Miseon Shim
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Miseon Shim has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Seung-Hwan Lee
Clinical Emotion and Cognition Research Laboratory, Inje University, Goyang, Korea
2 shared publications - Sungtaek Chung
Department of Computer Engineering, Tech University of Korea, Siheung 15073, Republic of Korea
2 shared publications - Young-Min Park
Department of Psychiatry, Ilsan Paik Hospital, Inje University College of Medicine, Goyang, Korea
2 shared publications - Eun-Gyoung Yi
NEUROPHET Inc
1 shared publication - Eunsang Jo1 shared publication
- Goomin Kwon
Clinical Emotion and Cognition Research Laboratory, Inje University, Goyang, Korea
1 shared publication
Latest Publications
- 28 February 2025
- Published byย Korean Institute of Information Technologyย inย The Journal of Korean Institute of Information Technology
- Vol.ย 23 ย (2) , 41-56
Research on AI-based Fall Detection Monitoring System using 4D Radar Imaging Sensors
๋ณธ ์ฐ๊ตฌ์์๋ ๋์์ ํจ๊ณผ์ ์ผ๋ก ๊ฒ์ถํ๊ธฐ ์ํด 4D ์ด๋ฏธ์ง ๋ ์ด๋ ์ผ์์ ์ธ๊ณต์ง๋ฅ(AI) ๊ธฐ๋ฐ์ ๋น์ ์ด ๋์ ๊ฐ์ง ์์คํ ์ ์ ์ํ์๋ค. ์ด ์์คํ ์ ๋ ์ด๋ ์ผ์๋ฅผ ํตํด ์ถ์ถํ Point Cloud ๋ฐ์ดํฐ๋ฅผ ๊ฐ๊ณตํ์ฌ ์ ์ฒด์ ์์น์ ์์ธ๋ฅผ ๋ถ์ํ๋ฉฐ, CNN ๋ชจ๋ธ์ ํ์ฉํ ์๊ธฐ, ์๊ธฐ, ๋๊ธฐ ๋ฑ์ ์์ธ๋ฅผ ๋ถ๋ฅํ ํ ๋์๊ณผ ์ฒ์ฒํ ๋๋ ๋์์ ๊ตฌ๋ณํ๊ธฐ ์ํด ์๋ ๋ฐ ์์น ๋ณํ๋ฅผ ๋น๊ตํ๋ ํ๋ณ ๊ธฐ์ค์ ์๋ฆฝํ์๋ค. ์ด์ ๋ํ ๊ฒฐ๊ณผ๋ก๋ ๋์ ๊ฐ์ง์ ํ๋ 90%, ์์ธ ๋ถ๋ฅ ์ ํ๋ 98.66%๋ฅผ ๋ฌ์ฑํ์๋ค. ๋๋ถ์ด, ์น ๊ธฐ๋ฐ ์ธํฐํ์ด์ค์ Unity ์์ง์ ํ์ฉํ ์๋ฐํ ์๋ฎฌ๋ ์ด์ ์ ํตํฉํ์ฌ ์ฌ์ฉ์ ์นํ์ ์ธ ์ค์๊ฐ ๋ชจ๋ํฐ๋ง ํ๊ฒฝ์ ์ ๊ณตํ๊ณ ์ ํ์๋ค. ํฅํ ์ฐ๊ตฌ์์๋ ๋ค์ํ ํ๊ฒฝ์์ ์ถ๊ฐ์ ์ธ ๊ฒ์ฆ์ ์ํํ๊ณ , ๋์์ ๋จ๊ณ๋ฅผ ๋์ฑ ์ธ๋ถํํ๋ ํํธ, ๋ ์ด๋ ์ผ์ ์ธ์ ์ถ๊ฐ์ ์ธ ์ผ์๋ฅผ ์ตํฉํ์ฌ ํตํฉ ํฌ์ค์ผ์ด ํ๋ซํผ์ผ๋ก ๋ฐ์ ์ํฌ ํ์๊ฐ ์๋ค.
- 28 February 2025
- Published byย Korean Institute of Information Technologyย inย The Journal of Korean Institute of Information Technology
- Vol.ย 23 ย (2) , 41-56
Research on AI-based Fall Detection Monitoring System using 4D Radar Imaging Sensors
๋ณธ ์ฐ๊ตฌ์์๋ ๋์์ ํจ๊ณผ์ ์ผ๋ก ๊ฒ์ถํ๊ธฐ ์ํด 4D ์ด๋ฏธ์ง ๋ ์ด๋ ์ผ์์ ์ธ๊ณต์ง๋ฅ(AI) ๊ธฐ๋ฐ์ ๋น์ ์ด ๋์ ๊ฐ์ง ์์คํ ์ ์ ์ํ์๋ค. ์ด ์์คํ ์ ๋ ์ด๋ ์ผ์๋ฅผ ํตํด ์ถ์ถํ Point Cloud ๋ฐ์ดํฐ๋ฅผ ๊ฐ๊ณตํ์ฌ ์ ์ฒด์ ์์น์ ์์ธ๋ฅผ ๋ถ์ํ๋ฉฐ, CNN ๋ชจ๋ธ์ ํ์ฉํ ์๊ธฐ, ์๊ธฐ, ๋๊ธฐ ๋ฑ์ ์์ธ๋ฅผ ๋ถ๋ฅํ ํ ๋์๊ณผ ์ฒ์ฒํ ๋๋ ๋์์ ๊ตฌ๋ณํ๊ธฐ ์ํด ์๋ ๋ฐ ์์น ๋ณํ๋ฅผ ๋น๊ตํ๋ ํ๋ณ ๊ธฐ์ค์ ์๋ฆฝํ์๋ค. ์ด์ ๋ํ ๊ฒฐ๊ณผ๋ก๋ ๋์ ๊ฐ์ง์ ํ๋ 90%, ์์ธ ๋ถ๋ฅ ์ ํ๋ 98.66%๋ฅผ ๋ฌ์ฑํ์๋ค. ๋๋ถ์ด, ์น ๊ธฐ๋ฐ ์ธํฐํ์ด์ค์ Unity ์์ง์ ํ์ฉํ ์๋ฐํ ์๋ฎฌ๋ ์ด์ ์ ํตํฉํ์ฌ ์ฌ์ฉ์ ์นํ์ ์ธ ์ค์๊ฐ ๋ชจ๋ํฐ๋ง ํ๊ฒฝ์ ์ ๊ณตํ๊ณ ์ ํ์๋ค. ํฅํ ์ฐ๊ตฌ์์๋ ๋ค์ํ ํ๊ฒฝ์์ ์ถ๊ฐ์ ์ธ ๊ฒ์ฆ์ ์ํํ๊ณ , ๋์์ ๋จ๊ณ๋ฅผ ๋์ฑ ์ธ๋ถํํ๋ ํํธ, ๋ ์ด๋ ์ผ์ ์ธ์ ์ถ๊ฐ์ ์ธ ์ผ์๋ฅผ ์ตํฉํ์ฌ ํตํฉ ํฌ์ค์ผ์ด ํ๋ซํผ์ผ๋ก ๋ฐ์ ์ํฌ ํ์๊ฐ ์๋ค.
- Open Access
- 1 January 2025
- Published byย Wileyย inย Depression and Anxiety
- Vol.ย 2025 ย (1)
LayerโWise Relevance Propagation Approach for Diagnosis of DrugโNaรฏve Men With Major Depressive Disorder Using RestingโState Electroencephalography
The advancement of artificial intelligence (AI) tools utilizing electroencephalography (EEG) for diagnosing major depressive disorder (MDD) has shown significant progress. However, the practical implementation of these tools is often impeded by the large amount of EEG data required for training AI models and the lack of explanations for the MDD diagnoses. This study aims to develop an interpretable deepโlearningโbased computerโaided diagnostic system for diagnosing male MDD patients using explainable AI (XAI) algorithms. The CAD system was designed to facilitate the diagnostic process by using a reduced number of EEG channels and data length while enhancing understanding of the neurophysiological characteristics of male MDD. Restingโstate EEG data were collected from 40 male MDD patients (20โ63 years) and 41 genderโmatched healthy controls (HCs, 19โ61 years). A shallow convolutional neural network (CNN; Shallow ConvNet) model was utilized to distinguish between MDD patients and HCs. Relevance scores were extracted by the layerโwise relevance propagation (LRP) method, integrated with the Shallow ConvNet, to interpret the outcomes of the deepโlearningโbased CAD system. Additionally, changes in diagnostic performance were assessed by progressively reducing the number of channels using an LRPโbased channel selection method, as well as EEG data length. Our XAIโbased CAD system showed a high diagnostic performance of 100% when using the whole 62 channels with 180โs EEG data. A relatively high diagnostic performance over 90% was retained with only five channels with 60โs EEG data. Neurophysiologically meaningful brain areas, such as frontoโcentral, centroโparietal, and occipital areas, also revealed significant differences in relevance scores extracted by the LRPโmethod between the two groups. This study successfully developed a high performance and practical XAIโbased CAD system for male MDD patients. Our developed CAD system not only achieves high diagnostic accuracy but also provides meaningful neurophysiological biomarkers for male MDD patients.
- 1 January 2025
- Published byย Wileyย inย Depression and Anxiety
- Vol.ย 2025 ย (1)
Open AccessLayerโWise Relevance Propagation Approach for Diagnosis of DrugโNaรฏve Men With Major Depressive Disorder Using RestingโState Electroencephalography
The advancement of artificial intelligence (AI) tools utilizing electroencephalography (EEG) for diagnosing major depressive disorder (MDD) has shown significant progress. However, the practical implementation of these tools is often impeded by the large amount of EEG data required for training AI models and the lack of explanations for the MDD diagnoses. This study aims to develop an interpretable deepโlearningโbased computerโaided diagnostic system for diagnosing male MDD patients using explainable AI (XAI) algorithms. The CAD system was designed to facilitate the diagnostic process by using a reduced number of EEG channels and data length while enhancing understanding of the neurophysiological characteristics of male MDD. Restingโstate EEG data were collected from 40 male MDD patients (20โ63 years) and 41 genderโmatched healthy controls (HCs, 19โ61 years). A shallow convolutional neural network (CNN; Shallow ConvNet) model was utilized to distinguish between MDD patients and HCs. Relevance scores were extracted by the layerโwise relevance propagation (LRP) method, integrated with the Shallow ConvNet, to interpret the outcomes of the deepโlearningโbased CAD system. Additionally, changes in diagnostic performance were assessed by progressively reducing the number of channels using an LRPโbased channel selection method, as well as EEG data length. Our XAIโbased CAD system showed a high diagnostic performance of 100% when using the whole 62 channels with 180โs EEG data. A relatively high diagnostic performance over 90% was retained with only five channels with 60โs EEG data. Neurophysiologically meaningful brain areas, such as frontoโcentral, centroโparietal, and occipital areas, also revealed significant differences in relevance scores extracted by the LRPโmethod between the two groups. This study successfully developed a high performance and practical XAIโbased CAD system for male MDD patients. Our developed CAD system not only achieves high diagnostic accuracy but also provides meaningful neurophysiological biomarkers for male MDD patients.
- 30 September 2024
- Published byย Korean Institute of Information Technologyย inย The Journal of Korean Institute of Information Technology
- Vol.ย 22 ย (9) , 169-184
Implementation of Smart Dumbbells using Inertial Sensors and Load Cells and Its Application Contents
๋ ธํ๋ก ์ธํ ๊ทผ๊ฐ์์ฆ์ ๊ทผ๋ ฅ ๊ฐ์๋ก ์ธํ์ฌ ์ถ์ ์ง์ ๋จ์ด๋จ๋ฆด ์ ์์ผ๋ฏ๋ก, ํนํ ๊ณ ๋ น์์ ์์ง ๊ทผ๋ ฅ ๊ฐํ๋ฅผ ์ํ ์ค์ฌ ๋ฐฉ๋ฒ์ด ํ์ํ๋ค. ๊ทผ๊ฐ์์ฆ ์๋ฐฉ๊ณผ ๊ด๋ฆฌ๋ ์ ์ฒด ๋ถํ๋ฅผ ์ค์ด๊ณ ๊ทผ์ก ์์ถ๊ณผ ์ด์์ ๋ฐ๋ณตํ๋ ์ด๋๊ธฐ๊ตฌ ์ฌ์ฉ์ด ํจ๊ณผ์ ์ด๋ค. ๋ณธ ์ฐ๊ตฌ์์๋ ์ ์ฒด์ ์์ง์์ ์ธก์ ํ๊ธฐ ์ํ IMU ์ผ์์ ์ ๋์ ์ธ ์ ๋ ฅ ์ธก์ ์ ์ํ ๋ก๋์ ์ ๊ฒฐํฉํ์ฌ, ์ฌ์ฉ์์ ๊ทผ๋ ฅ์ ๋ฐ๋ผ ๋ฌด๊ฒ๋ฅผ ์กฐ์ ํ ์ ์๋ Smart Dumbbell์ ์๋กญ๊ฒ ๊ตฌํํ์๋ค. ๋ํ, ์์ง ๊ทผ๋ ฅ์ ์ ๋์ ํ๊ฐ์ ์ ํญ์ฑ ์ด๋์ ์ํ ๊ทผ์ก ์์ถ ๋ฐ ์ด์ ์ด๋ ์ฝํ ์ธ ๋ฅผ ์ ์ํ์ฌ, ์์ง๊ทผ๋ ฅ ๊ฐํ๋ฅผ ์ํ ํตํฉ์ ์ธ ์ด๋ ํ๋ซํผ์ ์ ์ํ์๋ค. ์ ์๋ Smart Dumbbell๊ณผ ์ฝํ ์ธ ๋ฅผ ํ์ฉํ ์ด๋์ด ํ์ ๊ทผ์ก๊ตฐ์ ํ์ฑํ๋ฅผ ํจ๊ณผ์ ์ผ๋ก ์ ๋ํ์ฌ, ์์ง ๊ทผ๋ ฅ ๊ฐํ๋ฅผ ์ํ ์ค์ฌ ๋ฐฉ๋ฒ์ผ๋ก์ ์ ํฉํจ์ ํ์ธํ์๋ค.
- 30 September 2024
- Published byย Korean Institute of Information Technologyย inย The Journal of Korean Institute of Information Technology
- Vol.ย 22 ย (9) , 169-184
Implementation of Smart Dumbbells using Inertial Sensors and Load Cells and Its Application Contents
๋ ธํ๋ก ์ธํ ๊ทผ๊ฐ์์ฆ์ ๊ทผ๋ ฅ ๊ฐ์๋ก ์ธํ์ฌ ์ถ์ ์ง์ ๋จ์ด๋จ๋ฆด ์ ์์ผ๋ฏ๋ก, ํนํ ๊ณ ๋ น์์ ์์ง ๊ทผ๋ ฅ ๊ฐํ๋ฅผ ์ํ ์ค์ฌ ๋ฐฉ๋ฒ์ด ํ์ํ๋ค. ๊ทผ๊ฐ์์ฆ ์๋ฐฉ๊ณผ ๊ด๋ฆฌ๋ ์ ์ฒด ๋ถํ๋ฅผ ์ค์ด๊ณ ๊ทผ์ก ์์ถ๊ณผ ์ด์์ ๋ฐ๋ณตํ๋ ์ด๋๊ธฐ๊ตฌ ์ฌ์ฉ์ด ํจ๊ณผ์ ์ด๋ค. ๋ณธ ์ฐ๊ตฌ์์๋ ์ ์ฒด์ ์์ง์์ ์ธก์ ํ๊ธฐ ์ํ IMU ์ผ์์ ์ ๋์ ์ธ ์ ๋ ฅ ์ธก์ ์ ์ํ ๋ก๋์ ์ ๊ฒฐํฉํ์ฌ, ์ฌ์ฉ์์ ๊ทผ๋ ฅ์ ๋ฐ๋ผ ๋ฌด๊ฒ๋ฅผ ์กฐ์ ํ ์ ์๋ Smart Dumbbell์ ์๋กญ๊ฒ ๊ตฌํํ์๋ค. ๋ํ, ์์ง ๊ทผ๋ ฅ์ ์ ๋์ ํ๊ฐ์ ์ ํญ์ฑ ์ด๋์ ์ํ ๊ทผ์ก ์์ถ ๋ฐ ์ด์ ์ด๋ ์ฝํ ์ธ ๋ฅผ ์ ์ํ์ฌ, ์์ง๊ทผ๋ ฅ ๊ฐํ๋ฅผ ์ํ ํตํฉ์ ์ธ ์ด๋ ํ๋ซํผ์ ์ ์ํ์๋ค. ์ ์๋ Smart Dumbbell๊ณผ ์ฝํ ์ธ ๋ฅผ ํ์ฉํ ์ด๋์ด ํ์ ๊ทผ์ก๊ตฐ์ ํ์ฑํ๋ฅผ ํจ๊ณผ์ ์ผ๋ก ์ ๋ํ์ฌ, ์์ง ๊ทผ๋ ฅ ๊ฐํ๋ฅผ ์ํ ์ค์ฌ ๋ฐฉ๋ฒ์ผ๋ก์ ์ ํฉํจ์ ํ์ธํ์๋ค.
- Open Access
- 6 December 2023
- Published byย Korean College of Neuropsychopharmacologyย inย Clinical Psychopharmacology and Neuroscience
- Vol.ย 22 ย (3) , 451-457
Differences in Functional Connectivity between Patients with Depression with and without Nonsuicidal Self-injury
Hye-Jin Lee, Young-Min Park, Miseon Shim. Clin Psychopharmacol Neurosci 2024;22:451-7. https://doi.org/10.9758/cpn.23.1133
- 6 December 2023
- Published byย Korean College of Neuropsychopharmacologyย inย Clinical Psychopharmacology and Neuroscience
- Vol.ย 22 ย (3) , 451-457
Open AccessDifferences in Functional Connectivity between Patients with Depression with and without Nonsuicidal Self-injury
Hye-Jin Lee, Young-Min Park, Miseon Shim. Clin Psychopharmacol Neurosci 2024;22:451-7. https://doi.org/10.9758/cpn.23.1133
- Open Access
- 18 May 2023
- Published byย Korean College of Neuropsychopharmacologyย inย Clinical Psychopharmacology and Neuroscience
- Vol.ย 21 ย (4) , 742-748
Relationship between Loudness Dependence of Auditory-evoked Potentials and Suicidality
Youngjun Cho, Young-Min Park, Miseon Shim, Seung-Hwan Lee. Clin Psychopharmacol Neurosci 2023;21:742-8. https://doi.org/10.9758/cpn.23.1050
- 18 May 2023
- Published byย Korean College of Neuropsychopharmacologyย inย Clinical Psychopharmacology and Neuroscience
- Vol.ย 21 ย (4) , 742-748
Open AccessRelationship between Loudness Dependence of Auditory-evoked Potentials and Suicidality
Youngjun Cho, Young-Min Park, Miseon Shim, Seung-Hwan Lee. Clin Psychopharmacol Neurosci 2023;21:742-8. https://doi.org/10.9758/cpn.23.1050