Liang Guo

Prof. Liang Guo


Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications

26 February 2023 in Sensors
Verified
Journal Article
Open access
PDF file
MZMiao Zhang
Miao Zhang
MLMin Li
Min Li
LGLiang Guo
Liang Guo
JLJianya Liu
Jianya Liu
Cardiac and respiratory diseases are the primary causes of health problems. If we can automate anomalous heart and lung sound diagnosis, we can improve the early detection of disease and enable the screening of a wider population than possible with manual screening. We propose a lightweight yet powerful model for simultaneous lung and heart sound diagnosis, which is deployable in an embedded low-cost device and is valuable in remote areas or developing countries where Internet access may not be available. We trained and tested the proposed model with the ICBHI and the Yaseen datasets. The experimental results showed that our 11-class prediction model could achieve 99.94% accuracy, 99.84% precision, 99.89% specificity, 99.66% sensitivity, and 99.72% F1 score. We designed a digital stethoscope (around USD 5) and connected it to a low-cost, single-board-computer Raspberry Pi Zero 2W (around USD 20), on which our pretrained model can be smoothly run. This AI-empowered digital stethoscope is beneficial for anyone in the medical field, as it can automatically provide diagnostic results and produce digital audio records for further analysis.
1

XLXiaoming Lin
Xiaoming Lin
RLRuodan Lu
Ruodan Lu
LGLiang Guo
Liang Guo
BLBing Liu
Bing Liu
The objective of this study is to follow the composite theory approach to analyze the effect of social capital on self-rated mental health in rural and urban China. Our nationally representative sample includes 10,968 respondents from 130 county-level communities. Two-level random-coefficient linear regressions, which model individual and community variations in subjective mental health, were estimated by taking the hierarchical structure of the dataset into account. We found that a significant proportion of the total variations in self-rated mental health were explained at the community level. We also found an association between low contextual civic trust and poor self-rated mental health after adjusting for individual social capital and individual socioeconomic-demographic variables. The study also revealed that: (1) in rural areas a positive relationship between civic and political trust and mental health existed both at the individual and the community level, respectively; and (2) in urban areas, only political trust at the individual level contributed to better mental health. In addition, the individual and community level political participation exhibited a positive impact on mental health measures in both rural and urban China. The individual level civic participation was positively associated to the outcome variable. However, the community-level civic participation seemed to negatively impact mental health in urban area. Our findings emphasize the importance of both individual and community-level healthcare interventions in China. Finally, this study also found that human capital covariates remained important predictors of self-rated mental health status even after controlling social capital both at individual and community levels. This study suggested that the composite thesis could provide a more convincing narrative than other theories in explaining the effects of both human and social capital on health.

RLRuodan Lu
Ruodan Lu
ZWZiyi Wang
Ziyi Wang
XLXiaoming Lin
Xiaoming Lin
LGLiang Guo
Liang Guo
Sleep and work-family problems attract a great attention in the construction industry because construction professionals are usually prone to work-family conflicts and sleep problems. The objective of this study was to analyze the effect of Family-Role Overload (FRO) and Work Interference with Family (WIF) on sleep sufficiency. We also included life satisfaction as a mediator and family supportive supervision behaviors (FSSB) as a moderator. Using a sample of 193 Chinese construction professionals, we collected objectively-measured sleep sufficiency data with validated wrist actigraphies and self-reported sleep sufficiency data, FRO, WIF, life satisfaction and FSSB with questionnaires through multiple waves. Results demonstrated that FRO was negatively associated with both objectively-measured and self-reported sleep sufficiency and life satisfaction played an important mediating role in this relationship. The moderating effect of life satisfaction on the path between WIF and sleep sufficiency is trivial. In addition, no significant moderating effects of FSSB were found. More substantial policies should be taken to improve the life satisfaction and sleep sufficiency of construction professionals.

13 August 2021 in Remote Sensing
Verified
Journal Article
Open access
PDF file
SLShikun Li
Shikun Li
RLRuodan Lu
Ruodan Lu
JLJianya Liu
Jianya Liu
LGLiang Guo
Liang Guo
With the acceleration in three-dimensional (3D) high-frame-rate sensing technologies, dense point clouds collected from multiple standpoints pose a great challenge for the accuracy and efficiency of registration. The combination of coarse registration and fine registration has been extensively promoted. Unlike the requirement of small movements between scan pairs in fine registration, coarse registration can match scans with arbitrary initial poses. The state-of-the-art coarse methods, Super 4-Points Congruent Sets algorithm based on the 4-Points Congruent Sets, improves the speed of registration to a linear order via smart indexing. However, the lack of reduction in the scale of original point clouds limits the application. Besides, the coplanarity of registration bases prevents further reduction of search space. This paper proposes a novel registration method called the Super Edge 4-Points Congruent Sets to address the above problems. The proposed algorithm follows a three-step procedure, including boundary segmentation, overlapping regions extraction, and bases selection. Firstly, an improved method based on vector angle is used to segment the original point clouds aiming to thin out the scale of the initial point clouds. Furthermore, overlapping regions extraction is executed to find out the overlapping regions on the contour. Finally, the proposed method selects registration bases conforming to the distance constraints from the candidate set without consideration about coplanarity. Experiments on various datasets with different characteristics have demonstrated that the average time complexity of the proposed algorithm is improved by 89.76%, and the accuracy is improved by 5 mm on average than the Super 4-Points Congruent Sets algorithm. More encouragingly, the experimental results show that the proposed algorithm can be applied to various restrictive cases, such as few overlapping regions and massive noise. Therefore, the algorithm proposed in this paper is a faster and more robust method than Super 4-Points Congruent Sets under the guarantee of the promised quality.

22 October 2022 in Sensors
Verified
Journal Article
Open access
PDF file
SLShanshan Li
Shanshan Li
LGLiang Guo
Liang Guo
JLJianya Liu
Jianya Liu
In recent years, the focus of facial expression recognition (FER) has gradually shifted from laboratory settings to challenging natural scenes. This requires a great deal of real-world facial expression data. However, most existing real-world databases are based on European-American cultures, and only one is for Asian cultures. This is mainly because the data on European-American expressions are more readily accessed and publicly available online. Owing to the diversity of huge data, FER in European-American cultures has recently developed rapidly. In contrast, the development of FER in Asian cultures is limited by the data. To narrow this gap, we construct a challenging real-world East Asian facial expression (EAFE) database, which contains 10,000 images collected from 113 Chinese, Japanese, and Korean movies and five search engines. We apply three neural network baselines including VGG-16, ResNet-50, and Inception-V3 to classify the images in EAFE. Then, we conduct two sets of experiments to find the optimal learning rate schedule and loss function. Finally, by training with the cosine learning rate schedule and island loss, ResNet-50 can achieve the best accuracy of 80.53% on the testing set, proving that the database is challenging. In addition, we used the Microsoft Cognitive Face API to extract facial attributes in EAFE, so that the database can also be used for facial recognition and attribute analysis. The release of the EAFE can encourage more research on Asian FER in natural scenes and can also promote the development of FER in cross-cultural domains.