Kwangsub Song

Kwangsub Song

Auto-generated profile, based on publicly available information

Kwangsub Song

Department of AI Research, EXOSYSTEMS, Seongnam, Korea

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
14 October 2019 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
KSKwangsub Song
Kwangsub Song
KCKu-Young Chung
Ku-Young Chung
JCJoon-Hyuk Chang
Joon-Hyuk Chang
In this study, we propose a cuff-less 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 a smart wristwatch. Ground truth systolic BP (SBP) and diastolic BP (DBP) measurements are then obtained by a reference device, a mercury sphygmomanometer. In order to estimate the SBP and DBP, we extract feature vectors and reconstruct them through a feature selection process. Next, we design two-stage system of a stacked deep neural network (DNN)-based SBP and DBP estimation models and compare our results to those obtained using estimation techniques in the previously reported algorithms such as the polynomial regression (PR), support vector machine (SVM), artificial neural network (ANN), and deep belief network (DBN)-DNN. In order to verify the proposed algorithm against the conventional algorithms, we quantitatively compare the results in terms of mean error (ME) with standard deviation, mean absolute error (MAE) with standard deviation, Pearson correlation, box plot, and Bland-Altman plot. For this, 110 subjects contributed to the database (DB), each of which is collected three times for 20 seconds. The quantitative errors turn out lower compared to the existing methods, which shows the superiority of our approach. To further enhance the BP estimation performance for each individual user, we devise the personal adaptation algorithm for the BP estimation algorithm that yields better the BP estimates.

21 July 2017 in Sensors
Verified
Journal Article
Open access
PDF file
KCKu-Young Chung
Ku-Young Chung
KSKwangsub Song
Kwangsub Song
KSKangsoo Shin
Kangsoo Shin
JSJinho Sohn
Jinho Sohn
SCSeok Hyun Cho
Seok Hyun Cho
JCJoon-Hyuk Chang
Joon-Hyuk Chang
Polysomnography (PSG) is considered as the gold standard for determining sleep stages, but due to the obtrusiveness of its sensor attachments, sleep stage classification algorithms using noninvasive sensors have been developed throughout the years. However, the previous studies have not yet been proven reliable. In addition, most of the products are designed for healthy customers rather than for patients with sleep disorder. We present a novel approach to classify sleep stages via low cost and noncontact multi-modal sensor fusion, which extracts sleep-related vital signals from radar signals and a sound-based context-awareness technique. This work is uniquely designed based on the PSG data of sleep disorder patients, which were received and certified by professionals at Hanyang University Hospital. The proposed algorithm further incorporates medical/statistical knowledge to determine personal-adjusted thresholds and devise post-processing. The efficiency of the proposed algorithm is highlighted by contrasting sleep stage classification performance between single sensor and sensor-fusion algorithms. To validate the possibility of commercializing this work, the classification results of this algorithm were compared with the commercialized sleep monitoring device, ResMed S+. The proposed algorithm was investigated with random patients following PSG examination, and results show a promising novel approach for determining sleep stages in a low cost and unobtrusive manner.

26 April 2021 in Applied Sciences
Verified
Journal Article
Open access
PDF file
KSKwangsub Song
Kwangsub Song
Tae-Jun ParkTae-Jun Park
Tae-Jun Park
JCJoon-Hyuk Chang
Joon-Hyuk Chang
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 the features in a multi-dimensional feature vector to describe the correlated real-valued random variables successfully. To verify the proposed algorithm against the conventional algorithm, we compare the results in terms of mean error (ME) with standard deviation and Pearson correlation using 110 subjects contributed to the database (DB) which includes the systolic BP (SBP), diastolic BP (DBP), photoplethysmography (PPG) signal, and electrocardiography (ECG) signal. For each subject, 3 times (or 6 times) measurements are accomplished in which the PPG and ECG signals are recorded for 20 s. And, to compare with the performance of the BP estimation (BPE) using the data augmentation algorithms, we train the BPE model using the two-stage system, called the stacked NN. Since the proposed algorithm can express properly the correlation between the features than the conventional algorithm, the errors turn out lower compared to the conventional algorithm, which shows the superiority of our approach.

16 August 2024 in IEEE Transactions on Neural Systems and Rehabilitation Engineering
Verified
Journal Article
Open access
KSKwangsub Song
Kwangsub Song
HSHyung Eun Shin
Hyung Eun Shin
WPWookhyun Park
Wookhyun Park
DLDaehyun Lee
Daehyun Lee
JJJaeyoung Jang
Jaeyoung Jang
CWChang Won Won
Chang Won Won
Sarcopenia is a comprehensive degenerative disease with the progressive loss of skeletal muscle mass with age, accompanied by the loss of muscle strength and muscle dysfunction. Individuals with unmanaged sarcopenia may experience adverse outcomes. Periodically monitoring muscle function to detect muscle degeneration caused by sarcopenia and treating degenerated muscles is essential. We proposed a digital biomarker measurement technique using surface electromyography (sEMG) with electrical stimulation and wearable device to conveniently monitor muscle function at home. When motor neurons and muscle fibers are electrically stimulated, stimulated muscle contraction signals (SMCSs) can be obtained using an sEMG sensor. As motor neuron activation is important for muscle contraction and strength, their action potentials for electrical stimulation represent the muscle function. Thus, the SMCSs are closely related to muscle function, presumptively. Using the SMCSs data, a feature vector concatenating spectrogram-based features and deep learning features extracted from a convolutional neural network model using continuous wavelet transform images was used as the input to train a regression model for measuring the digital biomarker. To verify muscle function measurement technique, we recruited 98 healthy participants aged 20–60 years including 48 [49%] men who volunteered for this study. The Pearson correlation coefficient between the label and model estimates was 0.89, suggesting that the proposed model can robustly estimate the label using SMCSs, with mean error and standard deviation of -0.06 and 0.68, respectively. In conclusion, measuring muscle function using the proposed system that involves SMCSs is feasible.

1 March 2023 in IEEE Transactions on Neural Systems and Rehabilitation Engineering
Verified
Journal Article
Open access
KSKwangsub Song
Kwangsub Song
SCSangui Choi
Sangui Choi
JSJin-Hong Shin
Jin-Hong Shin
WSWoo-Hyeon Son
Woo-Hyeon Son
HPHyuntae Park
Hyuntae Park
NPNam-Jong Paik
Nam-Jong Paik
We propose a digital biomarker related to muscle strength and muscle endurance (DB/MS and DB/ME) for the diagnosis of muscle disorders based on a multi-layer perceptron (MLP) using stimulated muscle contraction. When muscle mass is reduced in patients with muscle-related diseases or disorders, measurement of DBs that are related to muscle strength and endurance is needed to suitably recover damaged muscles through rehabilitation training. Furthermore, it is difficult to measure DBs using traditional methods at home without an expert; moreover, the measuring equipment is expensive. Additionally, because traditional measurements depend on the subject’s volition, we propose a DB measurement technique that is unaffected by the subject’s volition. To achieve this, we employed an impact response signal (IRS) based on multi-frequency electrical stimulation (MFES) using an electromyography sensor. The feature vector was then extracted using the signal. Because the IRS is obtained from stimulated muscle contraction, which is caused by electrical stimulation, it provides biomedical information about the muscle. Finally, to estimate the strength and endurance of the muscle, the feature vector was passed through the DB estimation model learned through the MLP. To evaluate the performance of the DB measurement algorithm, we collected the MFES-based IRS database for 50 subjects and tested the model with quantitative evaluation methods using the reference for the DB. The reference was measured using torque equipment. The results were compared with the reference, indicating that it is possible to check for muscle disorders which cause decreased physical performance using the proposed algorithm.

1 January 2024 in Brain & Neurorehabilitation
Verified
Journal Article
Open access
PDF file
KSKwangsub Song
Kwangsub Song
HPHae-Yeon Park
Hae-Yeon Park
SCSangui Choi
Sangui Choi
SSSeungyup Song
Seungyup Song
HRHanee Rim
Hanee Rim
SISun Im
Sun Im
Song K, et al. Brain Neurorehabil. 2024 Jun;17(2):e12. https://doi.org/10.12786/bn.2024.17.e12