Yuan-Hao Huang

Prof. Yuan-Hao Huang

orcid

Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

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

Representative Publications

View All Publications
7 December 2016 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
YLYin-Yan Lin
Yin-Yan Lin
HWHau-Tieng Wu
Hau-Tieng Wu
CHChi-An Hsu
Chi-An Hsu
PHPo-Chiun Huang
Po-Chiun Huang
YHYuan-Hao Huang
Yuan-Hao Huang
YLYu-Lun Lo
Yu-Lun Lo
Physiologically, the thoracic (THO) and abdominal (ABD) movement signals, captured using wearable piezoelectric bands, provide information about various types of apnea, including central sleep apnea (CSA) and obstructive sleep apnea (OSA). However, the use of piezoelectric wearables in detecting sleep apnea events has been seldom explored in the literature. This study explored the possibility of identifying sleep apnea events, including OSA and CSA, by solely analyzing one or both the THO and ABD signals. An adaptive nonharmonic model was introduced to model the THO and ABD signals, which allows us to design features for sleep apnea events. To confirm the suitability of the extracted features, a support vector machine was applied to classify three categories - normal and hypopnea, OSA, and CSA. According to a database of 34 subjects, the overall classification accuracies were on average 75.9% ± 11.7% and 73.8% ± 4.4%, respectively, based on the cross validation. When the features determined from the THO and ABD signals were combined, the overall classification accuracy became 81.8% ± 9.4%. These features were applied for designing a state machine for online apnea event detection. Two event-by-event accuracy indexes, S and I, were proposed for evaluating the performance of the state machine. For the same database, the S index was 84.01% ± 9.06% and the I index was 77.21% ± 19.01%. The results indicate the considerable potential of applying the proposed algorithm to clinical examinations for both screening and homecare purposes.

25 October 2020 in Sensors
Verified
Journal Article
Open access
PDF file
HCHung-Chi Chang
Hung-Chi Chang
HWHau-tieng Wu
Hau-tieng Wu
PHPo-Chiun Huang
Po-Chiun Huang
HMHsi-Pin Ma
Hsi-Pin Ma
YLYu-Lun Lo
Yu-Lun Lo
YHYuan-Hao Huang
Yuan-Hao Huang
Obstructive sleep apnea/hypopnea syndrome (OSAHS) is characterized by repeated airflow partial reduction or complete cessation due to upper airway collapse during sleep. OSAHS can induce frequent awake and intermittent hypoxia that is associated with hypertension and cardiovascular events. Full-channel Polysomnography (PSG) is the gold standard for diagnosing OSAHS; however, this PSG evaluation process is unsuitable for home screening. To solve this problem, a measuring module integrating abdominal and thoracic triaxial accelerometers, a pulsed oximeter (SpO2) and an electrocardiogram sensor was devised in this study. Moreover, a long short-term memory recurrent neural network model is proposed to classify four types of sleep breathing patterns, namely obstructive sleep apnea (OSA), central sleep apnea (CSA), hypopnea (HYP) events and normal breathing (NOR). The proposed algorithm not only reports the apnea-hypopnea index (AHI) through the acquired overnight signals but also identifies the occurrences of OSA, CSA, HYP and NOR, which assists in OSAHS diagnosis. In the clinical experiment with 115 participants, the performances of the proposed system and algorithm were compared with those of traditional expert interpretation based on PSG signals. The accuracy of AHI severity group classification was 89.3%, and the AHI difference for PSG expert interpretation was 5.0±4.5. The overall accuracy of detecting abnormal OSA, CSA and HYP events was 92.3%.

22 August 2017 in IEEE Journal on Emerging and Selected Topics in Circuits and Systems
Verified
Journal Article
Closed access
CZChuan Zhang
Chuan Zhang
YHYuan-Hao Huang
Yuan-Hao Huang
FSFarhana Sheikh
Farhana Sheikh
ZWZhongfeng Wang
Zhongfeng Wang
The rapid emergence of 5G communications technology and standardization has seen an accelerated transfer of theoretical concepts to advanced development and implementation. Not only are 5G baseband signal processing algorithms becoming more important, but also the co-design and implementation of corresponding circuits, architectures, and platforms are becoming necessary due to rapid standardization of 5G communications. This timely overview paper introduces circuits and systems (CAS) for key enabling technologies for the new 5G era: massive MIMO, mmWave baseband systems, NOMA schemes, advanced channel coding, and so on. The state-of-the-art research progress in these areas is summarized for interested readers to initiate discussion on limitations of existing solutions and open research problems that are looking for innovative solutions, especially in the CAS area. We hope this paper can bridge the gap between the theoretical investigation and application implementation for 5G communications.

13 May 2016 in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
Verified
Journal Article
Closed access
JJJin-Wei Jhang
Jin-Wei Jhang
YHYuan-Hao Huang
Yuan-Hao Huang
Compressive sensing (CS) has recently become a critical technique to reduce the high computational cost of signal processing systems. One of the main signal processing modules of CS systems is the signal reconstruction processor. Orthogonal matching pursuit (OMP) is one of the main signal reconstruction algorithms because of its low complexity and high regularity compared with the greedy $l1$ algorithm. However, the main problem of an OMP-based signal reconstruction processor is its low reconstruction performance. Therefore, this paper proposed an enhanced projection-based atom selection orthogonal matching pursuit (POMP) algorithm to solve this problem. The original POMP algorithm has more favorable signal-to-reconstruction-noise ratio (SRNR) performance than the OMP algorithm, but the computational complexity of the POMP is too high to be realized in hardware. The proposed algorithm greatly reduces the computational complexity of the original POMP algorithm without any SRNR performance loss by using multiple index candidates and matrix-inversion-bypass method. The proposed reconstruction processor architecture was designed and implemented using the TSMC 90-nm 1P9M CMOS technology. The postlayout results showed that the proposed processor exhibited a lower normalized processing latency and achieved a higher SRNR of 34.9 dB compared with the processors in previous studies.

22 July 2022 in IEEE Transactions on Circuits and Systems I: Regular Papers
Verified
Journal Article
Closed access
CCChing-Te Chiu
Ching-Te Chiu
YDYu-Chun Ding
Yu-Chun Ding
WLWei-Chen Lin
Wei-Chen Lin
WCWei-Jyun Chen
Wei-Jyun Chen
SWShu-Yun Wu
Shu-Yun Wu
YHYuan-Hao Huang
Yuan-Hao Huang
Face classification is important in many applications such as surveillance, border control, and security systems. However, wide variations in environments such as insufficient light, large distances or pose angles make the task challenging. Depth sensors are added with RGB cameras for improving classification accuracy but commercial RGB-D sensors are most targeted for indoors applications. In this paper, we present and design a Chaos LiDAR depth sesnor that provides high-precision depth images through intelligent correlation processing for both indoors and outdoors applications. Our Chaos LiDAR depth sensor detects range from 2 to 40 meters with precision around 8mm at 20-meter. With the Chaos LiDAR depth as input, we design a RGB-D based face classification embedded CNN (eCNN) model for wide range applications such as dim illumination, various distances and large poses. Our Chaos LiDAR increases around 14.27% classification accuracy compared to RealSense D435i for distance from 3 to 5 meter. The eCNN face classification subsystem is implemented in Xilinx ZCU 102 and achieves 11.11 ms inference time. The eCNN engine achieves a peak throughput at 614.4 GOPS. The overall system including Chaos LiDAR, correlation and eCNN FPGA achieves face classification inference rate of 10fps.

6 May 2019 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
CCChiao-En Chen
Chiao-En Chen
YHYuan-Hao Huang
Yuan-Hao Huang
One-bit precoding is a recently proposed scheme that facilitates the use of one-bit digital-to-analog converters (DACs) to reduce the cost and power consumption in a massive antenna system. In line with this, we consider the massive multiuser multiple input multiple output (MU-MIMO) scenario and propose a lattice-reduction (LR)-aided one-bit precoding algorithm. The proposed algorithm solves the mean-square-error (MSE)-based one-bit precoder design problem by augmenting the Babai's nearest plane procedure with a newly proposed list generation algorithm. The proposed precoder contains no tuning parameters and hence avoids additional overheads for parameter tuning when applied to a practical system. Furthermore, the symbol precoding stage in our precoder is noniterative and can be implemented via distributed processing. These desirable features along with an excellent performance-complexity tradeoff demonstrated that the proposed precoder stands out as a competitive alternative in addition to the existing one-bit precoders.