DSI-24

@article{gupta2025extracting,

title = {Extracting Robust Single-Trial Somatosensory Evoked Potentials for Non-Invasive Brain Computer Interfaces},

author = {Disha Gupta and Jodi Ann Brangaccio and Helia Mojtabavi and Jonathan R Wolpaw and NJ Hill},

doi = {10.1088/1741-2552/adfd8a},

year  = {2025},

date = {2025-09-03},

urldate = {2025-01-01},

journal = {Journal of Neural Engineering},

abstract = {Objective. Reliable extraction of single-trial somatosensory evoked potentials (SEPs) is essential for developing brain-computer interface (BCI) applications to support rehabilitation after brain injury. For real-time feedback, these responses must be extracted prospectively on every trial, with minimal post-processing and artifact correction. However, noninvasive SEPs elicited by electrical stimulation at recommended parameter settings (0.1–0.2 msec pulse width, stimulation at or below motor threshold, 2–5 Hz frequency) are typically small and variable, often requiring averaging across multiple trials or extensive processing. Here, we describe and evaluate ways to optimize the stimulation setup to enhance the signal-to-noise ratio (SNR) of noninvasive single-trial SEPs, enabling more reliable extraction. Approach. SEPs were recorded with scalp electroencephalography in tibial nerve stimulation in thirteen healthy people, and two people with CNS injuries. Three stimulation frequencies (lower than recommended: 0.2 Hz, 1 Hz, 2 Hz) with a pulse width longer than recommended (1 msec), at a stimulation intensity based on H-reflex and M-wave at Soleus muscle were evaluated. Detectability of single-trial SEPs relative to background noise was tested offline and in a pseudo-online analysis, followed by a real-time demonstration. Main results. SEP N70 was observed predominantly at the central scalp regions. Online decoding performance was significantly higher with Laplacian filter. Generalization performance showed an expected degradation, at all frequencies, with an average decrease of 5.9% (multivariate) and 6.5% (univariate), with an AUC score ranging from 0.78–0.90. The difference across stimulation frequencies was not significant. In individuals with injuries, AUC of 0.86 (incomplete spinal cord injury) and 0.81 (stroke) was feasible. Real-time demonstration showed SEP detection with AUC of 0.89. Significance. This study describes and evaluates a system for extracting single-trial SEPs in real-time, suitable for a BCI-based operant conditioning. It enhances SNR of individual SEPs by alternate electrical stimulation parameters, dry headset, and optimized signal processing.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{colombo2025brain,

title = {Brain-derived neural networks distinguish design representations in different media},

author = {Samuele Colombo and Nayeon Kim and John Gero},

doi = {https://doi.org/10.1017/pds.2025.10089},

year  = {2025},

date = {2025-08-27},

urldate = {2025-01-01},

journal = {Proceedings of the Design Society},

volume = {5},

pages = {751–760},

publisher = {Cambridge University Press},

abstract = {Design activities rely on external representations to offload cognitive effort and communicate ideas. These representations, ranging from sketches to virtual reality (VR), influence cognitive processes and perceptual outcomes. This study investigates the impact of different media representations on brain activity by comparing neural responses to design representations in VR and desktop monitor conditions. Utilizing brain network analyses derived from EEG signals in alpha, beta, gamma, and theta bands, results demonstrate that VR elicits greater cognitive integration and sensory engagement. These patterns suggest that VR facilitates holistic evaluations, while desktop representations support precision-focused tasks. These findings provide actionable guidance for optimizing design media selection based on cognitive objectives and contribute to the emerging design neurocognition field.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{țenea2025co,

title = {The co-created city: neuroadaptive design for healthy environments},

author = {Sabin-Andrei Țenea and Alexandru Berceanu and Sergiu Nisioi and Andreea Robu-Movilă and Constantin Pistol and Grigore Burloiu},

doi = {https://doi.org/10.1080/17508975.2025.2542804},

year  = {2025},

date = {2025-08-21},

urldate = {2025-01-01},

journal = {Intelligent Buildings International},

pages = {1–17},

publisher = {Taylor & Francis},

abstract = {Urban environments profoundly influence human well-being and behavior, underscoring the need for design paradigms that seamlessly integrate ecological principles with stakeholder requirements. This study investigates the convergence of affective computing and generative design to develop adaptive, health-promoting urban environments. Initially, a genetic-generative algorithm was created to generate an extensive database of high-rise tower designs optimized for solar exposure and surface-to-volume ratio. Subsequently, an EEG-based Brain–Computer Interface (BCI) system was implemented to capture architects’ subconscious emotional responses to selected designs using Event-Related Potentials (ERPs) and Self-Assessment Manikin (SAM) scales. EEG data from 24 participants were analyzed to extract ERP markers of valence-based preference, revealing significant neural responses in early (250–350 ms) and late (600–800 ms) time windows. A random forest model, complemented by SHAP analysis, demonstrated nonlinear influences of critical design parameters on subjective preference. EEG-derived preference scores were then integrated into a multi-objective optimization workflow, facilitating a data-driven, user-centric design selection process. The findings support the potential for real-time, neuroadaptive architectural design that mitigates decision fatigue while harmonizing objective performance metrics with affective insights. Moreover, this work contributes to research-informed public consultation by providing an evidence-based, inclusive approach for incorporating subconscious user preferences into urban planning and architectural workflows.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{maksimenko2025video,

title = {Video-Based experiments better unveil societal biases towards ethical decisions of autonomous vehicles},

author = {Vladimir Maksimenko and Xinwei Li and Eui-Jin Kim and Prateek Bansal},

doi = {https://doi.org/10.1016/j.trc.2025.105284},

year  = {2025},

date = {2025-07-26},

urldate = {2025-01-01},

journal = {Transportation Research Part C: Emerging Technologies},

volume = {179},

pages = {105284},

publisher = {Elsevier},

abstract = {Autonomous vehicles (AVs) encounter moral dilemmas when determining whom to sacrifice in unavoidable crashes. To increase the trustworthiness of AVs, policymakers need to understand public judgment on how AVs should act in such ethically complex situations. Previous studies have evaluated public perception about these ethical matters using picture-based surveys and reported societal biases, i.e., systematic variations in ethical decisions based on the socioeconomic characteristics (e.g., gender) of the individuals involved. For instance, females may prioritise saving a female pedestrian in AV-pedestrian incidents. We investigate if these biases stem from personal beliefs or emerge during experiment engagement and if the presentation format affects bias manifestation. Analysing neural responses in moral experiments measured using electroencephalography (EEG) and behaviour model parameters, we find that video-based scenes better unveil societal biases than picture-based scenes. These biases emerge when the subject interacts with experimental information rather than being solely dictated by initial preferences. The findings support the use of realistic video-based scenes in moral experiments. These insights can inform data collection standards to shape socially acceptable ethical AI policies.

},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{zazon2025can,

title = {Can your brain signals reveal your romantic emotions?},

author = {Dor Zazon and Nir Nissim},

doi = {https://doi.org/10.1016/j.compbiomed.2025.110754},

year  = {2025},

date = {2025-07-14},

urldate = {2025-01-01},

journal = {Computers in Biology and Medicine},

volume = {196},

pages = {110754},

publisher = {Elsevier},

abstract = {The process of partner selection may result in emotions of romantic attraction when one expresses interest towards a potential partner, and rejection when one receives negative feedback from a potential partner. Previous EEG studies have found distinct neural correlates for both emotions in the context of dating apps. However, to the best of our knowledge, no study has demonstrated the ability to predict the associated intra-subject romantic emotions based on a single-trial analysis of event related potential (ERP). In this study, 61 participants (31 females and 30 males) agreed to use our simulated dating app, and their EEG brain activity was recorded during their engagement with the app. Based on each participant's EEG signals, we induced multiple machine and deep learning models aimed at predicting single-trial romantic attraction and rejection for each participant. Our results show that the best model obtained 71.38 % and 81.31 % average ROC-AUC scores across the participants respectively for romantic attraction and rejection. We also found that our learning models were able to predict romantic emotions more accurately for picky participants than they could for those that were less fussy, which might suggest that picky people have stronger brain activity signals when it comes to romantic preference.

},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{rueda2025test,

title = {Test-Retest Reliability of Kinematic and EEG Low-beta spectral features in a robot-based arm movement task},

author = {Sebastian Rueda Parra and Russell Lee Hardesty and DARREN Ethan GEMOETS and Jeremy Hill and Disha Gupta},

doi = {https://doi.org/10.1088/2057-1976/ade317},

year  = {2025},

date = {2025-06-10},

urldate = {2025-01-01},

journal = {Biomedical Physics & Engineering Express},

abstract = {Objective: Low-beta (Lβ, 13-20 Hz) power plays a key role in upper-limb motor control and afferent processing, making it a strong candidate for a neurophysiological biomarker. We investigate the test-retest reliability of Lβ power and kinematic features from a robotic task over extended intervals between sessions to assess its potential for tracking longitudinal changes in sensorimotor function.



Approach: We designed and optimized a testing protocol to evaluate Lβ power and kinematic features (maximal and mean speed, reaction time, and movement duration) in ten right-handed healthy individuals that performed a planar center-out task using a robotic device and EEG for data collection. The task was performed with both hands, and the experiment was repeated approximately 40 days later under similar conditions, to resemble real-life intervention periods. We first characterized the selected features within the task context for each session, then assessed intersession agreement, the test-retest reliability (Intraclass Correlation Coefficient, ICC), and established threshold values for meaningful changes in Lβ power using Bland-Altman plots and repeatability coefficients.



Main results: Lβ power showed the expected contralateral reduction during movement preparation and onset. Both Lβ power and kinematic features exhibited good to excellent test-retest reliability (ICC > 0.8), displaying no significant intersession differences. Kinematic results align with prior literature, reinforcing the robustness of these measures in tracking motor performance over time. Changes in Lβ power between sessions exceeding 11.4% for right-arm and 16.5% for left-arm movements reflect meaningful intersession differences.



Significance: This study provides evidence that Lβ power remains stable over extended intersession intervals comparable to rehabilitation timelines. The strong reliability of both Lβ power and kinematic features supports their use in monitoring upper-extremity sensorimotor function longitudinally, with Lβ power emerging as a promising biomarker for tracking therapeutic outcomes, postulating it as a reliable feature for long-term applications.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}