arXiv subjects

Thomas Engel

Publications and source records attributed to Thomas Engel.

12 recordsLinked to original sources

arXiv2025

Integrating a Causal Foundation Model into a Prescriptive Maintenance Framework for Optimising Production-Line OEE

The transition to prescriptive maintenance (PsM) in manufacturing is critically constrained by a dependence on predictive models. Such purely predictive models tend to capture statistical associations in the data without identifying the underlying causal drivers of failure, which can lead to costly misdiagnoses and ineffective measures. This fundamental limitation results in a key challenge: while we can predict that a failure may occur, we lack a systematic method to understand why a failure occurs. This paper proposes a model based on causal machine learning to bridge this gap. Our objective is to move beyond diagnosis to active prescription by simulating and evaluating potential fixes to optimise KPIs such as Overall Equipment Effectiveness (OEE). For this purpose, a pre-trained causal foundation model is used as a ``what-if'' simulator to estimate the effects of potential fixes. By estimating the causal effect of each intervention on system-level KPIs, specific actions can be recommended for the production line. This can help identify plausible root causes and quantify their operational impact. The model is evaluated using semi-synthetic manufacturing data and compared with non-causal and causal baseline machine learning models. This paper provides a technical basis for a human-centred approach, allowing engineers to test potential solutions in a causal environment to make more effective operational decisions and reduce costly downtimes.

cs.AI↗

arXiv2025

Belief Graphs with Reasoning Zones: Structure, Dynamics, and Epistemic Activation

Belief systems are rarely globally consistent, yet effective reasoning often persists locally. We propose a novel graph-theoretic framework that cleanly separates credibility--external, a priori trust in sources--from confidence--an internal, emergent valuation induced by network structure. Beliefs are nodes in a directed, signed, weighted graph whose edges encode support and contradiction. Confidence is obtained by a contractive propagation process that mixes a stated prior with structure-aware influence and guarantees a unique, stable solution. Within this dynamics, we define reasoning zones: high-confidence, structurally balanced subgraphs on which classical inference is safe despite global contradictions. We provide a near-linear procedure that seeds zones by confidence, tests balance using a parity-based coloring, and applies a greedy, locality-preserving repair with Jaccard de-duplication to build a compact atlas. To model belief change, we introduce shock updates that locally downscale support and elevate targeted contradictions while preserving contractivity via a simple backtracking rule. Re-propagation yields localized reconfiguration-zones may shrink, split, or collapse--without destabilizing the entire graph. We outline an empirical protocol on synthetic signed graphs with planted zones, reporting zone recovery, stability under shocks, and runtime. The result is a principled foundation for contradiction-tolerant reasoning that activates classical logic precisely where structure supports it.

cs.AI↗

arXiv2025

Cross-Model Semantics in Representation Learning

The internal representations learned by deep networks are often sensitive to architecture-specific choices, raising questions about the stability, alignment, and transferability of learned structure across models. In this paper, we investigate how structural constraints--such as linear shaping operators and corrective paths--affect the compatibility of internal representations across different architectures. Building on the insights from prior studies on structured transformations and convergence, we develop a framework for measuring and analyzing representational alignment across networks with distinct but related architectural priors. Through a combination of theoretical insights, empirical probes, and controlled transfer experiments, we demonstrate that structural regularities induce representational geometry that is more stable under architectural variation. This suggests that certain forms of inductive bias not only support generalization within a model, but also improve the interoperability of learned features across models. We conclude with a discussion on the implications of representational transferability for model distillation, modular learning, and the principled design of robust learning systems.

cs.LG↗

arXiv2025

Understanding Learning Dynamics Through Structured Representations

While modern deep networks have demonstrated remarkable versatility, their training dynamics remain poorly understood--often driven more by empirical tweaks than architectural insight. This paper investigates how internal structural choices shape the behavior of learning systems. Building on prior efforts that introduced simple architectural constraints, we explore the broader implications of structure for convergence, generalization, and adaptation. Our approach centers on a family of enriched transformation layers that incorporate constrained pathways and adaptive corrections. We analyze how these structures influence gradient flow, spectral sensitivity, and fixed-point behavior--uncovering mechanisms that contribute to training stability and representational regularity. Theoretical analysis is paired with empirical studies on synthetic and structured tasks, demonstrating improved robustness, smoother optimization, and scalable depth behavior. Rather than prescribing fixed templates, we emphasize principles of tractable design that can steer learning behavior in interpretable ways. Our findings support a growing view that architectural design is not merely a matter of performance tuning, but a critical axis for shaping learning dynamics in scalable and trustworthy neural systems.

cs.LG↗

arXiv2025

Reasoning Systems as Structured Processes: Foundations, Failures, and Formal Criteria

This paper outlines a general formal framework for reasoning systems, intended to support future analysis of inference architectures across domains. We model reasoning systems as structured tuples comprising phenomena, explanation space, inference and generation maps, and a principle base. The formulation accommodates logical, algorithmic, and learning-based reasoning processes within a unified structural schema, while remaining agnostic to any specific reasoning algorithm or logic system. We survey basic internal criteria--including coherence, soundness, and completeness-and catalog typical failure modes such as contradiction, incompleteness, and non-convergence. The framework also admits dynamic behaviors like iterative refinement and principle evolution. The goal of this work is to establish a foundational structure for representing and comparing reasoning systems, particularly in contexts where internal failure, adaptation, or fragmentation may arise. No specific solution architecture is proposed; instead, we aim to support future theoretical and practical investigations into reasoning under structural constraint.

cs.AI↗

arXiv2025

Structured Transformations for Stable and Interpretable Neural Computation

Despite their impressive performance, contemporary neural networks often lack structural safeguards that promote stable learning and interpretable behavior. In this work, we introduce a reformulation of layer-level transformations that departs from the standard unconstrained affine paradigm. Each transformation is decomposed into a structured linear operator and a residual corrective component, enabling more disciplined signal propagation and improved training dynamics. Our formulation encourages internal consistency and supports stable information flow across depth, while remaining fully compatible with standard learning objectives and backpropagation. Through a series of synthetic and real-world experiments, we demonstrate that models constructed with these structured transformations exhibit improved gradient conditioning, reduced sensitivity to perturbations, and layer-wise robustness. We further show that these benefits persist across architectural scales and training regimes. This study serves as a foundation for a more principled class of neural architectures that prioritize stability and transparency-offering new tools for reasoning about learning behavior without sacrificing expressive power.

cs.LG↗

arXiv2024

Mitigating Collisions in Sidelink NR V2X: A Study on Cooperative Resource Allocation

New Radio (NR) Vehicle-to-Everything (V2X) Sidelink (SL), an integral part of the 5G NR standard, is expected to revolutionize the automotive and rail industries by enabling direct and low-latency exchange of critical information between traffic participants independently of cellular networks. However, this advancement depends primarily on efficient SL resource allocation. Mode 2(a) is a well-known method for this purpose, where each node autonomously selects resources. However, this method is prone to packet collisions due to the hidden-node problem. In this paper, we propose a cooperative scheduling method that could potentially address this issue. We describe an extension of Mode 2(a) that allows nodes to share resource allocation information at two hops. Initial simulation results show a promising improvement over Mode 2(a).

cs.NI↗

arXiv2022

A Survey on Machine Learning-based Misbehavior Detection Systems for 5G and Beyond Vehicular Networks

Significant progress has been made towards deploying Vehicle-to-Everything (V2X) technology. Integrating V2X with 5G has enabled ultra-low latency and high-reliability V2X communications. However, while communication performance has enhanced, security and privacy issues have increased. Attacks have become more aggressive, and attackers have become more strategic. Public Key Infrastructure proposed by standardization bodies cannot solely defend against these attacks. Thus, in complementary of that, sophisticated systems should be designed to detect such attacks and attackers. Machine Learning (ML) has recently emerged as a key enabler to secure our future roads. Many V2X Misbehavior Detection Systems (MDSs) have adopted this paradigm. Yet, analyzing these systems is a research gap, and developing effective ML-based MDSs is still an open issue. To this end, this paper present a comprehensive survey and classification of ML-based MDSs. We analyze and discuss them from both security and ML perspectives. Then, we give some learned lessons and recommendations helping in developing, validating, and deploying ML-based MDSs. Finally, we highlight open research and standardization issues with some future directions.

cs.CR↗

arXiv2022

k-Pareto Optimality-Based Sorting with Maximization of Choice

Topological sorting is an important technique in numerous practical applications, such as information retrieval, recommender systems, optimization, etc. In this paper, we introduce a problem of generalized topological sorting with maximization of choice, that is, of choosing a subset of items of a predefined size that contains the maximum number of equally preferable options (items) with respect to a dominance relation. We formulate this problem in a very abstract form and prove that sorting by k-Pareto optimality yields a valid solution. Next, we show that the proposed theory can be useful in practice. We apply it during the selection step of genetic optimization and demonstrate that the resulting algorithm outperforms existing state-of-the-art approaches such as NSGA-II and NSGA-III. We also demonstrate that the provided general formulation allows discovering interesting relationships and applying the developed theory to different applications.

math.OC↗

arXiv2021

Causal Identification with Additive Noise Models: Quantifying the Effect of Noise

In recent years, a lot of research has been conducted within the area of causal inference and causal learning. Many methods have been developed to identify the cause-effect pairs in models and have been successfully applied to observational real-world data to determine the direction of causal relationships. Yet in bivariate situations, causal discovery problems remain challenging. One class of such methods, that also allows tackling the bivariate case, is based on Additive Noise Models (ANMs). Unfortunately, one aspect of these methods has not received much attention until now: what is the impact of different noise levels on the ability of these methods to identify the direction of the causal relationship. This work aims to bridge this gap with the help of an empirical study. We test Regression with Subsequent Independence Test (RESIT) using an exhaustive range of models where the level of additive noise gradually changes from 1\% to 10000\% of the causes' noise level (the latter remains fixed). Additionally, the experiments in this work consider several different types of distributions as well as linear and non-linear models. The results of the experiments show that ANMs methods can fail to capture the true causal direction for some levels of noise.

stat.ML↗

arXiv2020

Software-Defined Location Privacy Protection for Vehicular Networks

While the adoption of connected vehicles is growing, security and privacy concerns are still the key barriers raised by society. These concerns mandate automakers and standardization groups to propose convenient solutions for privacy preservation. One of the main proposed solutions is the use of Pseudonym-Changing Strategies (PCSs). However, ETSI has recently published a technical report which highlights the absence of standardized and efficient PCSs [1]. This alarming situation mandates an innovative shift in the way that the privacy of end-users is protected during their journey. Software-Defined Networking (SDN) is emerging as a key 5G enabler to manage the network in a dynamic manner. SDN-enabled wireless networks are opening up new programmable and highly-flexible privacy-aware solutions. We exploit this paradigm to propose an innovative software-defined location privacy architecture for vehicular networks. The proposed architecture is context-aware, programmable, extensible, and able to encompass all existing and future pseudonym-changing strategies. To demonstrate the merit of our architecture, we consider a case study that involves four pseudonym-changing strategies, which we deploy over our architecture and compare with their static implementations. We also detail how the SDN controller dynamically switches between the strategies according to the context.

cs.CR↗

arXiv2010

Law-Aware Access Control and its Information Model

Cross-border access to a variety of data such as market information, strategic information, or customer-related information defines the daily business of many global companies, including financial institutions. These companies are obliged by law to keep a data processing legal for all offered services. They need to fulfill different security objectives specified by the legislation. Therefore, they control access to prevent unauthorized users from using data. Those security objectives, for example confidentiality or secrecy, are often defined in the eXtensible Access Control Markup Language that promotes interoperability between different systems. In this paper, we show the necessity of incorporating the requirements of legislation into access control. Based on the work flow in a banking scenario we describe a variety of available contextual information and their interrelations. Different from other access control systems our main focus is on law-compliant cross-border data access. By including legislation directly into access decisions, this lawfulness can be ensured. We also describe our information model to demonstrate how these policies can be implemented into an existing network and how the components and contextual information interrelate. Finally, we outline an event flow for a request made from a remote user exemplifying how such a system decides about access.

cs.CR↗