Yun-Hsuan Chen

Dr. Yun-Hsuan Chen

Westlake University, Hangzhou, Zhejiang, China
orcid

Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

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

Representative Publications

View All Publications
1 September 2021 in Photoacoustics
Verified
Journal Article
Open access
XYXi Yang
Xi Yang
Yun-Hsuan ChenYun-Hsuan Chen
Yun-Hsuan Chen
FXFen Xia
Fen Xia
Mohamad SawanMohamad Sawan
Mohamad Sawan
• Summarizes photoacoustic imaging for monitoring of stroke diseases. • Focuses on the potential photoacoustic systems for human monitoring. • Reports the challenges of stroke monitoring in the human brain.

11 January 2021 in Sensors
Verified
Journal Article
Open access
PDF file
Yun-Hsuan ChenYun-Hsuan Chen
Yun-Hsuan Chen
Mohamad SawanMohamad Sawan
Mohamad Sawan
We review in this paper the wearable-based technologies intended for real-time monitoring of stroke-related physiological parameters. These measurements are undertaken to prevent death and disability due to stroke. We compare the various characteristics, such as weight, accessibility, frequency of use, data continuity, and response time of these wearables. It was found that the most user-friendly wearables can have limitations in reporting high-precision prediction outcomes. Therefore, we report also the trend of integrating these wearables into the internet of things (IoT) and combining electronic health records (EHRs) and machine learning (ML) algorithms to establish a stroke risk prediction system. Due to different characteristics, such as accessibility, time, and spatial resolution of various wearable-based technologies, strategies of applying different types of wearables to maximize the efficacy of stroke risk prediction are also reported. In addition, based on the various applications of multimodal electroencephalography–functional near-infrared spectroscopy (EEG–fNIRS) on stroke patients, the perspective of using this technique to improve the prediction performance is elaborated. Expected prediction has to be dynamically delivered with high-precision outcomes. There is a need for stroke risk stratification and management to reduce the resulting social and economic burden.

13 March 2024 in IEEE Reviews in Biomedical Engineering
Verified
Journal Article
Open access
FMFahimeh Marvi
Fahimeh Marvi
Yun-Hsuan ChenYun-Hsuan Chen
Yun-Hsuan Chen
Mohamad SawanMohamad Sawan
Mohamad Sawan
Alzheimer's disease (AD) progressively impairs the memory and thinking skills of patients, resulting in a significant global economic and social burden each year. However, diagnosis of this neurodegenerative disorder can be challenging, particularly in the early stages of developing cognitive decline. Current clinical techniques are expensive, laborious, and invasive, which hinders comprehensive studies on Alzheimer's biomarkers and the development of efficient devices for Point-of-Care testing (POCT) applications. To address these limitations, researchers have been investigating various biosensing techniques. Unfortunately, these methods have not been commercialized due to several drawbacks, such as low efficiency, reproducibility, and the lack of accurate identification of AD markers. In this review, we present diverse promising hallmarks of Alzheimer's disease identified in various biofluids and body behaviors. Additionally, we thoroughly discuss different biosensing mechanisms and the associated challenges in disease diagnosis. In each context, we highlight the potential of realizing new biosensors to study various features of the disease, facilitating its early diagnosis in POCT. This comprehensive study, focusing on recent efforts for different aspects of the disease and representing promising opportunities, aims to conduct the future trend toward developing a new generation of compact multipurpose devices that can address the challenges in the early detection of AD.

21 February 2023 in Bioengineering
Verified
Journal Article
Open access
PDF file
Tianjun WangTianjun Wang
Tianjun Wang
Yun-Hsuan ChenYun-Hsuan Chen
Yun-Hsuan Chen
Mohamad SawanMohamad Sawan
Mohamad Sawan
Motor imagery-based brain–computer interfaces (BCI) have been widely recognized as beneficial tools for rehabilitation applications. Moreover, visually guided motor imagery was introduced to improve the rehabilitation impact. However, the reported results to support these techniques remain unsatisfactory. Electroencephalography (EEG) signals can be represented by a sequence of a limited number of topographies (microstates). To explore the dynamic brain activation patterns, we conducted EEG microstate and microstate-specific functional connectivity analyses on EEG data under motor imagery (MI), motor execution (ME), and guided MI (GMI) conditions. By comparing sixteen microstate parameters, the brain activation patterns induced by GMI show more similarities to ME than MI from a microstate perspective. The mean duration and duration of microstate four are proposed as biomarkers to evaluate motor condition. A support vector machine (SVM) classifier trained with microstate parameters achieved average accuracies of 80.27% and 66.30% for ME versus MI and GMI classification, respectively. Further, functional connectivity patterns showed a strong relationship with microstates. Key node analysis shows clear switching of key node distribution between brain areas among different microstates. The neural mechanism of the switching pattern is discussed. While microstate analysis indicates similar brain dynamics between GMI and ME, graph theory-based microstate-specific functional connectivity analysis implies that visual guidance may reduce the functional integration of the brain network during MI. Thus, we proposed that combined MI and GMI for BCI can improve neurorehabilitation effects. The present findings provide insights for understanding the neural mechanism of microstates, the role of visual guidance in MI tasks, and the experimental basis for developing new BCI-aided rehabilitation systems.
1

2 June 2022 in Biosensors
Verified
Journal Article
Open access
PDF file
JWJiachen Wang
Jiachen Wang
Yun-Hsuan ChenYun-Hsuan Chen
Yun-Hsuan Chen
Jie YangJie Yang
Jie Yang
Mohamad SawanMohamad Sawan
Mohamad Sawan
To apply EEG-based brain-machine interfaces during rehabilitation, separating various tasks during motor imagery (MI) and assimilating MI into motor execution (ME) are needed. Previous studies were focusing on classifying different MI tasks based on complex algorithms. In this paper, we implement intelligent, straightforward, comprehensible, time-efficient, and channel-reduced methods to classify ME versus MI and left- versus right-hand MI. EEG of 30 healthy participants undertaking motional tasks is recorded to investigate two classification tasks. For the first task, we first propose a “follow-up” pattern based on the beta rebound. This method achieves an average classification accuracy of 59.77% ± 11.95% and can be up to 89.47% for finger-crossing. Aside from time-domain information, we map EEG signals to feature space using extraction methods including statistics, wavelet coefficients, average power, sample entropy, and common spatial patterns. To evaluate their practicability, we adopt a support vector machine as an intelligent classifier model and sparse logistic regression as a feature selection technique and achieve 79.51% accuracy. Similar approaches are taken for the second classification reaching 75.22% accuracy. The classifiers we propose show high accuracy and intelligence. The achieved results make our approach highly suitable to be applied to the rehabilitation of paralyzed limbs.

21 June 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
SSSiqi Sun
Siqi Sun
Jie YangJie Yang
Jie Yang
Yun-Hsuan ChenYun-Hsuan Chen
Yun-Hsuan Chen
JMJiaqi Miao
Jiaqi Miao
Mohamad SawanMohamad Sawan
Mohamad Sawan
Internet addiction (IA), as a new and often unrecognized psychosocial disorder, endangers people’s health and their lives. However, the common biometric analysis based on the combination of EEG signals and results of questionnaires is not quantitative, and thus difficult to ensure a specific biomarker. This work aims to develop a deep learning algorithm (no need to identify biomarkers) used for diagnosing IA and evaluating therapy efficacy. Herein, a five-layer CNN model combined with a fast Fourier transform is proposed to diagnose IA quantitatively. This algorithm is validated in the Lemon dataset by using it to process raw data, full spectral power, and alpha-beta-gamma spectral power (related to IA). In contrast to alpha-beta-gamma spectral power, the results based on full spectral power show better performance (87.59% accuracy, 88.80% sensitivity, and 86.41% specificity), which confirms that the proposed algorithm can diagnose IA without biomarkers. In addition, this proposed CNN model presents obvious advantages in processing raw data, achieving 81.1% accuracy. Such results verify that this method can contribute to the reduction of diagnosis time and be potentially used in real-time health monitoring systems. This work provides a quantitative approach to diagnose IA and evaluate therapy efficacy, as a general strategy, and can be widely used in other disorder diagnoses that affect EEG signals, such as psychiatric disorders, substance dependence, and depression.