A5101980109- Non-Invasive Vital Sign Monitoring
- Advanced Sensor and Energy Harvesting Materials
- Stroke Rehabilitation and Recovery
- Speech Recognition and Synthesis
- Nutrition and Health in Aging
- Muscle activation and electromyography studies
- Obstructive Sleep Apnea Research
- EEG and Brain-Computer Interfaces
- Music and Audio Processing
- Body Composition Measurement Techniques
- Hemodynamic Monitoring and Therapy
- Heart Rate Variability and Autonomic Control
- ECG Monitoring and Analysis
- Speech and Audio Processing
- GNSS positioning and interference
- Natural Language Processing Techniques
- Flow Measurement and Analysis
- Sleep and Work-Related Fatigue
- Neuroscience and Neural Engineering
- Hearing Loss and Rehabilitation
- Cerebral Palsy and Movement Disorders
- Physical Education and Gymnastics
Hanyang University
2016-2021
In this article, we propose a cuffless blood pressure (BP) estimation technique based on deep learning for smart wristwatches. Photoplethysmography (PPG) and electrocardiography (ECG) signals are first collected from the sensors installed at wristwatch. Ground-truth systolic BP (SBP) diastolic (DBP) measurements then obtained by reference device, mercury sphygmomanometer. order to estimate SBP DBP, extract feature vectors reconstruct them through selection process. Next, design two-stage...
Sarcopenia is a rapidly rising health concern in the fast-aging countries, but its demanding diagnostic process hurdle for making timely responses and devising active strategies. To address this, our study developed evaluated novel sarcopenia diagnosis system using Stimulated Muscle Contraction Signals (SMCS), aiming to facilitate rapid accessible community settings. We recruited 199 adults from Wonju Severance Christian Hospital between July 2022 October 2023. SMCS data were collected...
Polysomnography (PSG) is considered as the gold standard for determining sleep stages, but due to obtrusiveness of its sensor attachments, stage classification algorithms using noninvasive sensors have been developed throughout years. However, previous studies not yet proven reliable. In addition, most products are designed healthy customers rather than patients with disorder. We present a novel approach classify stages via low cost and noncontact multi-modal fusion, which extracts...
Sarcopenia is a comprehensive degenerative disease with the progressive loss of skeletal muscle mass age, accompanied by strength and dysfunction. Individuals unmanaged sarcopenia may experience adverse outcomes. Periodically monitoring function to detect degeneration caused treating degenerated muscles essential. We proposed digital biomarker measurement technique using surface electromyography (sEMG) electrical stimulation wearable device conveniently monitor at home. When motor neurons...
Sleep quality, which is an undervalued health issue that affects well-being and daily lives, checked through the polysomnography (PSG), considered as gold standard for determining sleep stages. Due to obtrusiveness of its sensor attachments, recent stage classification algorithms using noninvasive sensors have been developed commercialized. However, newly devices used in previous studies lacked detection non-rapid eye movement rapid sleep, are known be correlated with development disorders,...
In this paper, we propose a novel data augmentation technique employing multivariate Gaussian distribution (DA-MGD) for neural network (NN)-based blood pressure (BP) estimation, which incorporates the relationship between features in multi-dimensional feature vector to describe correlated real-valued random variables successfully. To verify proposed algorithm against conventional algorithm, compare results terms of mean error (ME) with standard deviation and Pearson correlation using 110...
We propose a digital biomarker related to muscle strength and endurance (DB/MS DB/ME) for the diagnosis of disorders based on multi-layer perceptron (MLP) using stimulated contraction. When mass is reduced in patients with muscle-related diseases or disorders, measurement DBs that are needed suitably recover damaged muscles through rehabilitation training. Furthermore, it difficult measure traditional methods at home without an expert; moreover, measuring equipment expensive. Additionally,...
In this paper, we propose an artificial intelligence (AI)-based sarcopenia diagnostic technique for stroke patients utilizing bio-signals from the neuromuscular system. Handgrip, skeletal muscle mass index, and gait speed are prerequisite components diagnoses. However, measurement of these parameters is often challenging most hemiplegic patients. For reasons, there imperative need to develop a that requires minimal volitional participation but nevertheless still assesses changes related...
Sarcopenia, a condition characterized by muscle weakness and mass loss, poses significant risks of accidents complications. Traditional diagnostic methods often rely on physical function measurements like handgrip strength which can be challenging for affected patients, including those with stroke. To address these challenges, we propose novel sarcopenia diagnosis model utilizing stimulated contraction signals captured via wearable devices. Our approach achieved impressive results, an...
The principal aim of this paper is to present a novel speech transmission system that conveys between an actuator in wearable wristwatch and the ear bone user through finger. If individual wears smart watch equipped with can play sent via communication lines, vibrations propagate from fingertips human tissue bone. When places his or her finger into their ear, conducted be registered heard. While listening finger-conducted speech, sounds are muffled, significantly degrading intelligibility...
In this paper, we present the experimental study based on filtering techniques to extract essential vital signals such respiration rate (RR) using continuous wave (CW) Doppler radar sensor. Due fact that CW offers very high sensitivity towards minor movements, technology, various were introduced and detection was compared reference devices conclude leading method for detection.
In this paper, multi speaker speech synthesis using embedding is proposed. The proposed model based on Tacotron network, but post-processing network of the modified with dilated convolution layers, which used in Wavenet architecture, to make it more adaptive speech. can generate voice only one neural by giving auxiliary input data, embedding, network. This shows successful result for generating two speaker's voices without significant deterioration quality.
In this paper, we propose the long–short-term memory (LSTM)-based voluntary and non-voluntary (VNV) muscle contraction classification algorithm in an electrical stimulation (ES) environment. order to measure quality (MQ), employ signal, which occurs by ES. However, if patient movement, such as contractionm, during ES, electromyography (EMG) sensor captures VNV signals. addition, signal is a noise component MQ measurement technique, uses only For reason, need classify mixed EMG signal. when...