YOTO (You Only Think Once): A Human EEG Dataset for Multisensory Perception and Mental Imagery

YOTO (You Only Think Once): A Human EEG Dataset for Multisensory Perception and Mental Imagery | bioRxiv /* */ /* */ <!-- <!-- /*! * yepnope1.5.4 * (c) WTFPL, GPLv2 */ (function(a,b,c){function d(a){return"[object Function]"==o.call(a)}function e(a){return"string"==typeof a}function f(){}function g(a){return!a||"loaded"==a||"complete"==a||"uninitialized"==a}function h(){var a=p.shift();q=1,a?a.t?m(function(){("c"==a.t?B.injectCss:B.injectJs)(a.s,0,a.a,a.x,a.e,1)},0):(a(),h()):q=0}function i(a,c,d,e,f,i,j){function k(b){if(!o&&g(l.readyState)&&(u.r=o=1,!q&&h(),l.onload=l.onreadystatechange=null,b)){"img"!=a&&m(function(){t.removeChild(l)},50);for(var d in y[c])y[c].hasOwnProperty(d)&&y[c][d].onload()}}var j=j||B.errorTimeout,l=b.createElement(a),o=0,r=0,u={t:d,s:c,e:f,a:i,x:j};1===y[c]&&(r=1,y[c]=[]),"object"==a?l.data=c:(l.src=c,l.type=a),l.width=l.height="0",l.onerror=l.onload=l.onreadystatechange=function(){k.call(this,r)},p.splice(e,0,u),"img"!=a&&(r||2===y[c]?(t.insertBefore(l,s?null:n),m(k,j)):y[c].push(l))}function j(a,b,c,d,f){return q=0,b=b||"j",e(a)?i("c"==b?v:u,a,b,this.i++,c,d,f):(p.splice(this.i++,0,a),1==p.length&&h()),this}function k(){var a=B;return a.loader={load:j,i:0},a}var l=b.documentElement,m=a.setTimeout,n=b.getElementsByTagName("script")[0],o={}.toString,p=[],q=0,r="MozAppearance"in l.style,s=r&&!!b.createRange().compareNode,t=s?l:n.parentNode,l=a.opera&&"[object Opera]"==o.call(a.opera),l=!!b.attachEvent&&!l,u=r?"object":l?"script":"img",v=l?"script":u,w=Array.isArray||function(a){return"[object Array]"==o.call(a)},x=[],y={},z={timeout:function(a,b){return b.length&&(a.timeout=b[0]),a}},A,B;B=function(a){function b(a){var a=a.split("!"),b=x.length,c=a.pop(),d=a.length,c={url:c,origUrl:c,prefixes:a},e,f,g;for(f=0;f<d;f++)g=a[f].split("="),(e=z[g.shift()])&&(c=e(c,g));for(f=0;f<b;f++)c=x[f](c);return c}function g(a,e,f,g,h){var i=b(a),j=i.autoCallback;i.url.split(".").pop().split("?").shift(),i.bypass||(e&&(e=d(e)?e:e[a]||e[g]||e[a.split("/").pop().split("?")[0]]),i.instead?i.instead(a,e,f,g,h):(y[i.url]?i.noexec=!0:y[i.url]=1,f.load(i.url,i.forceCSS||!i.forceJS&&"css"==i.url.split(".").pop().split("?").shift()?"c":c,i.noexec,i.attrs,i.timeout),(d(e)||d(j))&&f.load(function(){k(),e&&e(i.origUrl,h,g),j&&j(i.origUrl,h,g),y[i.url]=2})))}function h(a,b){function c(a,c){if(a){if(e(a))c||(j=function(){var a=[].slice.call(arguments);k.apply(this,a),l()}),g(a,j,b,0,h);else if(Object(a)===a)for(n in m=function(){var b=0,c;for(c in a)a.hasOwnProperty(c)&&b++;return b}(),a)a.hasOwnProperty(n)&&(!c&&!--m&&(d(j)?j=function(){var a=[].slice.call(arguments);k.apply(this,a),l()}:j[n]=function(a){return function(){var b=[].slice.call(arguments);a&&a.apply(this,b),l()}}(k[n])),g(a[n],j,b,n,h))}else!c&&l()}var h=!!a.test,i=a.load||a.both,j=a.callback||f,k=j,l=a.complete||f,m,n;c(h?a.yep:a.nope,!!i),i&&c(i)}var i,j,l=this.yepnope.loader;if(e(a))g(a,0,l,0);else if(w(a))for(i=0;i (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0];var j=d.createElement(s);var dl=l!='dataLayer'?'&l='+l:'';j.src='//www.googletagmanager.com/gtm.js?id='+i+dl;j.type='text/javascript';j.async=true;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-M677548'); Skip to main content Home About Submit ALERTS / RSS Search for this keyword Advanced Search New Results YOTO (You Only Think Once): A Human EEG Dataset for Multisensory Perception and Mental Imagery Yan-Han Chang , Hsi-An Chen , Min-Jiun Tsai , Chun-Lung Tseng , Ching-Huei Lo , Kuan-Chih Huang , Chun-Shu Wei doi: https://doi.org/10.1101/2025.04.17.645384 Yan-Han Chang 1 Department of Computer Science, National Yang Ming Chiao Tung University , Hsinchu, Taiwan 2 Interdisciplinary Science Degree Program, National Yang Ming Chiao Tung University , Hsinchu, Taiwan Find this author on Google Scholar Find this author on PubMed Search for this author on this site Hsi-An Chen 1 Department of Computer Science, National Yang Ming Chiao Tung University , Hsinchu, Taiwan Find this author on Google Scholar Find this author on PubMed Search for this author on this site Min-Jiun Tsai 3 Institute of Mathematical Modeling and Scientific Computing, National Yang Ming Chiao Tung University , Hsinchu, Taiwan Find this author on Google Scholar Find this author on PubMed Search for this author on this site Chun-Lung Tseng 4 Institute of Education, National Yang Ming Chiao Tung University , Hsinchu, Taiwan Find this author on Google Scholar Find this author on PubMed Search for this author on this site Ching-Huei Lo 4 Institute of Education, National Yang Ming Chiao Tung University , Hsinchu, Taiwan Find this author on Google Scholar Find this author on PubMed Search for this author on this site Kuan-Chih Huang 5 Brain Science and Technology Center, National Yang Ming Chiao Tung University , Hsinchu, Taiwan Find this author on Google Scholar Find this author on PubMed Search for this author on this site Chun-Shu Wei 1 Department of Computer Science, National Yang Ming Chiao Tung University , Hsinchu, Taiwan 4 Institute of Education, National Yang Ming Chiao Tung University , Hsinchu, Taiwan 5 Brain Science and Technology Center, National Yang Ming Chiao Tung University , Hsinchu, Taiwan 6 Institute of Biomedical Engineering, National Yang Ming Chiao Tung University , Hsinchu, Taiwan Find this author on Google Scholar Find this author on PubMed Search for this author on this site For correspondence: wei{at}nycu.edu.tw Abstract Full Text Info/History Metrics Preview PDF Abstract The YOTO (You Only Think Once) dataset presents a human electroencephalography (EEG) resource for exploring multisensory perception and mental imagery. The study enrolled 26 participants who performed tasks involving both unimodal and multimodal stimuli. Researchers collected high-resolution EEG signals at a 1000 Hz sampling rate to capture high-temporal-resolution neural activity related to internal mental representations. The protocol incorporated visual, auditory, and combined cues to investigate the integration of multiple sensory modalities, and participants provided self-reported vividness ratings that indicate subjective perceptual strength. Technical validation involved event-related potentials (ERPs) and power spectral density (PSD) analyses, which demonstrated the reliability of the data and confirmed distinct neural responses across stimuli. This dataset aims to foster studies on neural decoding, perception, and cognitive modeling, and it is publicly accessible for researchers who seek to advance multimodal mental imagery research and related applications. Introduction Mental imagery is an important component of human cognition and has value in many application domains. Mental imagery refers to an internal process in which perception-like representations of objects, scenes, events, or sensations emerge without direct external inputs 1 . Studies suggest that these internally generated representations activate neural substrates that also respond to actual perception, indicating that mental imagery functions as a neural simulation of real sensory experiences 2 , 3 . Among the various types of mental imagery, visual imagery has been studied in a more extensive way 4 . Previous research has shown that visual imagery activates early visual cortical areas (V1–V4) and is closely associated with spatial reasoning, visual memory, and visual creativity 5 , 6 . Auditory imagery engages the auditory cortex (A1) 7 , which plays an essential role in music memory, language comprehension, and speech learning processes. Motor imagery, associated with the motor cortex (M1), is frequently used in athletic training 8 , motor skill enhancement, and rehabilitation therapies to improve muscle coordination and precision of movement 9 . Beyond these widely studied types, olfactory imagery involves the olfactory cortex and related limbic structures, such as the piriform cortex and amygdala, and can trigger emotional and autobiographical memory activation 10 , 11 . Tactile imagery helps mentally reconstruct the sense of touch, including temperature, texture, and pressure 12 . Gustatory imagery activates the insular cortex and is closely related to emotional regulation and appetite control 13 . Emotional imagery involves emotional processing regions, including the amygdala and anterior cingulate cortex (ACC), and has been applied effectively in treatments for psychological disorders such as post-traumatic stress disorder (PTSD) and anxiety disorders 14 , 15 . Importantly, different types of mental imagery often co-occur in naturalistic settings. Neuroimaging findings suggest that these internally generated sensations partially recruit the same neural substrates that process real sensory input 1 , 16 . Mental imagery, in essence, is not merely symbolic or abstract representation; rather, on multiple levels, it simulates the brain’s response to actual perception. However, mental imagery does not occur exclusively in task-specific states; even in the absence of external stimuli, the brain remains highly active during resting states, particularly in the medial prefrontal cortex, the posterior cingulate cortex / precuneus, and the lateral cortical regions, which consistently exhibit coordinated activity during rest 17 , 18 . This network, known as the default mode network (DMN), is closely related to memory recall 19 , mind wandering and daydreaming 20 , memory retrieval, self-referential thought, and mental simulation 21 – 23 . Researchers have applied neural representations of mental imagery in electroen-cephalography (EEG) decoding technologies. The neural mechanisms of mental imagery include sensory simulation, memory retrieval, and internal thought regulation, and these mechanisms illuminate how the brain reconstructs sensory experiences in the absence of external inputs 4 , 24 . Studies indicate that mental imagery produces measurable EEG patterns, such as alpha-wave changes and altered occipital gamma waves 25 , 26 . These neural markers suggest that EEG signals offer a promising means to recognize and classify mental imagery without relying on external stimuli. Visual imagery appears in alpha-wave modulation and changes in gamma-band activity in occipital regions 25 , 26 . Auditory imagery involves cortical areas linked to auditory processing. Motor imagery modulates sensorimotor rhythms and aids rehabilitation and motor control. Each imagery type reflects distinct neural patterns, and EEG signals detect these patterns in real time. The ability to capture such activity advances interactive technologies that integrate mental imagery for communication or control. Most studies focus on unimodal sensory imagery, such as purely visual or auditory forms. Research on multisensory integration remains less extensive 27 . Concurrent processing of visual, auditory, and tactile imagery needs better understanding of neural mechanisms that integrate these modalities. Mental imagery EEG datasets also encounter technical constraints. A low signal-to-noise ratio (SNR) and high interindividual variability limit reproducibility of research findings 28 . Methods lack uniform standards, which complicates generalization of decoding results 29 . Observing EEG signals during mixed imagery tasks may clarify how the brain coordinates and merges several internal simulations. The YOTO (You Only Think Once) dataset holds strong potential for advancing research into the neural mechanisms of mental imagery and resting-state brain activity. It provides a rich collection of non-invasive EEG recordings during multimodal mental imagery tasks and spontaneous rest from a diverse group of participants. We anticipate a wide range of applications for this dataset. For instance, it can be used to develop and evaluate EEG-based decoding models of imagined sensory experiences, investigate and compare dynamics of perceived and imagined sensory responses, and explore the integration of multisensory representations. In sum, YOTO complements existing EEG resources by providing a high-quality, systematically curated dataset tailored to the study of internal mental states and multimodal cognitive process. Methodology Participants 26 healthy participants (16 males, 10 females) volunteered to participate in the study, with a mean age of 23.3 years (median: 23 years, range: 20–36 years). All participants had normal or corrected-to-normal vision and provided their written informed consent prior to the experiment. Exclusion criteria included screen-induced dizziness, major diseases, irregular sleep patterns, poor sleep quality, disability, psychiatric disorders, or pregnancy. This study was approved by the Human Subjects Research Ethics Committee of the National Chiao Tung University (Approval No. NCTU-REC-108-128F). EEG Data Acquisition EEG signals were recorded in an electromagnetically shielded chamber using a high-fidelity electrophysiological recording system. The Polhemus 3SPACE FASTRAK system was used to position the Cz reference point before securing the EEG headset ( Figure 1 ). Thirty-two electrodes, including two reference electrodes at A1 and A2, were placed according to the 10-20 international system. Thirty-channel EEG signals were amplified and transmitted to a computer via a SynAmps RT 64 channel amplifier (Compumedics Neuroscan), digitized at 1000 Hz, and event markers were transmitted via a parallel port to indicate the onset of the trial, stimulus presentation, resting phase, and imagery phases. Download figure Open in new tab Fig. 1: EEG Data Acquisition System Architecture. (a) The EEG cap with a 30-channel electrode configuration, (b) The 64-channel high-resolution EEG signal amplifier. Experimental Protocol Each participant completed two separate sessions on different days, each session consisting of four blocks of 48 trials, interspersed with short breaks( Figure 2 ). During the experiment, participants were instructed to keep fixation on a central cross while participating in mental imagery tasks associated with the stimuli presented. Download figure Open in new tab Fig. 2: Experimental Procedure and Trial Structure. Detailed presentation of the trial structure, clearly illustrating task phases including fixation, stimulus presentation, imagery phase, and subjective self-report. Each trial followed a structured sequence, as shown in Table 1 , beginning with a fixation period (2 s), during which the participants focused on a central cross to clear their thoughts. This was followed by a stimulus presentation phase (2 s), in which a visual, auditory, or combined stimulus was randomly displayed. Subsequently, the participants entered the imagery phase (4 s), during which they mentally visualized the stimulus received previously. Finally, during the self-report phase, participants rated the vividness of their mental imagery on a scale from 1 to 5. The duration of this phase varied across individuals. To assess baseline neural activity, resting-state EEG data were recorded both before and after the experimental session. View this table: View inline View popup Download powerpoint Table 1: Experimental procedure of a single trial consisting of four sequential phases. Stimuli Details In the imagery task, visual and auditory stimuli were presented, individually or in combination, to ensure a complete examination of sensory processing. The visual stimuli, as illustrated in Figure 3 , consisted of a gray square and two facial images (one male, one female) 30 , while the auditory stimuli included three human short vowels (/a/, /i/, /o/) and three piano tones (C: 261.63 Hz, D: 293.66 Hz, E: 329.63 Hz). These stimuli were systematically combined to create 27 unique stimulus conditions, which encompassed three categories: visual-only, auditory-only, and multimodal (visual-auditory) stimuli. To ensure a balanced distribution of stimuli in trials, a weighted randomization strategy was implemented ( Table 2 , Trials/Block). This weighted randomization approach prevented overrepresentation of specific conditions while maintaining sufficient exposure to all stimulus types, ensuring a balanced and unbiased experimental design. View this table: View inline View popup Download powerpoint Table 2: Stimuli types and their corresponding trials per block. Download figure Open in new tab Fig. 3: Example of Gray Square. Visual stimuli employed in the experiment, including a grayscale square. Data Preprocessing Pipeline Preprocessing of the EEG data was carried out using EEGLAB v2022 31 to ensure the integrity of the signal and the mitigation of artifacts. A causal FIR filter was used for bandpass filtering between 1 and 50 Hz, with a filter order of 500 and a buffer size of 30 seconds, effectively attenuating low-frequency drifts and high-frequency noise while preserving relevant neural oscillations. The data were subsequently resampled at 250 Hz to optimize computational efficiency while maintaining the fidelity of the recorded neural activity. To address non-neural artifacts, artifact subspace reconstruction (ASR) 32 was applied with a threshold parameter as suggested in 33 , which adaptively detects and reconstructs segments exhibiting excessive deviation from the statistical distribution of clean EEG data. The choice of the threshold parameter in ASR is essential for balancing between high-amplitude artifact removal and signal preservation, ensuring that transient high-amplitude artifacts (e.g. muscle activity, electrode displacement) are mitigated without excessively attenuating valid neural signals. Lower k values would result in overly aggressive rejection of artifacts, potentially removing informative neural activity, while higher values might allow significant artifacts to persist. Following high-amplitude artifact correction, independent component analysis (ICA) 34 with linear interpolation was performed to decompose the multichannel EEG signals into statistically independent sources, facilitating the isolation of neural components from non-neural artifacts. Finally, ICLabel 35 , a machine learning-based independent component classification tool, was utilized to automatically identify and remove artifacts related to ocular and muscular activities. Components classified as artifacts with a confidence probability greater than 0.8 were excluded from further analysis. This procedure effectively improved the SNR, ensuring that the retained components predominantly reflect neural activity. Data Records The raw EEG recordings, stored in the BIDS-compliant format, have been publicly released on OpenNeuro ( https://openneuro.org/datasets/ds005815/versions/1.0.1 ). The original data, initially in CNT format, were converted to BIDS using the MNE-Python and pybv packages. Technical Validation To ensure the reliability and validity of the dataset, we conducted both behavioral and neurophysiological analyzes. Subjective vividness ratings were assessed to evaluate participants’ self-reported imagery experiences under different stimulus conditions. In parallel, neural responses were examined using event-related potentials (ERPs) to capture time-locked brain activity and power spectral density (PSD) analysis to characterize frequency-domain neural oscillations. These analyses provide complementary insights into how different sensory modalities influence mental imagery and cognitive processing. Vividness Ratings Analysis Figure 4 presents the distribution of vividness ratings across different stimulus conditions. The results show that multimodal stimuli generally received higher and more consistent vividness ratings, while pure auditory stimuli exhibited greater variability. A three-way repeated measures ANOVA was conducted to analyze the effects of subject, stimulus condition, and session. Significant main effects were observed for subject ( F = 239.54, p < .001), stimulus condition ( F = 4.04, p < .001), and the session ( F = 14.61, p < .001), indicating that the vividness varied between individuals, the stimulus conditions and the sessions. Interaction effects between the stimulus condition and the subject ( F = 3.51, p < .001) and the subject and the session ( F = 16.21, p < .001), while the interaction between stimulus condition and session ( F = 0.67, p = .896)was not significant. A significant three-way interaction ( F = 1.16, p = 0.009) was also observed. Download figure Open in new tab Fig. 4: Distribution of Subjective Imagery Vividness Ratings Across Stimulus Conditions. Violin plot depicting the distribution of participant-rated vividness of mental imagery across different stimulus conditions. The horizontal axis categorizes auditory-only, visual-only, and multimodal stimuli, while the vertical axis indicates vividness ratings from 1 to 5. Event-Related Potentials (ERP) Analysis Figure 5 , 6 , 7 show the ERP waveforms across stimulus conditions. Download figure Open in new tab Fig. 5: Event-Related Potentials (ERP) Waveforms for Visual Stimuli. ERP waveforms elicited by visual stimuli (male faces, female faces, and squares) at FCz, Cz, and Pz electrode sites. Facial stimuli evoke stronger neural responses compared to non-facial shapes, reflecting specialized neural processing of face perception. Download figure Open in new tab Fig. 6: Event-Related Potentials (ERP) Waveforms for Auditory Stimuli. ERP waveforms comparing auditory stimuli responses (human vowels and musical tones) at different electrodes. Download figure Open in new tab Fig. 7: Event-Related Potentials (ERP) Waveforms for Multimodal (Visual + Auditory) Stimuli. ERP waveforms highlighting neural responses to combined visual and auditory stimuli. The ERP of the visual stimuli, as illustrated in Figure 5 , shows the waveform distributions of the visual stimuli, including male faces, female faces, and squares. The findings reveal that face stimuli evoke significantly higher amplitudes at the FCz, Cz, and Pz electrodes. These results highlight the role of neural networks involved in face processing, demonstrating greater sensitivity to facial stimuli compared to non-facial shapes 36 , 37 . The ERP of the auditory stimuli, depicted in Figure 6 , compare neural responses to vocal and musical stimuli. The data indicate that vowels elicit higher amplitudes during early sensory responses (0.1–0.2 seconds), reflecting the brain’s rapid response to language-related sounds. In contrast, musical stimuli engage higher-level cognitive processes, such as emotional and melodic interpretation 38 – 40 . The ERP of the mixture stimuli, shown in Figure 7 , illustrate the waveform characteristics of combined visual and auditory stimuli. The results demonstrate how sensory modalities are integrated, highlighting the brain’s ability to process and merge information from multiple sensory channels 41 – 43 . When comparing the differences in power spectral density (PSD) of brain waves between various types of imagined activities and the baseline condition (Fixation) ( Figure 8 ), significant regional brain wave characteristics were observed in mixed visual, auditory and audiovisual imagery. Download figure Open in new tab Fig. 8: Power Spectral Density (PSD) Differences b etween I magery Tasks and Baseline Fixation. Comparative PSD analysis illustrating EEG spectral changes between imagery conditions (visual, auditory, multimodal) and baseline fixation. Visual imagery significantly enhances Alpha oscillations in the occipital lobe; auditory imagery primarily boosts Theta activity centrally; multimodal imagery broadly elevates neural oscillations across frequency bands. Visual imagery ( Figure 8a ) primarily activated the enhancement of alpha wave responses in the occipital lobe, while auditory imagery ( Figure 8b ) showed a more pronounced enhancement of Theta waves in the central, frontal and parietal regions. Mixed audiovisual imagery ( Figure 8c ) showed significant changes in all frequency bands, with wave enhancements that significantly exceeded those of single-modality stimuli, further confirming that multimodal integration requires higher cognitive resources and integration of the brain network. In Figure 9a , it can be seen that Delta and Theta waves show significant reductions in the frontal region, with the reduction in Theta waves being more prominent. In contrast, the Alpha and Beta waves exhibit significant enhancements in the occipital lobe (O1, O2, Oz). Download figure Open in new tab Fig. 9: Power Spectral Density (PSD) Differences Among Various Imagery Conditions. Comparative PSD analyses highlighting neural spectral differences between (a) visual versus auditory imagery, (b) multimodal versus visual imagery, and (c) multimodal versus auditory imagery. Results underscore distinctive neural activation patterns across different b rain regions and frequency bands, notably heightened Alpha and Beta activities in multimodal imagery. In Figure 9b , the Delta waves show a slight enhancement in the occipital lobe, while the Theta waves demonstrate a significant improvement in the central (Cz) and parietal (Pz) regions. Alpha waves also show slight enhancement in the occipital lobe, while beta waves exhibit enhancement in the frontal and central regions, further confirming that mixed stimuli increase the demand for higher cognitive resources 44 – 47 . In Figure 9c , the Delta waves show an improvement in the occipital lobe, with negligible differences in the central and frontal regions. Theta waves demonstrate significant enhancement in the central region, with minimal differences in the frontal region. Alpha waves show significant enhancement in the occipital and parietal regions, while beta waves exhibit significant enhancement in the frontal and central regions without any noticeable reductions, confirming the generally stronger Beta wave activity in multimodal stimuli 48 – 50 . These findings clearly validate the effectiveness of the data and demonstrate the significance of the YOTO data set in providing support for the EEG signal for both the resting state and the task phases, allowing the exploration of the random cognitive transition mechanisms of the brain. Code Availability The source code used for all technical validations conducted in this experiment has been uploaded and is publicly available on GitHub ( https://github.com/CECNL/YOTO_You_Only_Think_Once ). Author Contributions Chun-Shu Wei: Conceptualization, Methodology, Investigation, Formal analysis, Visualization, Data Curation, Writing – Original Draft, Writing – Review & Editing, Supervision, Project administration. Yan-Han Chang: Formal analysis, Investigation, Visualization, Data Curation, Writing – Original Draft, Writing – Review & Editing. Hsi-An Chen: Formal analysis, Investigation, Visualization, Writing – Original Draft, Data Curation. Min-Jiun Tsai: Methodology, Investigation, Data Curation, Project administration. Chun-Lung Tseng: Investigation, Data Curation, Formal analysis. Ching-Huei Lo: Investigation, Data Curation. Kuan-Chih Huang: Methodology, Data Curation, Project administration. Competing Interests The authors declare that there are no competing interests. Acknowledgements This research was supported in part by the National Science and Technology Council (109-2222-E-009-006-MY3, 112-2321-B-A49-012 and 112-2222-E-A49-008-MY2); in part by the Healthy Longevity Global Grand Challenge Catalyst Award of National Academy of Medicine, USA, and Academia Sinica, Taiwan (AS-HLGC-113-06); in part by the National Health Research Institute, Taiwan (Grant NHRI-EX114-11418EC); and in part by the Higher Education Sprout Project of National Yang Ming Chiao Tung University and Ministry of Education. Funding National Science and Technology Council, https://ror.org/02kv4zf79 , 109-2222-E-009-006-MY3 , 112-2321-B-A49-012 , 112-2222-E-A49-008-MY2 Academia Sinica, https://ror.org/05bxb3784 , AS-HLGC-113-06 National Health Research Institutes, https://ror.org/02r6fpx29 , NHRI-EX114-11418EC References 1. ↵ Kosslyn , S. M. , Ganis , G. & Thompson , W. L. Neural foundations of imagery . Nat. Rev. Neurosci . 2 , 635 – 642 ( 2001 ). OpenUrl CrossRef PubMed Web of Science 2. ↵ Lang , P. J. Imagery in therapy: an information processing analysis of fear . Behav. Ther . 8 ( 5 ), 862 – 886 ( 1977 ). OpenUrl CrossRef Web of Science 3. ↵ Lang , P. J. A bio-informational theory of emotional imagery . Psychophysiology 16 ( 6 ), 495 – 512 ( 1979 ). OpenUrl CrossRef PubMed Web of Science 4. ↵ Pearson , J. , Naselaris , T. , Holmes , E. A. & Kosslyn , S. M. Mental imagery: functional mechanisms and clinical applications . Trends Cogn. Sci . 19 , 590 – 602 ( 2015 ). OpenUrl CrossRef PubMed 5. ↵ Coyle , S. M. , Ward , T. E. & Markham , C. M. Brain–computer interface using a simplified functional near-infrared spectroscopy system . J. Neural Eng . 4 , 219 ( 2007 ). OpenUrl CrossRef PubMed Web of Science 6. ↵ Lawhern , V. J. , et al. EEGNet: a compact convolutional neural network for EEG-based brain–computer interfaces . J. Neural Eng . 15 , 056013 ( 2018 ). OpenUrl CrossRef PubMed 7. ↵ Tian , X. , Ding , N. , Teng , X. , Bai , F. & Poeppel , D. Imagined speech influences perceived loudness of sound . Nat. Hum. Behav . 2 , 225 – 234 ( 2018 ). OpenUrl CrossRef 8. ↵ Jeannerod , M. Neural simulation of action: a unifying mechanism for motor cognition . Neuroimage 14 , S103 – S109 ( 2001 ). OpenUrl CrossRef PubMed Web of Science 9. ↵ Borst , G. & Kosslyn , S. M. Visual mental imagery and visual perception: structural equivalence revealed by scanning processes . Mem. Cognit . 36 , 849 – 862 ( 2008 ). OpenUrl CrossRef PubMed Web of Science 10. ↵ Bensafi , M. , Sobel , N. & Khan , R. M. Hedonic-specific activity in piriform cortex during odor imagery mimics that during odor perception . J. Neurophysiol . 98 ( 6 ), 3254 – 3262 ( 2007 ). OpenUrl CrossRef PubMed Web of Science 11. ↵ Schlintl , C. , Zorjan , S. & Schienle , A. Olfactory imagery as a retrieval method for autobiographical memories . Psychol. Res . 87 ( 3 ), 862 – 871 ( 2023 ). OpenUrl CrossRef PubMed 12. ↵ Lacey , S. & Sathian , K. Crossmodal and multisensory interactions between vision and touch . In Scholarpedia of Touch , 301 – 315 ( 2015 ). 13. ↵ Kobayashi , M. , Fujita , S. , Takei , H. , Song , L. , Chen , S. , Suzuki , I. , Yoshida , A. , Iwata , K. & Koshikawa , N. Functional mapping of gustatory neurons in the insular cortex revealed by pERK-immunohistochemistry and in vivo optical imaging . Synapse 64 ( 4 ), 323 – 334 ( 2010 ). OpenUrl CrossRef PubMed Web of Science 14. ↵ Holmes , E. A. , Geddes , J. R. , Colom , F. & Goodwin , G. M. Mental imagery as an emotional amplifier: application to bipolar disorder . Behav. Res. Ther . 46 ( 12 ), 1251 – 1258 ( 2008 ). OpenUrl CrossRef PubMed Web of Science 15. ↵ Ji , J. L. , Heyes , S. B. , MacLeod , C. & Holmes , E. A. Emotional mental imagery as simulation of reality: fear and beyond—a tribute to Peter Lang . Behav. Ther . 47 ( 5 ), 702 – 719 ( 2016 ). OpenUrl CrossRef PubMed 16. ↵ Kosslyn , S. , Thompson , W. , Shephard , J. , Ganis , G. , Bell , D. , Danovitch , J. , Wittenberg , L. & Alpert , N. Brain rCBF and performance in visual imagery tasks: common and distinct processes . Eur. J. Cogn. Psychol . 16 ( 5 ), 696 – 716 ( 2004 ). OpenUrl CrossRef 17. ↵ Kosslyn , S. M. & Ochsner , K. N. In search of occipital activation during visual mental imagery . Trends Neurosci . 17 , 290 – 292 ( 1994 ). OpenUrl CrossRef PubMed Web of Science 18. ↵ Buckner , R. L. , Andrews-Hanna , J. R. & Schacter , D. L. The brain’s default network: anatomy, function, and relevance to disease . Ann. N. Y. Acad. Sci . 1124 , 1 – 38 ( 2008 ). OpenUrl CrossRef PubMed Web of Science 19. ↵ Conway , M. A. & Pleydell-Pearce , C.W. The construction of autobiographical memories in the self-memory system . Psychol. Rev . 107 ( 2 ), 261 ( 2000 ). OpenUrl CrossRef PubMed Web of Science 20. ↵ Smallwood , J. & Schooler , J. W. The science of mind wandering: empirically navigating the stream of consciousness . Annu. Rev. Psychol . 66 ( 1 ), 487 – 518 ( 2015 ). OpenUrl CrossRef PubMed 21. ↵ Zatorre , R. J. & Halpern , A. R. Mental concerts: musical imagery and auditory cortex . Neuron 47 , 9 – 12 ( 2005 ). OpenUrl CrossRef PubMed Web of Science 22. Zhang , D. & Raichle , M. E. Disease and the brain’s dark energy . Nat. Rev. Neurol . 6 , 15 – 28 ( 2010 ). OpenUrl CrossRef PubMed Web of Science 23. ↵ Fox , K. C. R. , Spreng , R. N. , Ellamil , M. , Andrews-Hanna , J. R. & Christoff , K. The wandering brain: meta-analysis of functional neuroimaging studies of mind-wandering and related spontaneous thought processes . Neuroimage 111 , 611 – 621 ( 2015 ). OpenUrl CrossRef PubMed 24. ↵ Ganis , G. , Thompson , W. L. & Kosslyn , S. M. Brain areas underlying visual mental imagery and visual perception: an fMRI study . Cogn. Brain Res . 20 , 226 – 241 ( 2004 ). OpenUrl CrossRef PubMed 25. ↵ Pfurtscheller , G. & Neuper , C. Motor imagery and direct brain–computer communication . Proc. IEEE 89 , 1123 – 1134 ( 2001 ). OpenUrl CrossRef 26. ↵ Schlegel , A. , Kohler , P. J. , Fogelson , S. V. , Alexander , P. , Konuthula , D. & Tse , P. U. Network structure and dynamics of the mental workspace . Proc. Natl. Acad. Sci. USA 110 , 16277 – 16282 ( 2013 ). OpenUrl Abstract / FREE Full Text 27. ↵ Hubbard , T. L. Auditory imagery: empirical findings . Psychol. Bull . 136 , 302 ( 2010 ). OpenUrl CrossRef PubMed 28. ↵ Cichy , R. M. , Pantazis , D. & Oliva , A. Resolving human object recognition in space and time . Nat. Neurosci . 17 , 455 – 462 ( 2014 ). OpenUrl CrossRef PubMed 29. ↵ Keogh , R. & Pearson , J. The blind mind: no sensory visual imagery in aphantasia . Cortex 105 , 53 – 60 ( 2018 ). OpenUrl CrossRef PubMed 30. ↵ van Doorn , E. A. Emotion affords social influence: responding to others’ emotions in context. PhD thesis , University of Amsterdam ( 2013 ). Available at: https://dare.uva.nl/search?identifier=ace106c9-c580-4a7d-9070-083cb462b791 (8 March 2013). 31. ↵ Delorme , A. & Makeig , S. EEGLAB (version 2022) . Swartz Center for Computational Neuroscience . Retrieved from https://eeglab.org ( 2022 ). 32. ↵ Kothe , C. A. E. & Jung , T.-P. Artifact removal techniques with signal reconstruction. US Patent App . 14/ 895 , 440 . Google Patents ( 2016 ). OpenUrl 33. ↵ Chang , C.-Y. , Hsu , S.-H. , Pion-Tonachini , L. & Jung , T.-P. Evaluation of artifact subspace reconstruction for automatic artifact components removal in multi-channel EEG recordings . IEEE Trans. Biomed. Eng . 67 ( 4 ), 1114 – 1121 ( 2019 ). OpenUrl CrossRef PubMed 34. ↵ Comon , P. Independent component analysis, a new concept? Signal Process . 36 ( 3 ), 287 – 314 ( 1994 ). OpenUrl CrossRef Web of Science 35. ↵ Pion-Tonachini , L. , Kreutz-Delgado , K. & Makeig , S. ICLabel: an automated electroencephalographic independent component classifier, dataset, and website . NeuroImage 198 , 181 – 197 ( 2019 ). OpenUrl CrossRef PubMed 36. ↵ Rossion , B. Understanding face perception by means of human electrophysiology . Trends Cogn. Sci . 18 , 310 – 318 ( 2014 ). doi: 10.1016/j.tics.2014.02.013 OpenUrl CrossRef PubMed 37. ↵ Eimer , M. & Holmes , A. An ERP study on the time course of emotional face processing . Neuropsychologia 45 , 2296 – 2306 ( 2007 ). doi: 10.1016/j.neuropsychologia.2007.02.013 OpenUrl CrossRef 38. ↵ Obleser , J. , Elbert , T. & Eulitz , C. Auditory evoked potentials and neural rep-resentation of vowels . NeuroReport 14 ( 7 ), 987 – 990 ( 2003 ). doi: 10.1097/00001756-200305230-00024 OpenUrl CrossRef 39. Koelsch , S. , Fritz , T. & Schlaug , G. Amygdala activity can be modulated by unexpected chord functions during music listening . NeuroReport 19 ( 18 ), 1815 – 1819 ( 2008 ). doi: 10.1097/WNR.0b013e32831a8722 OpenUrl CrossRef PubMed Web of Science 40. ↵ Meyer , M. , Baumann , S. & Jancke , L. Electrical brain imaging reveals spatiotemporal dynamics of timbre perception in humans . Neuroimage 32 ( 4 ), 1510 – 1523 ( 2006 ). OpenUrl CrossRef PubMed Web of Science 41. ↵ Stevenson , R. A. , Bushmakin , M. , Kim , S. , Wallace , M. T. , Puce , A. & James , T. W. Inverse effectiveness and multisensory interactions in visual event-related potentials with audiovisual speech . Brain Topogr . 25 ( 3 ), 308 – 326 ( 2012 ). doi: 10.1007/s10548-012-0220-7 OpenUrl CrossRef PubMed Web of Science 42. van Wassenhove , V. , Grant , K. W. & Poeppel , D. Visual speech speeds up the neural processing of auditory speech . Proc. Natl. Acad. Sci. USA 102 ( 4 ), 1181 – 1186 ( 2005 ). doi: 10.1073/pnas.0408949102 OpenUrl Abstract / FREE Full Text 43. ↵ Giard , M. H. & Peronnet , F. Auditory-visual integration during multimodal object recognition in humans: a behavioral and electrophysiological study . J. Cogn. Neurosci . 11 ( 5 ), 473 – 490 ( 1999 ). doi: 10.1162/089892999563544 OpenUrl CrossRef PubMed Web of Science 44. ↵ Senkowski , D. , Schneider , T. R. , Foxe , J. J. & Engel , A. K. Crossmodal binding through neural coherence: implications for multisensory processing . Trends Neurosci . 31 ( 8 ), 401 – 409 ( 2008 ). doi: 10.1016/j.tins.2008.05.002 OpenUrl CrossRef PubMed Web of Science 45. Friese , U. , Daume , J. , Göschl , F. , König , P. & Wang , P. Oscillatory brain activity during multisensory attention reflects activation, disinhibition, and cognitive control . Sci. Rep . 6 , 32775 ( 2016 ). doi: 10.1038/srep32775 OpenUrl CrossRef PubMed 46. Klimesch , W. Alpha-band oscillations, attention, and controlled access to stored information . Trends Cogn. Sci . 16 ( 12 ), 606 – 617 ( 2012 ). doi: 10.1016/j.tics.2012.10.007 OpenUrl CrossRef PubMed Web of Science 47. ↵ Engel , A. K. & Fries , P. Beta-band oscillations—signalling the status quo? Curr. Opin. Neurobiol . 20 ( 2 ), 156 – 165 ( 2010 ). doi: 10.1016/j.conb.2010.02.015 OpenUrl CrossRef PubMed Web of Science 48. ↵ Mercier , M. R. , Molholm , S. , Fiebelkorn , I. C. , Butler , J. S. , Schwartz , T. H. & Foxe , J. J. Neuro-oscillatory phase alignment drives speeded multisensory response times . Cereb. Cortex 25 ( 2 ), 376 – 386 ( 2015 ). doi: 10.1093/cercor/bht194 OpenUrl CrossRef 49. Foxe , J. J. & Snyder , A. C. The role of alpha-band brain oscillations as a sensory suppression mechanism during selective attention . Front. Psychol . 2 , 154 ( 2011 ). doi: 10.3389/fpsyg.2011.00154 OpenUrl CrossRef PubMed 50. ↵ Senkowski , D. , Molholm , S. , Gomez-Ramirez , M. & Foxe , J. J. Oscillatory beta activity predicts response speed during a multisensory audiovisual reaction time task . J. Neurosci . 26 ( 40 ), 10120 – 10129 ( 2006 ). doi: 10.1523/JNEUROSCI.2427-06.2006 OpenUrl Abstract / FREE Full Text View the discussion thread. Back to top Previous Next Posted April 22, 2025. Download PDF Email Thank you for your interest in spreading the word about bioRxiv. NOTE: Your email address is requested solely to identify you as the sender of this article. Your Email * Your Name * Send To * Enter multiple addresses on separate lines or separate them with commas. You are going to email the following YOTO (You Only Think Once): A Human EEG Dataset for Multisensory Perception and Mental Imagery Message Subject (Your Name) has forwarded a page to you from bioRxiv Message Body (Your Name) thought you would like to see this page from the bioRxiv website. Your Personal Message CAPTCHA This question is for testing whether or not you are a human visitor and to prevent automated spam submissions. Share YOTO (You Only Think Once): A Human EEG Dataset for Multisensory Perception and Mental Imagery Yan-Han Chang , Hsi-An Chen , Min-Jiun Tsai , Chun-Lung Tseng , Ching-Huei Lo , Kuan-Chih Huang , Chun-Shu Wei bioRxiv 2025.04.17.645384; doi: https://doi.org/10.1101/2025.04.17.645384 Share This Article: Copy Citation Tools YOTO (You Only Think Once): A Human EEG Dataset for Multisensory Perception and Mental Imagery Yan-Han Chang , Hsi-An Chen , Min-Jiun Tsai , Chun-Lung Tseng , Ching-Huei Lo , Kuan-Chih Huang , Chun-Shu Wei bioRxiv 2025.04.17.645384; doi: https://doi.org/10.1101/2025.04.17.645384 Citation Manager Formats BibTeX Bookends EasyBib EndNote (tagged) EndNote 8 (xml) Medlars Mendeley Papers RefWorks Tagged Ref Manager RIS Zotero Tweet Widget Facebook Like Google Plus One Subject Area Neuroscience Subject Areas All Articles Animal Behavior and Cognition (7633) Biochemistry (17681) Bioengineering (13890) Bioinformatics (41929) Biophysics (21446) Cancer Biology (18586) Cell Biology (25492) Clinical Trials (138) Developmental Biology (13374) Ecology (19897) Epidemiology (2067) Evolutionary Biology (24308) Genetics (15606) Genomics (22497) Immunology (17736) Microbiology (40385) Molecular Biology (17175) Neuroscience (88584) Paleontology (666) Pathology (2831) Pharmacology and Toxicology (4822) Physiology (7641) Plant Biology (15149) Scientific Communication and Education (2045) Synthetic Biology (4293) Systems Biology (9822) Zoology (2271)