Recent advancements in XAI have radically changed the way that AI systems are evaluated, as transparency and trustworthiness are now valued as highly as performance. This is especially true in medical applications, as, in order for such tools to be used in practical applications, interpretability is a key requirement for clinical adoption. Electroencephalography (EEG) analysis, in particular, has seen a significant rise in research, as the difficult and complex nature of EEG signals benefits from these methods, enabling researchers and practitioners to gain new insights from the vast amount of data that is now available. This survey presents a comprehensive analysis of the latest trends and advancements in XAI for EEG analysis. First, we provide a brief overview of fundamental EEG tasks, available datasets, and AI model approaches used for analysis. Then, we classify XAI methods using well-established taxonomies in XAI research, such as locality and generalization of explanations. By exploring all relevant XAI techniques in EEG analysis, our study offers researchers a clear perspective on the current state of the field and identifies potential research gaps. Our review indicates that current XAI approaches for EEG often face limitations in robustness, consistency, and neuroscientific grounding. These findings highlight the need for more reliable and domain-informed explainability methods to support trustworthy EEG analysis in research and clinical practice.
In the era of music streaming platforms and recommendation systems, the automatic music auto-tagging task has gained a lot of traction and has motivated researchers to develop methods for solving the task focusing on improving performance metrics on baseline datasets. The majority of recent approaches rely on deep neural networks, which despite their impressive performance, are opaque, meaning it is difficult to explain their output on a given input. While the problem of interpretability has been highlighted in other domains, such as medicine, it has not been a priority for music-related tasks. In this work, we explored the usefulness of interpretability for music auto-tagging. We developed a pipeline incorporating three types of information extraction procedures: a) symbolic knowledge, b) auxiliary deep neural networks, and c) signal processing, to extract perceptual features of audio files, which were then used to train an explainable machine learning model to predict tags. We experimented on three datasets the MTG-Jamendo dataset, the GTZAN dataset, and the MagnaTagATune dataset. Our method outperforms baseline models in all tasks and in some cases is competitive with the state-of-the-art. We conducted a human survey to evaluate user trust in our methodology and in a state-of-the-art model, concluding that while the state-of-the-art model offers better performance, there are use cases where the slight deterioration in accuracy is outweighed by the increased trust and value provided by interpretability.
Four machine learning models (Decision Tree Regressor, Linear Regression, XGBoost Regression, K-Neighbors Regressor) were developed to predict the outcomes of a composting process based on key input parameters, including Ambient Temperature, mixture composition, and initial feedstock volume. The models were trained on data from 88 composting batches, monitoring temperature evolution, and compost yield. Performance evaluation demonstrated high accuracy in predicting compost maturity, process duration, and final product quantity. These predictive models could optimize composting operations by enabling real-time adjustments, improving efficiency, and enhancing resource management in sustainable waste processing.
Households are the major contributor to food waste generation in the European Union according to the recently published data from Eurostat. Promoting food systems sustainability and aspiring to achieve the United Nations SDG 12.3 requires a better insight to the underlying drivers of the household food waste occurrence. The present study presents the combination of a well-established method of acquiring information, the questionnaire surveys, with a state-of-the-art technology for data imputation and interpretation using machine learning (ML). The Food Loss and Waste Prevention Unit (FLWPU) of the municipality of Halandri employed two surveys within the framework of the European funded projects Food Connections and FOODRUS. The first questionnaire was designed for rapid completion, to maximize response rates and minimize respondent burden, ensuring the collection of a consistent core dataset. A total of 154 replies were collected. The second questionnaire, associated with FOODRUS, was more detailed, enabling the participants to provide more in-depth information on their household food waste (HHFW) practices. In total, 43 responses were collected. ML algorithms were applied for data enhancement and data clustering. Specifically, ML and statistical techniques are applied for data imputations. An XGBoost algorithm was trained so as to capture complex relationships between variables. Behavioral intentions and effective strategies for reducing food waste at the community level are identified from the responses of both questionnaires, while a clustering of respondents in five groups emerged by using k-means, thus providing valuable insight into targeted HHFW prevention action plans.
This paper describes the methodology followed and the lessons learned from employing crowdsourcing techniques as part of a homework assignment involving higher education students of computer science. Making use of a platform that supports crowdsourcing in the cultural heritage domain students were solicited to enrich the metadata associated with a selection of music tracks. The results of the campaign were further analyzed and exploited by students through the use of semantic web technologies. In total, 98 students participated in the campaign, contributing more than 6400 annotations concerning 854 tracks. The process also led to the creation of an openly available annotated dataset, which can be useful for machine learning models for music tagging. The campaign's results and the comments gathered through an online survey enable us to draw some useful insights about the benefits and challenges of integrating crowdsourcing into computer science curricula and how this can enhance students' engagement in the learning process.