arXiv subjects

Jörg Hähner

Publications and source records attributed to Jörg Hähner.

17 recordsLinked to original sources

arXiv2026

Have I Solved This Before? Retrieving Similar Segmentation Problems for Evolutionary Learning

Reliable integration and solid configuration of monitoring systems constitute a fundamental prerequisites for achieving high efficiency and productivity in contemporary manufacturing environments. Design decisions on sensor type and system architecture have to be made at an early stage and under comparably high uncertainty. This work investigates a research direction that deviates from the traditional monitoring-system development process by shifting the attention from algorithm design to a deeper analysis of the inspection problem. In contrast to traditional design cycles, this paper proposes to gradually collect knowledge and store it in an abstract system model. This enables the retrieval of similar solutions for future use cases, preventing the need for expensive model training from scratch and allowing instead for the incremental refinement of existing base configurations. Reuse of previously generated pipelines reduces the risk of late and costly revisions. As there is little knowledge on cross-domain transferability of filter pipelines, this study analyzes the potential of retrieving filter pipelines to transfer them to different but similar segmentation problems. Finally, we statistically analyze the benefits of this `transfer learning' variant which is predominantly applied to image segmentation problems. In addition, we discuss how simple models help balancing the trade-off between complexity, technical requirements, and reliability in the design process.

cs.LG↗

arXiv2026

Performance and Explainability Requirements of Evolutionary Algorithms in Real-World Physics-Informed Optimization

Evolutionary computation offers a variety of tools to solve complex real-world optimization problems. However, research often focuses on smaller, simplified problems and optimization algorithms that sometimes miss expectations in real-world scenarios. Additionally, trust in the applied algorithm and the solutions it provides is often essential in such settings, but requires an understanding of the search process itself. This leads to evolutionary computation often not being seriously considered by practitioners in many application contexts, among them physics-based modeling. In this article, techniques from evolutionary computation are detailed that can alleviate these problems. First, five real-world physics-based optimization problems are introduced and described by domain experts. For each of these, the requirements for the evolutionary algorithm regarding performance and explainability to increase trust and usability are presented. We found that all domain experts expect fast convergence to a good solution and want some explanations for how the results were formed, while other requirements strongly depend on the respective problem. Finally, we present existing approaches that can be leveraged to improve those aspects of evolutionary algorithms but have to our knowledge never been employed in complex real-world scenarios. This implies a gap between both domains that needs to be closed to exploit the full potential of evolutionary computation.

cs.NE↗

arXiv2026

Modernising Reinforcement Learning-Based Navigation for Embodied Semantic Scene Graph Generation

Semantic world models enable embodied agents to reason about objects, relations, and spatial context beyond purely geometric representations. In Organic Computing, such models are a key enabler for objective-driven self-adaptation under uncertainty and resource constraints. The core challenge is to acquire observations maximising model quality and downstream usefulness within a limited action budget. Semantic scene graphs (SSGs) provide a structured and compact representation for this purpose. However, constructing them within a finite action horizon requires exploration strategies that trade off information gain against navigation cost and decide when additional actions yield diminishing returns. This work presents a modular navigation component for Embodied Semantic Scene Graph Generation and modernises its decision-making by replacing the policy-optimisation method and revisiting the discrete action formulation. We study compact and finer-grained, larger discrete motion sets and compare a single-head policy over atomic actions with a factorised multi-head policy over action components. We evaluate curriculum learning and optional depth-based collision supervision, and assess SSG completeness, execution safety, and navigation behaviour. Results show that replacing the optimisation algorithm alone improves SSG completeness by 21\% relative to the baseline under identical reward shaping. Depth mainly affects execution safety (collision-free motion), while completeness remains largely unchanged. Combining modern optimisation with a finer-grained, factorised action representation yields the strongest overall completeness--efficiency trade-off.

cs.AI↗

arXiv2026

Unsupervised Anomaly Detection in Process-Complex Industrial Time Series: A Real-World Case Study

Industrial time-series data from real production environments exhibits substantially higher complexity than commonly used benchmark datasets, primarily due to heterogeneous, multi-stage operational processes. As a result, anomaly detection methods validated under simplified conditions often fail to generalize to industrial settings. This work presents an empirical study on a unique dataset collected from fully operational industrial machinery, explicitly capturing pronounced process-induced variability. We evaluate which model classes are capable of capturing this complexity, starting with a classical Isolation Forest baseline and extending to multiple autoencoder architectures. Experimental results show that Isolation Forest is insufficient for modeling the non-periodic, multi-scale dynamics present in the data, whereas autoencoders consistently perform better. Among them, temporal convolutional autoencoders achieve the most robust performance, while recurrent and variational variants require more careful tuning.

cs.LG↗

arXiv2026

Pareto-Optimal Anytime Algorithms via Bayesian Racing

Selecting an optimization algorithm requires comparing candidates across problem instances, but the computational budget for deployment is often unknown at benchmarking time. Current methods either collapse anytime performance into a scalar, require manual interpretation of plots, or produce conclusions that change when algorithms are added or removed. Moreover, methods based on raw objective values require normalization, which needs bounds or optima that are often unavailable and breaks coherent aggregation across instances. We propose a framework that formulates anytime algorithm comparison as Pareto optimization over time: an algorithm is non-dominated if no competitor beats it at every timepoint. By using rankings rather than objective values, our approach requires no bounds, no normalization, and aggregates coherently across arbitrary instance distributions without requiring known optima. We introduce PolarBear (Pareto-optimal anytime algorithms via Bayesian racing), a procedure that identifies the anytime Pareto set through adaptive sampling with calibrated uncertainty. Bayesian inference over a temporal Plackett-Luce ranking model provides posterior beliefs about pairwise dominance, enabling early elimination of confidently dominated algorithms. The output Pareto set together with the posterior supports downstream algorithm selection under arbitrary time preferences and risk profiles without additional experiments.

cs.NE↗

arXiv2025

HOIverse: A Synthetic Scene Graph Dataset With Human Object Interactions

When humans and robotic agents coexist in an environment, scene understanding becomes crucial for the agents to carry out various downstream tasks like navigation and planning. Hence, an agent must be capable of localizing and identifying actions performed by the human. Current research lacks reliable datasets for performing scene understanding within indoor environments where humans are also a part of the scene. Scene Graphs enable us to generate a structured representation of a scene or an image to perform visual scene understanding. To tackle this, we present HOIverse a synthetic dataset at the intersection of scene graph and human-object interaction, consisting of accurate and dense relationship ground truths between humans and surrounding objects along with corresponding RGB images, segmentation masks, depth images and human keypoints. We compute parametric relations between various pairs of objects and human-object pairs, resulting in an accurate and unambiguous relation definitions. In addition, we benchmark our dataset on state-of-the-art scene graph generation models to predict parametric relations and human-object interactions. Through this dataset, we aim to accelerate research in the field of scene understanding involving people.

cs.CV↗

arXiv2024

Analysing the Influence of Reorder Strategies for Cartesian Genetic Programming

Cartesian Genetic Programming (CGP) suffers from a specific limitation: Positional bias, a phenomenon in which mostly genes at the start of the genome contribute to a program output, while genes at the end rarely do. This can lead to an overall worse performance of CGP. One solution to overcome positional bias is to introduce reordering methods, which shuffle the current genotype without changing its corresponding phenotype. There are currently two different reorder operators that extend the classic CGP formula and improve its fitness value. In this work, we discuss possible shortcomings of these two existing operators. Afterwards, we introduce three novel operators which reorder the genotype of a graph defined by CGP. We show empirically on four Boolean and four symbolic regression benchmarks that the number of iterations until a solution is found and/or the fitness value improves by using CGP with a reorder method. However, there is no consistently best performing reorder operator. Furthermore, their behaviour is analysed by investigating their convergence plots and we show that all behave the same in terms of convergence type.

cs.NE↗

arXiv2023

PDPK: A Framework to Synthesise Process Data and Corresponding Procedural Knowledge for Manufacturing

Procedural knowledge describes how to accomplish tasks and mitigate problems. Such knowledge is commonly held by domain experts, e.g. operators in manufacturing who adjust parameters to achieve quality targets. To the best of our knowledge, no real-world datasets containing process data and corresponding procedural knowledge are publicly available, possibly due to corporate apprehensions regarding the loss of knowledge advances. Therefore, we provide a framework to generate synthetic datasets that can be adapted to different domains. The design choices are inspired by two real-world datasets of procedural knowledge we have access to. Apart from containing representations of procedural knowledge in Resource Description Framework (RDF)-compliant knowledge graphs, the framework simulates parametrisation processes and provides consistent process data. We compare established embedding methods on the resulting knowledge graphs, detailing which out-of-the-box methods have the potential to represent procedural knowledge. This provides a baseline which can be used to increase the comparability of future work. Furthermore, we validate the overall characteristics of a synthesised dataset by comparing the results to those achievable on a real-world dataset. The framework and evaluation code, as well as the dataset used in the evaluation, are available open source.

cs.AI↗

arXiv2022

Investigating the Impact of Independent Rule Fitnesses in a Learning Classifier System

Achieving at least some level of explainability requires complex analyses for many machine learning systems, such as common black-box models. We recently proposed a new rule-based learning system, SupRB, to construct compact, interpretable and transparent models by utilizing separate optimizers for the model selection tasks concerning rule discovery and rule set composition.This allows users to specifically tailor their model structure to fulfil use-case specific explainability requirements. From an optimization perspective, this allows us to define clearer goals and we find that -- in contrast to many state of the art systems -- this allows us to keep rule fitnesses independent. In this paper we investigate this system's performance thoroughly on a set of regression problems and compare it against XCSF, a prominent rule-based learning system. We find the overall results of SupRB's evaluation comparable to XCSF's while allowing easier control of model structure and showing a substantially smaller sensitivity to random seeds and data splits. This increased control can aid in subsequently providing explanations for both training and final structure of the model.

cs.LG↗

arXiv2022

Learning Classifier Systems for Self-Explaining Socio-Technical-Systems

In socio-technical settings, operators are increasingly assisted by decision support systems. By employing these, important properties of socio-technical systems such as self-adaptation and self-optimization are expected to improve further. To be accepted by and engage efficiently with operators, decision support systems need to be able to provide explanations regarding the reasoning behind specific decisions. In this paper, we propose the usage of Learning Classifier Systems, a family of rule-based machine learning methods, to facilitate transparent decision making and highlight some techniques to improve that. We then present a template of seven questions to assess application-specific explainability needs and demonstrate their usage in an interview-based case study for a manufacturing scenario. We find that the answers received did yield useful insights for a well-designed LCS model and requirements to have stakeholders actively engage with an intelligent agent.

cs.HC↗

arXiv2022

Separating Rule Discovery and Global Solution Composition in a Learning Classifier System

While utilization of digital agents to support crucial decision making is increasing, trust in suggestions made by these agents is hard to achieve. However, it is essential to profit from their application, resulting in a need for explanations for both the decision making process and the model. For many systems, such as common black-box models, achieving at least some explainability requires complex post-processing, while other systems profit from being, to a reasonable extent, inherently interpretable. We propose a rule-based learning system specifically conceptualised and, thus, especially suited for these scenarios. Its models are inherently transparent and easily interpretable by design. One key innovation of our system is that the rules' conditions and which rules compose a problem's solution are evolved separately. We utilise independent rule fitnesses which allows users to specifically tailor their model structure to fit the given requirements for explainability.

cs.LG↗

arXiv2020

An Adaptive Flow-Aware Packet Scheduling Algorithm for Multipath Tunnelling

This paper proposes AFMT, a packet scheduling algorithm to achieve adaptive flow-aware multipath tunnelling. AFMT has two unique properties. Firstly, it implements robust adaptive traffic splitting for the subtunnels. Secondly, it detects and schedules bursts of packets cohesively, a scheme that already enabled traffic splitting for load balancing with little to no packet reordering. Several NS-3 experiments over different network topologies show that AFMT successfully deals with changing path characteristics due to background traffic while increasing throughput and reliability.

cs.NI↗

arXiv2020

An Architectural Design for Measurement Uncertainty Evaluation in Cyber-Physical Systems

Several use cases from the areas of manufacturing and process industry, require highly accurate sensor data. As sensors always have some degree of uncertainty, methods are needed to increase their reliability. The common approach is to regularly calibrate the devices to enable traceability according to national standards and Système international (SI) units - which follows costly processes. However, sensor networks can also be represented as Cyber Physical Systems (CPS) and a single sensor can have a digital representation (Digital Twin) to use its data further on. To propagate uncertainty in a reliable way in the network, we present a system architecture to communicate measurement uncertainties in sensor networks utilizing the concept of Asset Administration Shells alongside methods from the domain of Organic Computing. The presented approach contains methods for uncertainty propagation as well as concepts from the Machine Learning domain that combine the need for an accurate uncertainty estimation. The mathematical description of the metrological uncertainty of fused or propagated values can be seen as a first step towards the development of a harmonized approach for uncertainty in distributed CPSs in the context of Industrie 4.0. In this paper, we present basic use cases, conceptual ideas and an agenda of how to proceed further on.

eess.SP↗

arXiv2020

SupRB: A Supervised Rule-based Learning System for Continuous Problems

We propose the SupRB learning system, a new Pittsburgh-style learning classifier system (LCS) for supervised learning on multi-dimensional continuous decision problems. SupRB learns an approximation of a quality function from examples (consisting of situations, choices and associated qualities) and is then able to make an optimal choice as well as predict the quality of a choice in a given situation. One area of application for SupRB is parametrization of industrial machinery. In this field, acceptance of the recommendations of machine learning systems is highly reliant on operators' trust. While an essential and much-researched ingredient for that trust is prediction quality, it seems that this alone is not enough. At least as important is a human-understandable explanation of the reasoning behind a recommendation. While many state-of-the-art methods such as artificial neural networks fall short of this, LCSs such as SupRB provide human-readable rules that can be understood very easily. The prevalent LCSs are not directly applicable to this problem as they lack support for continuous choices. This paper lays the foundations for SupRB and shows its general applicability on a simplified model of an additive manufacturing problem.

cs.LG↗

arXiv2020

XCS Classifier System with Experience Replay

XCS constitutes the most deeply investigated classifier system today. It bears strong potentials and comes with inherent capabilities for mastering a variety of different learning tasks. Besides outstanding successes in various classification and regression tasks, XCS also proved very effective in certain multi-step environments from the domain of reinforcement learning. Especially in the latter domain, recent advances have been mainly driven by algorithms which model their policies based on deep neural networks -- among which the Deep-Q-Network (DQN) is a prominent representative. Experience Replay (ER) constitutes one of the crucial factors for the DQN's successes, since it facilitates stabilized training of the neural network-based Q-function approximators. Surprisingly, XCS barely takes advantage of similar mechanisms that leverage stored raw experiences encountered so far. To bridge this gap, this paper investigates the benefits of extending XCS with ER. On the one hand, we demonstrate that for single-step tasks ER bears massive potential for improvements in terms of sample efficiency. On the shady side, however, we reveal that the use of ER might further aggravate well-studied issues not yet solved for XCS when applied to sequential decision problems demanding for long-action-chains.

cs.LG↗

arXiv2020

Bootstrapping a DQN Replay Memory with Synthetic Experiences

An important component of many Deep Reinforcement Learning algorithms is the Experience Replay which serves as a storage mechanism or memory of made experiences. These experiences are used for training and help the agent to stably find the perfect trajectory through the problem space. The classic Experience Replay however makes only use of the experiences it actually made, but the stored samples bear great potential in form of knowledge about the problem that can be extracted. We present an algorithm that creates synthetic experiences in a nondeterministic discrete environment to assist the learner. The Interpolated Experience Replay is evaluated on the FrozenLake environment and we show that it can support the agent to learn faster and even better than the classic version.

cs.LG↗

arXiv2019

On the Detection of Mutual Influences and Their Consideration in Reinforcement Learning Processes

Self-adaptation has been proposed as a mechanism to counter complexity in control problems of technical systems. A major driver behind self-adaptation is the idea to transfer traditional design-time decisions to runtime and into the responsibility of systems themselves. In order to deal with unforeseen events and conditions, systems need creativity -- typically realized by means of machine learning capabilities. Such learning mechanisms are based on different sources of knowledge. Feedback from the environment used for reinforcement purposes is probably the most prominent one within the self-adapting and self-organizing (SASO) systems community. However, the impact of other (sub-)systems on the success of the individual system's learning performance has mostly been neglected in this context. In this article, we propose a novel methodology to identify effects of actions performed by other systems in a shared environment on the utility achievement of an autonomous system. Consider smart cameras (SC) as illustrating example: For goals such as 3D reconstruction of objects, the most promising configuration of one SC in terms of pan/tilt/zoom parameters depends largely on the configuration of other SCs in the vicinity. Since such mutual influences cannot be pre-defined for dynamic systems, they have to be learned at runtime. Furthermore, they have to be taken into consideration when self-improving the own configuration decisions based on a feedback loop concept, e.g., known from the SASO domain or the Autonomic and Organic Computing initiatives. We define a methodology to detect such influences at runtime, present an approach to consider this information in a reinforcement learning technique, and analyze the behavior in artificial as well as real-world SASO system settings.

cs.MA↗