automated 3D point cloud data interpretation through explainable counterfactuals Open
View article: Gamifying information security: Adversarial risk exploration for IT/OT infrastructures
Gamifying information security: Adversarial risk exploration for IT/OT infrastructures Open
View article: Transformer-powered precision: A DETR-based approach for robust detection in medical ultrasound with cholelithiasis as a case study
Transformer-powered precision: A DETR-based approach for robust detection in medical ultrasound with cholelithiasis as a case study Open
View article: Is human oversight to AI systems still possible?
Is human oversight to AI systems still possible? Open
The rapid proliferation of artificial intelligence (AI) systems across diverse domains raises critical questions about the feasibility of meaningful human oversight, particularly in high-stakes domains such as new biotechnology. As AI syst…
View article: Integrating Belief-Desire-Intention agents with large language models for reliable human–robot interaction and explainable Artificial Intelligence
Integrating Belief-Desire-Intention agents with large language models for reliable human–robot interaction and explainable Artificial Intelligence Open
View article: NiaAML: AutoML for classification and regression pipelines
NiaAML: AutoML for classification and regression pipelines Open
In this paper we present NiaAML, an AutoML framework that we have developed for creating machine learning pipelines and hyperparameter tuning. The composition of machine learning pipelines is presented as an optimization problem that can b…
View article: Fine-tuning language model embeddings to reveal domain knowledge: An explainable artificial intelligence perspective on medical decision making
Fine-tuning language model embeddings to reveal domain knowledge: An explainable artificial intelligence perspective on medical decision making Open
View article: Tree smoothing: Post-hoc regularization of tree ensembles for interpretable machine learning
Tree smoothing: Post-hoc regularization of tree ensembles for interpretable machine learning Open
Random Forests (RFs) are powerful ensemble learning algorithms that are widely used in various machine learning tasks. However, they tend to overfit noisy or irrelevant features, which can result in decreased generalization performance. Po…
View article: Collaborative weighting in federated graph neural networks for disease classification with the human-in-the-loop
Collaborative weighting in federated graph neural networks for disease classification with the human-in-the-loop Open
The authors introduce a novel framework that integrates federated learning with Graph Neural Networks (GNNs) to classify diseases, incorporating Human-in-the-Loop methodologies. This advanced framework innovatively employs collaborative vo…
View article: From <scp>3D</scp> point‐cloud data to explainable geometric deep learning: State‐of‐the‐art and future challenges
From <span>3D</span> point‐cloud data to explainable geometric deep learning: State‐of‐the‐art and future challenges Open
We present an exciting journey from 3D point‐cloud data (PCD) to the state of the art in graph neural networks (GNNs) and their evolution with explainable artificial intelligence (XAI), and 3D geometric priors with the human‐in‐the‐loop. W…
View article: Front Cover: Raman Spectral Analysis in the CH<sub>x</sub>‐Stretching Region as a Guiding Beacon for Non‐Targeted, Disruption‐Free Monitoring of Germination and Biofilm Formation in the Green Seaweed <i>Ulva</i> (ChemPhysChem 17/2024)
Front Cover: Raman Spectral Analysis in the CH<sub>x</sub>‐Stretching Region as a Guiding Beacon for Non‐Targeted, Disruption‐Free Monitoring of Germination and Biofilm Formation in the Green Seaweed <i>Ulva</i> (ChemPhysChem 17/2024) Open
View article: Ethical ChatGPT: Concerns, Challenges, and Commandments
Ethical ChatGPT: Concerns, Challenges, and Commandments Open
Large language models, e.g., Chat Generative Pre-Trained Transformer (also known as ChatGPT), are currently contributing enormously to making artificial intelligence even more popular, especially among the general population. However, such…
View article: Multi-objective optimization of cable-road layouts in smart forestry
Multi-objective optimization of cable-road layouts in smart forestry Open
Current cable-road layouts for timber harvesting in steep terrain are often based on either manual planning or automated layouts generated from low-resolution GIS data, limiting potential benefits and informed decision-making. In this pape…
View article: Class imbalance in multi-resident activity recognition: an evaluative study on explainability of deep learning approaches
Class imbalance in multi-resident activity recognition: an evaluative study on explainability of deep learning approaches Open
Recognizing multiple residents’ activities is a pivotal domain within active and assisted living technologies, where the diversity of actions in a multi-occupant home poses a challenge due to their uneven distribution. Frequent activities …
View article: A Practical Tutorial on Explainable AI Techniques
A Practical Tutorial on Explainable AI Techniques Open
The past years have been characterized by an upsurge in opaque automatic decision support systems, such as Deep Neural Networks (DNNs). Although DNNs have great generalization and prediction abilities, it is difficult to obtain detailed ex…
View article: Raman Spectral Analysis in the CH<sub>x</sub>‐Stretching Region as a Guiding Beacon for Non‐Targeted, Disruption‐Free Monitoring of Germination and Biofilm Formation in the Green Seaweed <i>Ulva</i>
Raman Spectral Analysis in the CH<sub>x</sub>‐Stretching Region as a Guiding Beacon for Non‐Targeted, Disruption‐Free Monitoring of Germination and Biofilm Formation in the Green Seaweed <i>Ulva</i> Open
Raman spectroscopy was used to study the complex interactions and morphogenesis of the green seaweed Ulva (Chlorophyta) and its associated bacteria under controlled conditions in a reductionist model system. Integrating multiple imaging te…
View article: The Light-activated Effect of Natural Anthraquinone Parietin against Candida auris and Other Fungal Priority Pathogens
The Light-activated Effect of Natural Anthraquinone Parietin against Candida auris and Other Fungal Priority Pathogens Open
Antimicrobial photodynamic therapy (aPDT) is an evolving treatment strategy against human pathogenic microbes such as the Candida species, including the emerging pathogen C. auris. Using a modified EUCAST protocol, the light-enhanced antif…
View article: Post-hoc vs ante-hoc explanations: xAI design guidelines for data scientists
Post-hoc vs ante-hoc explanations: xAI design guidelines for data scientists Open
The growing field of explainable Artificial Intelligence (xAI) has given rise to a multitude of techniques and methodologies, yet this expansion has created a growing gap between existing xAI approaches and their practical application. Thi…
View article: Explainable Artificial Intelligence to Support Work Safety in Forestry: Insights from Two Large Datasets, Open Challenges, and Future Work
Explainable Artificial Intelligence to Support Work Safety in Forestry: Insights from Two Large Datasets, Open Challenges, and Future Work Open
Forestry work, which is considered one of the most demanding and dangerous professions in the world, is claiming more and more lives. In a country as small as Austria, more than 50 forestry workers are killed in accidents every year, and t…