Yuanchen Wang

Dr. Yuanchen Wang

orcid

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
24 June 2024 in PLOS ONE
Verified
Journal Article
Open access
PDF file
YWYuanchen Wang
Yuanchen Wang
YGYujie Guo
Yujie Guo
ZWZiqi Wang
Ziqi Wang
LYLinzi Yu
Linzi Yu
YYYujie Yan
Yujie Yan
ZGZifan Gu
Zifan Gu
Background: In medical imaging, the integration of deep-learning-based semantic segmentation algorithms with preprocessing techniques can reduce the need for human annotation and advance disease classification. Among established preprocessing techniques, Contrast Limited Adaptive Histogram Equalization (CLAHE) has demonstrated efficacy in improving segmentation algorithms across various modalities, such as X-rays and CT. However, there remains a demand for improved contrast enhancement methods considering the heterogeneity of datasets and the various contrasts across different anatomic structures. Method: This study proposes a novel preprocessing technique, ps-KDE, to investigate its impact on deep learning algorithms to segment major organs in posterior-anterior chest X-rays. Ps-KDE augments image contrast by substituting pixel values based on their normalized frequency across all images. We evaluate our approach on a U-Net architecture with ResNet34 backbone pre-trained on ImageNet. Five separate models are trained to segment the heart, left lung, right lung, left clavicle, and right clavicle. Results: The model trained to segment the left lung using ps-KDE achieved a Dice score of 0.780 (SD = 0.13), while that of trained on CLAHE achieved a Dice score of 0.717 (SD = 0.19), p<0.01. ps-KDE also appears to be more robust as CLAHE-based models misclassified right lungs in select test images for the left lung model. The algorithm for performing ps-KDE is available at https://github.com/wyc79/ps-KDE. Discussion: Our results suggest that ps-KDE offers advantages over current preprocessing techniques when segmenting certain lung regions. This could be beneficial in subsequent analyses such as disease classification and risk stratification.

7 December 2024 in Building and Environment
Verified
Journal Article
Closed access
WTWenhao Tang
Wenhao Tang
YLYiqun Li
Yiqun Li
YWYuanchen Wang
Yuanchen Wang
WYWei Ye
Wei Ye

24 April 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
YWYuanchen Wang
Yuanchen Wang
ATAnh Tuan Tran
Anh Tuan Tran
HHHA PHAM THI HAI
HA PHAM THI HAI
TNThi Hoa Nguyen
Thi Hoa Nguyen
KSKonstantinos Stergiaropoulos
Konstantinos Stergiaropoulos
DSDirk Schwede
Dirk Schwede
As part of the CAMaRSEC research project, long-term indoor environmental measurements with accompanying occupant surveys were conducted over one year in 49 households in 15 high-rise residential apartment buildings in Hanoi, Vietnam. A comprehensive analysis of the collected data revealed differences in the indoor environment and energy consumption patterns during the operational phase of the buildings, as well as their correlation with diverse occupant behaviors. In addition, by comparing subjective thermal evaluations based on occupant surveys with predictions based on comfort models, the limitations of existing models in predicting the thermal sensations of local people were identified. Furthermore, the findings indicated that the apartment building design standard in Vietnam underestimates the thermal adaptation of occupants, which may lead to significant building performance gaps. Larger scale surveys and measurements are required to provide sufficient databases to refine local building design standards, especially for mixed-mode buildings.

13 August 2019
Verified
Conference Paper
Open access
YWYuanchen Wang
Yuanchen Wang
CLChristian Lodroner
Christian Lodroner
MMMichael Müller
Michael Müller
KSKonstantinos Stergiaropoulos
Konstantinos Stergiaropoulos
Although airflow is invisible, it has a big influence on the indoor environment. An incorrectly planned HVAC systems can lead to draught and thermal discomfort in occupied zones. Since the commissioning tests required after the installation of HVAC systems are generally performed without occupancy, the tests results do not always accurately represent the airflow that occurs during ordinary usage. The airflow needs to be continuously monitored and controlled by an intelligent HVAC system. The aim of this study is to develop a new two-dimensional airflow sensor for the monitoring of indoor airflow, which can also indicate the flow direction. Several of these sensors can be placed in a planar sensor array, by which a two-dimensional section of the flow field is created. By recording data from several of these arrays simultaneously, an image of the three-dimensional flow could be acquired. The prototype of the sensor, which is made by Hahn-Schickard Society for Applied Research is currently being validated at the Institute for Building Energetics, Thermotechnology and Energy Storage. When the development is completed, it will greatly contribute to the control strategies of HVAC systems.