Spatial Activity Patterns Research Articles

Exploring Effects of Mental Stress with Data Augmentation and Classification Using fNIRS

Accurately identifying and discriminating between different brain states is a major emphasis of functional brain imaging research. Various machine learning techniques play an important role in this regard. However, when working with a small number of study participants, the lack of sufficient data and achieving meaningful classification results remain a challenge. In this study, we employ a classification strategy to explore stress and its impact on spatial activation patterns and brain connectivity caused by the Stroop color–word task (SCWT). To improve our results and increase our dataset, we use data augmentation with a deep convolutional generative adversarial network (DCGAN). The study is carried out at two separate times of day (morning and evening) and involves 21 healthy participants. Additionally, we introduce binaural beats (BBs) stimulation to investigate its potential for stress reduction. The morning session includes a control phase with 10 SCWT trials, whereas the afternoon session is divided into three phases: stress, mitigation (with 16 Hz BB stimulation), and post-mitigation, each with 10 SCWT trials. For a comprehensive evaluation, the acquired fNIRS data are classified using a variety of machine-learning approaches. Linear discriminant analysis (LDA) showed a maximum accuracy of 60%, whereas non-augmented data classified by a convolutional neural network (CNN) provided the highest classification accuracy of 73%. Notably, after augmenting the data with DCGAN, the classification accuracy increases dramatically to 96%. In the time series data, statistically significant differences were noticed in the data before and after BB stimulation, which showed an improvement in the brain state, in line with the classification results. These findings illustrate the ability to detect changes in brain states with high accuracy using fNIRS, underline the need for larger datasets, and demonstrate that data augmentation can significantly help when data are scarce in the case of brain signals.

Implications of neural integration of math and spatial experiences for math ability and math anxiety.

Mathematical and spatial abilities are positively related at both the behavioral and neural levels. Much of the evidence illuminating this relationship comes from classic laboratory-based experimental methods focused on cognitive performance despite most individuals also experiencing math and space in other contexts, such as in conversations or lectures. To broaden our understanding of math-space integration in these more commonplace situations, we used an auditory memory-encoding task with stimuli whose content evoked a range of educational and everyday settings related to math or spatial thinking. We used a multivariate approach to directly assess the extent of neural similarity between activity patterns elicited by these math and spatial stimuli. Results from whole-brain searchlight analysis revealed a highly specific positive relation between math and spatial activity patterns in bilateral anterior hippocampi. Examining individual variation in math-space similarity, we found that greater math-space similarity in bilateral anterior hippocampi was associated with poorer math skills and higher anxiety about math. Integration of neural responses to mathematical and spatial content may not always portend positive outcomes. We suggest that episodic simulation of quotidian contexts may link everyday experiences with math and spatial thinking-and the strength of this link is predictive of math in a manner that diverges from math-space associations derived from more lab-based tasks. On a methodological level, this work points to the value of considering a wider range of experimental paradigms, and of the value of combining multivariate fMRI analysis with behavioral data to better contextualize interpretations of brain data.

Spatial dynamics of spontaneous activity in the developing and adult cortices.

Even in the absence of external stimuli, the brain remains remarkably active, with neurons continuously firing and communicating with each other. It is not merely random firing of individual neurons but rather orchestrated patterns of activity that propagate throughout the intricate network. Over two decades, advancements in neuroscience observation tools for hemodynamics, membrane potential, and neural calcium signals, have allowed researchers to analyze the dynamics of spontaneous activity across different spatial scales, from individual neurons to macroscale brain networks. One of the remarkable findings from these studies is that the spatial patterns of spontaneous activity in the developing brain are vastly different from those in the mature adult brain. Spatial patterns of spontaneous activity during development are essential for connection refinement between brain regions, whereas the functional role in the adult brain is still controversial. In this paper, I review the differences in spatial dynamics of spontaneous activity between developing and adult cortices. Then, I delve into the cellular mechanisms underlying spontaneous activity, especially its generation and propagation manner, to contribute to a deeper understanding of brain function and its development.

Learning on the job? Foraging strategies of juvenile versus adult Lesser black-backed gulls at their first migratory stopover.

Developing efficient foraging strategies is critical for survival, especially during the high-mortality post-fledging period in birds. This period is particularly challenging for migratory species, where juveniles must navigate unfamiliar environments with limited experience and knowledge. Our study focused on the foraging strategies of 20 juvenile lesser black-backed gulls (Larus fuscus) during the first 20 days of their initial migratory stopover. We assessed learning through changes in their spatial (re)use and activity patterns using GPS tracking data, in direct comparison with similar data collected from 38 experienced adults. Juveniles were less exploratory and spent more time foraging than adults, but showed similar spatial consistency. Over time, both juveniles and adults reduced their range distribution areas, but only adults significantly reduced their flying time. Adults exhibited space use optimization by travelling shorter distances and spending progressively more time foraging. In contrast, juveniles showed no clear evidence of spatial learning or improved foraging skills, as there was no decrease in cumulative distance travelled nor a clear pattern in time spent foraging.

The Changing Geography of Innovation: Comparing Urban, Suburban and Rural Areas

ABSTRACTUsing novel geocoded patent data for Spain, we analyze the changing spatial pattern of innovative activity at the municipal level from 1995 to 2017 and find that patenting has become increasingly concentrated in urban areas, and more so for the most disruptive innovations. We also find that even though there was a convergence trend before the 2008 Great Recession between suburban and urban core locations, it has since vanished, and stark differences continue to persist. We test for path dependent dynamics along with different determinants of the changing spatial pattern of patenting. Our granular analysis unveils a more nuanced view of the geography of innovation for urban, suburban and rural areas and for different types of inventions according to their degree of radicalness.

Spatial and temporal patterns of brain neural activity mediating human thermal sensations

This study aimed to elucidate the spatial and temporal patterns of brain neural activity that are associated with cold and hot sensations. Participants (n = 20) sat in a controlled room with their eyes closed and received local thermal stimuli to the right finger using a Peltier apparatus. The thermal stimuli were repeated 40 times using a paired-thermal stimulus paradigm, comprising a 15 s-reference stimulus (32 °C), followed by 10 s-conditioned stimuli (24 °C and 40 °C, cold and hot conditions, respectively), for which 15-channel electroencephalography (EEG) signals were continuously monitored. To identify the patterns of brain neural activity, an independent component (IC) analysis was applied to the preprocessed EEG data. The equivalent current dipole locations were estimated, followed by clustering of the ICs with a dipole residual variance of <15 %. Subsequently, event-related spectral perturbations were analyzed in each identified cluster to calculate the power changes across specific frequency ranges. The right cingulate gyrus, medial frontal gyrus, precuneus, left frontal gyrus, and cingulate gyrus were activated in both cold and hot conditions. In most activated regions, EEG power temporal changes were observed across the frequency ranges and were different between the two conditions. These results may suggest that cold and hot sensations are processed through different temporal brain neural activity patterns in overlapping brain regions.

Spatio-temporal patterns of fish acoustic communities in Western Mediterranean coralligenous reefs: optimizing monitoring through recording duration

In this study, we explored the fish acoustic community at two coralligenous sites in Sardinia (Tavolara and Santa Teresa, western Mediterranean Sea) during the summer 2023. Our goal was to understand spatial and temporal patterns of fish acoustic activity on different temporal scales to offer insights for optimizing acoustic monitoring of this crucial ecosystem. We identified seventeen distinct sound types, revealing a diverse acoustic community. Tavolara had higher acoustic richness and abundance compared to Santa Teresa, which may be attributed to site-specific factors such as habitat structure, species composition, or levels of protection. Temporal analysis revealed clear diel patterns, with certain sounds associated with nocturnal or diurnal periods, reflecting the daily rhythms of different species. The study also examined how recording duration influenced acoustic richness, finding that longer recordings (15 minutes per hour and 15 minutes per hour at night) provided a more comprehensive detection of acoustic activity. Additionally, the number of recording days required to detect species richness varied depending on the site. While extended recordings improve the likelihood of detecting rare or sporadic sounds, they also present challenges in data management and equipment maintenance. The study underscores the importance of carefully planning sampling strategies to optimize acoustic monitoring and ensure effective and sustainable ecological research in coralligenous ecosystems.

Assessing Appropriation of Space in Urban Green Spaces: Three Case Studies in Downtown Shanghai

This study investigated patterns of activities in urban green spaces (UGSs) in downtown Shanghai. UGSs are essential public infrastructure, contributing to urban sustainability, quality of life, and social cohesion. Although widely studied, there is a gap in the literature regarding Chinese UGSs when the object of study is the nature the activities. In this sense, we aimed to investigate the activities from the perspective of appropriation of the space, considered here as different from the use of space. This study addressed this by analyzing user demographics, frequency, and spatial activity patterns to assess how these activities could be classified and scored according to a varying levels of appropriation. Through a mixed-methods design based on non-participant observation and behavior mapping, the study was conducted across three comprehensive parks in Shanghai, divided into nine observation zones. The data were analyzed through descriptive statistics, IBM SPSS, and qualitative coding, revealing, as the main findings, sixty distinct activity types, a soft to moderate level of appropriation, and notable variations in demographic presence and temporal trends. This research underscores the effectiveness of observational methods, validates appropriation as an analytical category, and emphasizes the importance of structured classification systems for improving the understanding of UGSs’ socio-spatial performance and their societal role.

Enhancing prediction of human traits and behaviors through ensemble learning of traditional and novel resting-state fMRI connectivity analyses

Recent advances in cognitive neuroscience have focused on using resting-state functional connectivity (RSFC) data from fMRI scans to more accurately predict human traits and behaviors. Traditional approaches generally analyze RSFC by correlating averaged time-series data across regions of interest (ROIs) or networks, which may overlook important spatial signal patterns. To address this limitation, we introduced a novel linear regression technique that estimates RSFC by predicting spatial brain activity patterns in a target ROI from those in a seed ROI. We applied both traditional and our novel RSFC estimation methods to a large-scale dataset from the Human Connectome Project and the Brain Genomics Superstruct Project, analyzing resting-state fMRI data to predict sex, age, personality traits, and psychological task performance. To enhance prediction accuracy, we developed an ensemble learner that combines these qualitatively different methods using a weighted average approach. Our findings revealed that hierarchical clustering of RSFC patterns using our novel method displays distinct whole-brain grouping patterns compared to the traditional approach. Importantly, the ensemble model, integrating these diverse weak learners, outperformed the traditional RSFC method in predicting human traits and behaviors. Notably, the predictions from the traditional and novel methods showed relatively low similarity, indicating that our novel approach captures unique and previously undetected information about human traits and behaviors through fine-grained local spatial patterns of neural activation. These results highlight the potential of combining traditional and innovative RSFC analysis techniques to enrich our understanding of the neural basis of human traits and behaviors.

Consistent activation differences versus differences in consistent activation: Evaluating meta-analytic contrasts

Abstract Meta-analytic contrasts are a promising aspect of coordinate-based meta-analyses in neuroimaging research as they facilitate the statistical comparison of two meta-analytic results. They have been used for a multitude of comparisons, such as task conditions, cognitive processes, and groups. However, it remains to be tested how the results of meta-analytic contrasts relate to those of classic meta-analyses and vice versa. Here we present a comprehensive empirical investigation of this issue using four datasets from three different cognitive domains: working memory, working memory load, cognitive interference processing, and emotional face processing. For all four datasets, we compared the results of a standard meta-analysis across prototypical contrasts (condition A &amp;gt; condition B) reported in individual experiments with those of a contrast between two individual meta-analyses of the same conditions (meta-analysis condition A &amp;gt; meta-analysis condition B). In the meta-analytic contrasts similar brain regions as in the standard meta-analysis were found but with relatively distinct spatial activation patterns. Additionally, fewer regions were revealed in the meta-analytic contrasts, especially in areas where the conditions spatially overlapped. This can be ascribed to the loss of information on the strength of activations in meta-analytic contrasts, across which standard meta-analysis summarize. In one dataset, additional regions were found in the meta-analytic contrast, potentially due to task effects. Our results demonstrate that meta-analytic contrasts can yield similar results to standard meta-analyses but are sparser. This confirms the overall validity, but also limited ability to capture all regions found in standard meta-analyses. Notable differences observed in some cases indicate that such contrasts cannot be taken as an easy substitute for classic meta-analyses of experiment-level contrasts, warranting further research into the boundary conditions for agreement.

Resting state of human brain measured by fMRI experiment is governed more dominantly by essential mode as a global signal rather than default mode network

Resting-state of the human brain has been described by a combination of various basis modes including the default mode network (DMN) identified by fMRI BOLD signals in human brains. Whether DMN is the most dominant representation of the resting-state has been under question. Here, we investigated the unexplored yet fundamental nature of the resting-state. In the absence of global signal regression for the analysis of brain-wide spatial activity pattern, the fMRI BOLD spatiotemporal signals during the rest were completely decomposed into time-invariant spatial-expression basis modes (SEBMs) and their time-evolution basis modes (TEBMs). Contrary to our conventional concept above, similarity clustering analysis of the SEBMs from 166 human brains revealed that the most dominant SEBM cluster is an asymmetric mode where the distribution of the sign of the components is skewed in one direction, for which we call essential mode (EM), whereas the second dominant SEBM cluster resembles the spatial pattern of DMN. Having removed the strong 1/f noise in the power spectrum of TEBMs, the genuine oscillatory behavior embedded in TEBMs of EM and DMN-like mode was uncovered around the low-frequency range below 0.2 Hz.

Allometry in limb regeneration and scale-invariant patterning as the basis of normal morphogenesis from different sizes of blastemas.

Axolotl (Ambystoma mexicanum) limb regeneration begins with blastemas of various sizes, in contrast to the limb developmental process. Despite this size variation, normal limb morphology, consistent with a limb stump size, is regenerated. This outcome suggests the existence of underlying scale-invariant mechanisms. To identify such mechanisms, we examined the allometric relationships between blastema size, and Sonic Hedgehog (Shh) and Fibroblast Growth Factor 8 (Fgf8) expression patterns against limb stump size. We found that all factors showed allometric rather than isometric scaling; specifically, their relative sizes decrease with an increase in limb stump size. However, the ratio of Shh/Fgf8 signaling dominant region was nearly constant, independent of blastema/body size. Furthermore, the relative spatial patterns of cell density and proliferation activity, and the relative position of first digit formation were scale invariant in the summed Shh/Fgf8 crosstalk region. This scale-invariant nature may underlie the morphogenesis of normal limbs from different sizes of blastemas.

Spatial patterns and effects of invasive plants on soil microbial activity and diversity along river corridors

Abstract Background and aims Invasive species represent a threat to the conservation of biological systems. Riparian ecosystems are vulnerable to plant invasions, as waterflow facilitates the dispersal of plant propagules, while invasive species may subsequently impact soil, including soil microbial communities. Downstream connectivity among disparate riverine segments is expected to cause spatial continuity of abiotic and biotic components of riparian ecosystems. Methods We studied diversity of microbial communities in three headwater streams in Central Europe. Plant diversity, soil properties and soil microbiota were assessed on 20 sample plots per river. Soil microbial activity and community-level physiological profiling were used to study the soil microbial community. Results While the α-diversity of plants and soil microbiota was similar among rivers, plant communities were substantially more differentiated than microbial communities. Richness in alien and invasive plants significantly differed among rivers, which was reflected in different spatial patterns of microbial activity and diversity. A high level of spatial continuity was observed in the Kysuca river with straightened riverbed and artificial surfaces in the adjacent areas. The cover of invasive plants affects the composition of microbial functional groups of riverbed soils. Conclusion The expectation of spatial continuity of riverbed soil properties including those of soil microbiota caused by connectivity between different river segments was only partially fulfilled. Spatial continuity strongly depends on the environmental setting and stream characteristics of a particular river. The presence of invasive herbs affected the functional composition of soil microbiota but had no effect on microbial activity and diversity.

Using RSQSim to Determine Seismic Sequence in Eastern Taiwan Fault System

Abstract Understanding the spatial and temporal patterns of seismic activity, along with fault interactions in Taiwan, is essential for earthquake hazard assessment and advancing knowledge of regional tectonics. This study employs the Rate and State Earthquake Simulator (RSQSim) to simulate the eastern Taiwan fault system, integrating fault geometry from the multidisciplinary Taiwan Earthquake Model. We applied long-term simulations spanning 400,000 yr to conduct earthquake sequences and recurrence intervals on five distinct faults in eastern Taiwan: Milun fault, Longitudinal Valley fault, Central Range structure, Luyeh fault, and Taimali Coastline structure. The simulated earthquake catalogs are compared against the historical record in terms of seismicity, frequency–magnitude statistics, and recurrence patterns. The model reasonably reproduces key observational constraints, including spatial patterns, magnitude probabilities fitting a gamma distribution, and periods of quiescence resulting from fault interactions. Overall, the results demonstrate RSQSim’s potential for physics-based seismic hazard modeling and provide insights into regional seismotectonic processes in eastern Taiwan for constructing sustainable cities and communities.

Sex-specific differences in brain activity dynamics of youth with a family history of substance use disorder.

An individual's risk of substance use disorder (SUD) is shaped by a complex interplay of potent biosocial factors. Current neurodevelopmental models posit vulnerability to SUD in youth is due to an overreactive reward system and reduced inhibitory control. Having a family history of SUD is a particularly strong risk factor, yet few studies have explored its impact on brain function and structure prior to substance exposure. Herein, we utilized a network control theory approach to quantify sex-specific differences in brain activity dynamics in youth with and without a family history of SUD, drawn from a large cohort of substance-naïve youth from the Adolescent Brain Cognitive Development Study. We summarize brain dynamics by calculating transition energy, which probes the ease with which a whole brain, region or network drives the brain towards a specific spatial pattern of activation (i.e., brain state). Our findings reveal that a family history of SUD is associated with alterations in the brain's dynamics wherein: i) independent of sex, certain regions' transition energies are higher in those with a family history of SUD and ii) there exist sex-specific differences in SUD family history groups at multiple levels of transition energy (global, network, and regional). Family history-by-sex effects reveal that energetic demand is increased in females with a family history of SUD and decreased in males with a family history of SUD, compared to their same-sex counterparts with no SUD family history. Specifically, we localize these effects to higher energetic demands of the default mode network in females with a family history of SUD and lower energetic demands of attention networks in males with a family history of SUD. These results suggest a family history of SUD may increase reward saliency in males and decrease efficiency of top-down inhibitory control in females. This work could be used to inform personalized intervention strategies that may target differing cognitive mechanisms that predispose individuals to the development of SUD.

Unraveling the impact of dog‐friendly spaces on urban–wildland pumas and other wildlife

As the most widespread large carnivore on the planet, domestic dogs Canis lupus familiaris can pose a major threat to wildlife, even within protected areas (PAs). Growing human presence in PAs, coupled with increasing pet dog ownership underscores the urgency to understand the influence of dogs on wildlife activity and health. This knowledge can mitigate the adverse repercussions of recreation, optimizing PA management. Drawing on five years (2017–2021) of data from 101 camera traps in the San Francisco Bay Area, California, United States, we measured the spatiotemporal responses of puma Puma concolor, bobcat Lynx rufus, coyote Canis latrans, and mule deer Odocoileus hemionus towards domestic dogs. Additionally, using six years (2017–2022) of community science data, we explored the impacts of PA dog policies on puma sightings outside park boundaries. Puma responses provide insights into broader ecological impacts, while analyses of bobcat, coyote, and mule deer offer a comprehensive understanding of species responses to dog‐friendly spaces. Because dogs can be perceived as predators or competitors by wildlife, we anticipated shifts in spatial and temporal activity patterns in response to dogs. Wildlife responses included avoidance (bobcat, puma) or spatial overlap (mule deer) for areas with more dogs, and no effect (coyote). Mule deer may benefit from a “human shield” provided by people with dogs, while pumas and bobcats appeared more sensitive, and coyotes more adaptable. Dog policies influenced puma and mule deer temporal activity, with increased nocturnal activity in dog‐friendly PAs. Bobcat temporal activity was less variable in dog‐friendly PAs and coyote activity was similar between treatments. Outside PAs, puma sightings increased with human disturbance. Our study underscores the trade‐offs between recreation and wildlife conservation, emphasizing the need to quantify the ecological impacts of dogs. This understanding is vital for informing conservation strategies and promoting coexistence between dogs, wildlife, and protected environments.

Identification of a stress-responsive subregion of the basolateral amygdala in male rats.

The basolateral amygdala (BLA) is reliably activated by psychological stress and hyperactive in conditions of pathological stress or trauma; however, subsets of BLA neurons are also readily activated by rewarding stimuli and can suppress fear and avoidance behaviours. The BLA is highly heterogeneous anatomically, exhibiting continuous molecular and connectivity gradients throughout the entire structure. A critical gap remains in understanding the anatomical specificity of amygdala subregions, circuits, and cell types explicitly activated by acute stress and how they are dynamically activated throughout stimulus exposure. Using a combination of topographical mapping for the activity-responsive protein FOS and fiber photometry to measure calcium transients in real-time, we sought to characterize the spatial and temporal patterns of BLA activation in response to a range of novel stressors (shock, swim, restraint, predator odour) and non-aversive, but novel stimuli (crackers, citral odour). We report four main findings: (1) the BLA exhibits clear spatial activation gradients in response to novel stimuli throughout the medial-lateral and dorsal-ventral axes, with aversive stimuli strongly biasing activation towards medial aspects of the BLA; (2) novel stimuli elicit distinct temporal activation patterns, with stressful stimuli exhibiting particularly enhanced or prolonged temporal activation patterns; (3) changes in BLA activity are associated with changes in behavioural state; and (4) norepinephrine enhances stress-induced activation of BLA neurons via the ß-noradrenergic receptor. Moving forward, it will be imperative to combine our understanding of activation gradients with molecular and circuit-specificity.

Influencing Factors of Street Vitality in Historic Districts Based on Multisource Data: Evidence from China

Amid urban expansion, historic districts face challenges such as declining vitality and deteriorating spatial quality. Using the streets of Xi’an’s historical and cultural district as examples, this research utilizes multisource data, including points of interest (POIs), street view images, and Baidu heatmaps, alongside analytical techniques such as machine learning. This study explores the determinants of street vitality from the dual perspectives of its external manifestation and spatial carriers. A quantitative framework for measuring street vitality in historic districts is established, thoroughly examining the driving factors behind street vitality. Additionally, the relationship between built environment indicators and street vitality is elucidated through statistical analysis methods. The findings reveal significant, time-varying influences of these spatial carriers on human vitality, with distinct spatial distribution patterns of human activity across different times, and the significance of the influence of external representations of human vitality and various types of spatial carriers varies over time. Based on these insights, this paper proposes strategies for enhancing the vitality of historic streets, aiming to rejuvenate and sustain the diverse and dynamic energy of these districts. It provides a foundation for revitalizing the vigor of cultural heritage zones and offers strategies applicable to similar urban contexts.

Stereotyped spatiotemporal dynamics of spontaneous activity in visual cortex prior to eye-opening.

Over the course of development, functional sensory representations emerge in the visual cortex. Prior to eye-opening, modular patterns of spontaneous activity form long-range networks that may serve as a precursor for mature network organization. Although the spatial structure of these networks has been well studied, their temporal features, which may contribute to their continued plasticity and development, remain largely uncharacterized. To address this, we imaged hours of spontaneous network activity in the visual cortex of developing ferrets of both sexes utilizing a fast calcium indicator (GCaMP8m) and widefield imaging at high temporal resolution (50Hz), then segmented out spatiotemporal events. The spatial structure of this activity was highly modular, exhibiting spatially segregated active domains consistent with prior work. We found that the vast majority of events showed a clear dynamic component in which modules activated sequentially across the field of view, but only a minority of events were well-fit with a linear traveling wave. We found that spatiotemporal events occur in repeated and stereotyped motifs, reoccurring across hours of imaging. Finally, we found that the most frequently occurring single-frame spatial activity patterns were predictive of future activity patterns over hundreds of milliseconds. Together, our results demonstrate that spontaneous activity in the early developing cortex exhibits a rich spatiotemporal structure, suggesting a potential role in the maturation and refinement of future functional representations.

A novel hybrid decoding neural network for EEG signal representation

In this paper, we proposed a novel hybrid decoding model that combines the superiority of CNNs and multi-head self-attention mechanisms, called HCANN, to finely characterizing EEG features. Depthwise separable convolution with multi-scale factors efficiently decouples temporal relevant information between brain-computer interface (BCI) tasks and EEG signals. Multi-head mechanism adaptively modified for EEG focuses on brain spatial activation patterns and extracts complementary spatial representation information from multiple subspaces. The proposed HCANN decodes the intent information of EEG recorded by three BCI paradigms, including one active and two passive BCI paradigms: rapid serial visual presentation, motor imagery, and imagined speech. We evaluated HCANN by comparing with the current state-of-the-art methods. The experimental results demonstrated that HCANN can effectively decode EEG and improves classification performance for all three BCI tasks. In addition, the visualization of spatial-temporal features at different decoding stages demonstrated that the proposed HCANN gradually extracts effective features related to the BCI tasks. The code of HCANN is publicly available at https://github.com/youshuoji/HCANN.