This paper presents a visual analytics workflow for detecting stable cross-impact patterns in time series pairs. A sliding window technique computes multiple impact measures, including a novel Kendall's tau variant that tolerates minor fluctuations. Evaluating these measures across various time lags reveals dynamic relationships between time series. An interactive Ikat plot facilitates the exploration of impact distributions, helping identify intervals where specific cross-impacts remain stable (e.g., trends in one series followed by similar or opposite trends in another after a lag). These intervals are extracted as events, whose temporal (and, when applicable, spatial) distributions can be analyzed to uncover broader patterns across multiple time series pairs and over extended time spans. This includes identifying co-occurring cross-impacts and variations in cross-impact presence or type across different periods and data subsets. Experiments on real-world datasets demonstrate the framework's ability to isolate robust patterns, providing a scalable and interpretable approach to analyzing complex temporal dynamics.

Rule-based machine learning models, including those derived from decision trees or forests, are often considered inherently interpretable. However, human understanding is hindered by model size, rule complexity, and interdependencies between features. Moreover, rule sets extracted from ensemble models can contain contradictory, incomplete, or counterintuitive logic, even when the overall model achieves high predictive accuracy. This paper introduces a visual analytics methodology designed to support systematic exploration of rule-based model logic and its alignment with domain knowledge. Our approach integrates overview visualizations, interactive filtering, contradiction analysis, and topic modeling. This enables analysts to detect illogical or implausible rules, assess their potential impact, and refine the model to improve its interpretability and trustworthiness. A key distinction of our method is its ability to support reasoning about model behavior both with and without access to labeled data. We demonstrate the approach through two real-world case studies: evaluating logical consistency in a vessel movement classifier and analyzing feature relationships in a COVID-19 prediction model. These studies show how visual analytics can facilitate logic-focused model critique beyond traditional performance metrics and enable valuable domain-relevant insights.

Abstract This paper presents a methodology for integrating human expert knowledge into machine learning (ML) workflows to improve both model interpretability and the quality of explanations produced by explainable AI (XAI) techniques. We strive to enhance standard ML and XAI pipelines without modifying underlying algorithms, focusing instead on embedding domain knowledge at two stages: (1) during model development through expert-guided data structuring and feature engineering, and (2) during explanation generation via domain-aware synthetic neighbourhoods. Visual analytics is used to support experts in transforming raw data into semantically richer representations. We validate the methodology in two case studies: predicting COVID-19 incidence and classifying vessel movement patterns. The studies demonstrated improved alignment of models with expert reasoning and better quality of synthetic neighbourhoods. We also explore using large language models (LLMs) to assist experts in developing domain-compliant data generators. Our findings highlight both the benefits and limitations of existing XAI methods and point to a research direction for addressing these gaps.

Wearable sensors are becoming a popular method of objectively evaluating motor performance in various exercise tasks. A challenge in working with this motion capture data is the personalised nature of the data where one individual’s data may be different to that of others due to factors such as differences in exercise form. Hence global models generally perform poorly in this domain. The aim of this study is to investigate a technique to push personalised classification models into global models. In this research, a dataset of Inertial Measurement Unit data consisting of fatigued and non-fatigued running is used to employ a clustering strategy where participants are grouped together using a hierarchical clustering methodology. These clusters are used to form semi-globalised models. The investigation shows that this strategy can improve the global model performance by up to 20%.