A Review of Brain–Computer Interface-Based Language Decoding: From Signal Interpretation to Intelligent Communication

Applied Sciences, Год журнала: 2025, Номер 15(1), С. 392 - 392

Опубликована: Янв. 3, 2025

Brain–computer interface (BCI) technologies for language decoding have emerged as a transformative bridge between neuroscience and artificial intelligence (AI), enabling direct neural–computational communication. The current literature provides detailed insights into individual components of BCI systems, from neural encoding mechanisms to paradigms clinical applications. However, comprehensive perspective that captures the parallel evolution cognitive understanding technological advancement in BCI-based remains notably absent. Here, we propose Interpretation–Communication–Interaction (ICI) architecture, novel three-stage an analytical lens examining development. Our analysis reveals field’s basic signal interpretation through dynamic communication intelligent interaction, marked by three key transitions: single-channel multimodal processing, traditional pattern recognition deep learning architectures, generic systems personalized platforms. This review establishes has achieved substantial improvements regard system accuracy, latency reduction, stability, user adaptability. proposed ICI architecture bridges gap computational methodologies, providing unified evolution. These offer valuable guidance future innovations their practical application assistive contexts.

Язык: Английский

---

Representational similarity learning reveals a graded multidimensional semantic space in the human anterior temporal cortex

Imaging Neuroscience, Год журнала: 2024, Номер 2, С. 1 - 22

Опубликована: Фев. 1, 2024

Abstract Neurocognitive models of semantic memory have proposed that the ventral anterior temporal lobes (vATLs) encode a graded and multidimensional space—yet neuroimaging studies seeking brain regions structure rarely identify these areas. In simulations, we show this discrepancy may arise from crucial mismatch between theory analysis approach. Utilizing an recently formulated to investigate representations, representational similarity learning (RSL), decoded ECoG data collected vATL cortical surface while participants named line drawings common items. The results reveal graded, space encoded in neural activity across vATL, which evolves over time simultaneously expresses both broad finer-grained among animate inanimate concepts. work resolves apparent within cognition literature and, more importantly, suggests new approach discovering generally.

Язык: Английский

---

A simple clustering approach to map the human brain's cortical semantic network organization during task

NeuroImage, Год журнала: 2025, Номер unknown, С. 121096 - 121096

Опубликована: Фев. 1, 2025

Constructing task-state large-scale brain networks can enhance our understanding of the organization functions during cognitive tasks. The primary goal network partitioning is to cluster functionally homogeneous regions. However, a region often serves multiple functions, complicating process. This study proposes novel clustering method for based on specific selecting semantic representation as target function evaluate validity proposed method. Specifically, we analyzed functional magnetic resonance imaging (fMRI) data from 11 subjects, each exposed 672 concepts, and correlated this with rating related these concepts. We identified distinct concept comprehension task validated robustness through methods. found that derived multidimensional activation exhibit high reliability cross-semantic model consistency (semantic ratings word embeddings extracted GPT-2), particularly in associated functions. Moreover, exhibits significant differences resting-state task-based obtained using traditional Further analysis revealed between networks, including disparities their capabilities, information modalities they rely acquire information, varying associations general domains. introduces approach analyzing tailored establishing standard parcellation seven future research, potentially enriching complex processes neural bases.

Язык: Английский

---

ROSE: A neurocomputational architecture for syntax

Journal of Neurolinguistics, Год журнала: 2023, Номер 70, С. 101180 - 101180

Опубликована: Ноя. 21, 2023

Язык: Английский

---

Feedback signals in visual cortex during episodic and schematic memory retrieval and their potential implications for aphantasia

Neuroscience & Biobehavioral Reviews, Год журнала: 2023, Номер 152, С. 105335 - 105335

Опубликована: Июль 29, 2023

Recent findings indicate that visual feedback derived from episodic memory can be traced down to the earliest stages of processing, whereas stemming schema-related memories only reach intermediate levels in processing hierarchy. In this opinion piece, we examine these differences light 'what' and 'where' streams perception. We build upon new framework propose deficits observed aphantasics might better understood as a difference high-level along stream, rather than an impairment.

Язык: Английский

---

Parallel cognitive maps for multiple knowledge structures in the hippocampal formation

Cerebral Cortex, Год журнала: 2024, Номер 34(2)

Опубликована: Янв. 9, 2024

Abstract The hippocampal-entorhinal system uses cognitive maps to represent spatial knowledge and other types of relational information. However, objects can often be characterized by different relations simultaneously. How does the hippocampal formation handle embedding stimuli in multiple structures that differ vastly their mode timescale acquisition? Does integrate stimulus dimensions into one conjunctive map or is each dimension represented a parallel map? Here, we reanalyzed human functional magnetic resonance imaging data from Garvert et al. (2017) had previously revealed coding for newly learnt transition structure. Using adaptation analysis, found degree representational similarity bilateral hippocampus also decreased as function semantic distance between presented objects. Importantly, while both map-like localized formation, was located more posterior regions than structure thus anatomically distinct. This finding supports idea forms reflect diverse structures.

Язык: Английский

---

ChineseEEG: A Chinese Linguistic Corpora EEG Dataset for Semantic Alignment and Neural Decoding

Scientific Data, Год журнала: 2024, Номер 11(1)

Опубликована: Май 29, 2024

Abstract An Electroencephalography (EEG) dataset utilizing rich text stimuli can advance the understanding of how brain encodes semantic information and contribute to decoding in brain-computer interface (BCI). Addressing scarcity EEG datasets featuring Chinese linguistic stimuli, we present ChineseEEG dataset, a high-density complemented by simultaneous eye-tracking recordings. This was compiled while 10 participants silently read approximately 13 hours from two well-known novels. provides long-duration recordings, along with pre-processed sensor-level data embeddings reading materials extracted pre-trained natural language processing (NLP) model. As pilot derived significantly support research across neuroscience, NLP, linguistics. It establishes benchmark for decoding, aids development BCIs, facilitates exploration alignment between large models human cognitive processes. also aid into brain’s mechanisms within context language.

Язык: Английский

---

Multi‐Level Linguistic Alignment in a Dynamic Collaborative Problem‐Solving Task

Cognitive Science, Год журнала: 2024, Номер 48(1)

Опубликована: Янв. 1, 2024

Abstract Cocreating meaning in collaboration is challenging. Success often determined by people's abilities to coordinate their language converge upon shared mental representations. Here we explore one set of low‐level linguistic behaviors, alignment, that both emerges from, and facilitates, outcomes high‐level convergence. Linguistic alignment captures the ways people reuse, is, “align to,” lexical, syntactic, semantic forms others' utterances. Our focus on temporal change multi‐level as well how related communicative within a unique collaborative problem‐solving paradigm. The primary task, situated virtual educational video game, requires creative thinking between three where paths for possible solutions are highly variable. We find over time interactions marked decreasing lexical syntactic with trade‐off increasing alignment. However, greater does not translate into better team performance. Overall, these findings provide clarity role coordination complex dynamic tasks.

Язык: Английский

---

Decoding face recognition abilities in the human brain

PNAS Nexus, Год журнала: 2024, Номер 3(3)

Опубликована: Фев. 29, 2024

Abstract Why are some individuals better at recognizing faces? Uncovering the neural mechanisms supporting face recognition ability has proven elusive. To tackle this challenge, we used a multimodal data-driven approach combining neuroimaging, computational modeling, and behavioral tests. We recorded high-density electroencephalographic brain activity of with extraordinary abilities—super-recognizers—and typical recognizers in response to diverse visual stimuli. Using multivariate pattern analyses, decoded abilities from 1 s up 80% accuracy. understand subtending decoding, compared representations brains our participants those artificial network models vision semantics, as well involved human judgments shape meaning similarity. Compared recognizers, found stronger associations between early super-recognizers midlevel similarity judgments. Moreover, late semantic model Overall, these results indicate that important individual variations processing, including computations extending beyond purely processes, support differences abilities. They provide first empirical evidence for an association believe such approaches will likely play critical role further revealing complex nature idiosyncratic brain.

Язык: Английский

---

Low-frequency neural activity tracks syntactic information through semantic mediation

Brain and Language, Год журнала: 2025, Номер 261, С. 105532 - 105532

Опубликована: Янв. 8, 2025

Язык: Английский

---