Seo Seo

Dr. Seo Seo


Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
6 January 2023 in Sensors
Verified
Journal Article
Open access
PDF file
KTKeshav Thapa
Keshav Thapa
SSSeo Seo
Seo Seo
SYSung-Hyun Yang
Sung-Hyun Yang
KKKyong Kim
Kyong Kim
The study of human activity recognition concentrates on classifying human activities and the inference of human behavior using modern sensing technology. However, the issue of domain adaptation for inertial sensing-based human activity recognition (HAR) is still burdensome. The existing requirement of labeled training data for adapting such classifiers to every new person, device, or on-body location is a significant barrier to the widespread adoption of HAR-based applications, making this a challenge of high practical importance. We propose the semi-supervised HAR method to improve reconstruction and generation. It executes proper adaptation with unlabeled data without changes to a pre-trained HAR classifier. Our approach decouples VAE with adversarial learning to ensure robust classifier operation, without newly labeled training data, under changes to the individual activity and the on-body sensor position. Our proposed framework shows the empirical results using the publicly available benchmark dataset compared to state-of-art baselines, achieving competitive improvement for handling new and unlabeled activity. The result demonstrates SAA has achieved a 5% improvement in classification score compared to the existing HAR platform.

28 February 2023 in Journal of Integrative Neuroscience
Verified
Journal Article
Open access
PDF file
SJSung Ho Jang
Sung Ho Jang
KKKyong Kim
Kyong Kim
SSSeo Seo
Seo Seo
Objectives: Using diffusion tensor tractography (DTT), we demonstrated the spinothalamic tract (STT) injury in patients with central pain following whiplash injury. Our primary hypothesis is that fractional anisotropy (FA) and tract volume (TV) of the STT in injured people differ from non-injured people. Our secondary hypothesis is that the direction of the collision results in a different type of injury. Methods: Nineteen central pain patients following whiplash injury and 19 normal control subjects were recruited. The STT was reconstructed by the DTT, the FA and TV of the STT were measured. In addition, different characteristics of the STT injury according to the collision direction were investigated. Results: The FA value did not differ significantly between the patient and control groups (p > 0.05). However, the significantly lower value of the TV was observed in patient group than the control group (p < 0.05). The onset of central pain was significantly delayed (13.5 days) in patients who were involved in a frontal collision, compared to patients with rear-end collision (0.6 days) (p < 0.05). In contrast, the Visual Analogue Scale was higher in the patients with rear-end collision (p < 0.05). Conclusions: We found the STT injury mild traumatic brain injury (TBI) who suffered central pain after whiplash injury, using DTT. In addition, we demonstrated different characteristics of the STT injury according to the collision direction. We believe that injury of the STT would be usefully detected by DTT following whiplash injury.