George A. Vouros

Ontology engineering plays a critical role in clinical decision support systems for Parkinson’s Disease (PD) monitoring and alerting. While Large Language Models (LLMs) have shown promise in knowledge modeling tasks, their effectiveness in autonomously constructing comprehensive ontologies for complex clinical domains remains unclear. This study investigates four ontology engineering methodologies for PD monitoring and alerting: One-shot (OS) prompting, Decomposed Sequential Prompting (DSP), X-HCOME, and SimX-HCOME+. Multiple LLMs were evaluated across these methodologies. Generated ontologies were assessed against a reference PD ontology using structural evaluation metrics focused on classes and object properties. Expert review was additionally conducted to analyze knowledge extensions beyond the gold standard. LLMs were able to autonomously generate syntactically valid and semantically meaningful ontologies using OS and DSP prompting; however, these ontologies exhibited limited conceptual coverage. Incorporating human expertise through X-HCOME significantly improved ontology completeness and evaluation metrics. Expert review further validated clinically relevant concepts absent from the reference ontology. SimX-HCOME+ demonstrated that iterative, supervised collaboration supports ontology refinement, although challenges persisted in natural language-to-rule formalization. The findings suggest that LLMs are more effective as collaborative assistants rather than standalone ontology engineers in the PD domain. Structured human–LLM collaboration is associated with improved ontology coverage and facilitates the identification of potential knowledge extensions in clinical monitoring applications. While the present evaluation focuses primarily on structural ontology elements, the proposed methodologies provide useful insights for LLM-assisted ontology engineering in complex healthcare domains.

Time-series classification (TSC) is an important task across sciences. Symbolic representations (especially SFA) are very effective at combating noise. In this paper, we employ symbolic representations to create state-of-the-art time-series classifiers, with the aim to advance scalability without sacrificing accuracy. First, we create a graph representation of the time series based on SFA words. We use this representation together with graph kernels and an SVM classifier to create a scalable time-series classifier. Next, we use the graph representation together with a Graph Convolutional Neural Network to test how it fares against state-of-the-art time-series classifiers. Additionally, we devised deep neural networks exploiting the SFA representation, inspired by the text classification domain, to study how they fare against state-of-the-art classifiers. The proposed deep learning classifiers have been adapted and evaluated for the multivariate time-series case and also against state-of-the-art time-series classification algorithms based on symbolic representations.

This article introduces an imitation learning method for learning maximum entropy policies that comply with constraints demonstrated by expert trajectories executing a task. The formulation of the method takes advantage of results connecting performance to bounds for the KL-divergence between demonstrated and learned policies, and its objective is rigorously justified through a connection to a probabilistic inference framework for reinforcement learning, incorporating the reinforcement learning objective and the objective to abide by constraints in an entropy maximization setting. The proposed algorithm optimizes the learning objective with dual gradient descent, supporting effective and stable training. Experiments show that the proposed method can learn effective policy models for constraints-abiding behaviour, in settings with multiple constraints of different types, accommodating different modalities of demonstrated behaviour, and with abilities to generalize.

Predicting bankruptcy is crucial for managing financial risk in corporations. This study emphasizes incorporating the auditor’s opinion text into prediction models to improve their ability to assess financial health. These opinions provide essential insights as they offer an independent assessment, complementing other predictive inputs like the management’s discussion and analysis. However, the rarity of bankruptcy cases in the data introduces a challenging issue due to severe class imbalance. To address this, we propose a method to generate synthetic positive samples using a variational autoencoder and integrate the multi-source input in a late fusion setting. We showcase that both data augmentation and using multiple textual sources improve the performance of existing models on a related benchmark dataset. Additionally, we evaluate LLMs when used for data augmentation in the proposed method and in a zero-shot prediction setting, discussing important aspects to consider when incorporating them in a predictive pipeline.

Complex microscopic simulation models of strategic Air Traffic Management (ATM) performance assessment and decision-making are hindered by several factors. One of the most important is the existence of hidden parameters—such as aircraft take-off weight (TOW) and the selected cost index (CI)—which, if known, would allow for more effective performance modeling methodologies for assessing Key Performance Indicators (KPIs) at various levels of abstraction/detail, e.g., system-wide, or at the level of individual flights. This research proposes a data-driven methodology for the estimation of flights’ hidden parameters combining mechanistic and advanced Artificial Intelligence/Machine Learning (AI/ML) models. Aiming at microsimulation models, our goal is to study the effect of these estimations on the prediction of flights’ KPIs. In so doing, we propose a novel methodology according to which data-driven methods are trained given optimal trajectories (produced by mechanistic models) corresponding to known hidden parameter values, with the aim of predicting hidden parameters’ values of unseen trajectories. The results show that estimations of hidden parameters support the accurate prediction of KPIs regarding the efficiency of flights: fuel consumption, gate-to-gate time and distance flown.

Natural disasters such as earthquakes, floods, and forest fires involve critical situations in which human lives and infrastructures are in jeopardy. People are often injured and/or trapped without being able to be assisted by first responders on time. Moreover, in most cases, the harsh environment jeopardizes first responders by significantly increasing the difficulty of their mission. In such scenarios, time is crucial and often of vital importance. First responders must have a clear and complete view of the current situation every few seconds/minutes to efficiently and timely tackle emerging challenges, ensuring the safety of both victims and personnel. Advances in related technology including robots, drones, and Internet of Things (IoT)-enabled equipment have increased their usability and importance in life- and time-critical decision support systems such as the ones designed and developed for Search and Rescue (SAR) missions. Such systems depend on efficiency in their ability to integrate large volumes of heterogeneous and streaming data and reason with this data in (near) real time. In addition, real-time critical data integration and reasoning need to be performed on edge devices that reside near the missions, instead of using cloud infrastructure. The aim of this paper is twofold: (a) to review technologies and approaches related to real-time semantic data integration and reasoning on IoT-enabled collaborative entities and edge devices in life- and time-critical decision support systems, with a focus on systems designed for SAR missions and (b) to identify open issues and challenges focusing on the specific topic. In addition, this paper proposes a novel approach that will go beyond the state-of-the-art in efficiently recognizing time-critical high-level events, supporting commanders and first responders with meaningful and life-critical insights about the current and predicted state of the environment in which they operate.

Time-Series-Classification (TSC) is an important machine learning task for many branches of science. Symbolic representations of time series, especially Symbolic Fourier Approximation (SFA), have been proven very effective for this task, given their abilities to reduce noise. In this paper, we improve upon SCALE-BOSS using multiple symbolic representations of time series. More specifically, the proposed SCALE-BOSS-MR incorporates into the process a variety of window sizes combined with multiple dilation parameters applied to the original and to first-order differences’ time series, with the latter modeling trend information. SCALE-BOSS-MR has been evaluated using the eight datasets with the largest training size of the UCR time series repository. The results indicate that SCALE-BOSS-MR can be instantiated to classifiers that are able to achieve state-of-the-art accuracy and can be tuned for scalability.