Search

Your search keyword '"Yan, Yulong"' showing total 479 results
Start Over Author "Yan, Yulong"
479 results on '"Yan, Yulong"'

7. Deep learning-based COVID-19 pneumonia classification using chest CT images: model generalizability

Author

Nguyen, Dan, Kay, Fernando, Tan, Jun, Yan, Yulong, Ng, Yee Seng, Iyengar, Puneeth, Peshock, Ron, and Jiang, Steve

Subjects
Physics - Medical Physics, Computer Science - Machine Learning, Electrical Engineering and Systems Science - Image and Video Processing
Abstract

Since the outbreak of the COVID-19 pandemic, worldwide research efforts have focused on using artificial intelligence (AI) technologies on various medical data of COVID-19-positive patients in order to identify or classify various aspects of the disease, with promising reported results. However, concerns have been raised over their generalizability, given the heterogeneous factors in training datasets. This study aims to examine the severity of this problem by evaluating deep learning (DL) classification models trained to identify COVID-19-positive patients on 3D computed tomography (CT) datasets from different countries. We collected one dataset at UT Southwestern (UTSW), and three external datasets from different countries: CC-CCII Dataset (China), COVID-CTset (Iran), and MosMedData (Russia). We divided the data into 2 classes: COVID-19-positive and COVID-19-negative patients. We trained nine identical DL-based classification models by using combinations of the datasets with a 72% train, 8% validation, and 20% test data split. The models trained on a single dataset achieved accuracy/area under the receiver operating characteristics curve (AUC) values of 0.87/0.826 (UTSW), 0.97/0.988 (CC-CCCI), and 0.86/0.873 (COVID-CTset) when evaluated on their own dataset. The models trained on multiple datasets and evaluated on a test set from one of the datasets used for training performed better. However, the performance dropped close to an AUC of 0.5 (random guess) for all models when evaluated on a different dataset outside of its training datasets. Including the MosMedData, which only contained positive labels, into the training did not necessarily help the performance on the other datasets. Multiple factors likely contribute to these results, such as patient demographics and differences in image acquisition or reconstruction, causing a data shift among different study cohorts.

Published
2021

11. Energy Conversion Efficiency of Wavy Conical Wind Energy Capture Structure

Author

ZOU Lin, YAN Yulong, TAO Fan, LIU Diwei, ZHENG Yunlong

Subjects
energy conversion, vortex-induced vibration, mass ratio, damping ratio, wavy conical structure, Engineering (General). Civil engineering (General), TA1-2040, Chemical engineering, TP155-156, Naval architecture. Shipbuilding. Marine engineering, VM1-989
Abstract

In order to improve the energy harvesting efficiency of the wind energy capture structure, this paper proposes a novel wavy conical bladeless wind energy capture structure, and establishes a mathematical model for energy conversion of the wavy conical wind energy capture structure. The Reynolds-averaged N-S equations in combination with the SST k-ω turbulence model is used to numerically simulate the vortex-induced vibration response of the energy capture structure, and analyze the effects of mass ratio and damping ratio on the vortex-induced vibration response and wind energy conversion efficiency of the wavy conical wind energy capture structure. The results show that the wavy conical energy capture structure with a mass ratio of m*=2 and a damping ratio of ζ=0.05 can obtain a wider lock-in interval and higher energy conversion efficiency. It is also found that the mass damping ratio m*ζ directly affects the energy conversion efficiency, a suitable combination of m*ζ can improve the energy conversion efficiency, with an average energy conversion efficiency of nearly 31% higher at m*ζ=0.10 than at m*ζ=0.05. The research results can provide theoretical support for the improvement of the energy conversion efficiency of bladeless wind turbines.

Published
2023
Full Text
View/download PDF

15. Development of a Real-time Indoor Location System using Bluetooth Low Energy Technology and Deep Learning to Facilitate Clinical Applications

Author

Tang, Guanglin, Yan, Yulong, Shen, Chenyang, Jia, Xun, Zinn, Meyer, Trivedi, Zipalkumar, Yingling, Alicia, Westover, Kenneth, and Jiang, Steve

Subjects
Electrical Engineering and Systems Science - Signal Processing, Computer Science - Computers and Society
Abstract

An indoor, real-time location system (RTLS) can benefit both hospitals and patients by improving clinical efficiency through data-driven optimization of procedures. Bluetooth-based RTLS systems are cost-effective but lack accuracy and robustness because Bluetooth signal strength is subject to fluctuation. We developed a machine learning-based solution using a Long Short-Term Memory (LSTM) network followed by a Multilayer Perceptron classifier and a posterior constraint algorithm to improve RTLS performance. Training and validation datasets showed that most machine learning models perform well in classifying individual location zones, although LSTM was most reliable. However, when faced with data indicating cross-zone trajectories, all models showed erratic zone switching. Thus, we implemented a history-based posterior constraint algorithm to reduce the variability in exchange for a slight decrease in responsiveness. This network increases robustness at the expense of latency. When latency is less of a concern, we computed the latency-corrected accuracy which is 100% for our testing data, significantly improved from LSTM without constraint which is 96.2%. The balance between robustness and responsiveness can be considered and adjusted on a case-by-case basis, according to the specific needs of downstream clinical applications. This system was deployed and validated in an academic medical center. Industry best practices enabled system scaling without substantial compromises to performance or cost., Comment: 20 pages, 6 figures, submitted to Physics in Medicine & Biology

Published
2019
Full Text
View/download PDF

27. Accurate Real Time Localization Tracking in A Clinical Environment using Bluetooth Low Energy and Deep Learning

Author

Iqbal, Zohaib, Luo, Da, Henry, Peter, Kazemifar, Samaneh, Rozario, Timothy, Yan, Yulong, Westover, Kenneth, Lu, Weiguo, Nguyen, Dan, Long, Troy, Wang, Jing, Choy, Hak, and Jiang, Steve

Subjects
Physics - Medical Physics, Computer Science - Machine Learning
Abstract

Deep learning has started to revolutionize several different industries, and the applications of these methods in medicine are now becoming more commonplace. This study focuses on investigating the feasibility of tracking patients and clinical staff wearing Bluetooth Low Energy (BLE) tags in a radiation oncology clinic using artificial neural networks (ANNs) and convolutional neural networks (CNNs). The performance of these networks was compared to relative received signal strength indicator (RSSI) thresholding and triangulation. By utilizing temporal information, a combined CNN+ANN network was capable of correctly identifying the location of the BLE tag with an accuracy of 99.9%. It outperformed a CNN model (accuracy = 94%), a thresholding model employing majority voting (accuracy = 95%), and a triangulation classifier utilizing majority voting (accuracy = 95%). Future studies will seek to deploy this affordable real time location system in hospitals to improve clinical workflow, efficiency, and patient safety.

Published
2017
Full Text
View/download PDF

28. Study on the Calculation of River Vertical Infiltration Based on Formula Simulation and Machine Learning.

Author

Yang, Jie, Li, Wanzi, Zuo, Rui, Wang, Jinsheng, Wang, Yunlong, and Yan, Yulong

Subjects
BACK propagation, GROUNDWATER recharge, MATHEMATICAL functions, GENETIC algorithms, MACHINE learning
Abstract

River infiltration is important to groundwater recharge. The vertical infiltration volume of rivers is an important index for studying the mutual recharge of surface water and groundwater. In this study, the factors influencing the vertical infiltration of heterogeneous sediments were identified, and a vertical infiltration model of heterogeneous sediments was constructed via mathematical functions and machine learning. This study also applied a calculation method to the calculation of tributaries in the upper reaches of the Wenyu River. The effective grain size d10 and the inhomogeneity coefficient Cu are the main controlling factors of the infiltration coefficient, and a genetic algorithm was introduced to fit a functional formula for the vertical infiltration volume based on the main controlling factors. It was found that the gradient boosting decision tree (GDBT) vertical infiltration model with the Lad function as the loss function was more effective than the back propagation neural network (BP) vertical infiltration model created with the Adam optimiser and ReLU activation function. The results of this study provide technical support for the quantitative calculation of natural sediment infiltration coefficients and principal support for the formulation of relevant standards for river ecological safety and management, which are of great theoretical significance and far‐reaching application value. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results