https://scholar.dgist.ac.kr/handle/20.500.11750/12478 2026-04-05T15:10:43Z https://scholar.dgist.ac.kr/handle/20.500.11750/59261 Title: EFRM: A Multimodal EEG–fNIRS Representation-learning Model for few-shot brain-signal classification Author(s): Jung, Euijin; An, Jinung Abstract: Recent advances in brain signal analysis highlight the need for robust classifiers that can be trained with minimal labeled data. To meet this demand, transfer learning has emerged as a promising strategy: large-scale unlabeled data is used to train pre-trained models, which are later adapted with minimal labeled data. However, while most existing transfer learning studies focus primarily on electroencephalography (EEG) signals, their generalization to other brain signal modalities such as functional near-infrared spectroscopy (fNIRS) remains limited. To address this issue, we propose a multimodal representation model compatible with EEG-only, fNIRS-only, and paired EEG–fNIRS datasets. The proposed method consists of two stages: a pre-training stage that learns both modality-specific and shared representations across EEG and fNIRS, followed by a transfer learning stage adapted to specific downstream tasks. By leveraging the shared domain across EEG and fNIRS, our model outperforms single-modality approaches. We constructed pre-training datasets containing approximately 1250 h of brain signal recordings from 918 participants. Unlike previous multimodal approaches that require both EEG and fNIRS data for training, our method enables adaptation to single-modality datasets, enhancing flexibility and practicality. Experimental results demonstrate that our method achieves competitive performance in comparison with state-of-the-art supervised learning models, even with minimal labeled data. Our method also outperforms previously pre-trained models, showing especially significant improvements in fNIRS classification performance. 2025-11-30T15:00:00Z https://scholar.dgist.ac.kr/handle/20.500.11750/58975 Title: Trained by demonstration humanoid robot controlled via a BCI system for telepresence Author(s): Saduanov, Batyrkhan; Alizadeh, Tohid; An, Jinung; Abibullaev, Berdakh Abstract: Onerous life of paralyzed people is a substantial problem of the world society and improving their life quality would be a great achievement. This paper proposes a solution in this regard based on telepresence, where a patient perceives and interacts with a world through an embodiment of a robot controlled by a Brain-Computer Interface (BCI) system. The proposed approach brings together two leading techniques: Programming by Demonstration and BCI. Several tasks could be learned by the robot observing someone performing the function. The end user would issue commands to the robot, using a BCI system, concerning its movement and the tasks to be performed. An experiment is designed and conducted, verifying the applicability of the proposed approach. © 2018 IEEE. 2018-01-16T15:00:00Z https://scholar.dgist.ac.kr/handle/20.500.11750/58541 Title: 사용자의 뇌에 대한 전류 자극 치료를 수행하기 위한 전자 장치 및 이의 제어 방법 Author(s): 안진웅 Abstract: 전자 장치 및 전자 장치의 제어 방법이 개시된다. 특히, 전자 장치는 사용자에게 통증을 유발하는 자극에 대한 사용자의 반응을 기록하기 위한 사용자 입력부, 자극에 대한 사용자의 뇌 신호를 복수의 채널 별로 획득하기 위한 센서부, 사용자의 뇌를 구분하는 복수의 영역에 전류 자극을 제공하기 위한 전류 자극부, 신경망 모델에 대한 정보를 저장하는 메모리 및 프로세서를 포함하고, 프로세서는 본 개시에 따른 전자 장치는 센서부를 통해 자극에 대한 복수의 채널 별 뇌 신호를 획득하고, 사용자 입력부를 통해 자극에 대한 사용자의 반응을 기록하기 위한 사용자 입력을 수신하며, 획득된 뇌 신호를 신경망 모델에 입력하여, 복수의 영역 중 통증에 관여하는 적어도 하나의 영역을 식별하고, 자극에 대한 사용자의 반응에 대한 정보를 기 정의된 통증 수준 모델에 매핑하여, 자극에 대한 사용자의 통증 수준을 식별하며, 전류 자극부를 통해, 식별된 통증 수준에 대응되는 전류 자극을 식별된 적어도 하나의 영역에 제공할 수 있다. https://scholar.dgist.ac.kr/handle/20.500.11750/58409 Title: fNIRS Foundation Model for Few-Shot based fNIRS Classification Author(s): Jung, Euijin; Lee, Hyunmin; An, Jinung Abstract: Functional near-infrared spectroscopy (fNIRS) is a non-invasive technique with significant potential for applications in brain-computer interfaces (BCIs) including mental health diagnostics and cognitive state monitoring. However, the reliance on large labeled datasets for high-performing classification methods poses a critical challenge, given the time-consuming and resource-intensive nature of fNIRS data collection. To address this, we propose a novel foundation model for fNIRS data based on a self-supervised masked autoencoder framework. The proposed method enables efficient pre-training on unlabeled data, reducing the dependence on labeled datasets while maintaining robust performance for downstream tasks. Experimental results demonstrate that the proposed model achieves performance comparable to supervised learning approaches while requiring only one-third of the labeled training data. It consistently outperforms state-of-the-art self-supervised models in both linear probing and fine-tuning settings. Moreover, ablation studies show that a larger masking size aligns with the low-frequency nature of fNIRS signals, enabling the model to capture broader patterns and further enhance classification accuracy. These findings validate the proposed method as an effective and scalable solution for fNIRS-based classification tasks. © 2025 IEEE. 2025-02-23T15:00:00Z