Lara Défayes
EPFL EPFL+ECAL Lab
ECAL 1 20.07 (Bâtiment ECAL)
Av. du 24-Janvier 11
1020 Renens VD 1
Office: ECAL 1 20.02
EPFL › VPA › VPA-AVP-CP › EPFL-ECAL-L › EPFL-ECAL-GE
Website: https://www.epfl-ecal-lab.ch/
Designing Feedback Stimuli in Neurofeedback: Preliminary Requirements from Experts and Users
This study presents the first phase of a transdisciplinary research project aimed at improving the design of visual feedback stimuli in neurofeedback (NFB) applications. While current NFB research has focused extensively on signal processing and feature extraction, limited attention has been given to the design and user experience of feedback stimuli. To address this gap, the research team conducted generative user research including site visits, expert consultations, and semistructured interviews with domain experts and previous NFB participants. Analysis of the collected data yielded a preliminary set of design requirements. User-centered requirements include minimizing cognitive load, enhancing attention and engagement, incorporating positive reinforcement, supporting a sense of agency, and providing clear instructions. Technical requirements include reducing artifacts, ensuring low-latency feedback, and promoting participant relaxation. These findings lay the groundwork for iterative design and evaluation phases, with the ultimate goal of delivering validated stimuli and design guidelines to the NFB research and clinical communities.
2025. 2025 IEEE 38th International Symposium on Computer-Based Medical Systems (CBMS), Madrid, Spain, 2025-06-18 - 2025-06-20. p. 941 - 944. DOI : 10.1109/CBMS65348.2025.00188.Advances on Real Time M/EEG Neural Feature Extraction
This paper introduces MNE-RT, a Python package designed for real-time neural feature extraction from magne-toencephalography (MEG) and electroencephalography (EEG) signals in Brain-Computer Interface (BCI) systems. The package incorporates efficient algorithms spanning traditional univariate metrics, such as frequency band power and entropy, to advanced bivariate connectivity measures. It is compatible with various recording systems, enabling the extraction of neural targets from brain signals in real time, with potential applications in enhancing neurofeedback efficacy.
2025. 2025 IEEE 38th International Symposium on Computer-Based Medical Systems (CBMS), Madrid, Spain, 2025-06-18 - 2025-06-20. p. 337 - 338. DOI : 10.1109/CBMS65348.2025.00074.ANT - Advancing Neurofeedback (In Tinnitus)
The Advancing Neurofeedback in Tinnitus (ANT) project aims to develop improved neurofeedback protocols and BCI technology by systematically designing engaging feedback stimuli and optimizing neural targets. General design principles for audiovisual feedback stimuli are established, system and software engineering for general purpose real-time M/EEG is developed, and ultimately integrated for the clinical use case tinnitus. This interdisciplinary effort combines expertise in clinical neuroscience, design, user experience research, psychology, and biomedical signal processing to create a novel neurofeedback approach with potential for both clinical and home-based applications.
2025. 2025 IEEE 38th International Symposium on Computer-Based Medical Systems (CBMS), Madrid, Spain, 2025-06-18 - 2025-06-20. p. 744 - 746. DOI : 10.1109/cbms65348.2025.00154.Toward Automatic Typography Analysis: Serif Classification and Font Similarities
Whether a document is of historical or contemporary significance, typography plays a crucial role in its composition. From the early days of modern printing, typographic techniques have evolved and transformed, resulting in changes to the features of typography. By analyzing these features, we can gain insights into specific time periods, geographical locations, and messages conveyed through typography. Therefore, in this paper, we aim to investigate the feasibility of training a model to classify serif typeswithout knowledge of the font and character. We also investigate how to train a vectorial-based image model able to group together fonts with similar features. Specifically, we compare the use of state-of-theart image classification methods, such as the EfficientNet-B2 and the Vision Transformer Base model with different patch sizes, and the state-of-the-art fine-grained image classification method, TransFG, on the serif classification task. We also evaluate the use of the DeepSVG model to learn to group fonts with similar features. Our investigation reveals that fine-grained image classification methods are better suited for the serif classification tasks and that leveraging the character labels helps to learn more meaningful font similarities.
Journal of Data Mining & Digital Humanities. 2024. DOI : 10.46298/jdmdh.10230.Poster World. Bespoke AI Meets Curator Expertise for Public Engagement
Though museums are digitising their archives, online consultations remain low. New forms of engagement bring these digital memories to life and can support museums in maintaining and developing digital resources. Artificial Intelligence presents opportunities to showcase this rich heritage, but it also raises issues of transparency and cultural relevance. We explored these questions through a collaboration with Zürich’s Museum für Gestaltüng on its unique poster collection. We looked at how calculating similarities between digitised documents could create new user experiences with emotional and cognitive impact. Throughout the project, designers worked with engineers to investigate bespoke algorithms and graphic representations of their outputs. After an initial state of the art and preliminary tests, we developed three scenarios for a museum installation. Investigating three hypotheses, we evaluated the prototype scenarios with user experience psychology protocols. Our results show the value of combining artificial intelligence with curator expertise, the impact of similarities extracted by mathematical modelling and the importance of how they are visualised. We also found no significant difference between the perception of novices and experts in our results. This fosters a strategy for museums which brings different audiences together. The final installation, which combines elements from all three scenarios, opened to the public at the Museum in February 2022.
Pages on Art and Design. 2022.Design standards for icons: The independent role of aesthetics, visual complexity and concreteness in icon design and icon understanding
Icons play an important role in modern interfaces and therefore recent empirical research has focused on enhancing icon processing — that is, icon perception and icon function understanding. However, in existing sets, icons vary simultaneously across different icon characteristics, confusing the contribution of each to icon processing. We developed icon design principles for aesthetics, complexity, and concreteness, and used them to create 64 icons that varied independently along each characteristic. Participants reported the icon function and rated each icon in terms of aesthetics, complexity and concreteness. The manipulated characteristics had independent effects on icon processing, with two exceptions, for which we propose evidence-based solutions. Based on these findings we propose guidelines for designing icons for research purposes.
Displays. 2022. DOI : 10.1016/j.displa.2022.102290.Automatic Content Curation of Visual Heritage
Digitization and preservation of large heritage induce high maintenance costs to keep up with the technical standards and ensure sustainable access. Creating impactful usage is instrumental to justify the resources for long-term preservation. The Museum für Gestaltung of Zurich holds one of the biggest poster collections of the world from which 52’000 were digitised. In the process of building a digital installation to valorize the collection, one objective was to develop an algorithm capable of predicting the next poster to show according to the ones already displayed. The work presented here describes the steps to build an algorithm able to automatically create sequences of posters reflecting associations performed by curator and professional designers. The exposed challenge finds similarities with the domain of song playlist algorithms. Recently, artificial intelligence techniques and more specifically, deep-learning algorithms have been used to facilitate their generations. Promising results were found thanks to Recurrent Neural Networks (RNN) trained on manually generated playlist and paired with clusters of extracted features from songs. We used the same principles to create the proposed algorithm but applied to a challenging medium, posters. First, a convolutional autoencoder was trained to extract features of the posters. The 52’000 digital posters were used as a training set. Poster features were then clustered. Next, an RNN learned to predict the next cluster according to the previous ones. RNN training set was composed of poster sequences extracted from a collection of books from the Gestaltung Museum of Zurich dedicated to displaying posters. Finally, within the predicted cluster, the poster with the best proximity compared to the previous poster is selected. The mean square distance between features of posters was used to compute the proximity. To validate the predictive model, we compared sequences of 15 posters produced by our model to randomly and manually generated sequences. Manual sequences were created by a professional graphic designer. We asked 21 participants working as professional graphic designers to sort the sequences from the one with the strongest graphic line to the one with the weakest and to motivate their answer with a short description. The sequences produced by the designer were ranked first 60%, second 25% and third 15% of the time. The sequences produced by our predictive model were ranked first 25%, second 45% and third 30% of the time. The sequences produced randomly were ranked first 15%, second 29%, and third 55% of the time. Compared to designer sequences, and as reported by participants, model and random sequences lacked thematic continuity. According to the results, the proposed model is able to generate better poster sequencing compared to random sampling. Eventually, our algorithm is sometimes able to outperform a professional designer. As a next step, the proposed algorithm should include a possibility to create sequences according to a selected theme. To conclude, this work shows the potentiality of artificial intelligence techniques to learn from existing content and provide a tool to curate large sets of data, with a permanent renewal of the presented content.
2021. ICDH 2021 : International Conference on Digital Heritage, London, United Kingdom, November 18-19, 2021.Ming Shan Digital Experience
The Ming Shan Digital Experience is an immersive installation designed to support meditation in the context of a new Taoist center. Its creation confronted current academic literature on digital technology for meditation with the practical and cultural requirements of Taoist practice. Quantitative and qualitative learnings show the effectiveness of multimodal biofeedback on individual and collective meditative experience. Now instated in the Taoist center, the installation opens new perspectives for combining digital technology with ancient practice.
2021. SIGGRAPH '21, Virtual, August 9-13, 2021. p. 1 - 10. DOI : 10.1145/3465620.Trust Indicators and Explainable AI: A Study on User Perceptions
Nowadays, search engines, social media or news aggregators are the preferred services for news access. Aggregation is mostly based on artificial intelligence technologies raising a new challenge: Trust has been ranked as the most important factor for media business. This paper reports findings of a study evaluating the influence of manipulations of interface design and information provided in the context of eXplainable Artificial Intelligence (XAI) on user perception and in the context of news content aggregators. In an experimental online study, various layouts and scenarios have been developed, implemented and tested with 266 participants. Measures of trust, understanding and preference were recorded. Results showed no influence of the factors on trust. However, data indicates that the influence of the layout, for example implicit integration of media source through layout structuration has a significant effect on perceived importance to cite the source of a media. Moreover, the amount of information presented to explain the AI showed a negative influence on user understanding. This highlights the importance and difficulty of making XAI understandable for its users.
2021. 18th IFIP TC 13 International Conference, Bari, Italy, 30 August - 3 September, 2021. p. 662 - 671. DOI : 10.1007/978-3-030-85616-8_39.Designing for visual appeal, simplicity and concreteness: the development and evaluation of design standards to manipulate icon characteristics
Good icon design is now recognized as crucial in determining user experience with mobile, PC and other applications. However, research examining icon use and processing is based on the use of existing icon sets. This leaves many questions about how new icons can be created with specific characteristics. Based on extensive design research, specific design principles were established. In an experimentally controlled study, a set of 64 icons was then developed by designers applying these design principles to create 8 versions for 8 new icon-functions, differing with regard to visual appeal (appealing vs. unappealing), simplicity (complex vs. simple) and concreteness (concrete vs. abstract icons). Once created, participants (N = 276) were asked to rate visual appeal, simplicity and concreteness of 8 icons (from the 64 versions created) in order to ascertain the extent to which the design principles were effective in creating icon sets with different characteristics. Results demonstrated that an independent manipulation of each design dimension was successful, indicating that the suggested design principles provide valuable hints for the design of icons. These findings will be used to illustrate how experimental design can shed light on building guidelines for creating effective interaction designs.
Human Factors and Ergonomics Society Annual Meeting 2017: Varieties of interaction, from User Experience to Neuroergonomics, Rome, Italy, Septembre 30, 2017.