A5046325089- Complex Network Analysis Techniques
- Advanced Graph Neural Networks
- Muscle activation and electromyography studies
- Functional Brain Connectivity Studies
- Cerebral Palsy and Movement Disorders
- Family and Disability Support Research
- Infant Development and Preterm Care
- Expert finding and Q&A systems
- Diverse Approaches in Healthcare and Education Studies
- Corrosion Behavior and Inhibition
- Advanced Computing and Algorithms
- Soft Robotics and Applications
- Opinion Dynamics and Social Influence
- Topic Modeling
- Concrete Corrosion and Durability
- Smart Materials for Construction
- Diabetic Foot Ulcer Assessment and Management
- Prosthetics and Rehabilitation Robotics
- Mental Health Research Topics
Hanyang University
2012-2024
The problem of signed network embedding (SNE) aims to represent nodes in a given as low-dimensional vectors. While several SNE methods based on graph convolutional networks (GCN) have been proposed, we point out that they significantly rely the assumption decades-old balance theory always holds real world. To address this limitation, propose novel GCN-based approach, named TrustSGCN, which measures trustworthiness edge signs for high-order relationships inferred by and corrects incorrect...
Mobility is a causal factor in infant development. Neural impaired Infants, e.g., born with cerebral palsy (CP), have motor disability and are at risk for further developmental delays due to lack of self-generated mobility. It possible that these infants may benefit from robot enhanced mobility where they learn drive via joystick, i.e., the comes but control motion joystick. our hypothesis such an enriched experience will minimize attaining other social childhood milestones. However,...
The corrosion risk of internal chloride and external from three different exposure conditions was evaluated. initiation detected by monitoring the galvanic current between cathode metal embedded steel. threshold determined measuring rate steel polarization technique for profiling test chloride. As result, accelerated with a cyclic wet/dry condition, compared to totally wet condition. In addition, it found that an increase drying ratio in condition resulted after initiation. level ranged 0.2...
The problem of representing nodes in a signed network as low-dimensional vectors, known embedding (SNE), has garnered considerable attention recent years. While several SNE methods based on graph convolutional networks (GCNs) have been proposed for this problem, we point out that they significantly rely the assumption decades-old balance theory always holds real-world. To address limitation, propose novel GCN-based approach, named TrustSGCN, which corrects incorrect propagation GCN by...
The goal of dynamic signed network embedding (DSNE) is to represent the nodes in a (DSN) as embeddings that preserve evolving nature conflicting relationships between nodes. While existing DSNE methods are useful for understanding polarization users diverse domains, they fail consider concept community boundary contributes network-wide and lack inductive ability due their reliance on homophily bias. To address these limitations, we propose novel method, named PolarDSN, which learns evolution...
Cerebral palsy (CP) is a disorder of movement and posture in children caused by non-progressive insult the immature brain. The characteristic features are weakness, spasticity, muscle contractures, poor motor coordination. gait patterns with CP slow, uncoordinated, unstable. Our hypothesis that these impaired will benefit from robot enhanced walkers to improve their balance, coordination, speed during gait. In addition, this experience also impact clinical scores relate functional...
The problem of representing nodes in a signed network as low-dimensional vectors, known embedding (SNE), has garnered considerable attention recent years. While several SNE methods based on graph convolutional networks (GCN) have been proposed for this problem, we point out that they significantly rely the assumption decades-old balance theory always holds real-world. To address limitation, propose novel GCN-based approach, named TrustSGCN, which corrects incorrect propagation GCN by...
본 연구는 ‘휠체어 중재 성과 측정(Wheelchair Outcome Measure: WhOM)’을 체계적으로 번역하고, 한국어판 WhOM의 내용타당도와 신뢰도를 검증할 목적으로 실시되었다. 우선 연구자 2명이 WhOM을 한국어로 재활 또는 재활공학을 전공한 검토자 3명이 번역본의 타당도를 검증하였다. 검증 결과에 따라 휠체어 측정(K-WhOM)을 완성한 후, 보조공학 임상전문가 10명을 대상으로 이해도 과정을 거쳤다. K-WhOM의 구문 전체를 46개 항목으로 구분하여 이해도를 평가한 결과, 응답자 80% 이상이 모든 항목의 3점 이상으로 표기하여 수정이 필요한 문항은 없었다. 다음으로, 신뢰도 검증을 위해 평가자 일주일 간격으로 사전-사후 검사를 실시하였다. 대상자는 척수손상인 사용자 30명이었다. 자료 분석을 급내상관계수(ICC)를 산출한 검사-재검사 및 검사자간 신뢰도가 높아 측정자료의 안정성이 확보되었다(ICC=.817~.919). 연구를 통해 추천과 적용에 사용할...