Grzegorz J. Nalepa

Victor Rodriguez-Fernandez, David Montalvo, Francesco Piccialli et al.

The field of Deep Visual Analytics (DVA) has recently arisen from the idea of developing Visual Interactive Systems supported by deep learning, in order to provide them with large-scale data processing capabilities and to unify their implementation across different data and domains. In this paper we present DeepVATS, an open-source tool that brings the field of DVA into time series data. DeepVATS trains, in a self-supervised way, a masked time series autoencoder that reconstructs patches of a time series, and projects the knowledge contained in the embeddings of that model in an interactive plot, from which time series patterns and anomalies emerge and can be easily spotted. The tool includes a back-end for data processing pipeline and model training, as well as a front-end with a interactive user interface. We report on results that validate the utility of DeepVATS, running experiments on both synthetic and real datasets. The code is publicly available on https://github.com/vrodriguezf/deepvats

Sepideh Pashami, Slawomir Nowaczyk, Yuantao Fan et al.

Explainable Artificial Intelligence (XAI) fills the role of a critical interface fostering interactions between sophisticated intelligent systems and diverse individuals, including data scientists, domain experts, end-users, and more. It aids in deciphering the intricate internal mechanisms of ``black box'' Machine Learning (ML), rendering the reasons behind their decisions more understandable. However, current research in XAI primarily focuses on two aspects; ways to facilitate user trust, or to debug and refine the ML model. The majority of it falls short of recognising the diverse types of explanations needed in broader contexts, as different users and varied application areas necessitate solutions tailored to their specific needs. One such domain is Predictive Maintenance (PdM), an exploding area of research under the Industry 4.0 \& 5.0 umbrella. This position paper highlights the gap between existing XAI methodologies and the specific requirements for explanations within industrial applications, particularly the Predictive Maintenance field. Despite explainability's crucial role, this subject remains a relatively under-explored area, making this paper a pioneering attempt to bring relevant challenges to the research community's attention. We provide an overview of predictive maintenance tasks and accentuate the need and varying purposes for corresponding explanations. We then list and describe XAI techniques commonly employed in the literature, discussing their suitability for PdM tasks. Finally, to make the ideas and claims more concrete, we demonstrate XAI applied in four specific industrial use cases: commercial vehicles, metro trains, steel plants, and wind farms, spotlighting areas requiring further research.

Luiz do Valle Miranda, Krzysztof Kutt, Elżbieta Sroka et al.

The rich metadata created nowadays for objects stored in libraries has nowhere to be stored, because core standards, namely MARC 21 and Dublin Core, are not flexible enough. The aim of this paper is to summarize our work-in-progress on tackling this problem in research on cultural heritage objects at the Jagiellonian University (JU). We compared the objects' metadata currently being collected at the JU (with examples of manuscript, placard, and obituary) with five widespread metadata standards used by the cultural heritage community: Dublin Core, EAD, MODS, EDM and Digital Scriptorium. Our preliminary results showed that mapping between them is indeed problematic, but we identified requirements that should be followed in further work on the JU cultural heritage metadata schema in order to achieve maximum interoperability. As we move forward, based on the successive versions of the conceptual model, we will conduct experiments to validate the practical feasibility of these mappings and the degree to which the proposed model will actually enable integration with data in these various metadata formats.

Szymon Bobek, Grzegorz J. Nalepa

Explainable artificial intelligence (XAI) is one of the most intensively developed area of AI in recent years. It is also one of the most fragmented with multiple methods that focus on different aspects of explanations. This makes difficult to obtain the full spectrum of explanation at once in a compact and consistent way. To address this issue, we present Local Universal Explainer (LUX), which is a rule-based explainer that can generate factual, counterfactual and visual explanations. It is based on a modified version of decision tree algorithms that allows for oblique splits and integration with feature importance XAI methods such as SHAP. It limits the use data generation in opposite to other algorithms, but is focused on selecting local concepts in a form of high-density clusters of real data that have the highest impact on forming the decision boundary of the explained model and generating artificial samples with novel SHAP-guided sampling algorithm. We tested our method on real and synthetic datasets and compared it with state-of-the-art rule-based explainers such as LORE, EXPLAN and Anchor. Our method outperforms the existing approaches in terms of simplicity, fidelity, representativeness, and consistency.

Natalia Wojak-Strzelecka, Szymon Bobek, Grzegorz J. Nalepa et al.

Anomaly and failure detection methods are crucial in identifying deviations from normal system operational conditions, which allows for actions to be taken in advance, usually preventing more serious damages. Long-lasting deviations indicate failures, while sudden, isolated changes in the data indicate anomalies. However, in many practical applications, changes in the data do not always represent abnormal system states. Such changes may be recognized incorrectly as failures, while being a normal evolution of the system, e.g. referring to characteristics of starting the processing of a new product, i.e. realizing a domain shift. Therefore, distinguishing between failures and such ''healthy'' changes in data distribution is critical to ensure the practical robustness of the system. In this paper, we propose a method that not only detects changes in the data distribution and anomalies but also allows us to distinguish between failures and normal domain shifts inherent to a given process. The proposed method consists of a modified Page-Hinkley changepoint detector for identification of the domain shift and possible failures and supervised domain-adaptation-based algorithms for fast, online anomaly detection. These two are coupled with an explainable artificial intelligence (XAI) component that aims at helping the human operator to finally differentiate between domain shifts and failures. The method is illustrated by an experiment on a data stream from the steel factory.

Bartłomiej Małkus, Szymon Bobek, Grzegorz J. Nalepa

Small and Medium Enterprises (SMEs), particularly freelancers and early-stage businesses, face unique financial management challenges due to limited resources, small customer bases, and constrained data availability. This paper presents the development and deployment of an integrated financial prediction system that combines accounts receivable prediction and cash flow forecasting specifically designed for SME operational constraints. Our system addresses the gap between enterprise-focused financial tools and the practical needs of freelancers and small businesses. The solution integrates two key components: a binary classification model for predicting invoice payment delays, and a multi-module cash flow forecasting model that handles incomplete and limited historical data. A prototype system has been implemented and deployed as a web application with integration into Cluee's platform, a startup providing financial management tools for freelancers, demonstrating practical feasibility for real-world SME financial management.

Bartłomiej Małkus, Szymon Bobek, Grzegorz J. Nalepa

Time series data is one of the most popular data modalities in critical domains such as industry and medicine. The demand for algorithms that not only exhibit high accuracy but also offer interpretability is crucial in such fields, as decisions made there bear significant consequences. In this paper, we present ProtoTSNet, a novel approach to interpretable classification of multivariate time series data, through substantial enhancements to the ProtoPNet architecture. Our method is tailored to overcome the unique challenges of time series analysis, including capturing dynamic patterns and handling varying feature significance. Central to our innovation is a modified convolutional encoder utilizing group convolutions, pre-trainable as part of an autoencoder and designed to preserve and quantify feature importance. We evaluated our model on 30 multivariate time series datasets from the UEA archive, comparing our approach with existing explainable methods as well as non-explainable baselines. Through comprehensive evaluation and ablation studies, we demonstrate that our approach achieves the best performance among ante-hoc explainable methods while maintaining competitive performance with non-explainable and post-hoc explainable approaches, providing interpretable results accessible to domain experts.

Krzysztof Kutt, Luiz do Valle Miranda, Jakub Gomułka et al.

In response to several cultural heritage initiatives at the Jagiellonian University, we developed a new digitization workflow in collaboration with the Jagiellonian Library (JL). The solution is based on easy-to-access technological solutions -- Microsoft 365 cloud with MS Excel files as metadata acquisition interfaces, Office Script for validation, and MS Sharepoint for storage -- that allows metadata acquisition by domain experts regardless of their experience with information systems. The ultimate goal is to create a knowledge graph that describes the analyzed collections, linked to general knowledge bases, as well as to other cultural heritage collections, so careful attention is paid to the high accuracy of metadata and proper links to external sources. The workflow was evaluated in two pilot studies and in two workshops, which allowed for its refinement and confirmation of its correctness and usability for JL. The knowledge graph created as a result of these pilot studies was made available in a public git repository. As the proposed workflow does not interfere with existing systems or domain guidelines regarding digitization and basic metadata collection in a given institution, but extends them in order to enable rich metadata collection, not previously possible, we believe that it could be of interest to all GLAMs.

Karol Dobiczek, Maciej Mozolewski, Szymon Bobek et al.

Deep learning models for 12-lead electrocardiogram (ECG) analysis achieve high diagnostic performance but lack the intuitive interpretability required for clinical integration. Standard feature attribution methods are limited by the inherent difficulty in mapping abstract waveform fluctuations to physical anatomical pathologies. To resolve this, we propose a cross-modal method that projects feature attributions from high-performance 12-lead ECG models onto the CineECG 3D anatomical space. Our study reveals that while models trained directly on CineECG signals suffer from reduced accuracy and incoherent attributions, the proposed mapping mechanism effectively recovers clinically relevant feature rankings. Validated against a ground-truth dataset of 20 cases annotated by domain experts, the mapped explanations yield a Dice score of 0.56, significantly outperforming the 0.47 baseline of standard 12-lead attributions. These findings indicate that cross-modal averaging mapping effectively filters attribution instability and improves the localization of pathological features, combining the diagnostic expressiveness of standard ECG with the intuitive clarity of anatomical visualization.

Szymon Bobek, Paloma Korycińska, Monika Krakowska et al.

This paper introduces a dataset that is the result of a user study on the comprehensibility of explainable artificial intelligence (XAI) algorithms. The study participants were recruited from 149 candidates to form three groups representing experts in the domain of mycology (DE), students with a data science and visualization background (IT) and students from social sciences and humanities (SSH). The main part of the dataset contains 39 transcripts of interviews during which participants were asked to complete a series of tasks and questions related to the interpretation of explanations of decisions of a machine learning model trained to distinguish between edible and inedible mushrooms. The transcripts were complemented with additional data that includes visualizations of explanations presented to the user, results from thematic analysis, recommendations of improvements of explanations provided by the participants, and the initial survey results that allow to determine the domain knowledge of the participant and data analysis literacy. The transcripts were manually tagged to allow for automatic matching between the text and other data related to particular fragments. In the advent of the area of rapid development of XAI techniques, the need for a multidisciplinary qualitative evaluation of explainability is one of the emerging topics in the community. Our dataset allows not only to reproduce the study we conducted, but also to open a wide range of possibilities for the analysis of the material we gathered.

Maciej Mozolewski, Szymon Bobek, Grzegorz J. Nalepa

Explaining machine learning (ML) models for time series (TS) classification remains challenging due to the difficulty of interpreting raw time series and the high dimensionality of the input space. We introduce PHAR-Post-hoc Attribution Rules - a unified framework that transforms numeric feature attributions from post-hoc, instance-wise explainers (e.g., LIME, SHAP) into structured, human-readable rules. These rules define human-readable intervals that indicate where and when decision-relevant segments occur and can enhance model transparency by localizing threshold-based conditions on the raw series. PHAR performs comparably to native rule-based methods, such as Anchor, while scaling more efficiently to long TS sequences and achieving broader instance coverage. A dedicated rule fusion step consolidates rule sets using strategies like weighted selection and lasso-based refinement, balancing key quality metrics: coverage, confidence, and simplicity. This fusion ensures each instance receives a concise and unambiguous rule, improving both explanation fidelity and consistency. We further introduce visualization techniques to illustrate specificity-generalization trade-offs in the derived rules. PHAR resolves conflicting and overlapping explanations - a common effect of the Rashomon phenomenon - into coherent, domain-adaptable insights. Comprehensive experiments on UCR/UEA Time Series Classification Archive demonstrate that PHAR may improve interpretability, decision transparency, and practical applicability for TS classification tasks by providing concise, human-readable rules aligned with model predictions.

Jan Ignatowicz, Krzysztof Kutt, Grzegorz J. Nalepa

Digitizing cultural heritage collections has become crucial for preservation of historical artifacts and enhancing their availability to the wider public. Galleries, libraries, archives and museums (GLAM institutions) are actively digitizing their holdings and creates extensive digital collections. Those collections are often enriched with metadata describing items but not exactly their contents. The Jagiellonian Digital Library, standing as a good example of such an effort, offers datasets accessible through protocols like OAI-PMH. Despite these improvements, metadata completeness and standardization continue to pose substantial obstacles, limiting the searchability and potential connections between collections. To deal with these challenges, we explore an integrated methodology of computer vision (CV), artificial intelligence (AI), and semantic web technologies to enrich metadata and construct knowledge graphs for digitized manuscripts and incunabula.

Szymon Bobek, Paloma Korycińska, Monika Krakowska et al.

This study is located in the Human-Centered Artificial Intelligence (HCAI) and focuses on the results of a user-centered assessment of commonly used eXplainable Artificial Intelligence (XAI) algorithms, specifically investigating how humans understand and interact with the explanations provided by these algorithms. To achieve this, we employed a multi-disciplinary approach that included state-of-the-art research methods from social sciences to measure the comprehensibility of explanations generated by a state-of-the-art lachine learning model, specifically the Gradient Boosting Classifier (XGBClassifier). We conducted an extensive empirical user study involving interviews with 39 participants from three different groups, each with varying expertise in data science, data visualization, and domain-specific knowledge related to the dataset used for training the machine learning model. Participants were asked a series of questions to assess their understanding of the model's explanations. To ensure replicability, we built the model using a publicly available dataset from the UC Irvine Machine Learning Repository, focusing on edible and non-edible mushrooms. Our findings reveal limitations in existing XAI methods and confirm the need for new design principles and evaluation techniques that address the specific information needs and user perspectives of different classes of AI stakeholders. We believe that the results of our research and the cross-disciplinary methodology we developed can be successfully adapted to various data types and user profiles, thus promoting dialogue and address opportunities in HCAI research. To support this, we are making the data resulting from our study publicly available.

Szymon Bobek, Łukasz Bałec, Grzegorz J. Nalepa

Counterfactual explanations enhance the actionable interpretability of machine learning models by identifying the minimal changes required to achieve a desired outcome of the model. However, existing methods often ignore the complex dependencies in real-world datasets, leading to unrealistic or impractical modifications. Motivated by cybersecurity applications in the email marketing domain, we propose a method for generating Diverse, Actionable, and kNowledge-Constrained Explanations (DANCE), which incorporates feature dependencies and causal constraints to ensure plausibility and real-world feasibility of counterfactuals. Our method learns linear and nonlinear constraints from data or integrates expert-provided dependency graphs, ensuring counterfactuals are plausible and actionable. By maintaining consistency with feature relationships, the method produces explanations that align with real-world constraints. Additionally, it balances plausibility, diversity, and sparsity, effectively addressing key limitations in existing algorithms. The work is developed based on a real-life case study with Freshmail, the largest email marketing company in Poland and supported by a joint R&D project Sendguard. Furthermore, we provide an extensive evaluation using 140 public datasets, which highlights its ability to generate meaningful, domain-relevant counterfactuals that outperform other existing approaches based on widely used metrics. The source code for reproduction of the results can be found in a GitHub repository we provide.

Maciej Mozolewski, Betül Bayrak, Kerstin Bach et al.

In eXplainable Artificial Intelligence (XAI), instance-based explanations for time series have gained increasing attention due to their potential for actionable and interpretable insights in domains such as healthcare. Addressing the challenges of explainability of state-of-the-art models, we propose a prototype-driven framework for generating sparse counterfactual explanations tailored to 12-lead ECG classification models. Our method employs SHAP-based thresholds to identify critical signal segments and convert them into interval rules, uses Dynamic Time Warping (DTW) and medoid clustering to extract representative prototypes, and aligns these prototypes to query R-peaks for coherence with the sample being explained. The framework generates counterfactuals that modify only 78% of the original signal while maintaining 81.3% validity across all classes and achieving 43% improvement in temporal stability. We evaluate three variants of our approach, Original, Sparse, and Aligned Sparse, with class-specific performance ranging from 98.9% validity for myocardial infarction (MI) to challenges with hypertrophy (HYP) detection (13.2%). This approach supports near realtime generation (< 1 second) of clinically valid counterfactuals and provides a foundation for interactive explanation platforms. Our findings establish design principles for physiologically-aware counterfactual explanations in AI-based diagnosis systems and outline pathways toward user-controlled explanation interfaces for clinical deployment.

Klaudia Ropel, Krzysztof Kutt, Luiz do Valle Miranda et al.

We developed a proof-of-concept method for the automatic analysis of the structure and content of incunabula pages. A custom dataset comprising 500 annotated pages from five different incunabula was created using resources from the Jagiellonian Digital Library. Each page was manually labeled with five predefined classes: Text, Title, Picture, Table, and Handwriting. Additionally, the publicly available DocLayNet dataset was utilized as supplementary training data. To perform object detection, YOLO11n and YOLO11s models were employed and trained using two strategies: a combined dataset (DocLayNet and the custom dataset) and the custom dataset alone. The highest performance (F1 = 0.94) was achieved by the YOLO11n model trained exclusively on the custom data. Optical character recognition was then conducted on regions classified as Text, using both Tesseract and Kraken OCR, with Tesseract demonstrating superior results. Subsequently, image classification was applied to the Picture class using a ResNet18 model, achieving an accuracy of 98.7% across five subclasses: Decorative_letter, Illustration, Other, Stamp, and Wrong_detection. Furthermore, the CLIP model was utilized to generate semantic descriptions of illustrations. The results confirm the potential of machine learning in the analysis of early printed books, while emphasizing the need for further advancements in OCR performance and visual content interpretation.

Jan Ignatowicz, Krzysztof Kutt, Grzegorz J. Nalepa

The digitization of cultural heritage collections has opened new directions for research, yet the lack of enriched metadata poses a substantial challenge to accessibility, interoperability, and cross-institutional collaboration. In several past years neural networks models such as YOLOv11 and Detectron2 have revolutionized visual data analysis, but their application to domain-specific cultural artifacts - such as manuscripts and incunabula - remains limited by the absence of methodologies that address structural feature extraction and semantic interoperability. In this position paper, we argue, that the integration of neural networks with semantic technologies represents a paradigm shift in cultural heritage digitization processes. We present the Metadata Enrichment Model (MEM), a conceptual framework designed to enrich metadata for digitized collections by combining fine-tuned computer vision models, large language models (LLMs) and structured knowledge graphs. The Multilayer Vision Mechanism (MVM) appears as the key innovation of MEM. This iterative process improves visual analysis by dynamically detecting nested features, such as text within seals or images within stamps. To expose MEM's potential, we apply it to a dataset of digitized incunabula from the Jagiellonian Digital Library and release a manually annotated dataset of 105 manuscript pages. We examine the practical challenges of MEM's usage in real-world GLAM institutions, including the need for domain-specific fine-tuning, the adjustment of enriched metadata with Linked Data standards and computational costs. We present MEM as a flexible and extensible methodology. This paper contributes to the discussion on how artificial intelligence and semantic web technologies can advance cultural heritage research, and also use these technologies in practice.

Jan Ignatowicz, Krzysztof Kutt, Grzegorz J. Nalepa

Experiments in affective computing are based on stimulus datasets that, in the process of standardization, receive metadata describing which emotions each stimulus evokes. In this paper, we explore an approach to creating stimulus datasets for affective computing using generative adversarial networks (GANs). Traditional dataset preparation methods are costly and time consuming, prompting our investigation of alternatives. We conducted experiments with various GAN architectures, including Deep Convolutional GAN, Conditional GAN, Auxiliary Classifier GAN, Progressive Augmentation GAN, and Wasserstein GAN, alongside data augmentation and transfer learning techniques. Our findings highlight promising advances in the generation of emotionally evocative synthetic images, suggesting significant potential for future research and improvements in this domain.

Szymon Bobek, Michał Kuk, Jakub Brzegowski et al.

Pattern discovery in multidimensional data sets has been the subject of research for decades. There exists a wide spectrum of clustering algorithms that can be used for this purpose. However, their practical applications share a common post-clustering phase, which concerns expert-based interpretation and analysis of the obtained results. We argue that this can be the bottleneck in the process, especially in cases where domain knowledge exists prior to clustering. Such a situation requires not only a proper analysis of automatically discovered clusters but also conformance checking with existing knowledge. In this work, we present Knowledge Augmented Clustering (KnAC). Its main goal is to confront expert-based labelling with automated clustering for the sake of updating and refining the former. Our solution is not restricted to any existing clustering algorithm. Instead, KnAC can serve as an augmentation of an arbitrary clustering algorithm, making the approach robust and a model-agnostic improvement of any state-of-the-art clustering method. We demonstrate the feasibility of our method on artificially, reproducible examples and in a real life use case scenario. In both cases, we achieved better results than classic clustering algorithms without augmentation.

Sławomir Konrad Tadeja, Krzysztof Kutt, Yupu Lu et al.

In this paper, we present a Virtual Reality (VR) based environment where the engineer interacts with incoming data from a fleet of aeroengines. This data takes the form of 3D computer-aided design (CAD) engine models coupled with characteristic plots for the subsystems of each engine. Both the plots and models can be interacted with and manipulated using speech or gestural input. The characteristic data is ported to a knowledge-based system underpinned by a knowledge-graph storing complex domain knowledge. This permits the system to respond to queries about the current state and health of each aeroengine asset. Responses to these questions require some degree of analysis, which is handled by a semantic knowledge representation layer managing information on aeroengine subsystems. This paper represents a significant step forward for aeroengine analysis in a bespoke VR environment and brings us a step closer to a Jarvis-like system for aeroengine analytics.

Krzysztof Kutt, Dominika Drążyk, Maciej Szelążek et al.

The paper describes BIRAFFE2 data set, which is a result of an affective computing experiment conducted between 2019 and 2020, that aimed to develop computer models for classification and recognition of emotion. Such work is important to develop new methods of natural Human-AI interaction. As we believe that models of emotion should be personalized by design, we present an unified paradigm allowing to capture emotional responses of different persons, taking individual personality differences into account. We combine classical psychological paradigms of emotional response collection with the newer approach, based on the observation of the computer game player. By capturing ones psycho-physiological reactions (ECG, EDA signal recording), mimic expressions (facial emotion recognition), subjective valence-arousal balance ratings (widget ratings) and gameplay progression (accelerometer and screencast recording), we provide a framework that can be easily used and developed for the purpose of the machine learning methods.

Mateusz Ślażyński, Salvador Abreu, Grzegorz J. Nalepa

Local Search meta-heuristics have been proven a viable approach to solve difficult optimization problems. Their performance depends strongly on the search space landscape, as defined by a cost function and the selected neighborhood operators. In this paper we present a logic programming based framework, named Noodle, designed to generate bespoke Local Search neighborhoods tailored to specific discrete optimization problems. The proposed system consists of a domain specific language, which is inspired by logic programming, as well as a genetic programming solver, based on the grammar evolution algorithm. We complement the description with a preliminary experimental evaluation, where we synthesize efficient neighborhood operators for the traveling salesman problem, some of which reproduce well-known results.

Barbara Giżycka, Grzegorz J. Nalepa, Paweł Jemioło

As technologies become more and more pervasive, there is a need for considering the affective dimension of interaction with computer systems to make them more human-like. Current demands for this matter include accurate emotion recognition, reliable emotion modeling, and use of unobtrusive, easily accessible and preferably wearable measurement devices. While AI methods provide many possibilities for better affective information processing, it is not a common scenario for both emotion recognition and modeling to be integrated in the design phase. To address this concern, we propose a new approach based on affective design patterns in the context of video games, together with summary of experiments conducted to test the preliminary hypotheses.