Article
Engineering, Industrial
Ye Tian-yuan, Liu Lin-lin, Pang He-wei, Zhou Yuan-zi
Summary: This paper extends the basic GO methodology to support the modeling and analysis of multi-state linear and circular consecutive-k-out-of-n systems. It defines new operators, provides their multi-state logic semantics and mapping rules to Bayesian networks, and presents a programmable process for transforming the extended model into BN and calculating reliability.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2023)
Article
Automation & Control Systems
Yi Jin, Yunxia Chen, Zhendan Lu, Qingyuan Zhang, Rui Kang
Summary: This article introduces an impedance network model to characterize the cascading failure of circuits, proposes a current-flow redistribution method to determine the effects of failed components on remaining components, and introduces a health confidence value to assess the health status of the circuit.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2021)
Article
Computer Science, Artificial Intelligence
Mina Akhavan, Mohammad Vahid Sebt, Mariam Ameli
Summary: This paper introduces a Bayesian network modeling framework for calculating project risk, providing a powerful tool for analyzing risk scenarios and their impact on project success.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Chemistry, Multidisciplinary
Matteo Miani, Matteo Dunnhofer, Fabio Rondinella, Evangelos Manthos, Jan Valentin, Christian Micheloni, Nicola Baldo
Summary: This study utilizes Artificial Neural Networks to predict Marshall test results, stiffness modulus, and air voids data of different bituminous mixtures. A novel approach for identifying the optimal ANN structure objectively and semi-automatically has been introduced. Results show that optimizing ANN hyperparameters using Bayesian optimization effectively improves model performance.
APPLIED SCIENCES-BASEL
(2021)
Article
Engineering, Mechanical
Julio Ariel Duenas Santana, Jesus Luis Orozco, Daniel Furka, Samuel Furka, Yinet Caridad Boza Matos, Dainelys Febles Lantigua, Amelia Gonzalez Miranda, Mary Carla Barrera Gonzalez
Summary: In recent years, domino effect accidents and prediction have been intensively studied due to their serious impact on people, the environment, economy, and society. A novel method for determining failure probability, considering various factors, has been proposed. A Bayesian network is used to quantify synergic effects, showing a high likelihood of domino effect occurrence.
ENGINEERING FAILURE ANALYSIS
(2021)
Article
Multidisciplinary Sciences
Hasini Nakulugamuwa Gamage, Madhu Chetty, Suryani Lim, Jennifer Hallinan
Summary: In this paper, a new hybrid fuzzy gene regulatory network inference model called MICFuzzy is proposed, which aggregates the effects of Maximal Information Coefficient (MIC) using information theory and fuzzy concepts. The model filters relevant genes using the MIC component in the preprocessing stage to reduce computational burden. By determining the regulatory effect of identified activator-repressor gene pairs, the model can determine the expression levels of target genes. Experimental results on DREAM3, DREAM4, and SOS gene expression datasets demonstrate that MICFuzzy outperforms other state-of-the-art methods in terms of accuracy and efficiency.
Article
Engineering, Industrial
Ding Zhang, Qiang Liu, Hong Yan, Min Xie
Summary: The accurate analytical model of Bayesian network is crucial for depicting endogenous failure mechanisms in the digital twin used in collaborative maintenance services for manufacturing systems. The connections between nodes in Bayesian networks correspond to linear, bilinear, or multilinear mappings of finite-state variables.
JOURNAL OF MANUFACTURING SYSTEMS
(2021)
Article
Engineering, Industrial
Yongjin Guo, Mingjun Zhong, Chao Gao, Hongdong Wang, Xiaofeng Liang, Hong Yi
Summary: The study proposes a reliability analysis model for dynamic systems with common cause failures based on discrete-time Bayesian networks, which investigates the impact of common cause failures on system reliability and calculates reliability through a Bayesian inference mechanism. The model is applied to a digital safety-level distributed control system in nuclear power plants, demonstrating the effectiveness and feasibility of the method.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2021)
Article
Ergonomics
Yanchao Song, Siyuan Kou, Chen Wang
Summary: This study developed risk indicators based on prior violation and crash records of drivers and roadways, and utilized a Bayesian network approach to explore the complex interactions among all contributing factors in crash severity. Results showed that prior crash/violation experiences of road users and roadways were important risk indicators, and certain variable combinations had enhanced impacts on severity outcome.
JOURNAL OF SAFETY RESEARCH
(2021)
Article
Computer Science, Artificial Intelligence
Kui Yu, Mingzhu Cai, Xingyu Wu, Lin Liu, Jiuyong Li
Summary: This article presents a novel multilabel feature selection algorithm, M2LC, which addresses the correlations between features and labels through local causal structure learning. The algorithm considers three types of feature relationships simultaneously and corrects false discoveries through two error-correction subroutines. Experimental results demonstrate the effectiveness of M2LC in multilabel feature selection tasks.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Engineering, Environmental
Song S. Qian, Jonathan G. Kennen, Jason May, Mary C. Freeman, Thomas F. Cuffney
Summary: The study utilizes a continuous-variable Bayesian network model to predict the impact of future climate change and watershed development on stream ecosystem indicators, showing different ecological condition trajectories predicted by different climate models but similar worst-case scenarios. This established modeling approach combines mechanistic understanding with field data to predict management relevant variables across a heterogeneous landscape.
Article
Economics
Xiaoyi Han, Chih-Sheng Hsieh, Stanley I. M. Ko
Summary: This study proposes a new modeling approach to analyze how social networks evolve over time and impact individual economic activity, by combining two well-known models in the field. The model effectively addresses issues related to network formation and activity interactions, providing insights into the dynamic nature of social networks.
JOURNAL OF BUSINESS & ECONOMIC STATISTICS
(2021)
Article
Engineering, Industrial
Xiaohu Zheng, Wen Yao, Yingchun Xu, Ning Wang
Summary: This paper proposes a BN block to process nodes with common cause failure (CCF) and presents an algorithm to reduce the memory storage requirements of BN reliability modeling. By deriving the intermediate inference factor constructing rules, a multistate BN compression inference algorithm under CCF is proposed. Two engineering cases are used to validate the performance of the proposed algorithms. The results show that the algorithms can significantly decrease the memory storage requirements of BN modeling and accurately analyze the reliability of complex multistate systems with CCF.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2024)
Article
Biochemistry & Molecular Biology
Asher Moshe, Elya Wygoda, Noa Ecker, Gil Loewenthal, Oren Avram, Omer Israeli, Einat Hazkani-Covo, Itsik Pe'er, Tal Pupko
Summary: This study developed a probabilistic approach to infer genome rearrangement rate parameters and used an Approximate Bayesian Computation framework for inference. The method can help elucidate the role of genome rearrangement in evolution and simulate genomes with empirical dynamics.
MOLECULAR BIOLOGY AND EVOLUTION
(2022)
Article
Computer Science, Artificial Intelligence
Zhicheng Liu, Jun Cao, Renjie Xie, Junyan Yang, Qiao Wang
Summary: Understanding the value of built environment and house characteristics in the housing market is crucial for urban planners and real estate developers. This paper proposes a probabilistic approach to model the submarket effect, incorporating a Bayesian network to capture the full scope of this effect. Experimental results in a metropolis in eastern China demonstrate the effectiveness of the proposed modeling method.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2021)
Article
Oncology
Maria Thor, Annemarie F. Shepherd, Isabel Preeshagul, Michael Offin, Daphna Y. Gelblum, Abraham J. Wu, Aditya Apte, Charles B. Simone, Matthew D. Hellmann, Andreas Rimner, Jamie E. Chaft, Daniel R. Gomez, Joseph O. Deasy, Narek Shaverdian
Summary: This study found that baseline differences in peripheral immune cell populations are associated with disease outcomes in NSCLC patients treated with cCRT and ICI. The pre-cCRT neutrophil-to-lymphocyte ratio (NLR) was the strongest predictor for progression-free survival (PFS).
RADIOTHERAPY AND ONCOLOGY
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Kyung-Wook Jee, Thomas Bortfeld, Issam El Naqa, Lei Dong
Summary: This special issue collects and presents research and developmental works in the forefront of particle radiotherapy (pRT) investigations. It focuses on seven subfields that represent recent advances in medical physics communities, including ultrahigh dose rate (FLASH) particle therapy, online adaptive particle therapy, MR-particle RT systems, compact, affordable, and accessible particle RT systems, range uncertainty reduction, range verification, and artificial intelligence in particle therapy. The editorial provides visionary perspectives on each subfield's present activities and future research directions, along with a synopsis of the published articles pertaining to each subfield.
IEEE TRANSACTIONS ON RADIATION AND PLASMA MEDICAL SCIENCES
(2022)
Article
Computer Science, Interdisciplinary Applications
Wenbo Sun, Dipesh Niraula, Issam El Naqa, Randall K. Ten Haken, Ivo Dinov, Kyle Cuneo, Judy (Jionghua) Jin
Summary: This paper presents a systematic method to integrate expert human knowledge with AI recommendations for optimizing clinical decision making. It combines Gaussian process models with deep neural networks to quantify the uncertainty of treatment outcomes given by physicians and AI recommendations, providing guidance for clinical physicians and improving AI models performance.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2022)
Article
Biochemistry & Molecular Biology
Anh Phong Tran, Christopher J. Tralie, Jose Reyes, Caroline Moosmuller, Zehor Belkhatir, Ioannis G. Kevrekidis, Arnold J. Levine, Joseph O. Deasy, Allen R. Tannenbaum
Summary: In this study, the time evolution of p21 and p53 in retinal pigment epithelial cells exposed to different levels of radiation was analyzed to investigate the effect of radiation on cell cycle arrest. Results showed that p21 levels, along with p53 levels to a lesser extent, had an impact on cell cycle arrest and the frequency of mitosis events.
CELL DEATH AND DIFFERENTIATION
(2023)
Article
Engineering, Biomedical
Naveena Gorre, Eduardo Carranza, Jordan Fuhrman, Hui Li, Ravi K. Madduri, Maryellen Giger, Issam El Naqa
Summary: The objective of this study is to develop a modular and user-friendly software tool for clinical applications of machine learning models. This tool allows clinicians, researchers, and early AI developers to explore, train, and test AI algorithms, and provides visualization and interpretability of otherwise blackbox AI algorithms.
PHYSICS IN MEDICINE AND BIOLOGY
(2023)
Article
Biology
Jiening Zhu, Jung Hun Oh, Anish K. Simhal, Rena Elkin, Larry Norton, Joseph O. Deasy, Allen Tannenbaum
Summary: Geometric network analysis techniques combined with biological knowledge can predict the prognosis of cancer patients. We proposed a novel supervised deep learning method called geometric graph neural network (GGNN) that incorporates geometric features into deep learning, enhancing predictive power and interpretability.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Oncology
Islam Eljilany, Payman Ghasemi Saghand, James Chen, Aakrosh Ratan, Martin McCarter, John Carpten, Howard Colman, Alexandra P. Ikeguchi, Igor Puzanov, Susanne Arnold, Michelle Churchman, Patrick Hwu, Jose Conejo-Garcia, William S. Dalton, George J. Weiner, Issam M. El Naqa, Ahmad A. Tarhini
Summary: In this study, the prognostic value of immunoscore calculated from real-world transcriptomic data was evaluated in patients with advanced malignancies treated with immune checkpoint inhibitors. The results demonstrated that the immunoscore could predict patients at risk of death, with better overall survival observed in patients with intermediate-high immunoscore.
Article
Oncology
Dylan G. Hsu, Ase Ballangrud, Kayla Prezelski, Nathaniel C. Swinburne, Robert Young, Kathryn Beal, Joseph O. Deasy, Laura Cervino, Michalis Aristophanous
Summary: This study developed the METRO process to automatically process patient data and track brain metastases (BMs). Using a deep learning model, detections and volumetric measurements of BMs were obtained from longitudinal imaging. The accuracy of BM tracking was validated by comparing results with manual measurements and radiologists' assessments of new BMs.
PHYSICS & IMAGING IN RADIATION ONCOLOGY
(2023)
Review
Oncology
Rossybelle Amorrortu, Melany Garcia, Yayi Zhao, Issam El Naqa, Yoganand Balagurunathan, Dung-Tsa Chen, Thanh Thieu, Matthew B. Schabath, Dana E. Rollison
Summary: This narrative review summarizes existing literature on approaches to estimate real-world disease progression in lung cancer patients. Five approaches were identified, including manual abstraction, natural language processing, treatment-based algorithms, changes in tumor volume, and delta radiomics-based approaches. The accuracy of these approaches was assessed using different methods.
JNCI CANCER SPECTRUM
(2023)
Meeting Abstract
Oncology
Corey Weistuch, Kevin Murgas, Ken Dill, Larry Norton, Joseph Deasy, Allen Tannenbaum
Meeting Abstract
Oncology
Jiening Zhu, Jung Hun Oh, Anish K. Simhal, Rena Elkin, Larry Norton, Joseph O. Deasy, Allen R. Tannenbaum
Meeting Abstract
Oncology
Anish K. Simhal, Kylee H. Maclachlan, Rena Elkin, Jiening Zhu, Saad Z. Usmani, Jonathan J. Keats, Larry Norton, Joseph O. Deasy, Jung Hun Oh, Allen Tannenbaum
Meeting Abstract
Oncology
Kevin A. Murgas, Jung H. Oh, Joseph O. Deasy, Allen R. Tannenbaum
Meeting Abstract
Oncology
Rena Elkin, Jung Hun Oh, Filemon Dela Cruz, Larry Norton, Joseph O. Deasy, Andrew L. Kung, Allen R. Tannenbaum
Article
Oncology
Z. A. R. Gouw, J. Jeong, A. Rimner, N. Y. Lee, A. Jackson, A. Fu, J-j. Sonke, J. O. Deasy
Summary: This study investigates the effectiveness of non-uniform fractionation schedules in radiotherapy for early-stage non-small cell lung cancer. Through modeling, optimized schedules are proposed to minimize local failures and toxicity risk. The results suggest that non-standard primer shot fractionation can reduce hypoxia-induced radioresistance and improve treatment outcomes.
RADIOTHERAPY AND ONCOLOGY
(2024)