Wearable neurotechnology and multimodal biosignal research take center stage at MoBI 2026
The 6th International Mobile Brain/Body Imaging Conference (MoBI 2026) takes place August 25 to 28, 2026, at Technische Universität Berlin, hosted by TU Berlin's Biopsychology and Neuroergonomics research group. At the conference, BIFOLD's Intelligent Biomedical Sensing (IBS) Lab presents five posters on wearable neurotechnology, multimodal brain and body monitoring, and machine learning for biosignal analysis.
MoBI 2026 brings together researchers from neuroscience, psychology, engineering, movement science, and the humanities to discuss simultaneous measurement and analysis of brain activity, such as mobile EEG, and body movement in real, active situations.
The IBS Lab is a research group at BIFOLD and the Machine Learning group at TU Berlin, led by Dr.-Ing. Alexander von Lühmann. The lab develops miniaturized wearable neurotechnology and sensors for everyday use, captures and analyzes multimodal biosignals such as fNIRS, EEG, DOT, ECG, and EMG, and applies machine learning to extract biomarkers from these signals for early health assessment.
Beyond the five posters, a hands-on community workshop was held before the conference. It introduced about 140 researchers, neuroscientists, engineers, data scientists, and physicians to Cedalion, a Python-based toolbox for multimodal fNIRS and DOT analysis. Workshop topics ranged from core data structures and preprocessing to quality assessment, motion correction, and pipeline building. Moreover, a special session on “Advances in Mobile and Multimodal fNIRS-based Brain-Imaging” is held during the conference where IBS research group member Tomas Codina gives a talk on “Multimodal DOT–EEG Mapping of Single-Finger Sensorimotor Responses.” Additionally, Alexander von Lühmann moderates the panel discussion Future of fNIRS-EEG in MoBI and serves as Conference Co-Chair of MoBI 2026 with Anna Wunderlich. Klaus Gramann serves as Main Chair.
BIFOLD is pleased to contribute to MoBI 2026 through its research and role in organizing the conference. Below is an overview of the IBS Lab's contributions:
Cedalion tutorial: a Python-based framework for comprehensive analysis of multimodal fNIRS and DOT from the lab to the everyday world.
- Authors: Eike Middell, Laura B. Carlton, Shakiba Moradi, Tomás Codina, Thomas Fischer, Josef Cutler, Shannon M. Kelley, Jacqueline Behrendt, Theekshana Dissanayake, Nils Harmening, Meryem A. Yücel, David A. Boas, Alexander von Lühmann.
- DOI: https://doi.org/10.1117/1.NPh.13.S3.S32602Project Page: http://www.cedalion.tools/
- Presented by Eike Middell.
- Additional Material: Interview with Alexander von Lühmann on Cedalion: https://www.bifold.berlin/news-events/news/view/news-detail/cedalion
- TLDR: A paper presenting the latest version of Cedalion, our toolbox for multimodal fNIRS / DOT analysis in the everyday world.
Fully integrated colocalized optodes for whole-head high density diffuse optical tomography and water based electroencephalography.
- Authors: Bilal Siddique, Alexander von Lühmann.
- Presented by Bilal Siddique.
- TLDR: A paper on fully integrated water-based active EEG-fNIRS opto-electrodes that allow simultaneous acquisition of both modalities even in a high-density setting at fast setup time, with no gel residue and without compromise in signal quality.
Head model individualization in electrical and optical brain imaging without MRI.
- Authors: Nils Harmening, Benjamin Blankertz, David Boas, Alexander von Lühmann.
- Presented by Nils Harmening.
- TLDR: A paper on data-driven individualized headmodels for EEG/ MEG and fNIRS without an MRI scan using photogrammetry, and how they compare against individual anatomies and standard atlases.
Deep Learning from Sparse fNIRS Data to Augment High-Density Datasets Improves Decoding Performance.
- Authors: Mohammad Orabe, Theekshana Dissanayake, Shakiba Moradi, Alexander von Lühmann.
- Poster: https://orabe.github.io/assets/papers/IBS_BIFOLD_MoBI_mohammad_24-08-2026.pdf
- Presented by Mohammad Orabe.
- TLDR: A paper on data augmentation strategies for deep learning on fNIRS data to improve generalizability.
Cross-Modality Augmentation of fNIRS Signals Using fMRI for Transfer Learning.
- Authors: Shakiba Moradi, Theekshana Dissanayake, Nils Harmening, Eike Middell, Alexander von Lühmann.
- Presented by Shakiba Moradi.
- TLDR: A paper on transfer learning with deep learning from large fMRI data to DOT data to leverage large datasets for a domain where this data does not yet exist, and thus also helping to transfer insights from fMRI to the brain measured with DOT in the everyday world.