Jamiyan Sukhbaatar

Jamiyan Sukhbaatar

Auto-generated profile, based on publicly available information

Jamiyan Sukhbaatar

National University of Mongolia

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2026 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Open access
JSJamiyan Sukhbaatar
Jamiyan Sukhbaatar
SISatoshi Imamura
Satoshi Imamura
IIIbuki Inoue
Ibuki Inoue
SMShoya Murakami
Shoya Murakami
Kazi Mahmudul HassanKazi Mahmudul Hassan
Kazi Mahmudul Hassan
Toshihisa TanakaToshihisa Tanaka
Toshihisa Tanaka
Current deep learning models for electroencephalography (EEG) are often task-specific and depend on large labeled datasets, limiting their adaptability. Although EEG foundation models seek broader applicability, many still rely on predefined multi-channel inputs, electrode-layout assumptions, or model-specific channel handling. To address these limitations, we introduce the Single-Channel Large EEG Model (SingLEM), a self-supervised foundation model whose hybrid convolutional-Transformer encoder maps each channel independently to a reusable representation capturing local and long-range temporal structure. These representations can be used individually or combined through channel-wise feature concatenation. We assembled 71 public EEG datasets comprising approximately 9,200 subjects and 357,000 single-channel hours. For leakage-controlled evaluation, downstream results were obtained with a model pretrained on 68 datasets after excluding the three source datasets underlying the six tasks. A model pretrained on all 71 datasets is provided for general reuse. Across six motor imagery and cognitive tasks under strict leave-one-subject-out (LOSO) evaluation, the leakage-controlled model with concatenated representations and a support vector machine (SVM) classifier achieved the best overall performance among the compared pretrained and classical feature-based methods. Additional classifier and subject-adapted analyses supported the robustness of its representations. These findings support single-channel self-supervised learning as a montage-flexible foundation for reusable EEG feature extraction and electrode-level spatial analysis. The source code and pretrained models are available at https://github.com/ttlabtuat/SingLEM.

21 April 2021
Verified
Book Chapter
Closed access
PDF file
JSJamiyan Sukhbaatar
Jamiyan Sukhbaatar
BZBold Zagd
Bold Zagd
NJNyamjav Jambaljav
Nyamjav Jambaljav

13 March 2022 in Физик сэтгүүл
Verified
Journal Article
Open access
PDF file
JSJamiyan S
Jamiyan S
BJBattogtokh J
Battogtokh J
TOTsendayush O
Tsendayush O
NJNyamjav J
Nyamjav J
In this paper, the statistical analysis of surface radio refractivity in Mongolia is studied. The method proposed in the recommendation of the International Telecommunication Union ITU has been used. Meteorological data derived from fifty nine weather stations which cover the most populated areas in Mongolia. A total of more than five million refractivity measurements was considered in this analysis. The result showed that the highest average values of the radio refractivity were observed in January while the lowest values were observed in April and May. The annual refractivity values were higher in the northern region and lower in the southern part of the geographical map. The monthly maximum radio refractivity value, 342 N-Units was in Zavkhan aimag in January. The lowest value was 290 N-Units in Umnugovi aimag in May. The result also shows that the seasonal refractivity variation is caused follows the climatic condition and geographical region.

18 May 2022 in Физик сэтгүүл
Verified
Journal Article
Open access
PDF file
JSJamiyan Sukhbaatar
Jamiyan Sukhbaatar
NJNyamjav Jambaljav
Nyamjav Jambaljav
BJBattogtokh Jigjidsuren
Battogtokh Jigjidsuren
Энэ ажлаар агаарын РМ2.5 тоосонцорд цаг уурын параметрүүд болон температур, чийгшил, даралт, салхины хурд хэрхэн нөлөөлж байгааг куантайль регресс арга ашиглан судлав. Куантайль регресс нь хувьсагчдын хамаарлыг том зургаар харах боломжийг олгодог. Цаг уурын параметр тус бүр нь агаарын бохирдолд хэрхэн нөлөөлж байгааг судлахаас гадна аль параметр агаарын бохирдолд илүү нөлөөлж байгааг куантайль регресс ашиглан судалсан. Судалгааны үр дүнгээс үзэхэд температур болон салхины хурд агаарын бохирдолд илүү нөлөөтэй байв. Мөн температур, салхины хурд бага үед РМ2.5 тоосонцрын түгэлтийн варианс их байсан бол температур, салхины хурд их үед варианс бага байв.